diff --git a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_nta4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_nta4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml index 4fea5c807b02..45d1ba1488f9 100644 --- a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_nta4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml +++ b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_nta4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml @@ -154,8 +154,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -474,8 +473,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -794,8 +792,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1114,8 +1111,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1434,8 +1430,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1754,8 +1749,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2074,8 +2068,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2394,8 +2387,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2714,8 +2706,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3034,8 +3025,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3354,8 +3344,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3674,8 +3663,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3994,8 +3982,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4314,8 +4301,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4634,8 +4620,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4954,8 +4939,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5274,8 +5258,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5594,8 +5577,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5914,8 +5896,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6234,8 +6215,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6554,8 +6534,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_16_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6874,8 +6853,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT16_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7194,8 +7172,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7514,8 +7491,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7834,8 +7810,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8154,8 +8129,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8474,8 +8448,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8794,8 +8767,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9114,8 +9086,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9434,8 +9405,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9754,8 +9724,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10074,8 +10043,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10394,8 +10362,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10714,8 +10681,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -11034,8 +11000,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11354,8 +11319,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11674,8 +11638,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11994,8 +11957,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12314,8 +12276,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x160x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12634,8 +12595,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12954,8 +12914,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13274,8 +13233,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13594,8 +13552,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13914,8 +13871,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14234,8 +14190,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14554,8 +14509,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14874,8 +14828,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15194,8 +15147,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15514,8 +15466,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT288x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT18_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15834,8 +15785,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16154,8 +16104,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16474,8 +16423,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16734,6 +16682,8769 @@ tailLoopOptB: false tailLoopOptMXSA: false tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfHC8ds5FItnPPsTA1Lxvrxe3BhCuBX5i-JTGw5q37tE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 36864 + LdsOffsetB_Blk: 106496 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 102400 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 36864 + LdsOffsetMetadata_Blk: 106496 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 4] + MIWaveTileA: 4 + MIWaveTileB: 4 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 128 + MacroTileA: 128 + MacroTileB: 128 + MacroTileMXSA: 128 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 52 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 4 + ThreadTileA: 16 + ThreadTileB: 4 + ThreadTileMXSA: 16 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA9eUzmfZ6ZKEf84l-FWU2NT76I0i-A-LRBhgne5Q8OgA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 10 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 115712 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 111104 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 115712 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 10] + MIWaveTileA: 2 + MIWaveTileB: 10 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 160 + MacroTileA: 128 + MacroTileB: 160 + MacroTileMXSA: 128 + MacroTileMXSB: 160 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 53 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 10 + ThreadTileA: 8 + ThreadTileB: 10 + ThreadTileMXSA: 8 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAh892y4cvtfxkmJwwj6gJ0D10i9UJ-bFbyRRRQaPIW2A= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 7 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 96256 + LdsInitCVgprs: false + LdsNumBytes: 96256 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 28672 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 48128 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 67584 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 64512 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 65536 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 67584 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 14] + MIWaveTileA: 2 + MIWaveTileB: 14 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 14 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 224 + MacroTileA: 128 + MacroTileB: 224 + MacroTileMXSA: 128 + MacroTileMXSB: 224 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 112 + NumGlobalWriteVectorsPerThread: 112 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 7 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 7 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 54 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 14 + ThreadTileA: 8 + ThreadTileB: 14 + ThreadTileMXSA: 8 + ThreadTileMXSB: 14 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 28672 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1792 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HABCnu5CxUjGRw4Aut9jrvw7ezkr8Aouazn_niHkelphc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 2 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 35328 + LdsOffsetB_Blk: 78848 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 76288 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 78336 + LdsOffsetMetadata: 35328 + LdsOffsetMetadata_Blk: 78848 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 32 + MacroTileA: 128 + MacroTileB: 32 + MacroTileMXSA: 128 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 2 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 2 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 55 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAC-1J1SsCeCSCeRdmCizmhlU1HPaWYPPFrDkZ1maVODE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 35840 + LdsOffsetB_Blk: 88064 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 84992 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 35840 + LdsOffsetMetadata_Blk: 88064 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 64 + MacroTileA: 128 + MacroTileB: 64 + MacroTileMXSA: 128 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 56 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAqaTOPJ6O45mECD0lgup_PTZ5VJD1yqpl0cFH2_7hWQQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 96 + MacroTileA: 128 + MacroTileB: 96 + MacroTileMXSA: 128 + MacroTileMXSB: 96 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 57 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAU99Xei1X_TYa-8CDtv0oJ_UIQlM2jLw2R5T1TYVJeUM= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 10 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 45568 + LdsOffsetB_Blk: 123904 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 119296 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 45568 + LdsOffsetMetadata_Blk: 123904 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 2] + MIWaveTileA: 10 + MIWaveTileB: 2 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 128 + MacroTileA: 160 + MacroTileB: 128 + MacroTileMXSA: 160 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 58 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 2 + ThreadTileA: 40 + ThreadTileB: 2 + ThreadTileMXSA: 40 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAL-8vbd3urR3vktIUaUCvDJVbr3z16iPL_BT9tfzLKQc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 5 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 20480 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 25088 + LdsOffsetB_Blk: 99328 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 20480 + LdsOffsetMXSA_Blk: 94720 + LdsOffsetMXSB: 22016 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 25088 + LdsOffsetMetadata_Blk: 99328 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 384 + MacroTileA: 160 + MacroTileB: 384 + MacroTileMXSA: 160 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 5 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 5 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 59 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 20480 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1280 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAHIBhOXLB4McgQaR2q95N5F8--Ra8VCIvMooUOgEjKWw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 28672 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 28672 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 10] + MIWaveTileA: 6 + MIWaveTileB: 10 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 320 + MacroTileA: 192 + MacroTileB: 320 + MacroTileMXSA: 192 + MacroTileMXSB: 320 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 60 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 10 + ThreadTileA: 24 + ThreadTileB: 10 + ThreadTileMXSA: 24 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA_OR2JEejA4Fn4GAchbtfEcvI_qrSFAlyuZMRXJD83mY= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 29184 + LdsOffsetB_Blk: 107520 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 102912 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 29184 + LdsOffsetMetadata_Blk: 107520 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 12] + MIWaveTileA: 6 + MIWaveTileB: 12 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 12 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 384 + MacroTileA: 192 + MacroTileB: 384 + MacroTileMXSA: 192 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 61 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 12 + ThreadTileA: 24 + ThreadTileB: 12 + ThreadTileMXSA: 24 + ThreadTileMXSB: 12 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAi5VUyg_zPoXxrkyn0Vz-LWZhinV24CMtCBnnxjekzmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 12 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 53248 + LdsOffsetB_Blk: 122880 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 118784 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 53248 + LdsOffsetMetadata_Blk: 122880 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 64 + MacroTileA: 192 + MacroTileB: 64 + MacroTileMXSA: 192 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 62 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAN2AlIbp2AIAriVo2mTgTiDbZLFY1eBVMGUIgTFkFAow= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 7 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 131072 + LdsInitCVgprs: false + LdsNumBytes: 131072 + LdsNumElementsAlignedA: 28672 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 65536 + LdsOffsetB: 32768 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 28672 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 30720 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 32768 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [14, 4] + MIWaveTileA: 14 + MIWaveTileB: 4 + MIWaveTileMXSA: 14 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 224 + MacroTile1: 256 + MacroTileA: 224 + MacroTileB: 256 + MacroTileMXSA: 224 + MacroTileMXSB: 256 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 224 + NumGlobalWriteVectorsPerThread: 224 + NumLdsBlk: 2 + NumLoadsA: 7 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 7 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 63 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 56 + ThreadTile1: 4 + ThreadTileA: 56 + ThreadTileB: 4 + ThreadTileMXSA: 56 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 28672 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1792 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAsWiVHmjjOTq9HollfQar4OLCfsuak_u0WSKntHxZXIU= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [8, 6] + MIWaveTileA: 8 + MIWaveTileB: 6 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 192 + MacroTileA: 256 + MacroTileB: 192 + MacroTileMXSA: 256 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 192 + NumGlobalWriteVectorsPerThread: 192 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 64 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 6 + ThreadTileA: 32 + ThreadTileB: 6 + ThreadTileMXSA: 32 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA8WohwIPyOji8FPX88sS2psVZCU1IXCZRGNVpon87tmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 36864 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 111616 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 107008 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 111616 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [4, 18] + MIWaveTileA: 4 + MIWaveTileB: 18 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 18 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 288 + MacroTileA: 256 + MacroTileB: 288 + MacroTileMXSA: 256 + MacroTileMXSB: 288 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 9 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 9 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 65 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 18 + ThreadTileA: 16 + ThreadTileB: 18 + ThreadTileMXSA: 16 + ThreadTileMXSB: 18 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 36864 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2304 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0-ZhUpOAu49LEMBe8AfP67nX4RWPbpzKUMNUHYP6gfw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 45056 + LdsOffsetB_Blk: 114688 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 110592 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 45056 + LdsOffsetMetadata_Blk: 114688 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 320 + MacroTile1: 192 + MacroTileA: 320 + MacroTileB: 192 + MacroTileMXSA: 320 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 66 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAPV16musbRandP2tS6fXNpfn2VAGqOWZD-vjUbZpDyIw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 16 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 8 + LSPB: 8 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 10752 + LdsOffsetB_Blk: 54272 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 51712 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 10752 + LdsOffsetMetadata_Blk: 54272 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 2] + MIWaveTile: [2, 4] + MIWaveTileA: 2 + MIWaveTileB: 4 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 128 + MacroTileA: 32 + MacroTileB: 128 + MacroTileMXSA: 32 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 16 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 16 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 128 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 2 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 67 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 32 + SubGroupA: 4 + SubGroupB: 32 + SubGroupMXSA: 4 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 4 + ThreadTileA: 8 + ThreadTileB: 4 + ThreadTileMXSA: 8 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0uQbUyeulwox8_zDp_7BCHPGVlpVEgAnxrcFfCRIh2c= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 4 + LSPB: 4 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 34816 + LdsInitCVgprs: false + LdsNumBytes: 34816 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 17408 + LdsOffsetB: 9216 + LdsOffsetB_Blk: 26624 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 25600 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 26112 + LdsOffsetMetadata: 9216 + LdsOffsetMetadata_Blk: 26624 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 32 + MacroTileA: 32 + MacroTileB: 32 + MacroTileMXSA: 32 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 64 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 1 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 68 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 16 + SubGroupA: 4 + SubGroupB: 16 + SubGroupMXSA: 4 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfA3b4suT5h50CxgF2vVTMooxyKosIJMOqBk6rckTsZ4= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 113664 + LdsInitCVgprs: false + LdsNumBytes: 113664 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 56832 + LdsOffsetB: 52736 + LdsOffsetB_Blk: 109568 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 105984 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 52736 + LdsOffsetMetadata_Blk: 109568 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 384 + MacroTile1: 32 + MacroTileA: 384 + MacroTileB: 32 + MacroTileMXSA: 384 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 69 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAJgnufLvnXFxioMXL-xiFC-wfgvQp8bRITd7W0wR5-Xs= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 65536 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 4096 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 70144 + LdsOffsetB_Blk: 144384 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 65536 + LdsOffsetMXSA_Blk: 139776 + LdsOffsetMXSB: 69632 + LdsOffsetMXSB_Blk: 143872 + LdsOffsetMetadata: 70144 + LdsOffsetMetadata_Blk: 144384 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [8, 2] + MIWaveTileA: 8 + MIWaveTileB: 2 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 512 + MacroTile1: 32 + MacroTileA: 512 + MacroTileB: 32 + MacroTileMXSA: 512 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 16 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 16 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 70 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 2 + ThreadTileA: 32 + ThreadTileB: 2 + ThreadTileMXSA: 32 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 65536 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 4096 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAKomIW0ENtnzTginRJmIKCZZKBgqHK3KPJOKZ_RUKSTQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 71680 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 68608 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 69632 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 71680 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 128 + MacroTileA: 64 + MacroTileB: 128 + MacroTileMXSA: 64 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 71 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAbzJnONOQUHXnXGQx7g02QrLEM-VLxoa7mXV1qHHgy4U= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 12 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 20480 + LdsOffsetB_Blk: 90112 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 86016 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 20480 + LdsOffsetMetadata_Blk: 90112 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 192 + MacroTileA: 64 + MacroTileB: 192 + MacroTileMXSA: 64 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 72 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAp9BNjAEH2-qgvZ2kxWs3cWX2HAosmYigJl-TzxZN2lA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 69632 + LdsInitCVgprs: false + LdsNumBytes: 69632 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 34816 + LdsOffsetB: 18432 + LdsOffsetB_Blk: 53248 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 51200 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 18432 + LdsOffsetMetadata_Blk: 53248 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 64 + MacroTileA: 64 + MacroTileB: 64 + MacroTileMXSA: 64 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 73 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAGLjFC74vOGP0WTvMKozOBd2zA_KHASGT6VwYASRcAhA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 28160 + LdsOffsetB_Blk: 89088 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 85504 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 28160 + LdsOffsetMetadata_Blk: 89088 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 96 + MacroTile1: 128 + MacroTileA: 96 + MacroTileB: 128 + MacroTileMXSA: 96 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 4 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 74 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA4_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false - null - null - null diff --git a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_ntb4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_ntb4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml index 21d30cb7464f..db399cfd8caa 100644 --- a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_ntb4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml +++ b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/Origami_ntb4/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml @@ -154,8 +154,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -474,8 +473,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -794,8 +792,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1114,8 +1111,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1434,8 +1430,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1754,8 +1749,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2074,8 +2068,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2394,8 +2387,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2714,8 +2706,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3034,8 +3025,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3354,8 +3344,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3674,8 +3663,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3994,8 +3982,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4314,8 +4301,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4634,8 +4620,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4954,8 +4939,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5274,8 +5258,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5594,8 +5577,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5914,8 +5896,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6234,8 +6215,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6554,8 +6534,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_16_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6874,8 +6853,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT16_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7194,8 +7172,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7514,8 +7491,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7834,8 +7810,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8154,8 +8129,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8474,8 +8448,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8794,8 +8767,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9114,8 +9086,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9434,8 +9405,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9754,8 +9724,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10074,8 +10043,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10394,8 +10362,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10714,8 +10681,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -11034,8 +11000,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11354,8 +11319,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11674,8 +11638,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11994,8 +11957,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12314,8 +12276,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x160x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12634,8 +12595,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12954,8 +12914,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13274,8 +13233,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13594,8 +13552,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13914,8 +13871,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14234,8 +14190,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14554,8 +14509,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14874,8 +14828,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15194,8 +15147,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15514,8 +15466,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT288x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT18_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15834,8 +15785,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16154,8 +16104,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16474,8 +16423,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16734,6 +16682,8769 @@ tailLoopOptB: false tailLoopOptMXSA: false tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfHC8ds5FItnPPsTA1Lxvrxe3BhCuBX5i-JTGw5q37tE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 36864 + LdsOffsetB_Blk: 106496 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 102400 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 36864 + LdsOffsetMetadata_Blk: 106496 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 4] + MIWaveTileA: 4 + MIWaveTileB: 4 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 128 + MacroTileA: 128 + MacroTileB: 128 + MacroTileMXSA: 128 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 52 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 4 + ThreadTileA: 16 + ThreadTileB: 4 + ThreadTileMXSA: 16 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA9eUzmfZ6ZKEf84l-FWU2NT76I0i-A-LRBhgne5Q8OgA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 10 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 115712 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 111104 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 115712 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 10] + MIWaveTileA: 2 + MIWaveTileB: 10 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 160 + MacroTileA: 128 + MacroTileB: 160 + MacroTileMXSA: 128 + MacroTileMXSB: 160 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 53 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 10 + ThreadTileA: 8 + ThreadTileB: 10 + ThreadTileMXSA: 8 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAh892y4cvtfxkmJwwj6gJ0D10i9UJ-bFbyRRRQaPIW2A= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 7 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 96256 + LdsInitCVgprs: false + LdsNumBytes: 96256 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 28672 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 48128 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 67584 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 64512 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 65536 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 67584 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 14] + MIWaveTileA: 2 + MIWaveTileB: 14 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 14 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 224 + MacroTileA: 128 + MacroTileB: 224 + MacroTileMXSA: 128 + MacroTileMXSB: 224 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 112 + NumGlobalWriteVectorsPerThread: 112 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 7 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 7 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 54 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 14 + ThreadTileA: 8 + ThreadTileB: 14 + ThreadTileMXSA: 8 + ThreadTileMXSB: 14 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 28672 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1792 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HABCnu5CxUjGRw4Aut9jrvw7ezkr8Aouazn_niHkelphc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 2 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 35328 + LdsOffsetB_Blk: 78848 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 76288 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 78336 + LdsOffsetMetadata: 35328 + LdsOffsetMetadata_Blk: 78848 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 32 + MacroTileA: 128 + MacroTileB: 32 + MacroTileMXSA: 128 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 2 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 2 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 55 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAC-1J1SsCeCSCeRdmCizmhlU1HPaWYPPFrDkZ1maVODE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 35840 + LdsOffsetB_Blk: 88064 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 84992 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 35840 + LdsOffsetMetadata_Blk: 88064 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 64 + MacroTileA: 128 + MacroTileB: 64 + MacroTileMXSA: 128 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 56 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAqaTOPJ6O45mECD0lgup_PTZ5VJD1yqpl0cFH2_7hWQQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 96 + MacroTileA: 128 + MacroTileB: 96 + MacroTileMXSA: 128 + MacroTileMXSB: 96 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 57 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAU99Xei1X_TYa-8CDtv0oJ_UIQlM2jLw2R5T1TYVJeUM= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 10 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 45568 + LdsOffsetB_Blk: 123904 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 119296 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 45568 + LdsOffsetMetadata_Blk: 123904 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 2] + MIWaveTileA: 10 + MIWaveTileB: 2 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 128 + MacroTileA: 160 + MacroTileB: 128 + MacroTileMXSA: 160 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 58 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 2 + ThreadTileA: 40 + ThreadTileB: 2 + ThreadTileMXSA: 40 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAL-8vbd3urR3vktIUaUCvDJVbr3z16iPL_BT9tfzLKQc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 5 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 20480 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 25088 + LdsOffsetB_Blk: 99328 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 20480 + LdsOffsetMXSA_Blk: 94720 + LdsOffsetMXSB: 22016 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 25088 + LdsOffsetMetadata_Blk: 99328 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 384 + MacroTileA: 160 + MacroTileB: 384 + MacroTileMXSA: 160 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 5 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 5 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 59 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 20480 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1280 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAHIBhOXLB4McgQaR2q95N5F8--Ra8VCIvMooUOgEjKWw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 28672 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 28672 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 10] + MIWaveTileA: 6 + MIWaveTileB: 10 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 320 + MacroTileA: 192 + MacroTileB: 320 + MacroTileMXSA: 192 + MacroTileMXSB: 320 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 60 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 10 + ThreadTileA: 24 + ThreadTileB: 10 + ThreadTileMXSA: 24 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA_OR2JEejA4Fn4GAchbtfEcvI_qrSFAlyuZMRXJD83mY= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 29184 + LdsOffsetB_Blk: 107520 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 102912 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 29184 + LdsOffsetMetadata_Blk: 107520 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 12] + MIWaveTileA: 6 + MIWaveTileB: 12 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 12 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 384 + MacroTileA: 192 + MacroTileB: 384 + MacroTileMXSA: 192 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 61 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 12 + ThreadTileA: 24 + ThreadTileB: 12 + ThreadTileMXSA: 24 + ThreadTileMXSB: 12 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAi5VUyg_zPoXxrkyn0Vz-LWZhinV24CMtCBnnxjekzmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 12 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 53248 + LdsOffsetB_Blk: 122880 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 118784 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 53248 + LdsOffsetMetadata_Blk: 122880 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 64 + MacroTileA: 192 + MacroTileB: 64 + MacroTileMXSA: 192 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 62 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAN2AlIbp2AIAriVo2mTgTiDbZLFY1eBVMGUIgTFkFAow= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 7 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 131072 + LdsInitCVgprs: false + LdsNumBytes: 131072 + LdsNumElementsAlignedA: 28672 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 65536 + LdsOffsetB: 32768 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 28672 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 30720 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 32768 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [14, 4] + MIWaveTileA: 14 + MIWaveTileB: 4 + MIWaveTileMXSA: 14 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 224 + MacroTile1: 256 + MacroTileA: 224 + MacroTileB: 256 + MacroTileMXSA: 224 + MacroTileMXSB: 256 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 224 + NumGlobalWriteVectorsPerThread: 224 + NumLdsBlk: 2 + NumLoadsA: 7 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 7 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 63 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 56 + ThreadTile1: 4 + ThreadTileA: 56 + ThreadTileB: 4 + ThreadTileMXSA: 56 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 28672 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1792 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAsWiVHmjjOTq9HollfQar4OLCfsuak_u0WSKntHxZXIU= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [8, 6] + MIWaveTileA: 8 + MIWaveTileB: 6 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 192 + MacroTileA: 256 + MacroTileB: 192 + MacroTileMXSA: 256 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 192 + NumGlobalWriteVectorsPerThread: 192 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 64 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 6 + ThreadTileA: 32 + ThreadTileB: 6 + ThreadTileMXSA: 32 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA8WohwIPyOji8FPX88sS2psVZCU1IXCZRGNVpon87tmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 36864 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 111616 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 107008 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 111616 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [4, 18] + MIWaveTileA: 4 + MIWaveTileB: 18 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 18 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 288 + MacroTileA: 256 + MacroTileB: 288 + MacroTileMXSA: 256 + MacroTileMXSB: 288 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 9 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 9 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 65 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 18 + ThreadTileA: 16 + ThreadTileB: 18 + ThreadTileMXSA: 16 + ThreadTileMXSB: 18 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 36864 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2304 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0-ZhUpOAu49LEMBe8AfP67nX4RWPbpzKUMNUHYP6gfw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 45056 + LdsOffsetB_Blk: 114688 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 110592 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 45056 + LdsOffsetMetadata_Blk: 114688 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 320 + MacroTile1: 192 + MacroTileA: 320 + MacroTileB: 192 + MacroTileMXSA: 320 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 66 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAPV16musbRandP2tS6fXNpfn2VAGqOWZD-vjUbZpDyIw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 16 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 8 + LSPB: 8 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 10752 + LdsOffsetB_Blk: 54272 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 51712 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 10752 + LdsOffsetMetadata_Blk: 54272 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 2] + MIWaveTile: [2, 4] + MIWaveTileA: 2 + MIWaveTileB: 4 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 128 + MacroTileA: 32 + MacroTileB: 128 + MacroTileMXSA: 32 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 16 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 16 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 128 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 2 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 67 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 32 + SubGroupA: 4 + SubGroupB: 32 + SubGroupMXSA: 4 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 4 + ThreadTileA: 8 + ThreadTileB: 4 + ThreadTileMXSA: 8 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0uQbUyeulwox8_zDp_7BCHPGVlpVEgAnxrcFfCRIh2c= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 4 + LSPB: 4 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 34816 + LdsInitCVgprs: false + LdsNumBytes: 34816 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 17408 + LdsOffsetB: 9216 + LdsOffsetB_Blk: 26624 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 25600 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 26112 + LdsOffsetMetadata: 9216 + LdsOffsetMetadata_Blk: 26624 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 32 + MacroTileA: 32 + MacroTileB: 32 + MacroTileMXSA: 32 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 64 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 1 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 68 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 16 + SubGroupA: 4 + SubGroupB: 16 + SubGroupMXSA: 4 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfA3b4suT5h50CxgF2vVTMooxyKosIJMOqBk6rckTsZ4= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 113664 + LdsInitCVgprs: false + LdsNumBytes: 113664 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 56832 + LdsOffsetB: 52736 + LdsOffsetB_Blk: 109568 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 105984 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 52736 + LdsOffsetMetadata_Blk: 109568 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 384 + MacroTile1: 32 + MacroTileA: 384 + MacroTileB: 32 + MacroTileMXSA: 384 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 69 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAJgnufLvnXFxioMXL-xiFC-wfgvQp8bRITd7W0wR5-Xs= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 65536 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 4096 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 70144 + LdsOffsetB_Blk: 144384 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 65536 + LdsOffsetMXSA_Blk: 139776 + LdsOffsetMXSB: 69632 + LdsOffsetMXSB_Blk: 143872 + LdsOffsetMetadata: 70144 + LdsOffsetMetadata_Blk: 144384 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [8, 2] + MIWaveTileA: 8 + MIWaveTileB: 2 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 512 + MacroTile1: 32 + MacroTileA: 512 + MacroTileB: 32 + MacroTileMXSA: 512 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 16 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 16 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 70 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 2 + ThreadTileA: 32 + ThreadTileB: 2 + ThreadTileMXSA: 32 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 65536 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 4096 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAKomIW0ENtnzTginRJmIKCZZKBgqHK3KPJOKZ_RUKSTQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 71680 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 68608 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 69632 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 71680 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 128 + MacroTileA: 64 + MacroTileB: 128 + MacroTileMXSA: 64 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 71 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAbzJnONOQUHXnXGQx7g02QrLEM-VLxoa7mXV1qHHgy4U= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 12 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 20480 + LdsOffsetB_Blk: 90112 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 86016 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 20480 + LdsOffsetMetadata_Blk: 90112 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 192 + MacroTileA: 64 + MacroTileB: 192 + MacroTileMXSA: 64 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 72 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAp9BNjAEH2-qgvZ2kxWs3cWX2HAosmYigJl-TzxZN2lA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 69632 + LdsInitCVgprs: false + LdsNumBytes: 69632 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 34816 + LdsOffsetB: 18432 + LdsOffsetB_Blk: 53248 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 51200 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 18432 + LdsOffsetMetadata_Blk: 53248 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 64 + MacroTileA: 64 + MacroTileB: 64 + MacroTileMXSA: 64 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 73 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAGLjFC74vOGP0WTvMKozOBd2zA_KHASGT6VwYASRcAhA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 28160 + LdsOffsetB_Blk: 89088 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 85504 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 28160 + LdsOffsetMetadata_Blk: 89088 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 96 + MacroTile1: 128 + MacroTileA: 96 + MacroTileB: 128 + MacroTileMXSA: 96 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 4 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 74 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB4_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false - null - null - null diff --git a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml index 9688f80e0dbd..302cd815d7ef 100644 --- a/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml +++ b/projects/hipblaslt/library/src/amd_detail/rocblaslt/src/Tensile/Logic/asm_full/gfx950/gfx950/Origami/gfx950_Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs.yaml @@ -154,8 +154,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -474,8 +473,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -794,8 +792,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1114,8 +1111,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1434,8 +1430,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -1754,8 +1749,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2074,8 +2068,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2394,8 +2387,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -2714,8 +2706,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3034,8 +3025,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3354,8 +3344,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3674,8 +3663,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -3994,8 +3982,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4314,8 +4301,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4634,8 +4620,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -4954,8 +4939,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5274,8 +5258,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5594,8 +5577,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -5914,8 +5896,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6234,8 +6215,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6554,8 +6534,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_16_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -6874,8 +6853,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT16_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7194,8 +7172,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7514,8 +7491,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -7834,8 +7810,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8154,8 +8129,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8474,8 +8448,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -8794,8 +8767,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x320x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9114,8 +9086,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9434,8 +9405,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x64x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -9754,8 +9724,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x448x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_14_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10074,8 +10043,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT448x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10394,8 +10362,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -10714,8 +10681,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x192x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT12_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1 @@ -11034,8 +11000,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11354,8 +11319,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11674,8 +11638,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -11994,8 +11957,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12314,8 +12276,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x160x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_10_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12634,8 +12595,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -12954,8 +12914,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13274,8 +13233,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x96x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13594,8 +13552,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1 @@ -13914,8 +13871,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14234,8 +14190,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14554,8 +14509,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -14874,8 +14828,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15194,8 +15147,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15514,8 +15466,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT288x256x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT18_4_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -15834,8 +15785,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16154,8 +16104,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x512x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_8_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16474,8 +16423,7 @@ ISA: [9, 5, 0] InnerUnroll: 1 InterleaveAlpha: 0 - InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, - SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} Kernel: true KernelLanguage: Assembly KernelNameMin: Cijk_Alik_Bljk_F4BS_MXA32_MXB32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x384x256_MI16x16x1_SN_LDSB0_AFC0_AG0_AFEM1_AFEM1_ASEM32_CLR1_CADS0_DTLA1_DTLB1_DTVA0_DTVB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_ISA950_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPM0_LPA0_LPB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_6_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD4_NTM0_NEPBS0_NLCA1_NLCB1_ONLL1_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKXCCM0_SGRO0_TIN0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UIOFGRO0_UPLRP0_USFGROn1_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1 @@ -16734,6 +16682,8769 @@ tailLoopOptB: false tailLoopOptMXSA: false tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfHC8ds5FItnPPsTA1Lxvrxe3BhCuBX5i-JTGw5q37tE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 36864 + LdsOffsetB_Blk: 106496 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 102400 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 36864 + LdsOffsetMetadata_Blk: 106496 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 4] + MIWaveTileA: 4 + MIWaveTileB: 4 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 128 + MacroTileA: 128 + MacroTileB: 128 + MacroTileMXSA: 128 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 52 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 4 + ThreadTileA: 16 + ThreadTileB: 4 + ThreadTileMXSA: 16 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA9eUzmfZ6ZKEf84l-FWU2NT76I0i-A-LRBhgne5Q8OgA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 10 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 115712 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 111104 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 115712 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 10] + MIWaveTileA: 2 + MIWaveTileB: 10 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 160 + MacroTileA: 128 + MacroTileB: 160 + MacroTileMXSA: 128 + MacroTileMXSB: 160 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 53 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x160x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 10 + ThreadTileA: 8 + ThreadTileB: 10 + ThreadTileMXSA: 8 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAh892y4cvtfxkmJwwj6gJ0D10i9UJ-bFbyRRRQaPIW2A= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 7 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 96256 + LdsInitCVgprs: false + LdsNumBytes: 96256 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 28672 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 48128 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 67584 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 64512 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 65536 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 67584 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 14] + MIWaveTileA: 2 + MIWaveTileB: 14 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 14 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 224 + MacroTileA: 128 + MacroTileB: 224 + MacroTileMXSA: 128 + MacroTileMXSB: 224 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 112 + NumGlobalWriteVectorsPerThread: 112 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 7 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 7 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 54 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x224x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_14_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 14 + ThreadTileA: 8 + ThreadTileB: 14 + ThreadTileMXSA: 8 + ThreadTileMXSB: 14 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 28672 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1792 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HABCnu5CxUjGRw4Aut9jrvw7ezkr8Aouazn_niHkelphc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 2 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 35328 + LdsOffsetB_Blk: 78848 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 76288 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 78336 + LdsOffsetMetadata: 35328 + LdsOffsetMetadata_Blk: 78848 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 32 + MacroTileA: 128 + MacroTileB: 32 + MacroTileMXSA: 128 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 2 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 2 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 55 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAC-1J1SsCeCSCeRdmCizmhlU1HPaWYPPFrDkZ1maVODE= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 35840 + LdsOffsetB_Blk: 88064 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 84992 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 35840 + LdsOffsetMetadata_Blk: 88064 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 64 + MacroTileA: 128 + MacroTileB: 64 + MacroTileMXSA: 128 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 56 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAqaTOPJ6O45mECD0lgup_PTZ5VJD1yqpl0cFH2_7hWQQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 128 + MacroTile1: 96 + MacroTileA: 128 + MacroTileB: 96 + MacroTileMXSA: 128 + MacroTileMXSB: 96 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 57 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT128x96x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAU99Xei1X_TYa-8CDtv0oJ_UIQlM2jLw2R5T1TYVJeUM= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 10 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 45568 + LdsOffsetB_Blk: 123904 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 119296 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 45568 + LdsOffsetMetadata_Blk: 123904 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 2] + MIWaveTileA: 10 + MIWaveTileB: 2 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 128 + MacroTileA: 160 + MacroTileB: 128 + MacroTileMXSA: 160 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 80 + NumGlobalWriteVectorsPerThread: 80 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 58 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 2 + ThreadTileA: 40 + ThreadTileB: 2 + ThreadTileMXSA: 40 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAL-8vbd3urR3vktIUaUCvDJVbr3z16iPL_BT9tfzLKQc= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 5 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 20480 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 25088 + LdsOffsetB_Blk: 99328 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 20480 + LdsOffsetMXSA_Blk: 94720 + LdsOffsetMXSB: 22016 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 25088 + LdsOffsetMetadata_Blk: 99328 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 160 + MacroTile1: 384 + MacroTileA: 160 + MacroTileB: 384 + MacroTileMXSA: 160 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 5 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 5 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 59 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT160x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 20480 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1280 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAHIBhOXLB4McgQaR2q95N5F8--Ra8VCIvMooUOgEjKWw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 40960 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 28672 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 28672 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 10] + MIWaveTileA: 6 + MIWaveTileB: 10 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 10 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 320 + MacroTileA: 192 + MacroTileB: 320 + MacroTileMXSA: 192 + MacroTileMXSB: 320 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 10 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 10 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 60 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x320x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_10_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 10 + ThreadTileA: 24 + ThreadTileB: 10 + ThreadTileMXSA: 24 + ThreadTileMXSB: 10 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 40960 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2560 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA_OR2JEejA4Fn4GAchbtfEcvI_qrSFAlyuZMRXJD83mY= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 156672 + LdsInitCVgprs: false + LdsNumBytes: 156672 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 78336 + LdsOffsetB: 29184 + LdsOffsetB_Blk: 107520 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 102912 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 104448 + LdsOffsetMetadata: 29184 + LdsOffsetMetadata_Blk: 107520 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 12] + MIWaveTileA: 6 + MIWaveTileB: 12 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 12 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 384 + MacroTileA: 192 + MacroTileB: 384 + MacroTileMXSA: 192 + MacroTileMXSB: 384 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 61 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x384x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_12_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 12 + ThreadTileA: 24 + ThreadTileB: 12 + ThreadTileMXSA: 24 + ThreadTileMXSB: 12 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAi5VUyg_zPoXxrkyn0Vz-LWZhinV24CMtCBnnxjekzmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 12 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 53248 + LdsOffsetB_Blk: 122880 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 118784 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 121856 + LdsOffsetMetadata: 53248 + LdsOffsetMetadata_Blk: 122880 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 192 + MacroTile1: 64 + MacroTileA: 192 + MacroTileB: 64 + MacroTileMXSA: 192 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 62 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT192x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAN2AlIbp2AIAriVo2mTgTiDbZLFY1eBVMGUIgTFkFAow= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 7 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 131072 + LdsInitCVgprs: false + LdsNumBytes: 131072 + LdsNumElementsAlignedA: 28672 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 65536 + LdsOffsetB: 32768 + LdsOffsetB_Blk: 98304 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 28672 + LdsOffsetMXSA_Blk: 94208 + LdsOffsetMXSB: 30720 + LdsOffsetMXSB_Blk: 96256 + LdsOffsetMetadata: 32768 + LdsOffsetMetadata_Blk: 98304 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [14, 4] + MIWaveTileA: 14 + MIWaveTileB: 4 + MIWaveTileMXSA: 14 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 224 + MacroTile1: 256 + MacroTileA: 224 + MacroTileB: 256 + MacroTileMXSA: 224 + MacroTileMXSB: 256 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 224 + NumGlobalWriteVectorsPerThread: 224 + NumLdsBlk: 2 + NumLoadsA: 7 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 7 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 63 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT224x256x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT14_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 56 + ThreadTile1: 4 + ThreadTileA: 56 + ThreadTileB: 4 + ThreadTileMXSA: 56 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 28672 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1792 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAsWiVHmjjOTq9HollfQar4OLCfsuak_u0WSKntHxZXIU= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 36352 + LdsOffsetB_Blk: 97280 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 93696 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 95744 + LdsOffsetMetadata: 36352 + LdsOffsetMetadata_Blk: 97280 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [8, 6] + MIWaveTileA: 8 + MIWaveTileB: 6 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 192 + MacroTileA: 256 + MacroTileB: 192 + MacroTileMXSA: 256 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 192 + NumGlobalWriteVectorsPerThread: 192 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 64 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 6 + ThreadTileA: 32 + ThreadTileB: 6 + ThreadTileMXSA: 32 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA8WohwIPyOji8FPX88sS2psVZCU1IXCZRGNVpon87tmk= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 32768 + LdsNumElementsAlignedB: 36864 + LdsNumElementsAlignedMXSA: 2048 + LdsNumElementsAlignedMXSB: 2560 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 37376 + LdsOffsetB_Blk: 111616 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 32768 + LdsOffsetMXSA_Blk: 107008 + LdsOffsetMXSB: 34816 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 37376 + LdsOffsetMetadata_Blk: 111616 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [4, 18] + MIWaveTileA: 4 + MIWaveTileB: 18 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 18 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 256 + MacroTile1: 288 + MacroTileA: 256 + MacroTileB: 288 + MacroTileMXSA: 256 + MacroTileMXSB: 288 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 288 + NumGlobalWriteVectorsPerThread: 288 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 9 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 9 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 65 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT256x288x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_18_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 18 + ThreadTileA: 16 + ThreadTileB: 18 + ThreadTileMXSA: 16 + ThreadTileMXSB: 18 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 32768 + ldsNumBytesB: 36864 + ldsNumBytesMXSA: 2048 + ldsNumBytesMXSB: 2304 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0-ZhUpOAu49LEMBe8AfP67nX4RWPbpzKUMNUHYP6gfw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 6 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 40960 + LdsNumElementsAlignedB: 24576 + LdsNumElementsAlignedMXSA: 2560 + LdsNumElementsAlignedMXSB: 1536 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 45056 + LdsOffsetB_Blk: 114688 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 40960 + LdsOffsetMXSA_Blk: 110592 + LdsOffsetMXSB: 43520 + LdsOffsetMXSB_Blk: 113152 + LdsOffsetMetadata: 45056 + LdsOffsetMetadata_Blk: 114688 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [10, 6] + MIWaveTileA: 10 + MIWaveTileB: 6 + MIWaveTileMXSA: 10 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 320 + MacroTile1: 192 + MacroTileA: 320 + MacroTileB: 192 + MacroTileMXSA: 320 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 240 + NumGlobalWriteVectorsPerThread: 240 + NumLdsBlk: 2 + NumLoadsA: 10 + NumLoadsB: 6 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 10 + NumLoadsPerpendicularB: 6 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 66 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT320x192x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT10_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 40 + ThreadTile1: 6 + ThreadTileA: 40 + ThreadTileB: 6 + ThreadTileMXSA: 40 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 40960 + ldsNumBytesB: 24576 + ldsNumBytesMXSA: 2560 + ldsNumBytesMXSB: 1536 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAPV16musbRandP2tS6fXNpfn2VAGqOWZD-vjUbZpDyIw= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 16 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 8 + LSPB: 8 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 87040 + LdsInitCVgprs: false + LdsNumBytes: 87040 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 43520 + LdsOffsetB: 10752 + LdsOffsetB_Blk: 54272 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 51712 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 10752 + LdsOffsetMetadata_Blk: 54272 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 2] + MIWaveTile: [2, 4] + MIWaveTileA: 2 + MIWaveTileB: 4 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 4 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 128 + MacroTileA: 32 + MacroTileB: 128 + MacroTileMXSA: 32 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 16 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 16 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 128 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 2 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 67 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_4_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 32 + SubGroupA: 4 + SubGroupB: 32 + SubGroupMXSA: 4 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 4 + ThreadTileA: 8 + ThreadTileB: 4 + ThreadTileMXSA: 8 + ThreadTileMXSB: 4 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HA0uQbUyeulwox8_zDp_7BCHPGVlpVEgAnxrcFfCRIh2c= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: true + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 4 + LSPB: 4 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 34816 + LdsInitCVgprs: false + LdsNumBytes: 34816 + LdsNumElementsAlignedA: 8192 + LdsNumElementsAlignedB: 8192 + LdsNumElementsAlignedMXSA: 512 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 17408 + LdsOffsetB: 9216 + LdsOffsetB_Blk: 26624 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 8192 + LdsOffsetMXSA_Blk: 25600 + LdsOffsetMXSB: 8704 + LdsOffsetMXSB_Blk: 26112 + LdsOffsetMetadata: 9216 + LdsOffsetMetadata_Blk: 26624 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 1] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 32 + MacroTile1: 32 + MacroTileA: 32 + MacroTileB: 32 + MacroTileMXSA: 32 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 8 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 8 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 64 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 1 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 1 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 68 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT32x32x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS1_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR1_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 16 + SubGroupA: 4 + SubGroupB: 16 + SubGroupMXSA: 4 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 8192 + ldsNumBytesB: 8192 + ldsNumBytesMXSA: 512 + ldsNumBytesMXSB: 512 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAfA3b4suT5h50CxgF2vVTMooxyKosIJMOqBk6rckTsZ4= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 113664 + LdsInitCVgprs: false + LdsNumBytes: 113664 + LdsNumElementsAlignedA: 49152 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 3072 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 56832 + LdsOffsetB: 52736 + LdsOffsetB_Blk: 109568 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 49152 + LdsOffsetMXSA_Blk: 105984 + LdsOffsetMXSB: 52224 + LdsOffsetMXSB_Blk: 109056 + LdsOffsetMetadata: 52736 + LdsOffsetMetadata_Blk: 109568 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 384 + MacroTile1: 32 + MacroTileA: 384 + MacroTileB: 32 + MacroTileMXSA: 384 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 12 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 12 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 69 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT384x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 49152 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 3072 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAJgnufLvnXFxioMXL-xiFC-wfgvQp8bRITd7W0wR5-Xs= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 256 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 8 + GlobalReadVectorWidthMXSB: 1 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGMXCCn1 + LDSTrInst: false + LSCA: 256 + LSCB: 256 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 32 + LSPB: 32 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 8 + LVCB: 8 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 148480 + LdsInitCVgprs: false + LdsNumBytes: 148480 + LdsNumElementsAlignedA: 65536 + LdsNumElementsAlignedB: 4096 + LdsNumElementsAlignedMXSA: 4096 + LdsNumElementsAlignedMXSB: 512 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 74240 + LdsOffsetB: 70144 + LdsOffsetB_Blk: 144384 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 65536 + LdsOffsetMXSA_Blk: 139776 + LdsOffsetMXSB: 69632 + LdsOffsetMXSB_Blk: 143872 + LdsOffsetMetadata: 70144 + LdsOffsetMetadata_Blk: 144384 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 2 + LoopUnroll: 256 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [4, 1] + MIWaveTile: [8, 2] + MIWaveTileA: 8 + MIWaveTileB: 2 + MIWaveTileMXSA: 8 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 512 + MacroTile1: 32 + MacroTileA: 512 + MacroTileB: 32 + MacroTileMXSA: 512 + MacroTileMXSB: 32 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 64 + NumGlobalWriteVectorsPerThread: 64 + NumLdsBlk: 2 + NumLoadsA: 16 + NumLoadsB: 1 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 16 + NumLoadsPerpendicularB: 1 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 70 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT512x32x256_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT8_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG64_4_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 16 + SubGroup1: 16 + SubGroupA: 16 + SubGroupB: 16 + SubGroupMXSA: 16 + SubGroupMXSB: 16 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 32 + ThreadTile1: 2 + ThreadTileA: 32 + ThreadTileB: 2 + ThreadTileMXSA: 32 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [64, 4, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 256 + _DepthUA: 256 + _DepthUB: 256 + _DepthUMXSA: 8 + _DepthUMXSB: 8 + _DepthUMetadata: 256 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 1 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 65536 + ldsNumBytesB: 4096 + ldsNumBytesMXSA: 4096 + ldsNumBytesMXSB: 256 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAKomIW0ENtnzTginRJmIKCZZKBgqHK3KPJOKZ_RUKSTQ= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 104448 + LdsInitCVgprs: false + LdsNumBytes: 104448 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 52224 + LdsOffsetB: 19456 + LdsOffsetB_Blk: 71680 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 68608 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 69632 + LdsOffsetMetadata: 19456 + LdsOffsetMetadata_Blk: 71680 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [4, 2] + MIWaveTileA: 4 + MIWaveTileB: 2 + MIWaveTileMXSA: 4 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 128 + MacroTileA: 64 + MacroTileB: 128 + MacroTileMXSA: 64 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 32 + NumGlobalWriteVectorsPerThread: 32 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 71 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT4_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 16 + ThreadTile1: 2 + ThreadTileA: 16 + ThreadTileB: 2 + ThreadTileMXSA: 16 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAbzJnONOQUHXnXGQx7g02QrLEM-VLxoa7mXV1qHHgy4U= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 12 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 139264 + LdsInitCVgprs: false + LdsNumBytes: 139264 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 49152 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 3072 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 69632 + LdsOffsetB: 20480 + LdsOffsetB_Blk: 90112 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 86016 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 20480 + LdsOffsetMetadata_Blk: 90112 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 6] + MIWaveTileA: 2 + MIWaveTileB: 6 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 6 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 192 + MacroTileA: 64 + MacroTileB: 192 + MacroTileMXSA: 64 + MacroTileMXSB: 192 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 12 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 12 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 72 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x192x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_6_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: true + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 6 + ThreadTileA: 8 + ThreadTileB: 6 + ThreadTileMXSA: 8 + ThreadTileMXSB: 6 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 49152 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 3072 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAp9BNjAEH2-qgvZ2kxWs3cWX2HAosmYigJl-TzxZN2lA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 4 + GlobalReadVectorWidthMXSB: 4 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 69632 + LdsInitCVgprs: false + LdsNumBytes: 69632 + LdsNumElementsAlignedA: 16384 + LdsNumElementsAlignedB: 16384 + LdsNumElementsAlignedMXSA: 1024 + LdsNumElementsAlignedMXSB: 1024 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 34816 + LdsOffsetB: 18432 + LdsOffsetB_Blk: 53248 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 16384 + LdsOffsetMXSA_Blk: 51200 + LdsOffsetMXSB: 17408 + LdsOffsetMXSB_Blk: 52224 + LdsOffsetMetadata: 18432 + LdsOffsetMetadata_Blk: 53248 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [2, 2] + MIWaveTile: [2, 2] + MIWaveTileA: 2 + MIWaveTileB: 2 + MIWaveTileMXSA: 2 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 64 + MacroTile1: 64 + MacroTileA: 64 + MacroTileB: 64 + MacroTileMXSA: 64 + MacroTileMXSB: 64 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 16 + NumGlobalWriteVectorsPerThread: 16 + NumLdsBlk: 2 + NumLoadsA: 4 + NumLoadsB: 4 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 4 + NumLoadsPerpendicularB: 4 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 73 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT64x64x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT2_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG32_8_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 8 + SubGroup1: 32 + SubGroupA: 8 + SubGroupB: 32 + SubGroupMXSA: 8 + SubGroupMXSB: 32 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 8 + ThreadTile1: 2 + ThreadTileA: 8 + ThreadTileB: 2 + ThreadTileMXSA: 8 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [32, 8, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 16384 + ldsNumBytesB: 16384 + ldsNumBytesMXSA: 1024 + ldsNumBytesMXSB: 1024 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false + - 1LDSBuffer: 0 + ActivationAlt: false + ActivationFuncCall: false + ActivationFused: true + AdaptiveGemm: 0 + AdaptiveGemmGSUA: 0 + AdaptiveGemmNTAB: 0 + AssertAIGreaterThanEqual: -1 + AssertAILessThanEqual: -1 + AssertFree0ElementMultiple: 1 + AssertFree1ElementMultiple: 1 + AssertSummationElementMultiple: 32 + AssignedDerivedParameters: true + AssignedProblemIndependentDerivedParameters: true + BaseName: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_Bias_HAGLjFC74vOGP0WTvMKozOBd2zA_KHASGT6VwYASRcAhA= + BufferLoad: true + BufferStore: true + CUCount: null + CUOccupancy: -1 + ClusterBarrier: false + ClusterDim: [1, 1] + ClusterLocalRead: 1 + CodeObjectVersion: '4' + CompactLoopStore: false + ConvertAfterDS: false + CustomKernelName: '' + DebugPersistentKernelLoopForever: false + DebugStreamK: 0 + DepthU: 512 + DirectToLds: 0 + DirectToLdsA: false + DirectToLdsB: false + DirectToLdsMXSA: false + DirectToLdsMXSB: false + DirectToLdsMetadata: 0 + DirectToVgprA: false + DirectToVgprB: false + DirectToVgprMXSA: false + DirectToVgprMXSB: false + DirectToVgprSparseMetadata: false + DtlPlusLdsBuf: 0 + ESMRuntimeGate: false + EdgeType: ShiftPtr + EnableF32XdlMathOp: false + EnableMatrixInstruction: true + EnableStinkyTofuESM2: false + ExpandPointerSwap: false + ExpertSchedulingMode: 0 + ExtraLatencyForLR: 0 + ExtraMiLatencyLeft: -1 + ForceDisableShadowInit: false + ForceUnrollSubIter: false + GlobalReadPerMfma: 1.0 + GlobalReadVectorWidthA: 32 + GlobalReadVectorWidthB: 32 + GlobalReadVectorWidthMXSA: 6 + GlobalReadVectorWidthMXSB: 8 + GlobalSplitU: 0 + GlobalSplitUAlgorithm: MultipleBuffer + GlobalSplitUCoalesced: false + GlobalSplitUWorkGroupMappingRoundRobin: false + GlobalWriteVectorWidth: 1 + GroupLoadStore: false + GuaranteeNoPartialA: true + GuaranteeNoPartialB: true + GuaranteeNoPartialMetadata: true + HalfPLR: 0 + HalfPLRA: false + HalfPLRB: false + ISA: [9, 5, 0] + InitCIterWmma: 0 + InnerUnroll: 1 + InterleaveAlpha: 0 + InternalSupportParams: {KernArgsVersion: 2, SupportCustomStaggerU: true, SupportCustomWGM: true, SupportUserGSU: false, UseSFC: false, UseUniversalArgs: true} + Kernel: true + KernelLanguage: Assembly + KernelNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGMXCCn1 + LDSTrInst: false + LSCA: 512 + LSCB: 512 + LSCMXSA: 0 + LSCMXSB: 0 + LSPA: 16 + LSPB: 16 + LSPMXSA: 0 + LSPMXSB: 0 + LVCA: 16 + LVCB: 16 + LVCMXSA: 0 + LVCMXSB: 0 + LVPA: 1 + LVPB: 1 + LVPMXSA: 0 + LVPMXSB: 0 + LdsBlockSizePerPadA: 0 + LdsBlockSizePerPadB: 0 + LdsBlockSizePerPadMXSA: 0 + LdsBlockSizePerPadMXSB: 0 + LdsBlockSizePerPadMetadata: 0 + LdsBytesNoAmax: 121856 + LdsInitCVgprs: false + LdsNumBytes: 121856 + LdsNumElementsAlignedA: 24576 + LdsNumElementsAlignedB: 32768 + LdsNumElementsAlignedMXSA: 1536 + LdsNumElementsAlignedMXSB: 2048 + LdsNumElementsAlignedMetadata: 0 + LdsOffsetA: 0 + LdsOffsetA_Blk: 60928 + LdsOffsetB: 28160 + LdsOffsetB_Blk: 89088 + LdsOffsetBias: 0 + LdsOffsetBiasGSU: 0 + LdsOffsetBiasNonGSU: 0 + LdsOffsetMXSA: 24576 + LdsOffsetMXSA_Blk: 85504 + LdsOffsetMXSB: 26112 + LdsOffsetMXSB_Blk: 87040 + LdsOffsetMetadata: 28160 + LdsOffsetMetadata_Blk: 89088 + LdsPadA: 0 + LdsPadB: 0 + LdsPadMXSA: 0 + LdsPadMXSB: 0 + LdsPadMetadata: 0 + LocalReadVectorWidth: -1 + LocalReadVectorWidthA: 32 + LocalReadVectorWidthB: 32 + LocalReadVectorWidthMXS: 1 + LocalReadVectorWidthMXSA: 1 + LocalReadVectorWidthMXSB: 1 + LocalSplitU: 1 + LocalSplitUReuseLDS: 1 + LocalWritePerMfma: -1 + LocalWriteUseSgprA: false + LocalWriteUseSgprB: false + LocalWriteUseSgprMXSA: false + LocalWriteUseSgprMXSB: false + LocalWriteUseSgprMetadata: false + LoopIters: 4 + LoopUnroll: 512 + MFMA_BF16_1K: false + MIArchVgpr: false + MIBlock: [16, 16, 128, 1, 1, 1] + MIInputPerThread: 32 + MIInputPerThreadA: 32 + MIInputPerThreadB: 32 + MIInputPerThreadMXSA: 1 + MIInputPerThreadMXSB: 1 + MIInputPerThreadMetadata: 32 + MIOutputVectorWidth: 4 + MIRegPerOut: 1 + MIWaveGroup: [1, 4] + MIWaveTile: [6, 2] + MIWaveTileA: 6 + MIWaveTileB: 2 + MIWaveTileMXSA: 6 + MIWaveTileMXSB: 2 + MIWaveTileMetadata: 0 + MXLoadInst: BufferLoad + MXScaleFormat: HostPreSwizzle + MacroTile0: 96 + MacroTile1: 128 + MacroTileA: 96 + MacroTileB: 128 + MacroTileMXSA: 96 + MacroTileMXSB: 128 + MagicDivAlg: 2 + MathClocksUnrolledLoop: 0 + MatrixInstB: 1 + MatrixInstBM: 1 + MatrixInstBN: 1 + MatrixInstK: 128 + MatrixInstM: 16 + MatrixInstN: 16 + MatrixInstruction: [16, 16, 128, 1] + MaxLDS: 163840 + MaxOccupancy: 40 + MbskPrefetchMethod: 0 + MfmaInitCVgprs: false + MinGRIncPerMfma: 3 + Multicast: false + NoLdsWriteCode: false + NoReject: false + NoTailLoop: false + NonDTLTailLoopA: false + NonDTLTailLoopB: false + NonDTLTailLoopMXSA: false + NonDTLTailLoopMXSB: false + NonDTLTailLoopMetadata: false + NonTemporal: -1 + NonTemporalA: 0 + NonTemporalB: 0 + NonTemporalC: 0 + NonTemporalD: 0 + NonTemporalE: 0 + NonTemporalMXSA: 0 + NonTemporalMXSB: 0 + NonTemporalMetadata: 0 + NonTemporalWS: 0 + NonVolatile: -1 + NonVolatileA: 0 + NonVolatileB: 0 + NonVolatileC: 0 + NonVolatileD: 0 + NonVolatileE: 0 + NonVolatileMXSA: 0 + NonVolatileMXSB: 0 + NonVolatileMetadata: 0 + NonVolatileWS: 0 + NumElementsPerBatchStore: 0 + NumElementsPerThread: 48 + NumGlobalWriteVectorsPerThread: 48 + NumLdsBlk: 2 + NumLoadsA: 6 + NumLoadsB: 8 + NumLoadsCoalescedA: 1 + NumLoadsCoalescedB: 1 + NumLoadsCoalescedMXSA: 1 + NumLoadsCoalescedMXSB: 1 + NumLoadsPerpendicularA: 6 + NumLoadsPerpendicularB: 8 + NumLoadsPerpendicularMXSA: 0 + NumLoadsPerpendicularMXSB: 0 + NumThreads: 256 + NumTotalPackedLoadsA: -1 + NumTotalPackedLoadsB: -1 + NumTotalPackedLoadsMXSA: 0 + NumTotalPackedLoadsMXSB: 0 + NumWaveSplitK: 1 + NumWaves: 4 + OptNoLoadLoop: 1 + PackedC0IdxChars: [I] + PackedC0IndicesX: [0] + PackedC1IdxChars: [J] + PackedC1IndicesX: [1] + PrefetchAcrossPersistent: 0 + PrefetchGL2: 0 + PrefetchGlobalRead: 2 + PrefetchLocalRead: 1 + PreloadKernArgs: true + SFCWGM: + - [1, 1] + - [1, 1] + ScheduleGROverBarrier: 0 + ScheduleGlobalRead: 1 + ScheduleIterAlg: 3 + ScheduleLocalWrite: 1 + SolutionIndex: 74 + SolutionNameMin: Cijk_Alik_Bljk_F4BS_MXAE8B32_MXBE8B32_BH_BiasSB_HAS_SAB_SAV_UserArgs_MT96x128x512_MI16x16x1_SN_LDSB0_AFC1_AG0_AGGSUA0_AGNTAB0_AFEM1_AFEM1_ASEM32_BL1_BS1_CD1_1_CLR1_CLS0_CADS0_DTLA0_DTLB0_DTLM0_DTVA0_DTVB0_DTVMXSA0_DTVMXSB0_DTVSM0_DPLB0_EPS0_ELFLR0_EMLLn1_FDSI0_GRPM1_GRVWA32_GRVWB32_GSU0_GSUAMB_GSUC0_GSUWGMRR0_GLS0_HPLR0_ISA950_ICIW0_IU1_K1_LDSTI0_LBSPPA0_LBSPPB0_LBSPPMXSA0_LBSPPMXSB0_LBSPPM0_LPA0_LPB0_LPMXSA0_LPMXSB0_LPM0_LRVWn1_LWPMn1_MIAV0_MIWT6_2_MXLIBL_MXSFHPS_MO40_MGRIPM3_NTn1_NTA0_NTB0_NTC0_NTD0_NTE0_NTMXSA0_NTMXSB0_NTM0_NTWS0_NVn1_NVA0_NVB0_NVC0_NVD0_NVE0_NVMXSA0_NVMXSB0_NVM0_NVWS0_NEPBS0_NLCA1_NLCB1_ONLL1_PAP0_PGL0_PGR2_PLR1_PKA1_SGROB0_SIA3_SS0_SU32_SUM0_SUS256_SPO0_SRVW0_SSO0_SVW4_SK3_SKFTR0_SKFDPO0_SKXCCM0_SNLL0_SIP1_SGRO0_TDMI0_TDMIM0_TDMS0_TIN0_THn1_THA0_THB0_THC0_THD0_THE0_THMXSA0_THMXSB0_THM0_THWS0_TLDS1_TLDSMn1_ULSGRO0_USL0_USLMX0_UDFMAC0_UIOFGRO0_UPLRP0_USFGRO0_USI1_VSn1_VWA1_VWB1_WSGRA0_WSGRB0_WS64_WG16_16_1_WGM0_WGMXCCn1_WGMXCCGn1 + SourceSwap: false + SpaceFillingAlgo: [] + StaggerU: 32 + StaggerUMapping: 0 + StaggerUStride: 256 + StorePriorityOpt: false + StoreRemapVectorWidth: 0 + StoreSwapAddr: false + StoreSyncOpt: 0 + StoreVectorWidth: 4 + StreamK: 3 + StreamKAtomic: 0 + StreamKFixupTreeReduction: 0 + StreamKForceDPOnly: 0 + StreamKXCCMapping: 0 + SubGroup0: 4 + SubGroup1: 64 + SubGroupA: 4 + SubGroupB: 64 + SubGroupMXSA: 4 + SubGroupMXSB: 64 + SuppressNoLoadLoop: false + SwInstructionPrefetch: true + SwapGlobalReadOrder: 0 + TDMInst: 0 + TDMIterateMode: 0 + TDMSplit: false + TailloopInNll: false + TemporalHint: -1 + TemporalHintA: 0 + TemporalHintB: 0 + TemporalHintC: 0 + TemporalHintD: 0 + TemporalHintE: 0 + TemporalHintMXSA: 0 + TemporalHintMXSB: 0 + TemporalHintMetadata: 0 + TemporalHintWS: 0 + ThreadTile: [1, 1] + ThreadTile0: 24 + ThreadTile1: 2 + ThreadTileA: 24 + ThreadTileB: 2 + ThreadTileMXSA: 24 + ThreadTileMXSB: 2 + TransposeLDS: 1 + TransposeLDSMetadata: -1 + ULSGRODoubleG2L: 0 + UnrollLoopSwapGlobalReadOrder: 0 + UnrollMajorLDSA: true + UnrollMajorLDSB: true + UnrollMajorLDSMXSA: true + UnrollMajorLDSMXSB: true + Use64bShadowLimit: false + Use64bShadowLimitMX: false + UseCustomMainLoopSchedule: 0 + UseDirect32XEmulation: false + UseDot2F32XEmulation: false + UseDotInstruction: false + UseDualFMAC: false + UseF32XEmulation: false + UseGeneralizedNLCOneA: false + UseGeneralizedNLCOneB: false + UseGeneralizedNLCOneMXSA: false + UseGeneralizedNLCOneMXSB: false + UseGeneralizedNLCOneMetadata: false + UseInstOffsetForGRO: 0 + UseMFMAF32XEmulation: false + UsePLRPack: 0 + UseSgprForGRO: 0 + UseSubtileImpl: true + Valid: true + VectorStore: -1 + VectorWidthA: 1 + VectorWidthB: 1 + VectorWidthMXSA: 1 + VectorWidthMXSB: 1 + WaveSeparateGlobalReadA: 0 + WaveSeparateGlobalReadB: 0 + WaveSeparateGlobalReadMXSA: 0 + WaveSeparateGlobalReadMXSB: 0 + WaveSeparateGlobalReadMetadata: 0 + WaveSplitK: false + WavefrontSize: 64 + WorkGroup: [16, 16, 1] + WorkGroupMapping: 0 + WorkGroupMappingXCC: -1 + WorkGroupMappingXCCGroup: -1 + WorkGroupReduction: false + WorkspaceCheck: [4, 0, 0] + _ABTilePairA: AB_B4 + _ABTilePairB: AB_B4 + _DepthU: 512 + _DepthUA: 512 + _DepthUB: 512 + _DepthUMXSA: 16 + _DepthUMXSB: 16 + _DepthUMetadata: 512 + _GlobalAccumulation: PartialsBuffer + _ScheduleIterAlg: 3 + _StinkyTofuOptLevel: 0 + _UseSgprForGRO: 0 + _VectorStore: 1 + _WorkspaceSizePerElemBias: 0 + _WorkspaceSizePerElemC: 4 + _inputVWA_was_auto: false + _inputVWB_was_auto: false + _staggerStrideShift: 0 + enableGLTrA: false + enableGLTrB: false + enableLDSTrA: false + enableLDSTrB: false + enableLDSTrMXSA: false + enableLDSTrMXSB: false + enableLDSTrMetadata: 0 + enableTDMA: false + enableTDMB: false + enableTDMMetadata: false + isTuned: true + ldsNumBytesA: 24576 + ldsNumBytesB: 32768 + ldsNumBytesMXSA: 1536 + ldsNumBytesMXSB: 2048 + ldsNumBytesMetadata: 0 + numSubTiles: 1 + reorderGRInstForDTVA: false + reorderGRInstForDTVB: false + tailLoopOptA: false + tailLoopOptB: false + tailLoopOptMXSA: false + tailLoopOptMXSB: false - null - null - null