Request for supporting Krackan Point models (eg. Ryzen AI 7 350)

[johncs]

Hi,

I have an AMD Ryzen AI 7 350, which is a Krackan Point, and wanted to provide some vital information to help with adding/refining support in ryzenadj in the future. If you need more data let me know.

Overview

Architecture:
Core design: Big.LITTLE (similar to ARM-style)
➔ 4x Zen 5 performance cores + 4x Zen 5c efficiency cores
Fabrication node: TSMC 4nm (high-density, low-power)
Code name: Kraken Point (part of Ryzen AI 300 series)

Total Cores: 8 (4P + 4E)
Total Threads: 16
Base Frequency (P-cores): ~2.0 GHz
Boost Frequency (P-cores): ~5.0 GHz
Boost Frequency (E-cores): ~3.5 GHz
L3 Cache: 16MB Shared
L2 Cache: 1MB per core

CPUs 0,2,4,6,8,10,12,14 → 5090 MHz → Zen 5 Performance Cores
CPUs 1,3,5,7,9,11,13,15 → 3506 MHz → Zen 5c Efficiency Cores

CPU Info (lscpu & uname -r):

Architecture:             x86_64
  CPU op-mode(s):         32-bit, 64-bit
  Address sizes:          48 bits physical, 48 bits virtual
  Byte Order:             Little Endian
CPU(s):                   16
  On-line CPU(s) list:    0-15
Vendor ID:                AuthenticAMD
  Model name:             AMD Ryzen AI 7 350 w/ Radeon 860M
    CPU family:           26
    Model:                96
    Thread(s) per core:   2
    Core(s) per socket:   8
    Socket(s):            1
    Stepping:             0
    Frequency boost:      disabled
    CPU(s) scaling MHz:   70%
    CPU max MHz:          2000.0000
    CPU min MHz:          599.0000
    BogoMIPS:             3992.51
    Flags:                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36
                           clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp
                           lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid e
                          xtd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 
                          sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm ex
                          tapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wd
                          t tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_
                          l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced v
                          mmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a a
                          vx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha
                          _ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_
                          llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero 
                          irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save 
                          tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold 
                          avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku o
                          spke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512
                          _vpopcntdq rdpid bus_lock_detect movdiri movdir64b overflow_recov succo
                          r smca fsrm avx512_vp2intersect flush_l1d amd_lbr_pmc_freeze
Virtualization features:  
  Virtualization:         AMD-V
Caches (sum of all):      
  L1d:                    384 KiB (8 instances)
  L1i:                    256 KiB (8 instances)
  L2:                     8 MiB (8 instances)
  L3:                     16 MiB (1 instance)
NUMA:                     
  NUMA node(s):           1
  NUMA node0 CPU(s):      0-15
Vulnerabilities:          
  Gather data sampling:   Not affected
  Ghostwrite:             Not affected
  Itlb multihit:          Not affected
  L1tf:                   Not affected
  Mds:                    Not affected
  Meltdown:               Not affected
  Mmio stale data:        Not affected
  Reg file data sampling: Not affected
  Retbleed:               Not affected
  Spec rstack overflow:   Mitigation; IBPB on VMEXIT only
  Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
  Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
  Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-o
                          n; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
  Srbds:                  Not affected
  Tsx async abort:        Not affected

RyzenAdj Version (git rev-parse HEAD):

c9b07e009a51c2fb9a6fc40ea74fbee27994b4a5

RyzenAdj Info (sudo ./ryzenadj -i):

Fam1ah: unsupported model 96
Unsupported family: 1ah
Only Ryzen Mobile Series are supported
Unable to init ryzenadj

RyzenAdj SMU Table (sudo ./ryzenadj --dump-table):

Fam1ah: unsupported model 96
Unsupported family: 1ah
Only Ryzen Mobile Series are supported
Unable to init ryzenadj

[stefanor]

There is some initial support in 0c05bdc (#368)

But not enough to make any adjustments yet.

[inode64]

Check my fork https://github.com/inode64/RyzenAdj/tree/feature/Dragon-Range

[kariudo]

Check my fork https://github.com/inode64/RyzenAdj/tree/feature/Dragon-Range

Are you citing this PR as a resolution? It does not appear to be currently associated with this issue.
#408

[oxGorou]

You can check out my Python rewrite of ryzenadj at https://github.com/HorizonUnix/ZenMaster