Add backend-keyed to_backend; make cuda/rocm aliases#302
Merged
Conversation
Introduce `to_backend(backend::KA.Backend, x)` — moves `x` onto a given KernelAbstractions backend. CPU is identity (CPU-built data already lives on the CPU backend); CUDABackend/ROCBackend are provided by the CUDA and AMDGPU package extensions. An unknown backend errors with a hint to load the corresponding GPU package. This lets downstream packages select a device by passing a KA.Backend object, instead of depending on CUDA.jl/AMDGPU.jl directly and calling the named cuda()/rocm() functions. cuda(x) and rocm(x) are kept as back-compat aliases that delegate to to_backend. FEC test suite passes.
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #302 +/- ##
==========================================
+ Coverage 55.00% 61.33% +6.32%
==========================================
Files 55 55
Lines 4801 4811 +10
==========================================
+ Hits 2641 2951 +310
+ Misses 2160 1860 -300 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
cmhamel
approved these changes
May 27, 2026
| # Move `x` onto the given KernelAbstractions backend. CPU is identity — | ||
| # CPU-built data already lives on the CPU backend. GPU backends (CUDABackend, | ||
| # ROCBackend) are provided by the CUDA / AMDGPU package extensions. | ||
| to_backend(::KA.CPU, x) = x |
Contributor
There was a problem hiding this comment.
My only suggestion here is that in the future we add an additional method to_host(x) = to_backend(KA.CPU(), x)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduce
to_backend(backend::KA.Backend, x)— movesxonto a givenKernelAbstractions backend. CPU is identity (CPU-built data already lives
on the CPU backend); CUDABackend/ROCBackend are provided by the CUDA and
AMDGPU package extensions. An unknown backend errors with a hint to load
the corresponding GPU package.
This lets downstream packages select a device by passing a KA.Backend
object, instead of depending on CUDA.jl/AMDGPU.jl directly and calling
the named cuda()/rocm() functions.
cuda(x) and rocm(x) are kept as back-compat aliases that delegate to
to_backend. FEC test suite passes.