[CINN] x86 runtime intrinsics for composite reduce #72371
Merged
Conversation
This file contains 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
|
你的PR提交成功，感谢你对开源项目的贡献! |
This was referenced Apr 19, 2025
lshpku
approved these changes
Apr 21, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
PR Category
CINN
PR Types
Improvements
Description
The following PRs forms the support for x86 end composite reduce (Welford variance & argmin/argmax):
This PR adds the intrinsic functions on the x86 end to support composite reduce ops. Note that, due to the ABI optimization of LLVM, functions defined in
cinn_runtimebasically do the same thing as those incinn_cuda_runtime_source, but the function signatures differ a lot (on x86 end, most of the struct in/outputs are pointer-typed).Also, we removed
pd_op.variance,cinn_op.argmax,cinn_op.argminfrom the denied ops on CPU. These kernels are now allowed to be generated on x86 end.Pcard-89620