Skip to content

[ROCm] fix kernel explorer GemmSoftmaxGemm test#16735

Merged
PeixuanZuo merged 2 commits into
mainfrom
peixuanzuo/fix_ke
Jul 18, 2023
Merged

[ROCm] fix kernel explorer GemmSoftmaxGemm test#16735
PeixuanZuo merged 2 commits into
mainfrom
peixuanzuo/fix_ke

Conversation

@PeixuanZuo
Copy link
Copy Markdown
Contributor

@PeixuanZuo PeixuanZuo commented Jul 17, 2023

GemmSoftmaxGemmTunble occasionally broken with large numerical error. The root cause of this error is CK's Strided Batched Gemm has larger error under a specific initialization distribution (multinormal_distribution).

Generic(Gemm1 + Softmax + Gemm2) implementation is one instance of GemmSoftmaxGemmTunble. Gemm1 and Gemm2 in Generic implementation are TunableOps when tuning enabled. In some case GemmSoftmaxGemmTunble select Generic implentation, while Gemm1 or Gemm2 select ck implementation, the result of GemmSoftmaxGemmTunble affect by CK.

  • Make tolerance more loosen.
  • Add GemmSoftmaxGemmPermuteGenericNestedTunable to test Generic implementation with tuning enabled.

@PeixuanZuo PeixuanZuo requested a review from cloudhan July 18, 2023 03:19
@PeixuanZuo PeixuanZuo merged commit 9b549c6 into main Jul 18, 2023
@PeixuanZuo PeixuanZuo deleted the peixuanzuo/fix_ke branch July 18, 2023 08:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants