Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[GEMM Codegen] Add epilogue fusion support. #329

Merged
merged 1 commit into from
Jun 19, 2024

Conversation

Xinyu302
Copy link

Analysis of the linalg.copy op which copies shared memory back to global memory and fuses the linalg.generic after it. Add an example of fused matmul and relu.

@Xinyu302 Xinyu302 changed the title [Gemm Codegen] Add epilogue fusion support. [GEMM Codegen] Add epilogue fusion support. Jun 12, 2024
@XG-zheng XG-zheng merged commit d81a078 into bytedance:main Jun 19, 2024
3 checks passed
Vremold added a commit that referenced this pull request Jul 4, 2024
  - 92ca4b6 [compiler] remove useless cat ops (#351)
  - 78b1d16 [compiler] fix missing return value in removeCopy (#355)
  - d81a078 [GEMM Codegen] Add epilogue fusion support. (#329)
  - dec2e5a [torch-frontend] mark attention rewriter test (#353)
  - cff508b [onnx] fix l2norm to custom call (#349)
  - 3739b4d [tf-frontend] lowering tf.if -> tf.if_region -> scf.if (#...
  - c32a17b [compiler] attach  attr to shape func (#346)
  - b6dffa5 [e2e] add testset for every backend (#348)
  - a5987bc [compiler] fuse transposeOp into dotGeneralOp (#344)
  - 4b19634 [e2e] support profile mode (#341)
  (And 16 more changes)

GitOrigin-RevId: 92ca4b6
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