[PATCH] D125997: [AMDGPU] Instruction Type Pipeline

[Jeffrey Byrnes via Phabricator via llvm-commits]

jrbyrnes updated this revision to Diff 432422.
jrbyrnes marked an inline comment as done.
jrbyrnes added a comment.

Testing on CK uncovered an edge case error w/ the way bundle iteration was done.

Experimentation on gemm_xdl_fp16 shows ~6% improvement from this mutation


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D125997/new/

https://reviews.llvm.org/D125997

Files:
  llvm/lib/Target/AMDGPU/AMDGPUMFMAClustering.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMFMAClustering.h
  llvm/lib/Target/AMDGPU/AMDGPUMFMAIGroupLP.cpp
  llvm/lib/Target/AMDGPU/AMDGPUMFMAIGroupLP.h
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/lib/Target/AMDGPU/CMakeLists.txt
  llvm/test/CodeGen/AMDGPU/mfma-cluster-edges.mir
  llvm/test/CodeGen/AMDGPU/mfma-cluster.mir
  llvm/test/CodeGen/AMDGPU/mfma-igrouplp-dag-mutation.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D125997.432422.patch
Type: text/x-patch
Size: 65030 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220526/9b554ed5/attachment.bin>