[PATCH] D132079: [AMDGPU] Add iglp_opt builtin and MFMA GEMM Opt strategy

[Austin Kerbow via Phabricator via cfe-commits]

kerbowa created this revision.
kerbowa added reviewers: jrbyrnes, rampitec.
Herald added subscribers: kosarev, ormris, foad, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
Herald added a project: All.
kerbowa requested review of this revision.
Herald added subscribers: llvm-commits, cfe-commits, wdng.
Herald added projects: clang, LLVM.

Adds a builtin that serves as an optimization hint to apply specific optimized
DAG mutations during scheduling. This also disables any other mutations or
clustering that may interfere with the desired pipeline. The first optimization
strategy that is added here is designed to improve the performance of small gemm
kernels on gfx90a.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D132079

Files:
  clang/include/clang/Basic/BuiltinsAMDGPU.def
  clang/test/CodeGenOpenCL/builtins-amdgcn.cl
  clang/test/SemaOpenCL/builtins-amdgcn-error.cl
  llvm/include/llvm/IR/IntrinsicsAMDGPU.td
  llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.cpp
  llvm/lib/Target/AMDGPU/AMDGPUIGroupLP.h
  llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
  llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
  llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/lib/Target/AMDGPU/SIPostRABundler.cpp
  llvm/test/CodeGen/AMDGPU/igrouplp-dag-mutation.ll
  llvm/test/CodeGen/AMDGPU/igrouplp-dag-mutation.mir
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.iglp.opt.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.sched.group.barrier.ll
  llvm/test/CodeGen/AMDGPU/sched-group-barrier-pipeline-solver.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D132079.453455.patch
Type: text/x-patch
Size: 151114 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220817/70712fac/attachment-0001.bin>