[PATCH] D128682: [AMDGPU] gfx11 CodeGen for new DPP instructions

[Joe Nash via Phabricator via llvm-commits]

Joe_Nash created this revision.
Herald added subscribers: kosarev, jsilvanus, foad, kerbowa, kbarton, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, nemanjai, kzhuravl, arsenm.
Herald added a project: All.
Joe_Nash requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Modifies the GCNDPPCombine pass to enable DPP formation for the new DPP
instruction in gfx11, namely VOP3 encoded instructions with DPP and VOPC
with DPP.

Depends on D128656 <https://reviews.llvm.org/D128656>


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D128682

Files:
  llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
  llvm/lib/Target/AMDGPU/SIInstrInfo.h
  llvm/lib/Target/AMDGPU/SIInstrInfo.td
  llvm/lib/Target/AMDGPU/VOPInstructions.td
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.mov.dpp.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.update.dpp.ll
  llvm/test/CodeGen/AMDGPU/dpp64_combine.ll
  llvm/test/CodeGen/AMDGPU/dpp_combine.ll
  llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
  llvm/test/CodeGen/AMDGPU/vopc_dpp.mir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D128682.440385.patch
Type: text/x-patch
Size: 66501 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220627/681f156a/attachment.bin>