[PATCH] D116270: [AMDGPU] Enable divergence-driven XNOR selection

[Alexander via Phabricator via llvm-commits]

alex-t created this revision.
alex-t added a reviewer: rampitec.
Herald added subscribers: foad, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
alex-t requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

Currently not (xor_one_use) pattern is always selected to S_XNOR irrelative od the node divergence.
This relies on further custom selection pass which converts to VALU if necessary and replaces with V_NOT_B32 ( V_XOR_B32)
on those targets which have no V_XNOR.
Current change enables the patterns which explicitly select the not (xor_one_use) to appropriate form.
We assume that xor (not) is already turned into the not (xor) by the combiner.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D116270

Files:
  llvm/lib/Target/AMDGPU/SOPInstructions.td
  llvm/lib/Target/AMDGPU/VOP2Instructions.td
  llvm/lib/Target/AMDGPU/VOPInstructions.td
  llvm/test/CodeGen/AMDGPU/divergence-driven-xnor.ll
  llvm/test/CodeGen/AMDGPU/fused-bitlogic.ll
  llvm/test/CodeGen/AMDGPU/xnor.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D116270.396158.patch
Type: text/x-patch
Size: 6691 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211224/1532dc96/attachment.bin>