[PATCH] D112317: [AMDGPU] Fix latency for implicit vcc_lo operands on GFX10 wave32

[Jay Foad via Phabricator via llvm-commits]

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

As described in the comment, the way we change vcc to vcc_lo in these
operands confuses addPhysRegDataDeps into treating them as implicit
pseudo operands. Fix this by setting the correct latency from the
SchedModel after addPhysRegDataDeps wrongly set it to 0.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D112317

Files:
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/lib/Target/AMDGPU/SIInstrInfo.h
  llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.div.fmas.ll
  llvm/test/CodeGen/AMDGPU/ds-sub-offset.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D112317.381546.patch
Type: text/x-patch
Size: 4926 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211022/c35fd288/attachment.bin>