[PATCH] D134757: AMDGPU: Make various vector undefs legal

[Matt Arsenault via Phabricator via llvm-commits]

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

Surprisingly these were getting legalized to something
zero initialized.

     

This fixes an infinite loop when combining some vector types.
Also fixes zero initializing some undef values.

      

SimplifyDemandedVectorElts / SimplifyDemandedBits are not checking
for the legality of the output undefs they are replacing unused
operations with. This resulted in turnind vectors into undefs
that were later re-legalized back into zero vectors.


https://reviews.llvm.org/D134757

Files:
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/commute-shifts.ll
  llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
  llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll
  llvm/test/CodeGen/AMDGPU/extract-subvector-16bit.ll
  llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
  llvm/test/CodeGen/AMDGPU/select-undef.ll
  llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
  llvm/test/CodeGen/AMDGPU/v1024.ll
  llvm/test/CodeGen/AMDGPU/vgpr-tuple-allocation.ll
  llvm/test/CodeGen/AMDGPU/wmma_modifiers.ll
  llvm/test/CodeGen/AMDGPU/wqm.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D134757.463302.patch
Type: text/x-patch
Size: 55747 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220927/05543ca7/attachment-0001.bin>