[PATCH] D73483: [AMDGPU] fixed divergence driven shift operations selection

[Alexander via Phabricator via llvm-commits]

alex-t created this revision.
alex-t added reviewers: arsenm, rampitec.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
Herald added a project: LLVM.

change https://reviews.llvm.org/D64725 removes “isDivergent” predicates from the scalar shifts.
As a result we easy can select S_LSHL_B32 for divergent arguments.


https://reviews.llvm.org/D73483

Files:
  llvm/lib/Target/AMDGPU/SOPInstructions.td
  llvm/lib/Target/AMDGPU/VOP2Instructions.td
  llvm/lib/Target/AMDGPU/VOP3Instructions.td
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-add.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-ashr.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-ctpop.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-lshr.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-shl.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-sub.mir
  llvm/test/CodeGen/AMDGPU/ashr.v2i16.ll
  llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
  llvm/test/CodeGen/AMDGPU/commute-shifts.ll
  llvm/test/CodeGen/AMDGPU/extract-lowbits.ll
  llvm/test/CodeGen/AMDGPU/inline-asm.ll
  llvm/test/CodeGen/AMDGPU/lshr.v2i16.ll
  llvm/test/CodeGen/AMDGPU/sext-in-reg.ll
  llvm/test/CodeGen/AMDGPU/shl.v2i16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D73483.240590.patch
Type: text/x-patch
Size: 25480 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200127/4819893d/attachment-0001.bin>