[PATCH] D33860: [AMDGPU] Untangle SDWA pass from SIShrinkInstructions

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl.

Remove dependency of SDWA pass on SIShrinkInstructions.
The goal is to move SDWA even higher in the stack to avoid second run
of MachineLICM, MachineCSE and SIFoldOperands.

Also fixed bug uncovered with this change:
SDWA did not preserve original src modifiers.

TODO: Check what happens to incoming dst modifiers. They might be
lost as well.


Repository:
  rL LLVM

https://reviews.llvm.org/D33860

Files:
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/SIPeepholeSDWA.cpp
  test/CodeGen/AMDGPU/add.v2i16.ll
  test/CodeGen/AMDGPU/ashr.v2i16.ll
  test/CodeGen/AMDGPU/fabs.f16.ll
  test/CodeGen/AMDGPU/fadd.f16.ll
  test/CodeGen/AMDGPU/fcanonicalize.f16.ll
  test/CodeGen/AMDGPU/fmul.f16.ll
  test/CodeGen/AMDGPU/fneg-fabs.f16.ll
  test/CodeGen/AMDGPU/fneg.f16.ll
  test/CodeGen/AMDGPU/fptosi.f16.ll
  test/CodeGen/AMDGPU/fptoui.f16.ll
  test/CodeGen/AMDGPU/fsub.f16.ll
  test/CodeGen/AMDGPU/immv216.ll
  test/CodeGen/AMDGPU/insert_vector_elt.v2i16.ll
  test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll
  test/CodeGen/AMDGPU/llvm.maxnum.f16.ll
  test/CodeGen/AMDGPU/llvm.minnum.f16.ll
  test/CodeGen/AMDGPU/scratch-simple.ll
  test/CodeGen/AMDGPU/sdwa-peephole.ll
  test/CodeGen/AMDGPU/shl.v2i16.ll
  test/CodeGen/AMDGPU/sminmax.v2i16.ll
  test/CodeGen/AMDGPU/sub.v2i16.ll
  test/CodeGen/AMDGPU/v_mac_f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D33860.101309.patch
Type: text/x-patch
Size: 60540 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170603/aadaa28c/attachment.bin>