[PATCH] D36292: AMDGPU: Add pass to cleanup DAG SALU/VALU messes

[Matt Arsenault via Phabricator via llvm-commits]

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

This is a pass for selecting instructions which
should be patterns, if we were aware of whether
it's a scalar or vector operation.

For now select v_cvt_pk_u16_u32 with it. This should
be enabled for SDWA subtargets, but that requires more
work and test updates.


https://reviews.llvm.org/D36292

Files:
  lib/Target/AMDGPU/AMDGPU.h
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/CMakeLists.txt
  lib/Target/AMDGPU/SIFixupVectorISel.cpp
  lib/Target/AMDGPU/SIInstrInfo.cpp
  lib/Target/AMDGPU/SIInstrInfo.h
  test/CodeGen/AMDGPU/ashr.v2i16.ll
  test/CodeGen/AMDGPU/cvt_f32_ubyte.ll
  test/CodeGen/AMDGPU/fabs.f16.ll
  test/CodeGen/AMDGPU/fadd.f16.ll
  test/CodeGen/AMDGPU/fmul.f16.ll
  test/CodeGen/AMDGPU/fptosi.f16.ll
  test/CodeGen/AMDGPU/fptrunc.f16.ll
  test/CodeGen/AMDGPU/fsub.f16.ll
  test/CodeGen/AMDGPU/half.ll
  test/CodeGen/AMDGPU/llvm.ceil.f16.ll
  test/CodeGen/AMDGPU/llvm.cos.f16.ll
  test/CodeGen/AMDGPU/llvm.exp2.f16.ll
  test/CodeGen/AMDGPU/llvm.floor.f16.ll
  test/CodeGen/AMDGPU/llvm.fma.f16.ll
  test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll
  test/CodeGen/AMDGPU/llvm.log2.f16.ll
  test/CodeGen/AMDGPU/llvm.maxnum.f16.ll
  test/CodeGen/AMDGPU/llvm.minnum.f16.ll
  test/CodeGen/AMDGPU/llvm.rint.f16.ll
  test/CodeGen/AMDGPU/llvm.sin.f16.ll
  test/CodeGen/AMDGPU/llvm.sqrt.f16.ll
  test/CodeGen/AMDGPU/llvm.trunc.f16.ll
  test/CodeGen/AMDGPU/load-weird-sizes.ll
  test/CodeGen/AMDGPU/lshr.v2i16.ll
  test/CodeGen/AMDGPU/scalar_to_vector.ll
  test/CodeGen/AMDGPU/shl.v2i16.ll
  test/CodeGen/AMDGPU/sitofp.f16.ll
  test/CodeGen/AMDGPU/uitofp.f16.ll
  test/CodeGen/AMDGPU/v_mac_f16.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36292.109649.patch
Type: text/x-patch
Size: 79039 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170803/1b4ae29c/attachment.bin>