[PATCH] D34973: AMDGPU: Add macro fusion schedule DAG mutation

[Matt Arsenault via Phabricator via llvm-commits]

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

Try to increase opportunities to shrink vcc uses.


https://reviews.llvm.org/D34973

Files:
  lib/Target/AMDGPU/AMDGPUMacroFusion.cpp
  lib/Target/AMDGPU/AMDGPUMacroFusion.h
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
  lib/Target/AMDGPU/CMakeLists.txt
  test/CodeGen/AMDGPU/addrspacecast.ll
  test/CodeGen/AMDGPU/ctlz.ll
  test/CodeGen/AMDGPU/ctlz_zero_undef.ll
  test/CodeGen/AMDGPU/fcmp.f16.ll
  test/CodeGen/AMDGPU/inline-asm.ll
  test/CodeGen/AMDGPU/macro-fusion-cluster-vcc-uses.mir
  test/CodeGen/AMDGPU/multi-divergent-exit-region.ll
  test/CodeGen/AMDGPU/sad.ll
  test/CodeGen/AMDGPU/select.f16.ll
  test/CodeGen/AMDGPU/setcc.ll
  test/CodeGen/AMDGPU/uaddo.ll
  test/CodeGen/AMDGPU/usubo.ll
  test/CodeGen/AMDGPU/v_cndmask.ll
  test/CodeGen/AMDGPU/vselect.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D34973.105138.patch
Type: text/x-patch
Size: 49302 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170704/f3d9c18a/attachment-0001.bin>