[PATCH] D77020: AMDGPU/GlobalISel: Combines for V_CVT_F32_UBYTE[0-3]

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: nhaehnle, kerbowa, foad, hsmhsm.
Herald added subscribers: hiraditya, t-tye, tpr, dstuttard, rovka, yaxunl, wdng, jvesely, kzhuravl.

Ports the existing DAG combines, minus the simplify demanded bits
which seems to have no equivalent now. Without these, this isn't
particularly helpful in most of the IR sample cases.


https://reviews.llvm.org/D77020

Files:
  llvm/lib/Target/AMDGPU/AMDGPUCombine.td
  llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/GlobalISel/combine-amdgpu-cvt-f32-ubyte.mir
  llvm/test/CodeGen/AMDGPU/GlobalISel/cvt_f32_ubyte.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D77020.253437.patch
Type: text/x-patch
Size: 69636 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200329/10d106b6/attachment-0001.bin>