[PATCH] D28833: AMDGPU: Generalize matching of v_med3_f32

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
Herald added a reviewer: tstellarAMD.
Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng, kzhuravl.

I think this is safe as long as no inputs are known to ever be nans.

      

Also add an intrinsic for fmed3 to be able to handle all safe math cases.


https://reviews.llvm.org/D28833

Files:
  include/llvm/IR/IntrinsicsAMDGPU.td
  lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
  lib/Target/AMDGPU/AMDGPUInstructions.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  lib/Target/AMDGPU/SIInstrInfo.td
  lib/Target/AMDGPU/SIInstructions.td
  test/CodeGen/AMDGPU/fmed3.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D28833.84763.patch
Type: text/x-patch
Size: 47046 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170118/85a97369/attachment.bin>