[PATCH] D21437: AMDGPU: Fold more custom nodes to undef

[Matt Arsenault via llvm-commits]

arsenm created this revision.
arsenm added a reviewer: tstellarAMD.
arsenm added a subscriber: llvm-commits.
Herald added subscribers: kzhuravl, arsenm.

This will help sneak undefs past GVN into the DAG for some tests.
    
Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors.


http://reviews.llvm.org/D21437

Files:
  include/llvm/IR/IntrinsicsAMDGPU.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/llvm.amdgcn.class.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.fract.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.ldexp.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.rcp.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.rsq.clamp.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.rsq.legacy.ll
  test/CodeGen/AMDGPU/llvm.amdgcn.rsq.ll
  test/CodeGen/AMDGPU/vi-removed-intrinsics.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D21437.60984.patch
Type: text/x-patch
Size: 14901 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160616/506c97ed/attachment.bin>