[PATCH] D22328: AMDGPU: Remove legacy rsq.clamped intrinsic

[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.

Mesa still has a use of llvm.AMDGPU.rsq.f64 remaining.
    
Also fix mismatch with non-IEEE rsq selecting to IEEE rsq.



http://reviews.llvm.org/D22328

Files:
  include/llvm/IR/IntrinsicsAMDGPU.td
  lib/Target/AMDGPU/AMDGPUIntrinsics.td
  lib/Target/AMDGPU/R600ISelLowering.cpp
  lib/Target/AMDGPU/R600Instructions.td
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/big_alu.ll
  test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.f64.ll
  test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.clamped.ll
  test/CodeGen/AMDGPU/llvm.AMDGPU.rsq.ll
  test/CodeGen/AMDGPU/llvm.r600.recipsqrt.clamped.ll
  test/CodeGen/AMDGPU/llvm.r600.recipsqrt.ieee.ll
  test/CodeGen/AMDGPU/pv.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D22328.63900.patch
Type: text/x-patch
Size: 15145 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160714/c4120a6d/attachment.bin>