[PATCH] D42302: AMDGPU: Allow a SGPR for the conditional KILL operand.

[Bas Nieuwenhuizen via Phabricator via llvm-commits]

bnieuwenhuizen created this revision.
bnieuwenhuizen added reviewers: arsenm, mareko, nhaehnle.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, wdng, kzhuravl.

Just use the _e64 variant if needed. This should be possible as per

def : Pat <

  (int_amdgcn_kill (i1 (setcc f32:$src, InlineFPImm<f32>:$imm, cond:$cond))),
  (SI_KILL_F32_COND_IMM_PSEUDO $src, (bitcast_fpimm_to_i32 $imm), (cond_as_i32imm $cond))

> ;

I don't think we can get an immediate for the other operand for which we
need the second 32-bit word.


Repository:
  rL LLVM

https://reviews.llvm.org/D42302

Files:
  lib/Target/AMDGPU/SIInsertSkips.cpp
  test/CodeGen/AMDGPU/llvm.amdgcn.kill.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D42302.130627.patch
Type: text/x-patch
Size: 4246 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180119/f790c5aa/attachment.bin>