[PATCH] D121411: [AMDGPU] Support v_mov_b64 in dpp combine

[Joe Nash via Phabricator via llvm-commits]

Joe_Nash accepted this revision.
Joe_Nash added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp:169
   case AMDGPU::COPY:
   case AMDGPU::V_MOV_B32_e32:
+  case AMDGPU::V_MOV_B64_PSEUDO:
----------------
rampitec wrote:
> foad wrote:
> > I wonder why we don't include V_MOV_B32_e64? Maybe we never use it for an immediate copy?
> Probably... Or perhaps it was just forgotten.
The only reason I can think of to use V_MOV_B32_e64 over V_MOV_B32_e32 is to use operand modifiers, and our backend doesn't even support those for V_MOV_B32_e64 :) But I agree it should be present here, for completeness.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D121411/new/

https://reviews.llvm.org/D121411