[PATCH] D101481: [AMDGPU] Select V_CVT_*16_F16 more often

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Apr 30 15:42:41 PDT 2021


arsenm added a comment.

LGTM with nits



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2734-2737
+  if (SrcVT == MVT::f16) {
+    if (DestVT == MVT::i16)
+      return Op;
   }
----------------
Combine into one if? 


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2759
+    return LowerFP64_TO_INT(Op, DAG,
+                            OpOpcode == ISD::FP_TO_SINT ? true : false);
 
----------------
Don't need the ternary operator, just directly pass the bool expression


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101481/new/

https://reviews.llvm.org/D101481



More information about the llvm-commits mailing list