[llvm-branch-commits] [llvm] [InstCombine][AMDGPU] Fold select of intrinsics differing in one operand (PR #227737)

[Harrison Hao via llvm-branch-commits]

================
@@ -544,6 +586,9 @@ Instruction 
*InstCombinerImpl::foldSelectIntrinsic(SelectInst &SI) {
     return replaceInstUsesWith(SI, NewCall);
   }
   default:
+    if (isTriviallyVectorizable(IID))
+      return foldSelectIntoIntrinsicArg(SI, LHSIntrinsic, RHSIntrinsic,
+                                        Builder);
----------------
harrisonGPU wrote:

Thanks, I have removed it.

https://github.com/llvm/llvm-project/pull/227737
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits