[llvm] [AMDGPU] 32-bit ABS is a legal DAG node (PR #163907)

via llvm-commits llvm-commits at lists.llvm.org
Thu Oct 16 21:53:32 PDT 2025


================
@@ -14945,6 +14945,13 @@ SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
     }
   }
 
+  // max(x, neg(x)) -> abs(x)
----------------
LU-JOHN wrote:

> Can we do this in the generic part?

All ISD::SMAX nodes are sent to this function from the switch in PerformDAGCombine.  I don't see where else to put it.  This function is intended to process min or max nodes so it makes sense to put it here.

https://github.com/llvm/llvm-project/pull/163907


More information about the llvm-commits mailing list