[llvm] DAG: Stop forcibly adding nsz to expanded minnum/maxnum (PR #139615)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-selectiondag

Author: Matt Arsenault (arsenm)

<details>
<summary>Changes</summary>

Fuzzy 0 handling is no longer a property assumed of these opcodes.

---
Full diff: https://github.com/llvm/llvm-project/pull/139615.diff


1 Files Affected:

- (modified) llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp (+1-3) 


``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index 856e9d813bcdd..a476b191abf62 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -8490,9 +8490,7 @@ TargetLowering::createSelectForFMINNUM_FMAXNUM(SDNode *Node,
     SDValue Op1 = Node->getOperand(0);
     SDValue Op2 = Node->getOperand(1);
     SDValue SelCC = DAG.getSelectCC(SDLoc(Node), Op1, Op2, Op1, Op2, Pred);
-    // Copy FMF flags, but always set the no-signed-zeros flag
-    // as this is implied by the FMINNUM/FMAXNUM semantics.
-    SelCC->setFlags(Node->getFlags() | SDNodeFlags::NoSignedZeros);
+    SelCC->setFlags(Node->getFlags());
     return SelCC;
   }
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/139615