[llvm] [LV] Vectorize maxnum/minnum w/o fast-math flags. (PR #148239)

[Florian Hahn via llvm-commits]

================
@@ -1021,8 +1022,9 @@ for.body:                                         ; preds = %entry, %for.body
   br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
 }
 
+; This can be vectorized with additional runtime checks for NaNs.
----------------
fhahn wrote:

Updated to check for the additional FCmp, thanks

https://github.com/llvm/llvm-project/pull/148239