================
@@ -332,6 +332,19 @@ KnownFPClass KnownFPClass::fmul(const KnownFPClass
&KnownLHS,
return Known;
}
+KnownFPClass KnownFPClass::fma(const KnownFPClass &KnownLHS,
+ const KnownFPClass &KnownRHS,
+ const KnownFPClass &KnownAddend,
+ DenormalMode Mode) {
+ return fadd(fmul(KnownLHS, KnownRHS, Mode), KnownAddend, Mode);
----------------
dtcxzyw wrote:
Does it really work for fused-mul-add? I cannot prove/disprove this. I'd
suggest passing DenormalMode::Dynamic() to fmul/square since fma doesn't round
the intermediate result (I assume FTZ/DAZ don't apply either).
https://github.com/llvm/llvm-project/pull/175614
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
