[InstSimply] Simplify (fmul -x, +/-0) -> -/+0

We already handle the `+x` case, and noticed it was missing in the bug
affecting #82555

Proofs: https://alive2.llvm.org/ce/z/WUSvmV

Author: goldsteinn

llvm/lib/Analysis/InstructionSimplify.cpp

@@ -5767,11 +5767,18 @@ static Value *simplifyFMAFMul(Value *Op0, Value *Op1, FastMathFlags FMF,
     if (FMF.noNaNs() && FMF.noSignedZeros())
       return ConstantFP::getZero(Op0->getType());
 
-    // +normal number * (-)0.0 --> (-)0.0
     KnownFPClass Known =
         computeKnownFPClass(Op0, FMF, fcInf | fcNan, /*Depth=*/0, Q);
-    if (Known.SignBit == false && Known.isKnownNever(fcInf | fcNan))
-      return Op1;
+    if (Known.isKnownNever(fcInf | fcNan)) {
+      // +normal number * (-)0.0 --> (-)0.0
+      if (Known.SignBit == false)
+        return Op1;
+      // -normal number * (-)0.0 --> -(-)0.0
+      if (Known.SignBit == true)
+        return match(Op1, m_PosZeroFP())
+                   ? ConstantFP::getNegativeZero(Op0->getType())
+                   : ConstantFP::getZero(Op0->getType());
+    }
   }
 
   // sqrt(X) * sqrt(X) --> X, if we can:

llvm/test/Transforms/InstSimplify/floating-point-arithmetic.ll

@@ -213,17 +213,15 @@ define double @fmul_nnan_ninf_nneg_n0.0_commute(i127 %x) {
 
 define float @src_mul_nzero_neg(float nofpclass(inf nan pzero psub pnorm) %f) {
 ; CHECK-LABEL: @src_mul_nzero_neg(
-; CHECK-NEXT:    [[R:%.*]] = fmul float [[F:%.*]], -0.000000e+00
-; CHECK-NEXT:    ret float [[R]]
+; CHECK-NEXT:    ret float 0.000000e+00
 ;
   %r = fmul float %f, -0.0
   ret float %r
 }
 
 define float @src_mul_zero_neg(float nofpclass(inf nan pzero psub pnorm) %f) {
 ; CHECK-LABEL: @src_mul_zero_neg(
-; CHECK-NEXT:    [[R:%.*]] = fmul float [[F:%.*]], 0.000000e+00
-; CHECK-NEXT:    ret float [[R]]
+; CHECK-NEXT:    ret float -0.000000e+00
 ;
   %r = fmul float %f, 0.0
   ret float %r