[InstSimplify] reduce code duplication for fmul folds; NFC

The constant is already commuted for an fmul opcode,
but this code can be called more directly for fma,
so we have to swap for that caller. There are tests
in InstSimplify and InstCombine to verify that this
works as expected.

llvm/lib/Analysis/InstructionSimplify.cpp

@@ -5325,22 +5325,18 @@ static Value *simplifyFMAFMul(Value *Op0, Value *Op1, FastMathFlags FMF,
   if (!isDefaultFPEnvironment(ExBehavior, Rounding))
     return nullptr;
 
-  // fmul X, 1.0 ==> X
+  // Canonicalize constant as operand 1.
+  if (match(Op0, m_ImmConstant()))
+    std::swap(Op0, Op1);
+
+  // X * 1.0 --> X
   if (match(Op1, m_FPOne()))
     return Op0;
 
-  // fmul 1.0, X ==> X
-  if (match(Op0, m_FPOne()))
-    return Op1;
-
-  // fmul nnan nsz X, 0 ==> 0
+  // X * 0.0 --> 0.0 (with nnan and nsz)
   if (FMF.noNaNs() && FMF.noSignedZeros() && match(Op1, m_AnyZeroFP()))
     return ConstantFP::getNullValue(Op0->getType());
 
-  // fmul nnan nsz 0, X ==> 0
-  if (FMF.noNaNs() && FMF.noSignedZeros() && match(Op0, m_AnyZeroFP()))
-    return ConstantFP::getNullValue(Op1->getType());
-
   // sqrt(X) * sqrt(X) --> X, if we can:
   // 1. Remove the intermediate rounding (reassociate).
   // 2. Ignore non-zero negative numbers because sqrt would produce NAN.

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

@@ -161,9 +161,9 @@ define <2 x float> @fadd_x_n0_vec_undef_elt(<2 x float> %a) {
   ret <2 x float> %ret
 }
 
-; fmul X, 1.0 ==> X
-define double @fmul_X_1(double %a) {
-; CHECK-LABEL: @fmul_X_1(
+; fmul 1.0, X ==> X
+define double @fmul_1_X(double %a) {
+; CHECK-LABEL: @fmul_1_X(
 ; CHECK-NEXT:    ret double [[A:%.*]]
 ;
   %b = fmul double 1.0, %a