diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -2240,6 +2240,22 @@
     if (Instruction *I = canonicalizeConstantArg0ToArg1(CI))
       return I;
 
+    // Try to simplify the underlying FMul.
+    if (Value *V = SimplifyFMulInst(II->getArgOperand(0), II->getArgOperand(1),
+                                    II->getFastMathFlags(),
+                                    SQ.getWithInstruction(II))) {
+      Value *RHS, *LHS;
+      if (match(V, m_FMul(m_Value(LHS), m_Value(RHS)))) {
+        II->setArgOperand(0, LHS);
+        II->setArgOperand(1, LHS);
+        return II;
+      }
+
+      auto *FAdd = BinaryOperator::CreateFAdd(V, II->getArgOperand(2));
+      FAdd->copyFastMathFlags(II);
+      return FAdd;
+    }
+
     // fma fneg(x), fneg(y), z -> fma x, y, z
     Value *Src0 = II->getArgOperand(0);
     Value *Src1 = II->getArgOperand(1);
@@ -2258,15 +2274,9 @@
       return II;
     }
 
-    // fma x, 1, z -> fadd x, z
-    if (match(Src1, m_FPOne())) {
-      auto *FAdd = BinaryOperator::CreateFAdd(Src0, II->getArgOperand(2));
-      FAdd->copyFastMathFlags(II);
-      return FAdd;
-    }
-
     break;
   }
+
   case Intrinsic::fabs: {
     Value *Cond;
     Constant *LHS, *RHS;
diff --git a/llvm/test/Transforms/InstCombine/fma.ll b/llvm/test/Transforms/InstCombine/fma.ll
--- a/llvm/test/Transforms/InstCombine/fma.ll
+++ b/llvm/test/Transforms/InstCombine/fma.ll
@@ -182,7 +182,7 @@
 
 define float @fmuladd_fneg_x_fneg_y_fast(float %x, float %y, float %z) {
 ; CHECK-LABEL: @fmuladd_fneg_x_fneg_y_fast(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    [[FMULADD:%.*]] = fadd fast float [[TMP1]], [[Z:%.*]]
 ; CHECK-NEXT:    ret float [[FMULADD]]
 ;
@@ -194,7 +194,7 @@
 
 define float @fmuladd_unary_fneg_x_unary_fneg_y_fast(float %x, float %y, float %z) {
 ; CHECK-LABEL: @fmuladd_unary_fneg_x_unary_fneg_y_fast(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[Y:%.*]], [[X:%.*]]
 ; CHECK-NEXT:    [[FMULADD:%.*]] = fadd fast float [[TMP1]], [[Z:%.*]]
 ; CHECK-NEXT:    ret float [[FMULADD]]
 ;
@@ -369,5 +369,72 @@
   ret float %fmuladd
 }
 
+define <2 x double> @fmuladd_a_0_b(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fmuladd_a_0_b(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
+;
+entry:
+  %res = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> %a, <2 x double> zeroinitializer, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+define <2 x double> @fmuladd_0_a_b(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fmuladd_0_a_b(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
+;
+entry:
+  %res = call nnan nsz <2 x double> @llvm.fmuladd.v2f64(<2 x double> zeroinitializer, <2 x double> %a, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+define <2 x double> @fmuladd_a_0_b_missing_flags(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fmuladd_a_0_b_missing_flags(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[RES:%.*]] = call nnan <2 x double> @llvm.fmuladd.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[RES]]
+;
+entry:
+  %res = call nnan <2 x double> @llvm.fmuladd.v2f64(<2 x double> %a, <2 x double> zeroinitializer, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+declare <2 x double> @llvm.fmuladd.v2f64(<2 x double>, <2 x double>, <2 x double>)
+
+define <2 x double> @fma_a_0_b(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fma_a_0_b(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
+;
+entry:
+  %res = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> zeroinitializer, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+define <2 x double> @fma_0_a_b(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fma_0_a_b(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret <2 x double> [[B:%.*]]
+;
+entry:
+  %res = call nnan nsz <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> %a, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+define <2 x double> @fma_0_a_b_missing_flags(<2 x double> %a, <2 x double> %b) {
+; CHECK-LABEL: @fma_0_a_b_missing_flags(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[RES:%.*]] = call nsz <2 x double> @llvm.fma.v2f64(<2 x double> [[A:%.*]], <2 x double> zeroinitializer, <2 x double> [[B:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[RES]]
+;
+entry:
+  %res = call nsz <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> %a, <2 x double> %b)
+  ret <2 x double> %res
+}
+
+declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
+
+
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }