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
@@ -2258,15 +2258,24 @@
       return II;
     }
 
-    // fma x, 1, z -> fadd x, z
-    if (match(Src1, m_FPOne())) {
-      auto *FAdd = BinaryOperator::CreateFAdd(Src0, II->getArgOperand(2));
+    // Try to simplify the underlying FMul.
+    if (Value *V = SimplifyFMulInst(II->getArgOperand(0), II->getArgOperand(1),
+                                    II->getFastMathFlags(),
+                                    SQ.getWithInstruction(II))) {
+      if (match(V, m_FMul(m_Value(X), m_Value(Y)))) {
+        II->setArgOperand(0, X);
+        II->setArgOperand(1, Y);
+        return II;
+      }
+
+      auto *FAdd = BinaryOperator::CreateFAdd(V, 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
@@ -372,8 +372,7 @@
 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:    [[RES:%.*]] = call nnan nsz <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]]
+; 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)
@@ -383,8 +382,7 @@
 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:    [[RES:%.*]] = call nnan nsz <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]]
+; 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)
@@ -407,8 +405,7 @@
 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:    [[RES:%.*]] = call nnan 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]]
+; 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)
@@ -418,8 +415,7 @@
 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:    [[RES:%.*]] = call nnan 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]]
+; 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)
@@ -440,8 +436,7 @@
 define <2 x double> @fma_sqrt(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: @fma_sqrt(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[SQRT:%.*]] = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> [[A:%.*]])
-; CHECK-NEXT:    [[RES:%.*]] = call fast <2 x double> @llvm.fma.v2f64(<2 x double> [[SQRT]], <2 x double> [[SQRT]], <2 x double> [[B:%.*]])
+; CHECK-NEXT:    [[RES:%.*]] = fadd fast <2 x double> [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    ret <2 x double> [[RES]]
 ;
 entry: