Index: lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -8626,15 +8626,19 @@
 
   switch (Intrinsic) {
   case Intrinsic::experimental_vector_reduce_fadd:
-    if (FMF.isFast())
+    if (FMF.isFast()) {
       Res = DAG.getNode(ISD::VECREDUCE_FADD, dl, VT, Op2);
-    else
+      if (!Op1.isUndef())
+        Res = DAG.getNode(ISD::FADD, dl, VT, Op1, Res);
+    } else
       Res = DAG.getNode(ISD::VECREDUCE_STRICT_FADD, dl, VT, Op1, Op2);
     break;
   case Intrinsic::experimental_vector_reduce_fmul:
-    if (FMF.isFast())
+    if (FMF.isFast()) {
       Res = DAG.getNode(ISD::VECREDUCE_FMUL, dl, VT, Op2);
-    else
+      if (!Op1.isUndef())
+        Res = DAG.getNode(ISD::FMUL, dl, VT, Op1, Res);
+    } else
       Res = DAG.getNode(ISD::VECREDUCE_STRICT_FMUL, dl, VT, Op1, Op2);
     break;
   case Intrinsic::experimental_vector_reduce_add:
Index: test/CodeGen/AArch64/vecreduce-fadd.ll
===================================================================
--- test/CodeGen/AArch64/vecreduce-fadd.ll
+++ test/CodeGen/AArch64/vecreduce-fadd.ll
@@ -92,6 +92,33 @@
   ret double %r
 }
 
+define half @add_H_init42(<8 x half> %bin.rdx)  {
+; CHECK-LABEL: add_H_init42:
+; CHECK:       faddp h0, v0.2h
+; CHECK:       fadd h0
+; CHECK-NEXT:  ret
+  %r = call fast half @llvm.experimental.vector.reduce.fadd.f16.v8f16(half 42.0, <8 x half> %bin.rdx)
+  ret half %r
+}
+
+define float @add_S_init42(<4 x float> %bin.rdx)  {
+; CHECK-LABEL: add_S_init42:
+; CHECK:       faddp s0, v0.2s
+; CHECK:       fadd s0
+; CHECK-NEXT:  ret
+  %r = call fast float @llvm.experimental.vector.reduce.fadd.f32.v4f32(float 42.0, <4 x float> %bin.rdx)
+  ret float %r
+}
+
+define double @add_D_init42(<2 x double> %bin.rdx)  {
+; CHECK-LABEL: add_D_init42:
+; CHECK:       faddp d0, v0.2d
+; CHECK:       fadd d0
+; CHECK-NEXT:  ret
+  %r = call fast double @llvm.experimental.vector.reduce.fadd.f64.v2f64(double 42.0, <2 x double> %bin.rdx)
+  ret double %r
+}
+
 ; Function Attrs: nounwind readnone
 declare half @llvm.experimental.vector.reduce.fadd.f16.v4f16(half, <4 x half>)
 declare half @llvm.experimental.vector.reduce.fadd.f16.v8f16(half, <8 x half>)