diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 14880e40881..c6a79a2df5f 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -40114,11 +40114,10 @@ static SDValue combineInsertSubvector(SDNode *N, SelectionDAG &DAG,
             return Ld;
         }
       }
-      // If lower/upper loads are the same and the only users of the load, then
-      // lower to a VBROADCASTF128/VBROADCASTI128/etc.
+      // If lower/upper loads are the same and there's no other use of the lower
+      // load, then splat the loaded value with a broadcast.
       if (auto *Ld = dyn_cast<LoadSDNode>(peekThroughOneUseBitcasts(SubVec2)))
-        if (SubVec2 == SubVec && ISD::isNormalLoad(Ld) &&
-            SDNode::areOnlyUsersOf({N, Vec.getNode()}, SubVec2.getNode()))
+        if (SubVec2 == SubVec && ISD::isNormalLoad(Ld) && Vec.hasOneUse())
           return DAG.getNode(X86ISD::SUBV_BROADCAST, dl, OpVT, SubVec);
 
       // If this is subv_broadcast insert into both halves, use a larger
diff --git a/test/CodeGen/X86/avx-vbroadcastf128.ll b/test/CodeGen/X86/avx-vbroadcastf128.ll
index e35919d4f32..9bd41796e58 100644
--- a/test/CodeGen/X86/avx-vbroadcastf128.ll
+++ b/test/CodeGen/X86/avx-vbroadcastf128.ll
@@ -106,16 +106,14 @@ define void @subv_reuse_is_ok(<4 x float>* %a, <8 x float>* %b) {
 ; X32:       # %bb.0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    vmovups (%ecx), %xmm0
-; X32-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; X32-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
 ; X32-NEXT:    vmovups %ymm0, (%eax)
 ; X32-NEXT:    vzeroupper
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: subv_reuse_is_ok:
 ; X64:       # %bb.0:
-; X64-NEXT:    vmovups (%rdi), %xmm0
-; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; X64-NEXT:    vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
 ; X64-NEXT:    vmovups %ymm0, (%rsi)
 ; X64-NEXT:    vzeroupper
 ; X64-NEXT:    retq