diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -16966,6 +16966,15 @@
   }
   assert(VT.is128BitVector() && "Only 128-bit vector types should be left!");
 
+  // This will be just movd/movq/movss/movsd
+  if (IdxVal == 0 && ISD::isBuildVectorAllZeros(N0.getNode())) {
+    if (EltVT == MVT::i32 || EltVT == MVT::f32 || EltVT == MVT::f64 ||
+        (EltVT == MVT::i64 && Subtarget.is64Bit())) {
+      N1 = DAG.getNode(ISD::SCALAR_TO_VECTOR, dl, VT, N1);
+      return getShuffleVectorZeroOrUndef(N1, 0, true, Subtarget, DAG);
+    }
+  }
+
   // Transform it so it match pinsr{b,w} which expects a GR32 as its second
   // argument. SSE41 required for pinsrb.
   if (VT == MVT::v8i16 || (VT == MVT::v16i8 && Subtarget.hasSSE41())) {
diff --git a/llvm/test/CodeGen/X86/vec_insert_first.ll b/llvm/test/CodeGen/X86/vec_insert_first.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/vec_insert_first.ll
@@ -0,0 +1,24 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i386-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X32
+; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X64
+define <2 x i64> @pinsr(i32 %x, i32 %y) {
+; X32-LABEL: pinsr:
+; X32:       # %bb.0:
+; X32-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X32-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X32-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; X32-NEXT:    retl
+;
+; X64-LABEL: pinsr:
+; X64:       # %bb.0:
+; X64-NEXT:    movd %edi, %xmm0
+; X64-NEXT:    movd %esi, %xmm1
+; X64-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; X64-NEXT:    retq
+  %ins1 = insertelement <4 x i32> <i32 undef, i32 0, i32 undef, i32 undef>, i32 %x, i32 0
+  %ins2 = insertelement <4 x i32> <i32 undef, i32 0, i32 undef, i32 undef>, i32 %y, i32 0
+  %b1 = bitcast <4 x i32> %ins1 to <2 x i64>
+  %b2 = bitcast <4 x i32> %ins2 to <2 x i64>
+  %r = shufflevector <2 x i64> %b1, <2 x i64> %b2, <2 x i32> <i32 0, i32 2>
+  ret <2 x i64> %r
+}