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
@@ -50993,7 +50993,11 @@
   if (IsSplat &&
       (VT.is256BitVector() || (VT.is512BitVector() && Subtarget.hasAVX512()))) {
     // If this broadcast is inserted into both halves, use a larger broadcast.
-    if (Op0.getOpcode() == X86ISD::VBROADCAST)
+    // Before AVX2, we don't have vbroadcast instruction(128->256), we prohibit
+    // creating such vbroadcast.
+    if (Op0.getOpcode() == X86ISD::VBROADCAST &&
+        !(!Subtarget.hasAVX2() && VT.is256BitVector() &&
+          Op0.getOperand(0).getValueType().is128BitVector()))
       return DAG.getNode(Op0.getOpcode(), DL, VT, Op0.getOperand(0));
 
     // If this scalar/subvector broadcast_load is inserted into both halves, use
diff --git a/llvm/test/CodeGen/X86/combine-concatvectors.ll b/llvm/test/CodeGen/X86/combine-concatvectors.ll
--- a/llvm/test/CodeGen/X86/combine-concatvectors.ll
+++ b/llvm/test/CodeGen/X86/combine-concatvectors.ll
@@ -37,3 +37,38 @@
   %extr1 = extractelement <2 x float> %bc, i64 0
   unreachable
 }
+
+@qa_ = external unnamed_addr global [49216 x i8], align 32
+
+define void @prohibit_combine_concat_into_vbroadcast() {
+; CHECK-LABEL: prohibit_combine_concat_into_vbroadcast:
+; CHECK:       # %bb.0: # %alloca_0
+; CHECK-NEXT:    movq qa_@GOTPCREL(%rip), %rax
+; CHECK-NEXT:    movl $1091567616, 30256(%rax) # imm = 0x41100000
+; CHECK-NEXT:    movabsq $4294967297, %rcx # imm = 0x100000001
+; CHECK-NEXT:    movq %rcx, 46348(%rax)
+; CHECK-NEXT:    vmovaps {{.*#+}} xmm0 = <1.0E+0,1.0E+0,u,u>
+; CHECK-NEXT:    vmovddup {{.*#+}} xmm1 = xmm0[0,0]
+; CHECK-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
+; CHECK-NEXT:    vmovups %ymm1, 48296(%rax)
+; CHECK-NEXT:    vmovlps %xmm0, 47372(%rax)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+alloca_0:
+  store float 9.000000e+00, float* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 30256) to float*), align 16
+  store <2 x i32> <i32 1, i32 1>, <2 x i32>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 46348) to <2 x i32>*), align 4
+  br label %loop.4942
+
+loop.4942:                                        ; preds = %loop.4942, %alloca_0
+  br i1 undef, label %loop.4942, label %ifmerge.1298
+
+ifmerge.1298:                                     ; preds = %loop.4942
+  %gepload4638 = load float, float* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 28324) to float*), align 4
+  store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48296) to <2 x float>*), align 8
+  store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48304) to <2 x float>*), align 16
+  store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48312) to <2 x float>*), align 8
+  store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 48320) to <2 x float>*), align 32
+  store <2 x float> <float 1.000000e+00, float 1.000000e+00>, <2 x float>* bitcast (i8* getelementptr inbounds ([49216 x i8], [49216 x i8]* @qa_, i64 0, i64 47372) to <2 x float>*), align 4
+  ret void
+}
+