Index: llvm/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -37006,6 +37006,22 @@
           SrcElts.setBit(M);
       }
 
+    // As for OpInputs[Src] which has users excluding Op.getNode(),
+    // we assume that all elements are needed, i.e, set SrcElts.setAllBits()
+    // For example:
+    // t1317: v8i32 = insert_subvector undef:v8i32, t1414, Constant:i64<0>
+    // t1315: v8i32 = X86ISD::BLENDI t380, t1317, TargetConstant:i8<2>
+    // t1414: v4i32 = insert_vector_elt t679, t677, Constant:i64<2>
+    // t1416: v8i32 = X86ISD::VBROADCAST t1414
+    // When getTargetShuffleInputs(...) processed t1416, it created
+    //  NewNode: v8i32 = insert_subvector undef:v8i32, t1414, Constant:i64<0>
+    //  which is the same with t1317.
+    // So getTargetShuffleInputs(...) set
+    //  OpInputs[0] = t1317 which is used by t1315
+    // Before SimplifyDemandedVectorElts processes OpInputs[0] which is used by
+    // t1315, we assume that all elements are needed, i.e. SrcElts.setAllBits()
+    if (!OpInputs[Src].isOperandOf(Op.getNode()) && !OpInputs[Src].use_empty())
+      SrcElts.setAllBits();
     // TODO - Propagate input undef/zero elts.
     APInt SrcUndef, SrcZero;
     if (SimplifyDemandedVectorElts(OpInputs[Src], SrcElts, SrcUndef, SrcZero,
Index: llvm/test/CodeGen/X86/simplifydemandedvectorselts-broadcast.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/X86/simplifydemandedvectorselts-broadcast.ll
@@ -0,0 +1,20 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s
+
+; Function Attrs: noinline nounwind optnone uwtable
+define  <16 x i32> @main(<3 x i32>* %ptr) {
+; CHECK-LABEL: main:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
+; CHECK-NEXT:    vpinsrd $2, 8(%rdi), %xmm0, %xmm1
+; CHECK-NEXT:    vpxor %xmm2, %xmm2, %xmm2
+; CHECK-NEXT:    vpblendd {{.*#+}} ymm0 = ymm2[0],ymm0[1],ymm2[2,3,4,5,6,7]
+; CHECK-NEXT:    vpbroadcastd %xmm1, %ymm1
+; CHECK-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1],ymm1[2],ymm2[3,4,5,6,7]
+; CHECK-NEXT:    retq
+entry:
+  %int3 = load <3 x i32>, <3 x i32>* %ptr, align 1
+  %0 = shufflevector <3 x i32> %int3, <3 x i32> undef, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  %1 = shufflevector <16 x i32> <i32 0, i32 undef, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 undef, i32 0, i32 0, i32 0, i32 0, i32 0>, <16 x i32> %0, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 11, i32 12, i32 13, i32 14, i32 15>
+  ret <16 x i32 > %1
+}