diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index de909cc107956..235f0da86b908 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -20492,9 +20492,11 @@ SDValue DAGCombiner::replaceStoreOfInsertLoad(StoreSDNode *ST) {
   SDValue Elt = Value.getOperand(1);
   SDValue Idx = Value.getOperand(2);
 
-  // If the element isn't byte sized then we can't compute an offset
+  // If the element isn't byte sized or is implicitly truncated then we can't
+  // compute an offset.
   EVT EltVT = Elt.getValueType();
-  if (!EltVT.isByteSized())
+  if (!EltVT.isByteSized() ||
+      EltVT != Value.getOperand(0).getValueType().getVectorElementType())
     return SDValue();
 
   auto *Ld = dyn_cast<LoadSDNode>(Value.getOperand(0));
diff --git a/llvm/test/CodeGen/X86/pr64655.ll b/llvm/test/CodeGen/X86/pr64655.ll
index cd5775a61c23e..f2929527c88f2 100644
--- a/llvm/test/CodeGen/X86/pr64655.ll
+++ b/llvm/test/CodeGen/X86/pr64655.ll
@@ -41,7 +41,16 @@ define void @f(ptr %0) {
 ;
 ; AVX512-LABEL: f:
 ; AVX512:       # %bb.0:
-; AVX512-NEXT:    movb $1, 1(%rdi)
+; AVX512-NEXT:    kmovb (%rdi), %k0
+; AVX512-NEXT:    movb $-3, %al
+; AVX512-NEXT:    kmovd %eax, %k1
+; AVX512-NEXT:    kandb %k1, %k0, %k0
+; AVX512-NEXT:    movb $1, %al
+; AVX512-NEXT:    kmovd %eax, %k1
+; AVX512-NEXT:    kshiftlb $7, %k1, %k1
+; AVX512-NEXT:    kshiftrb $6, %k1, %k1
+; AVX512-NEXT:    korb %k1, %k0, %k0
+; AVX512-NEXT:    kmovb %k0, (%rdi)
 ; AVX512-NEXT:    retq
   %2 = load <8 x i1>, ptr %0
   %3 = insertelement <8 x i1> %2, i1 true, i32 1