diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
--- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -834,8 +834,17 @@
     if (SI->getAlign() < NSI->getAlign())
       NSI->setAlignment(SI->getAlign());
     replaceValue(I, *NSI);
+    auto *IEI = cast<Instruction>(SI->getOperand(0));
     // Need erasing the store manually.
     I.eraseFromParent();
+    // Removing the insertelement instruction may unlock further load/extract
+    // scalarization opportunities.
+    if (IEI->use_empty())
+      IEI->eraseFromParent();
+    if (!Load->user_empty()) {
+      Instruction *UI = cast<Instruction>(*Load->user_begin());
+      scalarizeLoadExtract(*UI);
+    }
     return true;
   }
 
diff --git a/llvm/test/Transforms/PhaseOrdering/AArch64/matrix-extract-insert.ll b/llvm/test/Transforms/PhaseOrdering/AArch64/matrix-extract-insert.ll
--- a/llvm/test/Transforms/PhaseOrdering/AArch64/matrix-extract-insert.ll
+++ b/llvm/test/Transforms/PhaseOrdering/AArch64/matrix-extract-insert.ll
@@ -20,13 +20,14 @@
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult i64 [[TMP5]], 225
 ; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP6]])
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast [225 x double]* [[B:%.*]] to <225 x double>*
-; CHECK-NEXT:    [[TMP8:%.*]] = load <225 x double>, <225 x double>* [[TMP7]], align 8
-; CHECK-NEXT:    [[MATRIXEXT4:%.*]] = extractelement <225 x double> [[TMP8]], i64 [[TMP5]]
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[TMP7]], i64 0, i64 [[TMP5]]
+; CHECK-NEXT:    [[MATRIXEXT4:%.*]] = load double, double* [[TMP8]], align 8
 ; CHECK-NEXT:    [[MUL:%.*]] = fmul double [[MATRIXEXT]], [[MATRIXEXT4]]
-; CHECK-NEXT:    [[MATRIXEXT7:%.*]] = extractelement <225 x double> [[TMP8]], i64 [[TMP1]]
-; CHECK-NEXT:    [[SUB:%.*]] = fsub double [[MATRIXEXT7]], [[MUL]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[TMP7]], i64 0, i64 [[TMP1]]
-; CHECK-NEXT:    store double [[SUB]], double* [[TMP9]], align 8
+; CHECK-NEXT:    [[MATRIXEXT7:%.*]] = load double, double* [[TMP9]], align 8
+; CHECK-NEXT:    [[SUB:%.*]] = fsub double [[MATRIXEXT7]], [[MUL]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[TMP7]], i64 0, i64 [[TMP1]]
+; CHECK-NEXT:    store double [[SUB]], double* [[TMP10]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
diff --git a/llvm/test/Transforms/VectorCombine/AArch64/load-extract-insert-store-scalarization.ll b/llvm/test/Transforms/VectorCombine/AArch64/load-extract-insert-store-scalarization.ll
--- a/llvm/test/Transforms/VectorCombine/AArch64/load-extract-insert-store-scalarization.ll
+++ b/llvm/test/Transforms/VectorCombine/AArch64/load-extract-insert-store-scalarization.ll
@@ -6,18 +6,19 @@
 define void @load_extract_insert_store_const_idx(<225 x double>* %A) {
 ; CHECK-LABEL: @load_extract_insert_store_const_idx(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[LV:%.*]] = load <225 x double>, <225 x double>* [[A:%.*]], align 8
-; CHECK-NEXT:    [[EXT_0:%.*]] = extractelement <225 x double> [[LV]], i64 0
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A:%.*]], i32 0, i64 1
+; CHECK-NEXT:    [[EXT_0:%.*]] = load double, double* [[TMP0]], align 8
 ; CHECK-NEXT:    [[MUL:%.*]] = fmul double 2.000000e+01, [[EXT_0]]
-; CHECK-NEXT:    [[EXT_1:%.*]] = extractelement <225 x double> [[LV]], i64 1
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i32 0, i64 1
+; CHECK-NEXT:    [[EXT_1:%.*]] = load double, double* [[TMP1]], align 8
 ; CHECK-NEXT:    [[SUB:%.*]] = fsub double [[EXT_1]], [[MUL]]
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i64 0, i64 1
-; CHECK-NEXT:    store double [[SUB]], double* [[TMP0]], align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i64 0, i64 1
+; CHECK-NEXT:    store double [[SUB]], double* [[TMP2]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %lv = load <225 x double>, <225 x double>* %A, align 8
-  %ext.0 = extractelement <225 x double> %lv, i64 0
+  %ext.0 = extractelement <225 x double> %lv, i64 1
   %mul = fmul double 20.0, %ext.0
   %ext.1 = extractelement <225 x double> %lv, i64 1
   %sub = fsub double %ext.1, %mul
@@ -33,13 +34,14 @@
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP_1]])
 ; CHECK-NEXT:    [[CMP_2:%.*]] = icmp ult i64 [[IDX_2:%.*]], 225
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP_2]])
-; CHECK-NEXT:    [[LV:%.*]] = load <225 x double>, <225 x double>* [[A:%.*]], align 8
-; CHECK-NEXT:    [[EXT_0:%.*]] = extractelement <225 x double> [[LV]], i64 [[IDX_1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A:%.*]], i32 0, i64 [[IDX_1]]
+; CHECK-NEXT:    [[EXT_0:%.*]] = load double, double* [[TMP0]], align 8
 ; CHECK-NEXT:    [[MUL:%.*]] = fmul double 2.000000e+01, [[EXT_0]]
-; CHECK-NEXT:    [[EXT_1:%.*]] = extractelement <225 x double> [[LV]], i64 [[IDX_2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i32 0, i64 [[IDX_2]]
+; CHECK-NEXT:    [[EXT_1:%.*]] = load double, double* [[TMP1]], align 8
 ; CHECK-NEXT:    [[SUB:%.*]] = fsub double [[EXT_1]], [[MUL]]
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i64 0, i64 [[IDX_1]]
-; CHECK-NEXT:    store double [[SUB]], double* [[TMP0]], align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds <225 x double>, <225 x double>* [[A]], i64 0, i64 [[IDX_1]]
+; CHECK-NEXT:    store double [[SUB]], double* [[TMP2]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry: