diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -5302,23 +5302,40 @@
     break;
   }
   case Intrinsic::experimental_vector_insert: {
-    VectorType *VecTy = cast<VectorType>(Call.getArgOperand(0)->getType());
-    VectorType *SubVecTy = cast<VectorType>(Call.getArgOperand(1)->getType());
+    Value *Vec = Call.getArgOperand(0);
+    Value *SubVec = Call.getArgOperand(1);
+    Value *Idx = Call.getArgOperand(2);
+    unsigned IdxN = cast<ConstantInt>(Idx)->getZExtValue();
 
+    VectorType *VecTy = cast<VectorType>(Vec->getType());
+    VectorType *SubVecTy = cast<VectorType>(SubVec->getType());
+    VectorType *ResultTy = cast<VectorType>(Call.getType());
+
+    Assert(VecTy == ResultTy,
+           "experimental_vector_insert vector type must match result type.");
     Assert(VecTy->getElementType() == SubVecTy->getElementType(),
            "experimental_vector_insert parameters must have the same element "
            "type.",
            &Call);
+    Assert(IdxN % SubVecTy->getElementCount().getKnownMinValue() == 0,
+           "experimental_vector_insert index must be a constant multiple of "
+           "the subvector's known minimum vector length.");
     break;
   }
   case Intrinsic::experimental_vector_extract: {
+    Value *Vec = Call.getArgOperand(0);
+    Value *Idx = Call.getArgOperand(1);
+    unsigned IdxN = cast<ConstantInt>(Idx)->getZExtValue();
     VectorType *ResultTy = cast<VectorType>(Call.getType());
-    VectorType *VecTy = cast<VectorType>(Call.getArgOperand(0)->getType());
+    VectorType *VecTy = cast<VectorType>(Vec->getType());
 
     Assert(ResultTy->getElementType() == VecTy->getElementType(),
            "experimental_vector_extract result must have the same element "
            "type as the input vector.",
            &Call);
+    Assert(IdxN % ResultTy->getElementCount().getKnownMinValue() == 0,
+           "experimental_vector_extract index must be a constant multiple of "
+           "the result type's known minimum vector length.");
     break;
   }
   case Intrinsic::experimental_noalias_scope_decl: {
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1863,9 +1863,8 @@
       unsigned SubVecNumElts = SubVecTy->getNumElements();
       unsigned IdxN = cast<ConstantInt>(Idx)->getZExtValue();
 
-      // The result of this call is undefined if IdxN is not a constant multiple
-      // of the SubVec's minimum vector length OR the insertion overruns Vec.
-      if (IdxN % SubVecNumElts != 0 || IdxN + SubVecNumElts > VecNumElts) {
+      // The result of this call is undefined if the insertion overruns Vec.
+      if (IdxN + SubVecNumElts > VecNumElts) {
         replaceInstUsesWith(CI, UndefValue::get(CI.getType()));
         return eraseInstFromFunction(CI);
       }
@@ -1917,10 +1916,8 @@
       unsigned VecNumElts = VecTy->getNumElements();
       unsigned IdxN = cast<ConstantInt>(Idx)->getZExtValue();
 
-      // The result of this call is undefined if IdxN is not a constant multiple
-      // of the result type's minimum vector length OR the extraction overruns
-      // Vec.
-      if (IdxN % DstNumElts != 0 || IdxN + DstNumElts > VecNumElts) {
+      // The result of this call is undefined if the extraction overruns Vec.
+      if (IdxN + DstNumElts > VecNumElts) {
         replaceInstUsesWith(CI, UndefValue::get(CI.getType()));
         return eraseInstFromFunction(CI);
       }
diff --git a/llvm/test/CodeGen/AArch64/sve-extract-vector.ll b/llvm/test/CodeGen/AArch64/sve-extract-vector.ll
--- a/llvm/test/CodeGen/AArch64/sve-extract-vector.ll
+++ b/llvm/test/CodeGen/AArch64/sve-extract-vector.ll
@@ -17,13 +17,20 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cntd x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #2
+; CHECK-NEXT:    cmp x9, #2 // =2
 ; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
-; CHECK-NEXT:    ldur q0, [sp, #8]
+; CHECK-NEXT:    lsl x8, x8, #3
+; CHECK-NEXT:    mov x9, sp
+; CHECK-NEXT:    ldr q0, [x9, x8]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-%retval = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> %vec, i64 1)
+%retval = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> %vec, i64 2)
 ret <2 x i64> %retval
 }
 
@@ -43,13 +50,20 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cntw x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #4
+; CHECK-NEXT:    cmp x9, #4 // =4
 ; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
-; CHECK-NEXT:    ldur q0, [sp, #4]
+; CHECK-NEXT:    lsl x8, x8, #2
+; CHECK-NEXT:    mov x9, sp
+; CHECK-NEXT:    ldr q0, [x9, x8]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> %vec, i64 1)
+  %retval = call <4 x i32> @llvm.experimental.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32> %vec, i64 4)
   ret <4 x i32> %retval
 }
 
@@ -69,13 +83,20 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cnth x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #8
+; CHECK-NEXT:    cmp x9, #8 // =8
 ; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
-; CHECK-NEXT:    ldur q0, [sp, #2]
+; CHECK-NEXT:    lsl x8, x8, #1
+; CHECK-NEXT:    mov x9, sp
+; CHECK-NEXT:    ldr q0, [x9, x8]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> %vec, i64 1)
+  %retval = call <8 x i16> @llvm.experimental.vector.extract.v8i16.nxv8i16(<vscale x 8 x i16> %vec, i64 8)
   ret <8 x i16> %retval
 }
 
@@ -95,13 +116,19 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    rdvl x9, #1
+; CHECK-NEXT:    sub x9, x9, #1 // =1
 ; CHECK-NEXT:    ptrue p0.b
+; CHECK-NEXT:    mov w8, #16
+; CHECK-NEXT:    cmp x9, #16 // =16
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
-; CHECK-NEXT:    ldur q0, [sp, #1]
+; CHECK-NEXT:    csel x8, x9, x8, lo
+; CHECK-NEXT:    mov x9, sp
+; CHECK-NEXT:    ldr q0, [x9, x8]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> %vec, i64 1)
+  %retval = call <16 x i8> @llvm.experimental.vector.extract.v16i8.nxv16i8(<vscale x 16 x i8> %vec, i64 16)
   ret <16 x i8> %retval
 }
 
diff --git a/llvm/test/CodeGen/AArch64/sve-insert-vector.ll b/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
--- a/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
+++ b/llvm/test/CodeGen/AArch64/sve-insert-vector.ll
@@ -17,19 +17,26 @@
   ret <vscale x 2 x i64> %retval
 }
 
-define <vscale x 2 x i64> @insert_v2i64_nxv2i64_idx1(<vscale x 2 x i64> %vec, <2 x i64> %subvec) nounwind {
-; CHECK-LABEL: insert_v2i64_nxv2i64_idx1:
+define <vscale x 2 x i64> @insert_v2i64_nxv2i64_idx2(<vscale x 2 x i64> %vec, <2 x i64> %subvec) nounwind {
+; CHECK-LABEL: insert_v2i64_nxv2i64_idx2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cntd x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #2
+; CHECK-NEXT:    cmp x9, #2 // =2
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    lsl x8, x8, #3
+; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    st1d { z0.d }, p0, [sp]
-; CHECK-NEXT:    stur q1, [sp, #8]
+; CHECK-NEXT:    str q1, [x9, x8]
 ; CHECK-NEXT:    ld1d { z0.d }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> %vec, <2 x i64> %subvec, i64 1)
+  %retval = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> %vec, <2 x i64> %subvec, i64 2)
   ret <vscale x 2 x i64> %retval
 }
 
@@ -49,19 +56,26 @@
   ret <vscale x 4 x i32> %retval
 }
 
-define <vscale x 4 x i32> @insert_v4i32_nxv4i32_idx1(<vscale x 4 x i32> %vec, <4 x i32> %subvec) nounwind {
-; CHECK-LABEL: insert_v4i32_nxv4i32_idx1:
+define <vscale x 4 x i32> @insert_v4i32_nxv4i32_idx2(<vscale x 4 x i32> %vec, <4 x i32> %subvec) nounwind {
+; CHECK-LABEL: insert_v4i32_nxv4i32_idx2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cntw x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #4
+; CHECK-NEXT:    cmp x9, #4 // =4
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    ptrue p0.s
+; CHECK-NEXT:    lsl x8, x8, #2
+; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    st1w { z0.s }, p0, [sp]
-; CHECK-NEXT:    stur q1, [sp, #4]
+; CHECK-NEXT:    str q1, [x9, x8]
 ; CHECK-NEXT:    ld1w { z0.s }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> %vec, <4 x i32> %subvec, i64 1)
+  %retval = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> %vec, <4 x i32> %subvec, i64 4)
   ret <vscale x 4 x i32> %retval
 }
 
@@ -81,19 +95,26 @@
   ret <vscale x 8 x i16> %retval
 }
 
-define <vscale x 8 x i16> @insert_v8i16_nxv8i16_idx1(<vscale x 8 x i16> %vec, <8 x i16> %subvec) nounwind {
-; CHECK-LABEL: insert_v8i16_nxv8i16_idx1:
+define <vscale x 8 x i16> @insert_v8i16_nxv8i16_idx2(<vscale x 8 x i16> %vec, <8 x i16> %subvec) nounwind {
+; CHECK-LABEL: insert_v8i16_nxv8i16_idx2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    cnth x9
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #8
+; CHECK-NEXT:    cmp x9, #8 // =8
+; CHECK-NEXT:    csel x8, x9, x8, lo
 ; CHECK-NEXT:    ptrue p0.h
+; CHECK-NEXT:    lsl x8, x8, #1
+; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    st1h { z0.h }, p0, [sp]
-; CHECK-NEXT:    stur q1, [sp, #2]
+; CHECK-NEXT:    str q1, [x9, x8]
 ; CHECK-NEXT:    ld1h { z0.h }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> %vec, <8 x i16> %subvec, i64 1)
+  %retval = call <vscale x 8 x i16> @llvm.experimental.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> %vec, <8 x i16> %subvec, i64 8)
   ret <vscale x 8 x i16> %retval
 }
 
@@ -113,19 +134,25 @@
   ret <vscale x 16 x i8> %retval
 }
 
-define <vscale x 16 x i8> @insert_v16i8_nxv16i8_idx1(<vscale x 16 x i8> %vec, <16 x i8> %subvec) nounwind {
-; CHECK-LABEL: insert_v16i8_nxv16i8_idx1:
+define <vscale x 16 x i8> @insert_v16i8_nxv16i8_idx2(<vscale x 16 x i8> %vec, <16 x i8> %subvec) nounwind {
+; CHECK-LABEL: insert_v16i8_nxv16i8_idx2:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    rdvl x9, #1
+; CHECK-NEXT:    sub x9, x9, #1 // =1
+; CHECK-NEXT:    mov w8, #16
+; CHECK-NEXT:    cmp x9, #16 // =16
 ; CHECK-NEXT:    ptrue p0.b
+; CHECK-NEXT:    csel x8, x9, x8, lo
+; CHECK-NEXT:    mov x9, sp
 ; CHECK-NEXT:    st1b { z0.b }, p0, [sp]
-; CHECK-NEXT:    stur q1, [sp, #1]
+; CHECK-NEXT:    str q1, [x9, x8]
 ; CHECK-NEXT:    ld1b { z0.b }, p0/z, [sp]
 ; CHECK-NEXT:    addvl sp, sp, #1
 ; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
-  %retval = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> %vec, <16 x i8> %subvec, i64 1)
+  %retval = call <vscale x 16 x i8> @llvm.experimental.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> %vec, <16 x i8> %subvec, i64 16)
   ret <vscale x 16 x i8> %retval
 }
 
diff --git a/llvm/test/Transforms/InstCombine/canonicalize-vector-extract.ll b/llvm/test/Transforms/InstCombine/canonicalize-vector-extract.ll
--- a/llvm/test/Transforms/InstCombine/canonicalize-vector-extract.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-vector-extract.ll
@@ -100,29 +100,6 @@
   ret <3 x i32> %1
 }
 
-; ============================================================================ ;
-; Invalid canonicalizations
-; ============================================================================ ;
-
-; Idx must be the be a constant multiple of the destination vector's length,
-; otherwise the result is undefined.
-define <4 x i32> @idx_not_constant_multiple(<8 x i32> %vec) {
-; CHECK-LABEL: @idx_not_constant_multiple(
-; CHECK-NEXT:    ret <4 x i32> undef
-;
-  %1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 1)
-  ret <4 x i32> %1
-}
-
-; If the extraction overruns the vector, the result is undefined.
-define <10 x i32> @extract_overrun(<8 x i32> %vec) {
-; CHECK-LABEL: @extract_overrun(
-; CHECK-NEXT:    ret <10 x i32> undef
-;
-  %1 = call <10 x i32> @llvm.experimental.vector.extract.v10i32.v8i32(<8 x i32> %vec, i64 0)
-  ret <10 x i32> %1
-}
-
 ; ============================================================================ ;
 ; Scalable cases
 ; ============================================================================ ;
diff --git a/llvm/test/Transforms/InstCombine/canonicalize-vector-insert.ll b/llvm/test/Transforms/InstCombine/canonicalize-vector-insert.ll
--- a/llvm/test/Transforms/InstCombine/canonicalize-vector-insert.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-vector-insert.ll
@@ -108,29 +108,6 @@
   ret <8 x i32> %1
 }
 
-; ============================================================================ ;
-; Invalid canonicalizations
-; ============================================================================ ;
-
-; Idx must be the be a constant multiple of the subvector's minimum vector
-; length, otherwise the result is undefined.
-define <8 x i32> @idx_not_constant_multiple(<8 x i32> %vec, <4 x i32> %subvec) {
-; CHECK-LABEL: @idx_not_constant_multiple(
-; CHECK-NEXT:    ret <8 x i32> undef
-;
-  %1 = call <8 x i32> @llvm.experimental.vector.insert.v8i32.v4i32(<8 x i32> %vec, <4 x i32> %subvec, i64 2)
-  ret <8 x i32> %1
-}
-
-; If the insertion overruns the vector, the result is undefined.
-define <8 x i32> @insert_overrun(<8 x i32> %vec, <8 x i32> %subvec) {
-; CHECK-LABEL: @insert_overrun(
-; CHECK-NEXT:    ret <8 x i32> undef
-;
-  %1 = call <8 x i32> @llvm.experimental.vector.insert.v8i32.v8i32(<8 x i32> %vec, <8 x i32> %subvec, i64 4)
-  ret <8 x i32> %1
-}
-
 ; ============================================================================ ;
 ; Scalable cases
 ; ============================================================================ ;
diff --git a/llvm/test/Verifier/insert-extract-intrinsics-invalid.ll b/llvm/test/Verifier/insert-extract-intrinsics-invalid.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Verifier/insert-extract-intrinsics-invalid.ll
@@ -0,0 +1,16 @@
+; RUN: not opt -verify -S < %s 2>&1 >/dev/null | FileCheck %s
+
+; CHECK: experimental_vector_extract index must be a constant multiple of the result type's known minimum vector length.
+define <4 x i32> @extract_idx_not_constant_multiple(<8 x i32> %vec) {
+  %1 = call <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32> %vec, i64 1)
+  ret <4 x i32> %1
+}
+
+; CHECK: experimental_vector_insert index must be a constant multiple of the subvector's known minimum vector length.
+define <8 x i32> @insert_idx_not_constant_multiple(<8 x i32> %vec, <4 x i32> %subvec) {
+  %1 = call <8 x i32> @llvm.experimental.vector.insert.v8i32.v4i32(<8 x i32> %vec, <4 x i32> %subvec, i64 2)
+  ret <8 x i32> %1
+}
+
+declare <4 x i32> @llvm.experimental.vector.extract.v4i32.v8i32(<8 x i32>, i64)
+declare <8 x i32> @llvm.experimental.vector.insert.v8i32.v4i32(<8 x i32>, <4 x i32>, i64)