diff --git a/llvm/lib/Target/ARM/MVETailPredication.cpp b/llvm/lib/Target/ARM/MVETailPredication.cpp
--- a/llvm/lib/Target/ARM/MVETailPredication.cpp
+++ b/llvm/lib/Target/ARM/MVETailPredication.cpp
@@ -299,7 +299,7 @@
         // MVE vectors are 128-bit, but don't support 128 x i1.
         // TODO: Can we support vectors larger than 128-bits?
         unsigned MaxWidth = TTI->getRegisterBitWidth(true); 
-        if (Lanes * ElementWidth != MaxWidth || Lanes == MaxWidth)
+        if (Lanes * ElementWidth > MaxWidth || Lanes == MaxWidth)
           return false;
         MaskedInsts.push_back(cast<IntrinsicInst>(&I));
       } else if (auto *Int = dyn_cast<IntrinsicInst>(&I)) {
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-tail-data-types.ll
@@ -9,41 +9,29 @@
 ; CHECK-NEXT:    moveq r0, #0
 ; CHECK-NEXT:    bxeq lr
 ; CHECK-NEXT:    push {r7, lr}
-; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    adds r3, r2, #3
-; CHECK-NEXT:    subs r2, #1
+; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
-; CHECK-NEXT:    vdup.32 q1, r2
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
-; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    adr r3, .LCPI0_0
-; CHECK-NEXT:    vldrw.u32 q2, [r3]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    movs r3, #0
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB0_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q4, q2, r2
-; CHECK-NEXT:    adds r3, r1, r2
-; CHECK-NEXT:    adds r2, #4
-; CHECK-NEXT:    vpt.u32 cs, q1, q4
-; CHECK-NEXT:    vldrbt.u32 q4, [r3]
-; CHECK-NEXT:    vmov q3, q0
-; CHECK-NEXT:    vmla.u32 q0, q4, r0
-; CHECK-NEXT:    le lr, .LBB0_1
+; CHECK-NEXT:    mov r12, r2
+; CHECK-NEXT:    adds r2, r1, r3
+; CHECK-NEXT:    vldrb.u32 q2, [r2]
+; CHECK-NEXT:    adds r3, #4
+; CHECK-NEXT:    sub.w r2, r12, #4
+; CHECK-NEXT:    vmov q1, q0
+; CHECK-NEXT:    vmla.u32 q0, q2, r0
+; CHECK-NEXT:    letp lr, .LBB0_1
 ; CHECK-NEXT:  @ %bb.2: @ %middle.block
-; CHECK-NEXT:    vpsel q0, q0, q3
+; CHECK-NEXT:    vctp.32 r12
+; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    vaddv.u32 r0, q0
-; CHECK-NEXT:    vpop {d8, d9}
 ; CHECK-NEXT:    pop {r7, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI0_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp7 = icmp eq i32 %N, 0
   br i1 %cmp7, label %for.cond.cleanup, label %vector.ph
@@ -94,41 +82,27 @@
 ; CHECK-NEXT:    moveq r0, #0
 ; CHECK-NEXT:    bxeq lr
 ; CHECK-NEXT:    push {r7, lr}
-; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    adds r3, r2, #3
-; CHECK-NEXT:    subs r2, #1
+; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
-; CHECK-NEXT:    vdup.32 q1, r2
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
-; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    adr r3, .LCPI1_0
-; CHECK-NEXT:    vldrw.u32 q2, [r3]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB1_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q4, q2, r2
-; CHECK-NEXT:    adds r2, #4
-; CHECK-NEXT:    vpt.u32 cs, q1, q4
-; CHECK-NEXT:    vldrht.s32 q4, [r1]
+; CHECK-NEXT:    vldrh.s32 q2, [r1]
+; CHECK-NEXT:    mov r3, r2
 ; CHECK-NEXT:    adds r1, #8
-; CHECK-NEXT:    vmov q3, q0
-; CHECK-NEXT:    vmla.u32 q0, q4, r0
-; CHECK-NEXT:    le lr, .LBB1_1
+; CHECK-NEXT:    subs r2, #4
+; CHECK-NEXT:    vmov q1, q0
+; CHECK-NEXT:    vmla.u32 q0, q2, r0
+; CHECK-NEXT:    letp lr, .LBB1_1
 ; CHECK-NEXT:  @ %bb.2: @ %middle.block
-; CHECK-NEXT:    vpsel q0, q0, q3
+; CHECK-NEXT:    vctp.32 r3
+; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    vaddv.u32 r0, q0
-; CHECK-NEXT:    vpop {d8, d9}
 ; CHECK-NEXT:    pop {r7, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI1_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp7 = icmp eq i32 %N, 0
   br i1 %cmp7, label %for.cond.cleanup, label %vector.ph
@@ -179,41 +153,29 @@
 ; CHECK-NEXT:    moveq r0, #0
 ; CHECK-NEXT:    bxeq lr
 ; CHECK-NEXT:    push {r7, lr}
-; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    adds r3, r2, #3
-; CHECK-NEXT:    subs r2, #1
+; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
-; CHECK-NEXT:    vdup.32 q1, r2
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
-; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    adr r3, .LCPI2_0
-; CHECK-NEXT:    vldrw.u32 q2, [r3]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    movs r3, #0
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB2_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q4, q2, r2
-; CHECK-NEXT:    adds r3, r1, r2
-; CHECK-NEXT:    adds r2, #4
-; CHECK-NEXT:    vpt.u32 cs, q1, q4
-; CHECK-NEXT:    vldrbt.u32 q4, [r3]
-; CHECK-NEXT:    vmov q3, q0
-; CHECK-NEXT:    vmla.u32 q0, q4, r0
-; CHECK-NEXT:    le lr, .LBB2_1
+; CHECK-NEXT:    mov r12, r2
+; CHECK-NEXT:    adds r2, r1, r3
+; CHECK-NEXT:    vldrb.u32 q2, [r2]
+; CHECK-NEXT:    adds r3, #4
+; CHECK-NEXT:    sub.w r2, r12, #4
+; CHECK-NEXT:    vmov q1, q0
+; CHECK-NEXT:    vmla.u32 q0, q2, r0
+; CHECK-NEXT:    letp lr, .LBB2_1
 ; CHECK-NEXT:  @ %bb.2: @ %middle.block
-; CHECK-NEXT:    vpsel q0, q0, q3
+; CHECK-NEXT:    vctp.32 r12
+; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    vaddv.u32 r0, q0
-; CHECK-NEXT:    vpop {d8, d9}
 ; CHECK-NEXT:    pop {r7, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI2_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp7 = icmp eq i32 %N, 0
   br i1 %cmp7, label %for.cond.cleanup, label %vector.ph
@@ -264,41 +226,27 @@
 ; CHECK-NEXT:    moveq r0, #0
 ; CHECK-NEXT:    bxeq lr
 ; CHECK-NEXT:    push {r7, lr}
-; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    adds r3, r2, #3
-; CHECK-NEXT:    subs r2, #1
+; CHECK-NEXT:    vmov.i32 q0, #0x0
 ; CHECK-NEXT:    bic r3, r3, #3
-; CHECK-NEXT:    vdup.32 q1, r2
 ; CHECK-NEXT:    sub.w r12, r3, #4
 ; CHECK-NEXT:    movs r3, #1
-; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    movs r2, #0
 ; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
-; CHECK-NEXT:    adr r3, .LCPI3_0
-; CHECK-NEXT:    vldrw.u32 q2, [r3]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB3_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q4, q2, r2
-; CHECK-NEXT:    adds r2, #4
-; CHECK-NEXT:    vpt.u32 cs, q1, q4
-; CHECK-NEXT:    vldrht.u32 q4, [r1]
+; CHECK-NEXT:    vldrh.u32 q2, [r1]
+; CHECK-NEXT:    mov r3, r2
 ; CHECK-NEXT:    adds r1, #8
-; CHECK-NEXT:    vmov q3, q0
-; CHECK-NEXT:    vmla.u32 q0, q4, r0
-; CHECK-NEXT:    le lr, .LBB3_1
+; CHECK-NEXT:    subs r2, #4
+; CHECK-NEXT:    vmov q1, q0
+; CHECK-NEXT:    vmla.u32 q0, q2, r0
+; CHECK-NEXT:    letp lr, .LBB3_1
 ; CHECK-NEXT:  @ %bb.2: @ %middle.block
-; CHECK-NEXT:    vpsel q0, q0, q3
+; CHECK-NEXT:    vctp.32 r3
+; CHECK-NEXT:    vpsel q0, q0, q1
 ; CHECK-NEXT:    vaddv.u32 r0, q0
-; CHECK-NEXT:    vpop {d8, d9}
 ; CHECK-NEXT:    pop {r7, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI3_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp7 = icmp eq i32 %N, 0
   br i1 %cmp7, label %for.cond.cleanup, label %vector.ph
@@ -414,66 +362,59 @@
 ; CHECK-LABEL: test_vec_mul_scalar_add_char:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, lr}
-; CHECK-NEXT:    ldr r7, [sp, #28]
-; CHECK-NEXT:    cmp r7, #0
+; CHECK-NEXT:    ldr.w r12, [sp, #28]
+; CHECK-NEXT:    cmp.w r12, #0
 ; CHECK-NEXT:    beq.w .LBB5_12
 ; CHECK-NEXT:  @ %bb.1: @ %for.body.lr.ph
-; CHECK-NEXT:    add.w r4, r3, r7, lsl #2
-; CHECK-NEXT:    adds r5, r1, r7
-; CHECK-NEXT:    cmp r4, r1
-; CHECK-NEXT:    add.w r6, r0, r7
-; CHECK-NEXT:    cset r12, hi
-; CHECK-NEXT:    cmp r5, r3
-; CHECK-NEXT:    cset r5, hi
-; CHECK-NEXT:    cmp r4, r0
-; CHECK-NEXT:    cset r4, hi
+; CHECK-NEXT:    add.w r5, r3, r12, lsl #2
+; CHECK-NEXT:    add.w r6, r1, r12
+; CHECK-NEXT:    cmp r5, r1
+; CHECK-NEXT:    add.w r4, r0, r12
+; CHECK-NEXT:    cset r7, hi
 ; CHECK-NEXT:    cmp r6, r3
 ; CHECK-NEXT:    cset r6, hi
-; CHECK-NEXT:    ands r6, r4
-; CHECK-NEXT:    lsls r6, r6, #31
+; CHECK-NEXT:    cmp r5, r0
+; CHECK-NEXT:    cset r5, hi
+; CHECK-NEXT:    cmp r4, r3
+; CHECK-NEXT:    cset r4, hi
+; CHECK-NEXT:    ands r5, r4
+; CHECK-NEXT:    lsls r5, r5, #31
 ; CHECK-NEXT:    itt eq
-; CHECK-NEXT:    andeq.w r6, r5, r12
-; CHECK-NEXT:    lslseq.w r6, r6, #31
+; CHECK-NEXT:    andeq r7, r6
+; CHECK-NEXT:    lslseq.w r7, r7, #31
 ; CHECK-NEXT:    beq .LBB5_4
 ; CHECK-NEXT:  @ %bb.2: @ %for.body.preheader
-; CHECK-NEXT:    subs r6, r7, #1
-; CHECK-NEXT:    and lr, r7, #3
-; CHECK-NEXT:    cmp r6, #3
+; CHECK-NEXT:    sub.w r4, r12, #1
+; CHECK-NEXT:    and lr, r12, #3
+; CHECK-NEXT:    cmp r4, #3
 ; CHECK-NEXT:    bhs .LBB5_6
 ; CHECK-NEXT:  @ %bb.3:
 ; CHECK-NEXT:    movs r7, #0
 ; CHECK-NEXT:    b .LBB5_9
 ; CHECK-NEXT:  .LBB5_4: @ %vector.ph
-; CHECK-NEXT:    adds r6, r7, #3
-; CHECK-NEXT:    movs r5, #1
-; CHECK-NEXT:    bic r6, r6, #3
-; CHECK-NEXT:    subs r7, #1
-; CHECK-NEXT:    subs r6, #4
-; CHECK-NEXT:    vdup.32 q0, r7
-; CHECK-NEXT:    movs r7, #0
-; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
-; CHECK-NEXT:    adr r6, .LCPI5_0
-; CHECK-NEXT:    vldrw.u32 q1, [r6]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    add.w r7, r12, #3
+; CHECK-NEXT:    movs r6, #1
+; CHECK-NEXT:    bic r7, r7, #3
+; CHECK-NEXT:    movs r4, #0
+; CHECK-NEXT:    subs r7, #4
+; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB5_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q2, q1, r7
-; CHECK-NEXT:    adds r4, r0, r7
-; CHECK-NEXT:    vpt.u32 cs, q0, q2
-; CHECK-NEXT:    vldrbt.u32 q2, [r4]
-; CHECK-NEXT:    adds r4, r1, r7
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrbt.u32 q3, [r4]
-; CHECK-NEXT:    vmul.i32 q2, q3, q2
-; CHECK-NEXT:    vadd.i32 q2, q2, r2
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q2, [r3]
+; CHECK-NEXT:    adds r5, r0, r4
+; CHECK-NEXT:    vldrb.u32 q0, [r5]
+; CHECK-NEXT:    adds r5, r1, r4
+; CHECK-NEXT:    vldrb.u32 q1, [r5]
+; CHECK-NEXT:    vmul.i32 q0, q1, q0
+; CHECK-NEXT:    vadd.i32 q0, q0, r2
+; CHECK-NEXT:    vstrw.32 q0, [r3]
 ; CHECK-NEXT:    adds r3, #16
-; CHECK-NEXT:    adds r7, #4
-; CHECK-NEXT:    le lr, .LBB5_5
+; CHECK-NEXT:    adds r4, #4
+; CHECK-NEXT:    sub.w r12, r12, #4
+; CHECK-NEXT:    letp lr, .LBB5_5
 ; CHECK-NEXT:    b .LBB5_12
 ; CHECK-NEXT:  .LBB5_6: @ %for.body.preheader.new
-; CHECK-NEXT:    sub.w r12, lr, r7
+; CHECK-NEXT:    sub.w r12, lr, r12
 ; CHECK-NEXT:    subs r4, r1, #3
 ; CHECK-NEXT:    subs r5, r0, #3
 ; CHECK-NEXT:    sub.w r7, r3, #16
@@ -517,13 +458,6 @@
 ; CHECK-NEXT:    le lr, .LBB5_11
 ; CHECK-NEXT:  .LBB5_12: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.13:
-; CHECK-NEXT:  .LCPI5_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %res12 = bitcast i32* %res to i8*
   %cmp10 = icmp eq i32 %N, 0
@@ -678,36 +612,21 @@
 ; CHECK-NEXT:    bic lr, lr, #3
 ; CHECK-NEXT:    sub.w lr, lr, #4
 ; CHECK-NEXT:    add.w lr, r4, lr, lsr #2
-; CHECK-NEXT:    sub.w r4, r12, #1
-; CHECK-NEXT:    vdup.32 q0, r4
-; CHECK-NEXT:    adr r4, .LCPI6_0
-; CHECK-NEXT:    vldrw.u32 q1, [r4]
-; CHECK-NEXT:    mov.w r12, #0
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB6_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q2, q1, r12
-; CHECK-NEXT:    add.w r12, r12, #4
-; CHECK-NEXT:    vptt.u32 cs, q0, q2
-; CHECK-NEXT:    vldrht.s32 q2, [r0]
-; CHECK-NEXT:    vldrht.s32 q3, [r1]
+; CHECK-NEXT:    vldrh.s32 q0, [r0]
+; CHECK-NEXT:    vldrh.s32 q1, [r1]
+; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    adds r0, #8
-; CHECK-NEXT:    vmul.i32 q2, q3, q2
+; CHECK-NEXT:    vadd.i32 q0, q0, r2
+; CHECK-NEXT:    vstrw.32 q0, [r3]
 ; CHECK-NEXT:    adds r1, #8
-; CHECK-NEXT:    vadd.i32 q2, q2, r2
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q2, [r3]
 ; CHECK-NEXT:    adds r3, #16
-; CHECK-NEXT:    le lr, .LBB6_1
+; CHECK-NEXT:    sub.w r12, r12, #4
+; CHECK-NEXT:    letp lr, .LBB6_1
 ; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r4, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI6_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp10 = icmp eq i32 %N, 0
   br i1 %cmp10, label %for.cond.cleanup, label %vector.ph
@@ -754,66 +673,59 @@
 ; CHECK-LABEL: test_vec_mul_scalar_add_uchar:
 ; CHECK:       @ %bb.0: @ %entry
 ; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, lr}
-; CHECK-NEXT:    ldr r7, [sp, #28]
-; CHECK-NEXT:    cmp r7, #0
+; CHECK-NEXT:    ldr.w r12, [sp, #28]
+; CHECK-NEXT:    cmp.w r12, #0
 ; CHECK-NEXT:    beq.w .LBB7_12
 ; CHECK-NEXT:  @ %bb.1: @ %for.body.lr.ph
-; CHECK-NEXT:    add.w r4, r3, r7, lsl #2
-; CHECK-NEXT:    adds r5, r1, r7
-; CHECK-NEXT:    cmp r4, r1
-; CHECK-NEXT:    add.w r6, r0, r7
-; CHECK-NEXT:    cset r12, hi
-; CHECK-NEXT:    cmp r5, r3
-; CHECK-NEXT:    cset r5, hi
-; CHECK-NEXT:    cmp r4, r0
-; CHECK-NEXT:    cset r4, hi
+; CHECK-NEXT:    add.w r5, r3, r12, lsl #2
+; CHECK-NEXT:    add.w r6, r1, r12
+; CHECK-NEXT:    cmp r5, r1
+; CHECK-NEXT:    add.w r4, r0, r12
+; CHECK-NEXT:    cset r7, hi
 ; CHECK-NEXT:    cmp r6, r3
 ; CHECK-NEXT:    cset r6, hi
-; CHECK-NEXT:    ands r6, r4
-; CHECK-NEXT:    lsls r6, r6, #31
+; CHECK-NEXT:    cmp r5, r0
+; CHECK-NEXT:    cset r5, hi
+; CHECK-NEXT:    cmp r4, r3
+; CHECK-NEXT:    cset r4, hi
+; CHECK-NEXT:    ands r5, r4
+; CHECK-NEXT:    lsls r5, r5, #31
 ; CHECK-NEXT:    itt eq
-; CHECK-NEXT:    andeq.w r6, r5, r12
-; CHECK-NEXT:    lslseq.w r6, r6, #31
+; CHECK-NEXT:    andeq r7, r6
+; CHECK-NEXT:    lslseq.w r7, r7, #31
 ; CHECK-NEXT:    beq .LBB7_4
 ; CHECK-NEXT:  @ %bb.2: @ %for.body.preheader
-; CHECK-NEXT:    subs r6, r7, #1
-; CHECK-NEXT:    and lr, r7, #3
-; CHECK-NEXT:    cmp r6, #3
+; CHECK-NEXT:    sub.w r4, r12, #1
+; CHECK-NEXT:    and lr, r12, #3
+; CHECK-NEXT:    cmp r4, #3
 ; CHECK-NEXT:    bhs .LBB7_6
 ; CHECK-NEXT:  @ %bb.3:
 ; CHECK-NEXT:    movs r7, #0
 ; CHECK-NEXT:    b .LBB7_9
 ; CHECK-NEXT:  .LBB7_4: @ %vector.ph
-; CHECK-NEXT:    adds r6, r7, #3
-; CHECK-NEXT:    movs r5, #1
-; CHECK-NEXT:    bic r6, r6, #3
-; CHECK-NEXT:    subs r7, #1
-; CHECK-NEXT:    subs r6, #4
-; CHECK-NEXT:    vdup.32 q0, r7
-; CHECK-NEXT:    movs r7, #0
-; CHECK-NEXT:    add.w lr, r5, r6, lsr #2
-; CHECK-NEXT:    adr r6, .LCPI7_0
-; CHECK-NEXT:    vldrw.u32 q1, [r6]
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    add.w r7, r12, #3
+; CHECK-NEXT:    movs r6, #1
+; CHECK-NEXT:    bic r7, r7, #3
+; CHECK-NEXT:    movs r4, #0
+; CHECK-NEXT:    subs r7, #4
+; CHECK-NEXT:    add.w lr, r6, r7, lsr #2
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB7_5: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q2, q1, r7
-; CHECK-NEXT:    adds r4, r0, r7
-; CHECK-NEXT:    vpt.u32 cs, q0, q2
-; CHECK-NEXT:    vldrbt.u32 q2, [r4]
-; CHECK-NEXT:    adds r4, r1, r7
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vldrbt.u32 q3, [r4]
-; CHECK-NEXT:    vmul.i32 q2, q3, q2
-; CHECK-NEXT:    vadd.i32 q2, q2, r2
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q2, [r3]
+; CHECK-NEXT:    adds r5, r0, r4
+; CHECK-NEXT:    vldrb.u32 q0, [r5]
+; CHECK-NEXT:    adds r5, r1, r4
+; CHECK-NEXT:    vldrb.u32 q1, [r5]
+; CHECK-NEXT:    vmul.i32 q0, q1, q0
+; CHECK-NEXT:    vadd.i32 q0, q0, r2
+; CHECK-NEXT:    vstrw.32 q0, [r3]
 ; CHECK-NEXT:    adds r3, #16
-; CHECK-NEXT:    adds r7, #4
-; CHECK-NEXT:    le lr, .LBB7_5
+; CHECK-NEXT:    adds r4, #4
+; CHECK-NEXT:    sub.w r12, r12, #4
+; CHECK-NEXT:    letp lr, .LBB7_5
 ; CHECK-NEXT:    b .LBB7_12
 ; CHECK-NEXT:  .LBB7_6: @ %for.body.preheader.new
-; CHECK-NEXT:    sub.w r12, lr, r7
+; CHECK-NEXT:    sub.w r12, lr, r12
 ; CHECK-NEXT:    subs r4, r1, #3
 ; CHECK-NEXT:    subs r5, r0, #3
 ; CHECK-NEXT:    sub.w r7, r3, #16
@@ -857,13 +769,6 @@
 ; CHECK-NEXT:    le lr, .LBB7_11
 ; CHECK-NEXT:  .LBB7_12: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.13:
-; CHECK-NEXT:  .LCPI7_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %res12 = bitcast i32* %res to i8*
   %cmp10 = icmp eq i32 %N, 0
@@ -1018,36 +923,21 @@
 ; CHECK-NEXT:    bic lr, lr, #3
 ; CHECK-NEXT:    sub.w lr, lr, #4
 ; CHECK-NEXT:    add.w lr, r4, lr, lsr #2
-; CHECK-NEXT:    sub.w r4, r12, #1
-; CHECK-NEXT:    vdup.32 q0, r4
-; CHECK-NEXT:    adr r4, .LCPI8_0
-; CHECK-NEXT:    vldrw.u32 q1, [r4]
-; CHECK-NEXT:    mov.w r12, #0
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, lr
 ; CHECK-NEXT:  .LBB8_1: @ %vector.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vadd.i32 q2, q1, r12
-; CHECK-NEXT:    add.w r12, r12, #4
-; CHECK-NEXT:    vptt.u32 cs, q0, q2
-; CHECK-NEXT:    vldrht.u32 q2, [r0]
-; CHECK-NEXT:    vldrht.u32 q3, [r1]
+; CHECK-NEXT:    vldrh.u32 q0, [r0]
+; CHECK-NEXT:    vldrh.u32 q1, [r1]
+; CHECK-NEXT:    vmul.i32 q0, q1, q0
 ; CHECK-NEXT:    adds r0, #8
-; CHECK-NEXT:    vmul.i32 q2, q3, q2
+; CHECK-NEXT:    vadd.i32 q0, q0, r2
+; CHECK-NEXT:    vstrw.32 q0, [r3]
 ; CHECK-NEXT:    adds r1, #8
-; CHECK-NEXT:    vadd.i32 q2, q2, r2
-; CHECK-NEXT:    vpst
-; CHECK-NEXT:    vstrwt.32 q2, [r3]
 ; CHECK-NEXT:    adds r3, #16
-; CHECK-NEXT:    le lr, .LBB8_1
+; CHECK-NEXT:    sub.w r12, r12, #4
+; CHECK-NEXT:    letp lr, .LBB8_1
 ; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
 ; CHECK-NEXT:    pop {r4, pc}
-; CHECK-NEXT:    .p2align 4
-; CHECK-NEXT:  @ %bb.3:
-; CHECK-NEXT:  .LCPI8_0:
-; CHECK-NEXT:    .long 0 @ 0x0
-; CHECK-NEXT:    .long 1 @ 0x1
-; CHECK-NEXT:    .long 2 @ 0x2
-; CHECK-NEXT:    .long 3 @ 0x3
 entry:
   %cmp10 = icmp eq i32 %N, 0
   br i1 %cmp10, label %for.cond.cleanup, label %vector.ph
@@ -1320,18 +1210,79 @@
   br i1 %niter.ncmp.3, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body
 }
 
-; Function Attrs: argmemonly nounwind readonly willreturn
-declare <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>*, i32 immarg, <4 x i1>, <4 x i8>) #2
+define dso_local arm_aapcs_vfpcc void @test_v8i8_to_v8i16(i16* noalias nocapture %a, i8* nocapture readonly %b, i8* nocapture readonly %c, i32 %N) {
+; CHECK-LABEL: test_v8i8_to_v8i16:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    push {r4, lr}
+; CHECK-NEXT:    cmp r3, #0
+; CHECK-NEXT:    it eq
+; CHECK-NEXT:    popeq {r4, pc}
+; CHECK-NEXT:    add.w r12, r3, #7
+; CHECK-NEXT:    mov.w lr, #1
+; CHECK-NEXT:    bic r12, r12, #7
+; CHECK-NEXT:    sub.w r12, r12, #8
+; CHECK-NEXT:    add.w lr, lr, r12, lsr #3
+; CHECK-NEXT:    mov.w r12, #0
+; CHECK-NEXT:    dlstp.16 lr, lr
+; CHECK-NEXT:  .LBB10_1: @ %vector.body
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    add.w r4, r1, r12
+; CHECK-NEXT:    vldrb.u16 q0, [r4]
+; CHECK-NEXT:    add.w r4, r2, r12
+; CHECK-NEXT:    vldrb.u16 q1, [r4]
+; CHECK-NEXT:    vmul.i16 q0, q1, q0
+; CHECK-NEXT:    vstrh.16 q0, [r0]
+; CHECK-NEXT:    adds r0, #16
+; CHECK-NEXT:    add.w r12, r12, #8
+; CHECK-NEXT:    subs r3, #8
+; CHECK-NEXT:    letp lr, .LBB10_1
+; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
+; CHECK-NEXT:    pop {r4, pc}
+entry:
+  %cmp10 = icmp eq i32 %N, 0
+  br i1 %cmp10, label %for.cond.cleanup, label %vector.ph
+
+vector.ph:                                        ; preds = %entry
+  %n.rnd.up = add i32 %N, 7
+  %n.vec = and i32 %n.rnd.up, -8
+  %trip.count.minus.1 = add i32 %N, -1
+  %broadcast.splatinsert12 = insertelement <8 x i32> undef, i32 %trip.count.minus.1, i32 0
+  %broadcast.splat13 = shufflevector <8 x i32> %broadcast.splatinsert12, <8 x i32> undef, <8 x i32> zeroinitializer
+  br label %vector.body
+
+vector.body:                                      ; preds = %vector.body, %vector.ph
+  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+  %broadcast.splatinsert = insertelement <8 x i32> undef, i32 %index, i32 0
+  %broadcast.splat = shufflevector <8 x i32> %broadcast.splatinsert, <8 x i32> undef, <8 x i32> zeroinitializer
+  %induction = add <8 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %0 = getelementptr inbounds i8, i8* %b, i32 %index
+  %1 = icmp ule <8 x i32> %induction, %broadcast.splat13
+  %2 = bitcast i8* %0 to <8 x i8>*
+  %wide.masked.load = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %2, i32 1, <8 x i1> %1, <8 x i8> undef)
+  %3 = zext <8 x i8> %wide.masked.load to <8 x i16>
+  %4 = getelementptr inbounds i8, i8* %c, i32 %index
+  %5 = bitcast i8* %4 to <8 x i8>*
+  %wide.masked.load14 = call <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>* %5, i32 1, <8 x i1> %1, <8 x i8> undef)
+  %6 = zext <8 x i8> %wide.masked.load14 to <8 x i16>
+  %7 = mul nuw <8 x i16> %6, %3
+  %8 = getelementptr inbounds i16, i16* %a, i32 %index
+  %9 = bitcast i16* %8 to <8 x i16>*
+  call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %7, <8 x i16>* %9, i32 2, <8 x i1> %1)
+  %index.next = add i32 %index, 8
+  %10 = icmp eq i32 %index.next, %n.vec
+  br i1 %10, label %for.cond.cleanup, label %vector.body
 
-; Function Attrs: nounwind readnone willreturn
-declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>) #3
+for.cond.cleanup:                                 ; preds = %vector.body, %entry
+  ret void
+}
 
-; Function Attrs: argmemonly nounwind readonly willreturn
-declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>) #2
+declare <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>*, i32 immarg, <4 x i1>, <4 x i8>)
+declare <8 x i8> @llvm.masked.load.v8i8.p0v8i8(<8 x i8>*, i32 immarg, <8 x i1>, <8 x i8>)
+declare <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>*, i32 immarg, <4 x i1>, <4 x i16>)
+declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
+declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32 immarg, <8 x i1>)
+declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
+declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
 
-; Function Attrs: argmemonly nounwind readonly willreturn
-declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #2
 
-; Function Attrs: argmemonly nounwind willreturn
-declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #4
 
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/nested.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/nested.ll
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/nested.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/nested.ll
@@ -1,9 +1,58 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -mtriple=armv8.1m.main -mattr=+mve -S -mve-tail-predication -disable-mve-tail-predication=false %s -o - | FileCheck %s
 
-; TODO: Support extending loads
-; CHECK-LABEL: mat_vec_sext_i16
-; CHECK-NOT: call {{.*}} @llvm.arm.vctp
 define void @mat_vec_sext_i16(i16** nocapture readonly %A, i16* nocapture readonly %B, i32* noalias nocapture %C, i32 %N) {
+; CHECK-LABEL: @mat_vec_sext_i16(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP24:%.*]] = icmp eq i32 [[N:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP24]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_COND1_PREHEADER_US_PREHEADER:%.*]]
+; CHECK:       for.cond1.preheader.us.preheader:
+; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 3
+; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -4
+; CHECK-NEXT:    [[TMP:%.*]] = add i32 [[N_VEC]], -4
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i32 [[TMP]], 2
+; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1
+; CHECK-NEXT:    br label [[FOR_COND1_PREHEADER_US:%.*]]
+; CHECK:       for.cond1.preheader.us:
+; CHECK-NEXT:    [[I_025_US:%.*]] = phi i32 [ [[INC10_US:%.*]], [[MIDDLE_BLOCK:%.*]] ], [ 0, [[FOR_COND1_PREHEADER_US_PREHEADER]] ]
+; CHECK-NEXT:    [[ARRAYIDX_US:%.*]] = getelementptr inbounds i16*, i16** [[A:%.*]], i32 [[I_025_US]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i16*, i16** [[ARRAYIDX_US]], align 4
+; CHECK-NEXT:    [[ARRAYIDX8_US:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[I_025_US]]
+; CHECK-NEXT:    [[ARRAYIDX8_PROMOTED_US:%.*]] = load i32, i32* [[ARRAYIDX8_US]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> <i32 undef, i32 0, i32 0, i32 0>, i32 [[ARRAYIDX8_PROMOTED_US]], i32 0
+; CHECK-NEXT:    call void @llvm.set.loop.iterations.i32(i32 [[TMP2]])
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER_US]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP4]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP14:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = phi i32 [ [[TMP2]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP15:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi i32 [ [[N]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[TMP3]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.vctp32(i32 [[TMP0]])
+; CHECK-NEXT:    [[TMP2]] = sub i32 [[TMP0]], 4
+; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i16* [[TMP6]] to <4 x i16>*
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP8]], i32 2, <4 x i1> [[TMP1]], <4 x i16> undef)
+; CHECK-NEXT:    [[TMP9:%.*]] = sext <4 x i16> [[WIDE_MASKED_LOAD]] to <4 x i32>
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i16, i16* [[B:%.*]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i16* [[TMP10]] to <4 x i16>*
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD30:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* [[TMP11]], i32 2, <4 x i1> [[TMP1]], <4 x i16> undef)
+; CHECK-NEXT:    [[TMP12:%.*]] = sext <4 x i16> [[WIDE_MASKED_LOAD30]] to <4 x i32>
+; CHECK-NEXT:    [[TMP13:%.*]] = mul nsw <4 x i32> [[TMP12]], [[TMP9]]
+; CHECK-NEXT:    [[TMP14]] = add nsw <4 x i32> [[TMP13]], [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP15]] = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 [[TMP5]], i32 1)
+; CHECK-NEXT:    [[TMP16:%.*]] = icmp ne i32 [[TMP15]], 0
+; CHECK-NEXT:    br i1 [[TMP16]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP17:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[TMP14]], <4 x i32> [[VEC_PHI]]
+; CHECK-NEXT:    [[TMP18:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP17]])
+; CHECK-NEXT:    store i32 [[TMP18]], i32* [[ARRAYIDX8_US]], align 4
+; CHECK-NEXT:    [[INC10_US]] = add nuw i32 [[I_025_US]], 1
+; CHECK-NEXT:    [[EXITCOND27:%.*]] = icmp eq i32 [[INC10_US]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND27]], label [[FOR_COND_CLEANUP]], label [[FOR_COND1_PREHEADER_US]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+;
 entry:
   %cmp24 = icmp eq i32 %N, 0
   br i1 %cmp24, label %for.cond.cleanup, label %for.cond1.preheader.us.preheader
@@ -64,16 +113,56 @@
   ret void
 }
 
-; CHECK-LABEL: mat_vec_i32
-; CHECK: phi
-; CHECK: phi
-; CHECK: phi
-; CHECK: [[IV:%[^ ]+]] = phi i32 [ %N, %for.cond1.preheader.us ], [ [[REM:%[^ ]+]], %vector.body ]
-; CHECK: [[VCTP:%[^ ]+]] = call <4 x i1> @llvm.arm.vctp32(i32 [[IV]])
-; CHECK: [[REM]] = sub i32 [[IV]], 4
-; CHECK: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{.*}}, i32 4, <4 x i1> [[VCTP]], <4 x i32> undef)
-; CHECK: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{.*}}, i32 4, <4 x i1> [[VCTP]], <4 x i32> undef)
 define void @mat_vec_i32(i32** nocapture readonly %A, i32* nocapture readonly %B, i32* noalias nocapture %C, i32 %N) {
+; CHECK-LABEL: @mat_vec_i32(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP23:%.*]] = icmp eq i32 [[N:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP23]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_COND1_PREHEADER_US_PREHEADER:%.*]]
+; CHECK:       for.cond1.preheader.us.preheader:
+; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], 3
+; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N_RND_UP]], -4
+; CHECK-NEXT:    [[TMP:%.*]] = add i32 [[N_VEC]], -4
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i32 [[TMP]], 2
+; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1
+; CHECK-NEXT:    br label [[FOR_COND1_PREHEADER_US:%.*]]
+; CHECK:       for.cond1.preheader.us:
+; CHECK-NEXT:    [[I_024_US:%.*]] = phi i32 [ [[INC9_US:%.*]], [[MIDDLE_BLOCK:%.*]] ], [ 0, [[FOR_COND1_PREHEADER_US_PREHEADER]] ]
+; CHECK-NEXT:    [[ARRAYIDX_US:%.*]] = getelementptr inbounds i32*, i32** [[A:%.*]], i32 [[I_024_US]]
+; CHECK-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[ARRAYIDX_US]], align 4
+; CHECK-NEXT:    [[ARRAYIDX7_US:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[I_024_US]]
+; CHECK-NEXT:    [[ARRAYIDX7_PROMOTED_US:%.*]] = load i32, i32* [[ARRAYIDX7_US]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> <i32 undef, i32 0, i32 0, i32 0>, i32 [[ARRAYIDX7_PROMOTED_US]], i32 0
+; CHECK-NEXT:    call void @llvm.set.loop.iterations.i32(i32 [[TMP2]])
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER_US]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP4]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP12:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = phi i32 [ [[TMP2]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi i32 [ [[N]], [[FOR_COND1_PREHEADER_US]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i1> @llvm.arm.vctp32(i32 [[TMP0]])
+; CHECK-NEXT:    [[TMP2]] = sub i32 [[TMP0]], 4
+; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP8]], i32 4, <4 x i1> [[TMP1]], <4 x i32> undef)
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD29:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* [[TMP10]], i32 4, <4 x i1> [[TMP1]], <4 x i32> undef)
+; CHECK-NEXT:    [[TMP11:%.*]] = mul nsw <4 x i32> [[WIDE_MASKED_LOAD29]], [[WIDE_MASKED_LOAD]]
+; CHECK-NEXT:    [[TMP12]] = add nsw <4 x i32> [[VEC_PHI]], [[TMP11]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP13]] = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 [[TMP5]], i32 1)
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp ne i32 [[TMP13]], 0
+; CHECK-NEXT:    br i1 [[TMP14]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP15:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[TMP12]], <4 x i32> [[VEC_PHI]]
+; CHECK-NEXT:    [[TMP16:%.*]] = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[TMP15]])
+; CHECK-NEXT:    store i32 [[TMP16]], i32* [[ARRAYIDX7_US]], align 4
+; CHECK-NEXT:    [[INC9_US]] = add nuw i32 [[I_024_US]], 1
+; CHECK-NEXT:    [[EXITCOND26:%.*]] = icmp eq i32 [[INC9_US]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND26]], label [[FOR_COND_CLEANUP]], label [[FOR_COND1_PREHEADER_US]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+;
 entry:
   %cmp23 = icmp eq i32 %N, 0
   br i1 %cmp23, label %for.cond.cleanup, label %for.cond1.preheader.us.preheader
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/wlstp.mir
@@ -0,0 +1,531 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
+
+--- |
+  define dso_local arm_aapcs_vfpcc void @test_wlstp8(i8* noalias nocapture %a, i8* noalias nocapture readonly %b, i8* noalias nocapture readonly %c, i32 %N) {
+  entry:
+    %0 = add i32 %N, 15
+    %1 = lshr i32 %0, 4
+    %2 = shl nuw i32 %1, 4
+    %3 = add i32 %2, -16
+    %4 = lshr i32 %3, 4
+    %n.vec = add nuw nsw i32 %4, 1
+    %cmp = call i1 @llvm.test.set.loop.iterations.i32(i32 %n.vec)
+    br i1 %cmp, label %for.cond.cleanup, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+    %count = phi i32 [ %n.vec, %vector.ph ], [ %loop.dec, %vector.body ]
+    %5 = phi i32 [ %N, %vector.ph ], [ %7, %vector.body ]
+    %6 = call <16 x i1> @llvm.arm.vctp8(i32 %5)
+    %7 = sub i32 %5, 16
+    %scevgep4 = getelementptr i8, i8* %b, i32 %index
+    %scevgep45 = bitcast i8* %scevgep4 to <16 x i8>*
+    %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %scevgep45, i32 1, <16 x i1> %6, <16 x i8> undef)
+    %scevgep2 = getelementptr i8, i8* %c, i32 %index
+    %scevgep23 = bitcast i8* %scevgep2 to <16 x i8>*
+    %wide.masked.load14 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %scevgep23, i32 1, <16 x i1> %6, <16 x i8> undef)
+    %tmp5 = mul <16 x i8> %wide.masked.load14, %wide.masked.load
+    %scevgep = getelementptr i8, i8* %a, i32 %index
+    %scevgep1 = bitcast i8* %scevgep to <16 x i8>*
+    call void @llvm.masked.store.v16i8.p0v16i8(<16 x i8> %tmp5, <16 x i8>* %scevgep1, i32 1, <16 x i1> %6)
+    %index.next = add i32 %index, 16
+    %loop.dec = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
+    %tmp8 = icmp eq i32 %loop.dec, 0
+    br i1 %tmp8, label %for.cond.cleanup, label %vector.body
+
+  for.cond.cleanup:                                 ; preds = %vector.body, %entry
+    ret void
+  }
+
+  define dso_local arm_aapcs_vfpcc void @test_wlstp16(i16* noalias nocapture %a, i16* noalias nocapture readonly %b, i16* noalias nocapture readonly %c, i32 %N) {
+  entry:
+    %0 = add i32 %N, 7
+    %1 = lshr i32 %0, 3
+    %2 = shl nuw i32 %1, 3
+    %3 = add i32 %2, -8
+    %4 = lshr i32 %3, 3
+    %n.vec = add nuw nsw i32 %4, 1
+    %cmp = call i1 @llvm.test.set.loop.iterations.i32(i32 %n.vec)
+    br i1 %cmp, label %for.cond.cleanup, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv5 = phi i16* [ %scevgep6, %vector.body ], [ %b, %vector.ph ]
+    %lsr.iv2 = phi i16* [ %scevgep3, %vector.body ], [ %c, %vector.ph ]
+    %lsr.iv = phi i16* [ %scevgep, %vector.body ], [ %a, %vector.ph ]
+    %count = phi i32 [ %n.vec, %vector.ph ], [ %loop.dec, %vector.body ]
+    %5 = phi i32 [ %N, %vector.ph ], [ %7, %vector.body ]
+    %lsr.iv57 = bitcast i16* %lsr.iv5 to <8 x i16>*
+    %lsr.iv24 = bitcast i16* %lsr.iv2 to <8 x i16>*
+    %lsr.iv1 = bitcast i16* %lsr.iv to <8 x i16>*
+    %6 = call <8 x i1> @llvm.arm.vctp16(i32 %5)
+    %7 = sub i32 %5, 8
+    %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %lsr.iv57, i32 2, <8 x i1> %6, <8 x i16> undef)
+    %wide.masked.load14 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %lsr.iv24, i32 2, <8 x i1> %6, <8 x i16> undef)
+    %tmp5 = mul <8 x i16> %wide.masked.load14, %wide.masked.load
+    call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %tmp5, <8 x i16>* %lsr.iv1, i32 2, <8 x i1> %6)
+    %loop.dec = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
+    %tmp8 = icmp eq i32 %loop.dec, 0
+    %scevgep = getelementptr i16, i16* %lsr.iv, i32 8
+    %scevgep3 = getelementptr i16, i16* %lsr.iv2, i32 8
+    %scevgep6 = getelementptr i16, i16* %lsr.iv5, i32 8
+    br i1 %tmp8, label %for.cond.cleanup, label %vector.body
+
+  for.cond.cleanup:                                 ; preds = %vector.body, %entry
+    ret void
+  }
+
+  define dso_local i32 @test_wlstp32(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) {
+  entry:
+    %0 = add i32 %N, 3
+    %1 = lshr i32 %0, 2
+    %2 = shl nuw i32 %1, 2
+    %3 = add i32 %2, -4
+    %4 = lshr i32 %3, 2
+    %n.vec = add nuw nsw i32 %4, 1
+    %cmp = call i1 @llvm.test.set.loop.iterations.i32(i32 %n.vec)
+    br i1 %cmp, label %for.cond.cleanup, label %vector.ph
+
+  vector.ph:                                        ; preds = %entry
+    br label %vector.body
+
+  vector.body:                                      ; preds = %vector.body, %vector.ph
+    %lsr.iv2 = phi i32* [ %scevgep3, %vector.body ], [ %a, %vector.ph ]
+    %lsr.iv = phi i32* [ %scevgep, %vector.body ], [ %b, %vector.ph ]
+    %count = phi i32 [ %n.vec, %vector.ph ], [ %loop.dec, %vector.body ]
+    %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %tmp6, %vector.body ]
+    %5 = phi i32 [ %N, %vector.ph ], [ %7, %vector.body ]
+    %lsr.iv24 = bitcast i32* %lsr.iv2 to <4 x i32>*
+    %lsr.iv1 = bitcast i32* %lsr.iv to <4 x i32>*
+    %6 = call <4 x i1> @llvm.arm.vctp32(i32 %5)
+    %7 = sub i32 %5, 4
+    %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv24, i32 4, <4 x i1> %6, <4 x i32> undef)
+    %wide.masked.load13 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv1, i32 4, <4 x i1> %6, <4 x i32> undef)
+    %tmp5 = mul nsw <4 x i32> %wide.masked.load13, %wide.masked.load
+    %tmp6 = add nsw <4 x i32> %tmp5, %vec.phi
+    %loop.dec = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %count, i32 1)
+    %tmp7 = icmp eq i32 %loop.dec, 0
+    %scevgep = getelementptr i32, i32* %lsr.iv, i32 4
+    %scevgep3 = getelementptr i32, i32* %lsr.iv2, i32 4
+    br i1 %tmp7, label %middle.block, label %vector.body
+
+  middle.block:                                     ; preds = %vector.body
+    %8 = call <4 x i1> @llvm.arm.vctp32(i32 %5)
+    %tmp8 = select <4 x i1> %8, <4 x i32> %tmp6, <4 x i32> %vec.phi
+    %tmp9 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %tmp8)
+    br label %for.cond.cleanup
+
+  for.cond.cleanup:                                 ; preds = %middle.block, %entry
+    %res.0.lcssa = phi i32 [ 0, %entry ], [ %tmp9, %middle.block ]
+    ret i32 %res.0.lcssa
+  }
+
+  declare i1 @llvm.test.set.loop.iterations.i32(i32)
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
+  declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32 immarg, <16 x i1>, <16 x i8>)
+  declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>)
+  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
+  declare void @llvm.masked.store.v16i8.p0v16i8(<16 x i8>, <16 x i8>*, i32 immarg, <16 x i1>)
+  declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32 immarg, <8 x i1>)
+  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
+  declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
+  declare <16 x i1> @llvm.arm.vctp8(i32)
+  declare void @llvm.stackprotector(i8*, i8**)
+  declare <8 x i1> @llvm.arm.vctp16(i32)
+  declare <4 x i1> @llvm.arm.vctp32(i32)
+...
+---
+name:            test_wlstp8
+alignment:       2
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+  - { reg: '$r3', virtual-reg: '' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    4
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 0
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: test_wlstp8
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.3(0x40000000), %bb.1(0x40000000)
+  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r4, $lr
+  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -8
+  ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 15, 14, $noreg, $noreg
+  ; CHECK:   renamable $lr = t2MOVi 1, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 15, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 16, 14, $noreg, $noreg
+  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14, $noreg, $noreg
+  ; CHECK:   $lr = MVE_WLSTP_8 renamable $lr, %bb.1
+  ; CHECK:   tB %bb.3, 14, $noreg
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   renamable $r12 = t2MOVi 0, 14, $noreg, $noreg
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.3(0x04000000), %bb.2(0x7c000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   renamable $r4 = t2ADDrr renamable $r1, renamable $r12, 14, $noreg, $noreg
+  ; CHECK:   renamable $q0 = MVE_VLDRBU8 killed renamable $r4, 0, 0, $noreg :: (load 16 from %ir.scevgep45, align 1)
+  ; CHECK:   renamable $r4 = t2ADDrr renamable $r2, renamable $r12, 14, $noreg, $noreg
+  ; CHECK:   renamable $q1 = MVE_VLDRBU8 killed renamable $r4, 0, 0, $noreg :: (load 16 from %ir.scevgep23, align 1)
+  ; CHECK:   renamable $r4 = t2ADDrr renamable $r0, renamable $r12, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2ADDri killed renamable $r12, 16, 14, $noreg, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14, $noreg
+  ; CHECK:   renamable $q0 = MVE_VMULt1i8 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+  ; CHECK:   MVE_VSTRBU8 killed renamable $q0, killed renamable $r4, 0, 0, killed $noreg :: (store 16 into %ir.scevgep1, align 1)
+  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.2
+  ; CHECK: bb.3.for.cond.cleanup:
+  ; CHECK:   tPOP_RET 14, $noreg, def $r4, def $pc
+  bb.0.entry:
+    successors: %bb.3(0x40000000), %bb.1(0x40000000)
+    liveins: $r0, $r1, $r2, $r3, $r4, $lr
+
+    frame-setup tPUSH 14, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r4, -8
+    renamable $r12 = t2ADDri renamable $r3, 15, 14, $noreg, $noreg
+    renamable $lr = t2MOVi 1, 14, $noreg, $noreg
+    renamable $r12 = t2BICri killed renamable $r12, 15, 14, $noreg, $noreg
+    renamable $r12 = t2SUBri killed renamable $r12, 16, 14, $noreg, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 35, 14, $noreg, $noreg
+    t2WhileLoopStart renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.3, 14, $noreg
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $lr, $r0, $r1, $r2, $r3
+
+    renamable $r12 = t2MOVi 0, 14, $noreg, $noreg
+
+  bb.2.vector.body:
+    successors: %bb.3(0x04000000), %bb.2(0x7c000000)
+    liveins: $lr, $r0, $r1, $r2, $r3, $r12
+
+    renamable $r4 = t2ADDrr renamable $r1, renamable $r12, 14, $noreg, $noreg
+    renamable $vpr = MVE_VCTP8 renamable $r3, 0, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $q0 = MVE_VLDRBU8 killed renamable $r4, 0, 1, renamable $vpr :: (load 16 from %ir.scevgep45, align 1)
+    renamable $r4 = t2ADDrr renamable $r2, renamable $r12, 14, $noreg, $noreg
+    MVE_VPST 8, implicit $vpr
+    renamable $q1 = MVE_VLDRBU8 killed renamable $r4, 0, 1, renamable $vpr :: (load 16 from %ir.scevgep23, align 1)
+    renamable $r4 = t2ADDrr renamable $r0, renamable $r12, 14, $noreg, $noreg
+    renamable $r12 = t2ADDri killed renamable $r12, 16, 14, $noreg, $noreg
+    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 16, 14, $noreg
+    renamable $q0 = MVE_VMULt1i8 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+    MVE_VPST 8, implicit $vpr
+    MVE_VSTRBU8 killed renamable $q0, killed renamable $r4, 0, 1, killed renamable $vpr :: (store 16 into %ir.scevgep1, align 1)
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.3, 14, $noreg
+
+  bb.3.for.cond.cleanup:
+    tPOP_RET 14, $noreg, def $r4, def $pc
+
+...
+---
+name:            test_wlstp16
+alignment:       2
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+  - { reg: '$r3', virtual-reg: '' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    4
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 0
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: test_wlstp16
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; CHECK:   liveins: $r0, $r1, $r2, $r3, $r7, $lr
+  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
+  ; CHECK:   renamable $r12 = t2ADDri renamable $r3, 7, 14, $noreg, $noreg
+  ; CHECK:   renamable $lr = t2MOVi 1, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2BICri killed renamable $r12, 7, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r12, 8, 14, $noreg, $noreg
+  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 27, 14, $noreg, $noreg
+  ; CHECK:   $lr = MVE_WLSTP_16 renamable $lr, %bb.1
+  ; CHECK:   tB %bb.2, 14, $noreg
+  ; CHECK: bb.1.vector.body:
+  ; CHECK:   successors: %bb.2(0x04000000), %bb.1(0x7c000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   renamable $q0 = MVE_VLDRHU16 renamable $r1, 0, 0, $noreg :: (load 16 from %ir.lsr.iv57, align 2)
+  ; CHECK:   renamable $q1 = MVE_VLDRHU16 renamable $r2, 0, 0, $noreg :: (load 16 from %ir.lsr.iv24, align 2)
+  ; CHECK:   renamable $q0 = MVE_VMULt1i16 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+  ; CHECK:   MVE_VSTRHU16 killed renamable $q0, renamable $r0, 0, 0, killed $noreg :: (store 16 into %ir.lsr.iv1, align 2)
+  ; CHECK:   renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tADDi8 killed renamable $r2, 16, 14, $noreg
+  ; CHECK:   renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 8, 14, $noreg
+  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.1
+  ; CHECK: bb.2.for.cond.cleanup:
+  ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc
+  bb.0.entry:
+    successors: %bb.2(0x40000000), %bb.1(0x40000000)
+    liveins: $r0, $r1, $r2, $r3, $r7, $lr
+
+    frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    renamable $r12 = t2ADDri renamable $r3, 7, 14, $noreg, $noreg
+    renamable $lr = t2MOVi 1, 14, $noreg, $noreg
+    renamable $r12 = t2BICri killed renamable $r12, 7, 14, $noreg, $noreg
+    renamable $r12 = t2SUBri killed renamable $r12, 8, 14, $noreg, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $lr, killed renamable $r12, 27, 14, $noreg, $noreg
+    t2WhileLoopStart renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.2, 14, $noreg
+
+  bb.1.vector.body:
+    successors: %bb.2(0x04000000), %bb.1(0x7c000000)
+    liveins: $lr, $r0, $r1, $r2, $r3
+
+    renamable $vpr = MVE_VCTP16 renamable $r3, 0, $noreg
+    MVE_VPST 4, implicit $vpr
+    renamable $q0 = MVE_VLDRHU16 renamable $r1, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv57, align 2)
+    renamable $q1 = MVE_VLDRHU16 renamable $r2, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 2)
+    renamable $q0 = MVE_VMULt1i16 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+    MVE_VPST 8, implicit $vpr
+    MVE_VSTRHU16 killed renamable $q0, renamable $r0, 0, 1, killed renamable $vpr :: (store 16 into %ir.lsr.iv1, align 2)
+    renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg
+    renamable $r2, dead $cpsr = tADDi8 killed renamable $r2, 16, 14, $noreg
+    renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg
+    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 8, 14, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.2, 14, $noreg
+
+  bb.2.for.cond.cleanup:
+    tPOP_RET 14, $noreg, def $r7, def $pc
+
+...
+---
+name:            test_wlstp32
+alignment:       2
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    4
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 0
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: test_wlstp32
+  ; CHECK: bb.0.entry:
+  ; CHECK:   successors: %bb.4(0x40000000), %bb.1(0x40000000)
+  ; CHECK:   liveins: $r0, $r1, $r2, $r7, $lr
+  ; CHECK:   frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
+  ; CHECK:   renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg
+  ; CHECK:   renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
+  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg
+  ; CHECK:   renamable $r12 = t2MOVi 0, 14, $noreg, $noreg
+  ; CHECK:   $lr = MVE_WLSTP_32 renamable $lr, %bb.1
+  ; CHECK:   tB %bb.4, 14, $noreg
+  ; CHECK: bb.1.vector.ph:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2
+  ; CHECK:   renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+  ; CHECK: bb.2.vector.body:
+  ; CHECK:   successors: %bb.3(0x04000000), %bb.2(0x7c000000)
+  ; CHECK:   liveins: $lr, $q1, $r0, $r1, $r2
+  ; CHECK:   $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0
+  ; CHECK:   renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 0, $noreg :: (load 16 from %ir.lsr.iv24, align 4)
+  ; CHECK:   renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 0, killed $noreg :: (load 16 from %ir.lsr.iv1, align 4)
+  ; CHECK:   $r3 = tMOVr $r2, 14, $noreg
+  ; CHECK:   renamable $q1 = nsw MVE_VMULt1i32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
+  ; CHECK:   renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg
+  ; CHECK:   renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed $r2, 4, 14, $noreg
+  ; CHECK:   renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1
+  ; CHECK:   $lr = MVE_LETP renamable $lr, %bb.2
+  ; CHECK: bb.3.middle.block:
+  ; CHECK:   successors: %bb.4(0x80000000)
+  ; CHECK:   liveins: $q0, $q1, $r3
+  ; CHECK:   renamable $vpr = MVE_VCTP32 killed renamable $r3, 0, $noreg
+  ; CHECK:   renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr
+  ; CHECK:   renamable $r12 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg
+  ; CHECK: bb.4.for.cond.cleanup:
+  ; CHECK:   liveins: $r12
+  ; CHECK:   $r0 = tMOVr killed $r12, 14, $noreg
+  ; CHECK:   tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0
+  bb.0.entry:
+    successors: %bb.4(0x40000000), %bb.1(0x40000000)
+    liveins: $r0, $r1, $r2, $r7, $lr
+
+    frame-setup tPUSH 14, $noreg, killed $r7, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg
+    renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg
+    renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg
+    renamable $r12 = t2MOVi 0, 14, $noreg, $noreg
+    t2WhileLoopStart renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.4, 14, $noreg
+
+  bb.1.vector.ph:
+    successors: %bb.2(0x80000000)
+    liveins: $lr, $r0, $r1, $r2
+
+    renamable $q1 = MVE_VMOVimmi32 0, 0, $noreg, undef renamable $q1
+
+  bb.2.vector.body:
+    successors: %bb.3(0x04000000), %bb.2(0x7c000000)
+    liveins: $lr, $q1, $r0, $r1, $r2
+
+    $q0 = MVE_VORR killed $q1, $q1, 0, $noreg, undef $q0
+    renamable $vpr = MVE_VCTP32 $r2, 0, $noreg
+    MVE_VPST 4, implicit $vpr
+    renamable $q1 = MVE_VLDRWU32 renamable $r0, 0, 1, renamable $vpr :: (load 16 from %ir.lsr.iv24, align 4)
+    renamable $q2 = MVE_VLDRWU32 renamable $r1, 0, 1, killed renamable $vpr :: (load 16 from %ir.lsr.iv1, align 4)
+    $r3 = tMOVr $r2, 14, $noreg
+    renamable $q1 = nsw MVE_VMULt1i32 killed renamable $q2, killed renamable $q1, 0, $noreg, undef renamable $q1
+    renamable $r0, dead $cpsr = tADDi8 killed renamable $r0, 16, 14, $noreg
+    renamable $r1, dead $cpsr = tADDi8 killed renamable $r1, 16, 14, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed $r2, 4, 14, $noreg
+    renamable $q1 = nsw MVE_VADDi32 killed renamable $q1, renamable $q0, 0, $noreg, undef renamable $q1
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    t2LoopEnd renamable $lr, %bb.2, implicit-def dead $cpsr
+    tB %bb.3, 14, $noreg
+
+  bb.3.middle.block:
+    successors: %bb.4(0x80000000)
+    liveins: $q0, $q1, $r3
+
+    renamable $vpr = MVE_VCTP32 killed renamable $r3, 0, $noreg
+    renamable $q0 = MVE_VPSEL killed renamable $q1, killed renamable $q0, 0, killed renamable $vpr
+    renamable $r12 = MVE_VADDVu32no_acc killed renamable $q0, 0, $noreg
+
+  bb.4.for.cond.cleanup:
+    liveins: $r12
+
+    $r0 = tMOVr killed $r12, 14, $noreg
+    tPOP_RET 14, $noreg, def $r7, def $pc, implicit killed $r0
+
+...