; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -tail-predication=enabled %s -o - | FileCheck %s

define arm_aapcs_vfpcc i32 @test_acc_scalar_char(i8 zeroext %a, i8* nocapture readonly %b, i32 %N) {
; CHECK-LABEL: test_acc_scalar_char:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #0
; CHECK-NEXT:    itt eq
; CHECK-NEXT:    moveq r0, #0
; CHECK-NEXT:    bxeq lr
; CHECK-NEXT:  .LBB0_1: @ %vector.ph
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    adds r3, r2, #3
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:  .LBB0_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vctp.32 r2
; CHECK-NEXT:    adds r3, #4
; CHECK-NEXT:    subs r2, #4
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrbt.u32 q2, [r1], #4
; CHECK-NEXT:    vmla.u32 q0, q2, r0
; CHECK-NEXT:    le lr, .LBB0_2
; CHECK-NEXT:  @ %bb.3: @ %middle.block
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    vaddv.u32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp7 = icmp eq i32 %N, 0
  br i1 %cmp7, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %conv = zext i8 %a to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %conv, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %5, %vector.body ]
  %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i8, i8* %b, i32 %index

; %1 = icmp ule <4 x i32> %induction, %broadcast.splat11
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i8* %0 to <4 x i8>*
  %wide.masked.load = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %2, i32 1, <4 x i1> %1, <4 x i8> undef)
  %3 = zext <4 x i8> %wide.masked.load to <4 x i32>
  %4 = mul nuw nsw <4 x i32> %broadcast.splat13, %3
  %5 = add nuw nsw <4 x i32> %4, %vec.phi
  %index.next = add i32 %index, 4
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %7 = select <4 x i1> %1, <4 x i32> %5, <4 x i32> %vec.phi
  %8 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %7)
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  %res.0.lcssa = phi i32 [ 0, %entry ], [ %8, %middle.block ]
  ret i32 %res.0.lcssa
}

define arm_aapcs_vfpcc i32 @test_acc_scalar_short(i16 signext %a, i16* nocapture readonly %b, i32 %N) {
; CHECK-LABEL: test_acc_scalar_short:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #0
; CHECK-NEXT:    itt eq
; CHECK-NEXT:    moveq r0, #0
; CHECK-NEXT:    bxeq lr
; CHECK-NEXT:  .LBB1_1: @ %vector.ph
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    adds r3, r2, #3
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:  .LBB1_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vctp.32 r2
; CHECK-NEXT:    adds r3, #4
; CHECK-NEXT:    subs r2, #4
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrht.s32 q2, [r1], #8
; CHECK-NEXT:    vmla.u32 q0, q2, r0
; CHECK-NEXT:    le lr, .LBB1_2
; CHECK-NEXT:  @ %bb.3: @ %middle.block
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    vaddv.u32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp7 = icmp eq i32 %N, 0
  br i1 %cmp7, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %conv = sext i16 %a to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %conv, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %5, %vector.body ]
  %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i16, i16* %b, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat11
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i16* %0 to <4 x i16>*
  %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %2, i32 2, <4 x i1> %1, <4 x i16> undef)
  %3 = sext <4 x i16> %wide.masked.load to <4 x i32>
  %4 = mul nsw <4 x i32> %broadcast.splat13, %3
  %5 = add nsw <4 x i32> %4, %vec.phi
  %index.next = add i32 %index, 4
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %7 = select <4 x i1> %1, <4 x i32> %5, <4 x i32> %vec.phi
  %8 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %7)
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  %res.0.lcssa = phi i32 [ 0, %entry ], [ %8, %middle.block ]
  ret i32 %res.0.lcssa
}

define arm_aapcs_vfpcc i32 @test_acc_scalar_uchar(i8 zeroext %a, i8* nocapture readonly %b, i32 %N) {
; CHECK-LABEL: test_acc_scalar_uchar:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #0
; CHECK-NEXT:    itt eq
; CHECK-NEXT:    moveq r0, #0
; CHECK-NEXT:    bxeq lr
; CHECK-NEXT:  .LBB2_1: @ %vector.ph
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    adds r3, r2, #3
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:  .LBB2_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vctp.32 r2
; CHECK-NEXT:    adds r3, #4
; CHECK-NEXT:    subs r2, #4
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrbt.u32 q2, [r1], #4
; CHECK-NEXT:    vmla.u32 q0, q2, r0
; CHECK-NEXT:    le lr, .LBB2_2
; CHECK-NEXT:  @ %bb.3: @ %middle.block
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    vaddv.u32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp7 = icmp eq i32 %N, 0
  br i1 %cmp7, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %conv = zext i8 %a to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %conv, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %5, %vector.body ]
  %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i8, i8* %b, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat11
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i8* %0 to <4 x i8>*
  %wide.masked.load = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %2, i32 1, <4 x i1> %1, <4 x i8> undef)
  %3 = zext <4 x i8> %wide.masked.load to <4 x i32>
  %4 = mul nuw nsw <4 x i32> %broadcast.splat13, %3
  %5 = add nuw nsw <4 x i32> %4, %vec.phi
  %index.next = add i32 %index, 4
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %7 = select <4 x i1> %1, <4 x i32> %5, <4 x i32> %vec.phi
  %8 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %7)
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  %res.0.lcssa = phi i32 [ 0, %entry ], [ %8, %middle.block ]
  ret i32 %res.0.lcssa
}

define arm_aapcs_vfpcc i32 @test_acc_scalar_ushort(i16 signext %a, i16* nocapture readonly %b, i32 %N) {
; CHECK-LABEL: test_acc_scalar_ushort:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #0
; CHECK-NEXT:    itt eq
; CHECK-NEXT:    moveq r0, #0
; CHECK-NEXT:    bxeq lr
; CHECK-NEXT:  .LBB3_1: @ %vector.ph
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    adds r3, r2, #3
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:  .LBB3_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vctp.32 r2
; CHECK-NEXT:    adds r3, #4
; CHECK-NEXT:    subs r2, #4
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrht.u32 q2, [r1], #8
; CHECK-NEXT:    vmla.u32 q0, q2, r0
; CHECK-NEXT:    le lr, .LBB3_2
; CHECK-NEXT:  @ %bb.3: @ %middle.block
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    vaddv.u32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp7 = icmp eq i32 %N, 0
  br i1 %cmp7, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %conv = sext i16 %a to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %conv, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %5, %vector.body ]
  %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i16, i16* %b, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat11
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i16* %0 to <4 x i16>*
  %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %2, i32 2, <4 x i1> %1, <4 x i16> undef)
  %3 = zext <4 x i16> %wide.masked.load to <4 x i32>
  %4 = mul nsw <4 x i32> %broadcast.splat13, %3
  %5 = add nsw <4 x i32> %4, %vec.phi
  %index.next = add i32 %index, 4
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %7 = select <4 x i1> %1, <4 x i32> %5, <4 x i32> %vec.phi
  %8 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %7)
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  %res.0.lcssa = phi i32 [ 0, %entry ], [ %8, %middle.block ]
  ret i32 %res.0.lcssa
}

define arm_aapcs_vfpcc i32 @test_acc_scalar_int(i32 %a, i32* nocapture readonly %b, i32 %N) {
; CHECK-LABEL: test_acc_scalar_int:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #0
; CHECK-NEXT:    itt eq
; CHECK-NEXT:    moveq r0, #0
; CHECK-NEXT:    bxeq lr
; CHECK-NEXT:  .LBB4_1: @ %vector.ph
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    adds r3, r2, #3
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:  .LBB4_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vctp.32 r2
; CHECK-NEXT:    adds r3, #4
; CHECK-NEXT:    subs r2, #4
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrwt.u32 q2, [r1], #16
; CHECK-NEXT:    vmla.u32 q0, q2, r0
; CHECK-NEXT:    le lr, .LBB4_2
; CHECK-NEXT:  @ %bb.3: @ %middle.block
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    vaddv.u32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp eq i32 %N, 0
  br i1 %cmp6, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert9 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat10 = shufflevector <4 x i32> %broadcast.splatinsert9, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert11 = insertelement <4 x i32> undef, i32 %a, i32 0
  %broadcast.splat12 = shufflevector <4 x i32> %broadcast.splatinsert11, <4 x i32> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %4, %vector.body ]
  %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i32, i32* %b, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat10
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i32* %0 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
  %3 = mul nsw <4 x i32> %wide.masked.load, %broadcast.splat12
  %4 = add nsw <4 x i32> %3, %vec.phi
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %6 = select <4 x i1> %1, <4 x i32> %4, <4 x i32> %vec.phi
  %7 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %6)
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  %res.0.lcssa = phi i32 [ 0, %entry ], [ %7, %middle.block ]
  ret i32 %res.0.lcssa
}

define arm_aapcs_vfpcc void @test_vec_mul_scalar_add_char(i8* nocapture readonly %a, i8* nocapture readonly %b, i8 zeroext %c, i32* nocapture %res, i32 %N) {
; 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.w r12, [sp, #28]
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    beq.w .LBB5_11
; CHECK-NEXT:  @ %bb.1: @ %for.body.lr.ph
; 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:    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 r7, r6
; CHECK-NEXT:    lslseq.w r7, r7, #31
; CHECK-NEXT:    beq .LBB5_4
; CHECK-NEXT:  @ %bb.2: @ %for.body.preheader
; 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:    mov.w r12, #0
; CHECK-NEXT:    b .LBB5_8
; CHECK-NEXT:  .LBB5_4: @ %vector.ph
; CHECK-NEXT:    movs r7, #0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB5_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r7, #4
; CHECK-NEXT:    vldrb.u32 q0, [r0], #4
; CHECK-NEXT:    vldrb.u32 q1, [r1], #4
; CHECK-NEXT:    vmlas.u32 q1, q0, r2
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB5_5
; CHECK-NEXT:    b .LBB5_11
; CHECK-NEXT:  .LBB5_6: @ %for.body.preheader.new
; CHECK-NEXT:    sub.w r8, r12, lr
; CHECK-NEXT:    add.w r5, r3, #8
; CHECK-NEXT:    adds r6, r0, #3
; CHECK-NEXT:    adds r7, r1, #1
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:  .LBB5_7: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldrb r9, [r6, #-3]
; CHECK-NEXT:    add.w r12, r12, #4
; CHECK-NEXT:    ldrb r4, [r7, #-1]
; CHECK-NEXT:    cmp r8, r12
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-8]
; CHECK-NEXT:    ldrb r9, [r6, #-2]
; CHECK-NEXT:    ldrb r4, [r7], #4
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-4]
; CHECK-NEXT:    ldrb r9, [r6, #-1]
; CHECK-NEXT:    ldrb r4, [r7, #-3]
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5]
; CHECK-NEXT:    ldrb r9, [r6], #4
; CHECK-NEXT:    ldrb r4, [r7, #-2]
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #4]
; CHECK-NEXT:    add.w r5, r5, #16
; CHECK-NEXT:    bne .LBB5_7
; CHECK-NEXT:  .LBB5_8: @ %for.cond.cleanup.loopexit.unr-lcssa
; CHECK-NEXT:    wls lr, lr, .LBB5_11
; CHECK-NEXT:  @ %bb.9: @ %for.body.epil.preheader
; CHECK-NEXT:    add r0, r12
; CHECK-NEXT:    add r1, r12
; CHECK-NEXT:    add.w r3, r3, r12, lsl #2
; CHECK-NEXT:  .LBB5_10: @ %for.body.epil
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldrb r7, [r0], #1
; CHECK-NEXT:    ldrb r6, [r1], #1
; CHECK-NEXT:    smlabb r7, r6, r7, r2
; CHECK-NEXT:    str r7, [r3], #4
; CHECK-NEXT:    le lr, .LBB5_10
; CHECK-NEXT:  .LBB5_11: @ %for.cond.cleanup
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
entry:
  %res12 = bitcast i32* %res to i8*
  %cmp10 = icmp eq i32 %N, 0
  br i1 %cmp10, label %for.cond.cleanup, label %for.body.lr.ph

for.body.lr.ph:                                   ; preds = %entry
  %conv3 = zext i8 %c to i32
  %scevgep = getelementptr i32, i32* %res, i32 %N
  %scevgep13 = bitcast i32* %scevgep to i8*
  %scevgep14 = getelementptr i8, i8* %a, i32 %N
  %scevgep15 = getelementptr i8, i8* %b, i32 %N
  %bound0 = icmp ugt i8* %scevgep14, %res12
  %bound1 = icmp ugt i8* %scevgep13, %a
  %found.conflict = and i1 %bound0, %bound1
  %bound016 = icmp ugt i8* %scevgep15, %res12
  %bound117 = icmp ugt i8* %scevgep13, %b
  %found.conflict18 = and i1 %bound016, %bound117
  %conflict.rdx = or i1 %found.conflict, %found.conflict18
  br i1 %conflict.rdx, label %for.body.preheader, label %vector.ph

for.body.preheader:                               ; preds = %for.body.lr.ph
  %0 = add i32 %N, -1
  %xtraiter = and i32 %N, 3
  %1 = icmp ult i32 %0, 3
  br i1 %1, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body.preheader.new

for.body.preheader.new:                           ; preds = %for.body.preheader
  %unroll_iter = sub i32 %N, %xtraiter
  br label %for.body

vector.ph:                                        ; preds = %for.body.lr.ph
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert19 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat20 = shufflevector <4 x i32> %broadcast.splatinsert19, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert22 = insertelement <4 x i32> undef, i32 %conv3, i32 0
  %broadcast.splat23 = shufflevector <4 x i32> %broadcast.splatinsert22, <4 x i32> undef, <4 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 <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %2 = getelementptr inbounds i8, i8* %a, i32 %index

  ; %3 = icmp ule <4 x i32> %induction, %broadcast.splat20
  %3 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %4 = bitcast i8* %2 to <4 x i8>*
  %wide.masked.load = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %4, i32 1, <4 x i1> %3, <4 x i8> undef)
  %5 = zext <4 x i8> %wide.masked.load to <4 x i32>
  %6 = getelementptr inbounds i8, i8* %b, i32 %index
  %7 = bitcast i8* %6 to <4 x i8>*
  %wide.masked.load21 = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %7, i32 1, <4 x i1> %3, <4 x i8> undef)
  %8 = zext <4 x i8> %wide.masked.load21 to <4 x i32>
  %9 = mul nuw nsw <4 x i32> %8, %5
  %10 = add nuw nsw <4 x i32> %9, %broadcast.splat23
  %11 = getelementptr inbounds i32, i32* %res, i32 %index
  %12 = bitcast i32* %11 to <4 x i32>*
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %12, i32 4, <4 x i1> %3)
  %index.next = add i32 %index, 4
  %13 = icmp eq i32 %index.next, %n.vec
  br i1 %13, label %for.cond.cleanup, label %vector.body

for.cond.cleanup.loopexit.unr-lcssa:              ; preds = %for.body, %for.body.preheader
  %i.011.unr = phi i32 [ 0, %for.body.preheader ], [ %inc.3, %for.body ]
  %lcmp.mod = icmp eq i32 %xtraiter, 0
  br i1 %lcmp.mod, label %for.cond.cleanup, label %for.body.epil

for.body.epil:                                    ; preds = %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil
  %i.011.epil = phi i32 [ %inc.epil, %for.body.epil ], [ %i.011.unr, %for.cond.cleanup.loopexit.unr-lcssa ]
  %epil.iter = phi i32 [ %epil.iter.sub, %for.body.epil ], [ %xtraiter, %for.cond.cleanup.loopexit.unr-lcssa ]
  %arrayidx.epil = getelementptr inbounds i8, i8* %a, i32 %i.011.epil
  %14 = load i8, i8* %arrayidx.epil, align 1
  %conv.epil = zext i8 %14 to i32
  %arrayidx1.epil = getelementptr inbounds i8, i8* %b, i32 %i.011.epil
  %15 = load i8, i8* %arrayidx1.epil, align 1
  %conv2.epil = zext i8 %15 to i32
  %mul.epil = mul nuw nsw i32 %conv2.epil, %conv.epil
  %add.epil = add nuw nsw i32 %mul.epil, %conv3
  %arrayidx4.epil = getelementptr inbounds i32, i32* %res, i32 %i.011.epil
  store i32 %add.epil, i32* %arrayidx4.epil, align 4
  %inc.epil = add nuw i32 %i.011.epil, 1
  %epil.iter.sub = add i32 %epil.iter, -1
  %epil.iter.cmp = icmp eq i32 %epil.iter.sub, 0
  br i1 %epil.iter.cmp, label %for.cond.cleanup, label %for.body.epil

for.cond.cleanup:                                 ; preds = %vector.body, %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil, %entry
  ret void

for.body:                                         ; preds = %for.body, %for.body.preheader.new
  %i.011 = phi i32 [ 0, %for.body.preheader.new ], [ %inc.3, %for.body ]
  %niter = phi i32 [ %unroll_iter, %for.body.preheader.new ], [ %niter.nsub.3, %for.body ]
  %arrayidx = getelementptr inbounds i8, i8* %a, i32 %i.011
  %16 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %16 to i32
  %arrayidx1 = getelementptr inbounds i8, i8* %b, i32 %i.011
  %17 = load i8, i8* %arrayidx1, align 1
  %conv2 = zext i8 %17 to i32
  %mul = mul nuw nsw i32 %conv2, %conv
  %add = add nuw nsw i32 %mul, %conv3
  %arrayidx4 = getelementptr inbounds i32, i32* %res, i32 %i.011
  store i32 %add, i32* %arrayidx4, align 4
  %inc = or i32 %i.011, 1
  %arrayidx.1 = getelementptr inbounds i8, i8* %a, i32 %inc
  %18 = load i8, i8* %arrayidx.1, align 1
  %conv.1 = zext i8 %18 to i32
  %arrayidx1.1 = getelementptr inbounds i8, i8* %b, i32 %inc
  %19 = load i8, i8* %arrayidx1.1, align 1
  %conv2.1 = zext i8 %19 to i32
  %mul.1 = mul nuw nsw i32 %conv2.1, %conv.1
  %add.1 = add nuw nsw i32 %mul.1, %conv3
  %arrayidx4.1 = getelementptr inbounds i32, i32* %res, i32 %inc
  store i32 %add.1, i32* %arrayidx4.1, align 4
  %inc.1 = or i32 %i.011, 2
  %arrayidx.2 = getelementptr inbounds i8, i8* %a, i32 %inc.1
  %20 = load i8, i8* %arrayidx.2, align 1
  %conv.2 = zext i8 %20 to i32
  %arrayidx1.2 = getelementptr inbounds i8, i8* %b, i32 %inc.1
  %21 = load i8, i8* %arrayidx1.2, align 1
  %conv2.2 = zext i8 %21 to i32
  %mul.2 = mul nuw nsw i32 %conv2.2, %conv.2
  %add.2 = add nuw nsw i32 %mul.2, %conv3
  %arrayidx4.2 = getelementptr inbounds i32, i32* %res, i32 %inc.1
  store i32 %add.2, i32* %arrayidx4.2, align 4
  %inc.2 = or i32 %i.011, 3
  %arrayidx.3 = getelementptr inbounds i8, i8* %a, i32 %inc.2
  %22 = load i8, i8* %arrayidx.3, align 1
  %conv.3 = zext i8 %22 to i32
  %arrayidx1.3 = getelementptr inbounds i8, i8* %b, i32 %inc.2
  %23 = load i8, i8* %arrayidx1.3, align 1
  %conv2.3 = zext i8 %23 to i32
  %mul.3 = mul nuw nsw i32 %conv2.3, %conv.3
  %add.3 = add nuw nsw i32 %mul.3, %conv3
  %arrayidx4.3 = getelementptr inbounds i32, i32* %res, i32 %inc.2
  store i32 %add.3, i32* %arrayidx4.3, align 4
  %inc.3 = add nuw i32 %i.011, 4
  %niter.nsub.3 = add i32 %niter, -4
  %niter.ncmp.3 = icmp eq i32 %niter.nsub.3, 0
  br i1 %niter.ncmp.3, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body
}

define arm_aapcs_vfpcc void @test_vec_mul_scalar_add_short(i16* nocapture readonly %a, i16* nocapture readonly %b, i16 signext %c, i32* nocapture %res, i32 %N) {
; CHECK-LABEL: test_vec_mul_scalar_add_short:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    ldr.w r12, [sp, #8]
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r4, pc}
; CHECK-NEXT:  .LBB6_1: @ %vector.ph
; CHECK-NEXT:    movs r4, #0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB6_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r4, #4
; CHECK-NEXT:    vldrh.s32 q0, [r0], #8
; CHECK-NEXT:    vldrh.s32 q1, [r1], #8
; CHECK-NEXT:    vmlas.u32 q1, q0, r2
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB6_2
; CHECK-NEXT:  @ %bb.3: @ %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
  %conv3 = sext i16 %c to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert15 = insertelement <4 x i32> undef, i32 %conv3, i32 0
  %broadcast.splat16 = shufflevector <4 x i32> %broadcast.splatinsert15, <4 x i32> undef, <4 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 <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i16, i16* %a, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat13
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i16* %0 to <4 x i16>*
  %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %2, i32 2, <4 x i1> %1, <4 x i16> undef)
  %3 = sext <4 x i16> %wide.masked.load to <4 x i32>
  %4 = getelementptr inbounds i16, i16* %b, i32 %index
  %5 = bitcast i16* %4 to <4 x i16>*
  %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %5, i32 2, <4 x i1> %1, <4 x i16> undef)
  %6 = sext <4 x i16> %wide.masked.load14 to <4 x i32>
  %7 = mul nsw <4 x i32> %6, %3
  %8 = add nsw <4 x i32> %7, %broadcast.splat16
  %9 = getelementptr inbounds i32, i32* %res, i32 %index
  %10 = bitcast i32* %9 to <4 x i32>*
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %8, <4 x i32>* %10, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %11 = icmp eq i32 %index.next, %n.vec
  br i1 %11, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_vec_mul_scalar_add_uchar(i8* nocapture readonly %a, i8* nocapture readonly %b, i8 zeroext %c, i32* nocapture %res, i32 %N) {
; 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.w r12, [sp, #28]
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    beq.w .LBB7_11
; CHECK-NEXT:  @ %bb.1: @ %for.body.lr.ph
; 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:    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 r7, r6
; CHECK-NEXT:    lslseq.w r7, r7, #31
; CHECK-NEXT:    beq .LBB7_4
; CHECK-NEXT:  @ %bb.2: @ %for.body.preheader
; 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:    mov.w r12, #0
; CHECK-NEXT:    b .LBB7_8
; CHECK-NEXT:  .LBB7_4: @ %vector.ph
; CHECK-NEXT:    movs r7, #0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB7_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r7, #4
; CHECK-NEXT:    vldrb.u32 q0, [r0], #4
; CHECK-NEXT:    vldrb.u32 q1, [r1], #4
; CHECK-NEXT:    vmlas.u32 q1, q0, r2
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB7_5
; CHECK-NEXT:    b .LBB7_11
; CHECK-NEXT:  .LBB7_6: @ %for.body.preheader.new
; CHECK-NEXT:    sub.w r8, r12, lr
; CHECK-NEXT:    add.w r5, r3, #8
; CHECK-NEXT:    adds r6, r0, #3
; CHECK-NEXT:    adds r7, r1, #1
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:  .LBB7_7: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldrb r9, [r6, #-3]
; CHECK-NEXT:    add.w r12, r12, #4
; CHECK-NEXT:    ldrb r4, [r7, #-1]
; CHECK-NEXT:    cmp r8, r12
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-8]
; CHECK-NEXT:    ldrb r9, [r6, #-2]
; CHECK-NEXT:    ldrb r4, [r7], #4
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-4]
; CHECK-NEXT:    ldrb r9, [r6, #-1]
; CHECK-NEXT:    ldrb r4, [r7, #-3]
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5]
; CHECK-NEXT:    ldrb r9, [r6], #4
; CHECK-NEXT:    ldrb r4, [r7, #-2]
; CHECK-NEXT:    smlabb r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #4]
; CHECK-NEXT:    add.w r5, r5, #16
; CHECK-NEXT:    bne .LBB7_7
; CHECK-NEXT:  .LBB7_8: @ %for.cond.cleanup.loopexit.unr-lcssa
; CHECK-NEXT:    wls lr, lr, .LBB7_11
; CHECK-NEXT:  @ %bb.9: @ %for.body.epil.preheader
; CHECK-NEXT:    add r0, r12
; CHECK-NEXT:    add r1, r12
; CHECK-NEXT:    add.w r3, r3, r12, lsl #2
; CHECK-NEXT:  .LBB7_10: @ %for.body.epil
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldrb r7, [r0], #1
; CHECK-NEXT:    ldrb r6, [r1], #1
; CHECK-NEXT:    smlabb r7, r6, r7, r2
; CHECK-NEXT:    str r7, [r3], #4
; CHECK-NEXT:    le lr, .LBB7_10
; CHECK-NEXT:  .LBB7_11: @ %for.cond.cleanup
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
entry:
  %res12 = bitcast i32* %res to i8*
  %cmp10 = icmp eq i32 %N, 0
  br i1 %cmp10, label %for.cond.cleanup, label %for.body.lr.ph

for.body.lr.ph:                                   ; preds = %entry
  %conv3 = zext i8 %c to i32
  %scevgep = getelementptr i32, i32* %res, i32 %N
  %scevgep13 = bitcast i32* %scevgep to i8*
  %scevgep14 = getelementptr i8, i8* %a, i32 %N
  %scevgep15 = getelementptr i8, i8* %b, i32 %N
  %bound0 = icmp ugt i8* %scevgep14, %res12
  %bound1 = icmp ugt i8* %scevgep13, %a
  %found.conflict = and i1 %bound0, %bound1
  %bound016 = icmp ugt i8* %scevgep15, %res12
  %bound117 = icmp ugt i8* %scevgep13, %b
  %found.conflict18 = and i1 %bound016, %bound117
  %conflict.rdx = or i1 %found.conflict, %found.conflict18
  br i1 %conflict.rdx, label %for.body.preheader, label %vector.ph

for.body.preheader:                               ; preds = %for.body.lr.ph
  %0 = add i32 %N, -1
  %xtraiter = and i32 %N, 3
  %1 = icmp ult i32 %0, 3
  br i1 %1, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body.preheader.new

for.body.preheader.new:                           ; preds = %for.body.preheader
  %unroll_iter = sub i32 %N, %xtraiter
  br label %for.body

vector.ph:                                        ; preds = %for.body.lr.ph
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert19 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat20 = shufflevector <4 x i32> %broadcast.splatinsert19, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert22 = insertelement <4 x i32> undef, i32 %conv3, i32 0
  %broadcast.splat23 = shufflevector <4 x i32> %broadcast.splatinsert22, <4 x i32> undef, <4 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 <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %2 = getelementptr inbounds i8, i8* %a, i32 %index

;  %3 = icmp ule <4 x i32> %induction, %broadcast.splat20
  %3 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %4 = bitcast i8* %2 to <4 x i8>*
  %wide.masked.load = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %4, i32 1, <4 x i1> %3, <4 x i8> undef)
  %5 = zext <4 x i8> %wide.masked.load to <4 x i32>
  %6 = getelementptr inbounds i8, i8* %b, i32 %index
  %7 = bitcast i8* %6 to <4 x i8>*
  %wide.masked.load21 = call <4 x i8> @llvm.masked.load.v4i8.p0v4i8(<4 x i8>* %7, i32 1, <4 x i1> %3, <4 x i8> undef)
  %8 = zext <4 x i8> %wide.masked.load21 to <4 x i32>
  %9 = mul nuw nsw <4 x i32> %8, %5
  %10 = add nuw nsw <4 x i32> %9, %broadcast.splat23
  %11 = getelementptr inbounds i32, i32* %res, i32 %index
  %12 = bitcast i32* %11 to <4 x i32>*
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %10, <4 x i32>* %12, i32 4, <4 x i1> %3)
  %index.next = add i32 %index, 4
  %13 = icmp eq i32 %index.next, %n.vec
  br i1 %13, label %for.cond.cleanup, label %vector.body

for.cond.cleanup.loopexit.unr-lcssa:              ; preds = %for.body, %for.body.preheader
  %i.011.unr = phi i32 [ 0, %for.body.preheader ], [ %inc.3, %for.body ]
  %lcmp.mod = icmp eq i32 %xtraiter, 0
  br i1 %lcmp.mod, label %for.cond.cleanup, label %for.body.epil

for.body.epil:                                    ; preds = %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil
  %i.011.epil = phi i32 [ %inc.epil, %for.body.epil ], [ %i.011.unr, %for.cond.cleanup.loopexit.unr-lcssa ]
  %epil.iter = phi i32 [ %epil.iter.sub, %for.body.epil ], [ %xtraiter, %for.cond.cleanup.loopexit.unr-lcssa ]
  %arrayidx.epil = getelementptr inbounds i8, i8* %a, i32 %i.011.epil
  %14 = load i8, i8* %arrayidx.epil, align 1
  %conv.epil = zext i8 %14 to i32
  %arrayidx1.epil = getelementptr inbounds i8, i8* %b, i32 %i.011.epil
  %15 = load i8, i8* %arrayidx1.epil, align 1
  %conv2.epil = zext i8 %15 to i32
  %mul.epil = mul nuw nsw i32 %conv2.epil, %conv.epil
  %add.epil = add nuw nsw i32 %mul.epil, %conv3
  %arrayidx4.epil = getelementptr inbounds i32, i32* %res, i32 %i.011.epil
  store i32 %add.epil, i32* %arrayidx4.epil, align 4
  %inc.epil = add nuw i32 %i.011.epil, 1
  %epil.iter.sub = add i32 %epil.iter, -1
  %epil.iter.cmp = icmp eq i32 %epil.iter.sub, 0
  br i1 %epil.iter.cmp, label %for.cond.cleanup, label %for.body.epil

for.cond.cleanup:                                 ; preds = %vector.body, %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil, %entry
  ret void

for.body:                                         ; preds = %for.body, %for.body.preheader.new
  %i.011 = phi i32 [ 0, %for.body.preheader.new ], [ %inc.3, %for.body ]
  %niter = phi i32 [ %unroll_iter, %for.body.preheader.new ], [ %niter.nsub.3, %for.body ]
  %arrayidx = getelementptr inbounds i8, i8* %a, i32 %i.011
  %16 = load i8, i8* %arrayidx, align 1
  %conv = zext i8 %16 to i32
  %arrayidx1 = getelementptr inbounds i8, i8* %b, i32 %i.011
  %17 = load i8, i8* %arrayidx1, align 1
  %conv2 = zext i8 %17 to i32
  %mul = mul nuw nsw i32 %conv2, %conv
  %add = add nuw nsw i32 %mul, %conv3
  %arrayidx4 = getelementptr inbounds i32, i32* %res, i32 %i.011
  store i32 %add, i32* %arrayidx4, align 4
  %inc = or i32 %i.011, 1
  %arrayidx.1 = getelementptr inbounds i8, i8* %a, i32 %inc
  %18 = load i8, i8* %arrayidx.1, align 1
  %conv.1 = zext i8 %18 to i32
  %arrayidx1.1 = getelementptr inbounds i8, i8* %b, i32 %inc
  %19 = load i8, i8* %arrayidx1.1, align 1
  %conv2.1 = zext i8 %19 to i32
  %mul.1 = mul nuw nsw i32 %conv2.1, %conv.1
  %add.1 = add nuw nsw i32 %mul.1, %conv3
  %arrayidx4.1 = getelementptr inbounds i32, i32* %res, i32 %inc
  store i32 %add.1, i32* %arrayidx4.1, align 4
  %inc.1 = or i32 %i.011, 2
  %arrayidx.2 = getelementptr inbounds i8, i8* %a, i32 %inc.1
  %20 = load i8, i8* %arrayidx.2, align 1
  %conv.2 = zext i8 %20 to i32
  %arrayidx1.2 = getelementptr inbounds i8, i8* %b, i32 %inc.1
  %21 = load i8, i8* %arrayidx1.2, align 1
  %conv2.2 = zext i8 %21 to i32
  %mul.2 = mul nuw nsw i32 %conv2.2, %conv.2
  %add.2 = add nuw nsw i32 %mul.2, %conv3
  %arrayidx4.2 = getelementptr inbounds i32, i32* %res, i32 %inc.1
  store i32 %add.2, i32* %arrayidx4.2, align 4
  %inc.2 = or i32 %i.011, 3
  %arrayidx.3 = getelementptr inbounds i8, i8* %a, i32 %inc.2
  %22 = load i8, i8* %arrayidx.3, align 1
  %conv.3 = zext i8 %22 to i32
  %arrayidx1.3 = getelementptr inbounds i8, i8* %b, i32 %inc.2
  %23 = load i8, i8* %arrayidx1.3, align 1
  %conv2.3 = zext i8 %23 to i32
  %mul.3 = mul nuw nsw i32 %conv2.3, %conv.3
  %add.3 = add nuw nsw i32 %mul.3, %conv3
  %arrayidx4.3 = getelementptr inbounds i32, i32* %res, i32 %inc.2
  store i32 %add.3, i32* %arrayidx4.3, align 4
  %inc.3 = add nuw i32 %i.011, 4
  %niter.nsub.3 = add i32 %niter, -4
  %niter.ncmp.3 = icmp eq i32 %niter.nsub.3, 0
  br i1 %niter.ncmp.3, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body
}

define arm_aapcs_vfpcc void @test_vec_mul_scalar_add_ushort(i16* nocapture readonly %a, i16* nocapture readonly %b, i16 signext %c, i32* nocapture %res, i32 %N) {
; CHECK-LABEL: test_vec_mul_scalar_add_ushort:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    ldr.w r12, [sp, #8]
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r4, pc}
; CHECK-NEXT:  .LBB8_1: @ %vector.ph
; CHECK-NEXT:    movs r4, #0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB8_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r4, #4
; CHECK-NEXT:    vldrh.u32 q0, [r0], #8
; CHECK-NEXT:    vldrh.u32 q1, [r1], #8
; CHECK-NEXT:    vmlas.u32 q1, q0, r2
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB8_2
; CHECK-NEXT:  @ %bb.3: @ %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
  %conv3 = sext i16 %c to i32
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert12 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat13 = shufflevector <4 x i32> %broadcast.splatinsert12, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert15 = insertelement <4 x i32> undef, i32 %conv3, i32 0
  %broadcast.splat16 = shufflevector <4 x i32> %broadcast.splatinsert15, <4 x i32> undef, <4 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 <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %0 = getelementptr inbounds i16, i16* %a, i32 %index

;  %1 = icmp ule <4 x i32> %induction, %broadcast.splat13
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %2 = bitcast i16* %0 to <4 x i16>*
  %wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %2, i32 2, <4 x i1> %1, <4 x i16> undef)
  %3 = zext <4 x i16> %wide.masked.load to <4 x i32>
  %4 = getelementptr inbounds i16, i16* %b, i32 %index
  %5 = bitcast i16* %4 to <4 x i16>*
  %wide.masked.load14 = call <4 x i16> @llvm.masked.load.v4i16.p0v4i16(<4 x i16>* %5, i32 2, <4 x i1> %1, <4 x i16> undef)
  %6 = zext <4 x i16> %wide.masked.load14 to <4 x i32>
  %7 = mul nuw nsw <4 x i32> %6, %3
  %8 = add nsw <4 x i32> %7, %broadcast.splat16
  %9 = getelementptr inbounds i32, i32* %res, i32 %index
  %10 = bitcast i32* %9 to <4 x i32>*
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %8, <4 x i32>* %10, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %11 = icmp eq i32 %index.next, %n.vec
  br i1 %11, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_vec_mul_scalar_add_int(i32* nocapture readonly %a, i32* nocapture readonly %b, i32 %c, i32* nocapture %res, i32 %N) {
; CHECK-LABEL: test_vec_mul_scalar_add_int:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, lr}
; CHECK-NEXT:    ldr.w r12, [sp, #28]
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    beq.w .LBB9_11
; CHECK-NEXT:  @ %bb.1: @ %vector.memcheck
; CHECK-NEXT:    add.w r5, r3, r12, lsl #2
; CHECK-NEXT:    add.w r6, r1, r12, lsl #2
; CHECK-NEXT:    cmp r5, r1
; CHECK-NEXT:    add.w r4, r0, r12, lsl #2
; CHECK-NEXT:    cset r7, hi
; CHECK-NEXT:    cmp r6, r3
; CHECK-NEXT:    cset r6, hi
; 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 r7, r6
; CHECK-NEXT:    lslseq.w r7, r7, #31
; CHECK-NEXT:    beq .LBB9_4
; CHECK-NEXT:  @ %bb.2: @ %for.body.preheader
; CHECK-NEXT:    sub.w r4, r12, #1
; CHECK-NEXT:    and lr, r12, #3
; CHECK-NEXT:    cmp r4, #3
; CHECK-NEXT:    bhs .LBB9_6
; CHECK-NEXT:  @ %bb.3:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    b .LBB9_8
; CHECK-NEXT:  .LBB9_4: @ %vector.ph
; CHECK-NEXT:    movs r7, #0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB9_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r7, #4
; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vmlas.u32 q1, q0, r2
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB9_5
; CHECK-NEXT:    b .LBB9_11
; CHECK-NEXT:  .LBB9_6: @ %for.body.preheader.new
; CHECK-NEXT:    sub.w r8, r12, lr
; CHECK-NEXT:    add.w r5, r3, #8
; CHECK-NEXT:    add.w r6, r0, #8
; CHECK-NEXT:    add.w r7, r1, #8
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:  .LBB9_7: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r9, [r6, #-8]
; CHECK-NEXT:    add.w r12, r12, #4
; CHECK-NEXT:    ldr r4, [r7, #-8]
; CHECK-NEXT:    cmp r8, r12
; CHECK-NEXT:    mla r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-8]
; CHECK-NEXT:    ldr r9, [r6, #-4]
; CHECK-NEXT:    ldr r4, [r7, #-4]
; CHECK-NEXT:    mla r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #-4]
; CHECK-NEXT:    ldr.w r9, [r6]
; CHECK-NEXT:    ldr r4, [r7]
; CHECK-NEXT:    mla r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5]
; CHECK-NEXT:    ldr.w r9, [r6, #4]
; CHECK-NEXT:    add.w r6, r6, #16
; CHECK-NEXT:    ldr r4, [r7, #4]
; CHECK-NEXT:    add.w r7, r7, #16
; CHECK-NEXT:    mla r4, r4, r9, r2
; CHECK-NEXT:    str r4, [r5, #4]
; CHECK-NEXT:    add.w r5, r5, #16
; CHECK-NEXT:    bne .LBB9_7
; CHECK-NEXT:  .LBB9_8: @ %for.cond.cleanup.loopexit.unr-lcssa
; CHECK-NEXT:    wls lr, lr, .LBB9_11
; CHECK-NEXT:  @ %bb.9: @ %for.body.epil.preheader
; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
; CHECK-NEXT:    add.w r1, r1, r12, lsl #2
; CHECK-NEXT:    add.w r3, r3, r12, lsl #2
; CHECK-NEXT:  .LBB9_10: @ %for.body.epil
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r7, [r0], #4
; CHECK-NEXT:    ldr r6, [r1], #4
; CHECK-NEXT:    mla r7, r6, r7, r2
; CHECK-NEXT:    str r7, [r3], #4
; CHECK-NEXT:    le lr, .LBB9_10
; CHECK-NEXT:  .LBB9_11: @ %for.cond.cleanup
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
entry:
  %cmp8 = icmp eq i32 %N, 0
  br i1 %cmp8, label %for.cond.cleanup, label %vector.memcheck

vector.memcheck:                                  ; preds = %entry
  %scevgep = getelementptr i32, i32* %res, i32 %N
  %scevgep13 = getelementptr i32, i32* %a, i32 %N
  %scevgep16 = getelementptr i32, i32* %b, i32 %N
  %bound0 = icmp ugt i32* %scevgep13, %res
  %bound1 = icmp ugt i32* %scevgep, %a
  %found.conflict = and i1 %bound0, %bound1
  %bound018 = icmp ugt i32* %scevgep16, %res
  %bound119 = icmp ugt i32* %scevgep, %b
  %found.conflict20 = and i1 %bound018, %bound119
  %conflict.rdx = or i1 %found.conflict, %found.conflict20
  br i1 %conflict.rdx, label %for.body.preheader, label %vector.ph

for.body.preheader:                               ; preds = %vector.memcheck
  %0 = add i32 %N, -1
  %xtraiter = and i32 %N, 3
  %1 = icmp ult i32 %0, 3
  br i1 %1, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body.preheader.new

for.body.preheader.new:                           ; preds = %for.body.preheader
  %unroll_iter = sub i32 %N, %xtraiter
  br label %for.body

vector.ph:                                        ; preds = %vector.memcheck
  %n.rnd.up = add i32 %N, 3
  %n.vec = and i32 %n.rnd.up, -4
  %trip.count.minus.1 = add i32 %N, -1
  %broadcast.splatinsert21 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
  %broadcast.splat22 = shufflevector <4 x i32> %broadcast.splatinsert21, <4 x i32> undef, <4 x i32> zeroinitializer
  %broadcast.splatinsert24 = insertelement <4 x i32> undef, i32 %c, i32 0
  %broadcast.splat25 = shufflevector <4 x i32> %broadcast.splatinsert24, <4 x i32> undef, <4 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 <4 x i32> undef, i32 %index, i32 0
  %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
  %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
  %2 = getelementptr inbounds i32, i32* %a, i32 %index

;  %3 = icmp ule <4 x i32> %induction, %broadcast.splat22
  %3 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)

  %4 = bitcast i32* %2 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %4, i32 4, <4 x i1> %3, <4 x i32> undef)
  %5 = getelementptr inbounds i32, i32* %b, i32 %index
  %6 = bitcast i32* %5 to <4 x i32>*
  %wide.masked.load23 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %6, i32 4, <4 x i1> %3, <4 x i32> undef)
  %7 = mul nsw <4 x i32> %wide.masked.load23, %wide.masked.load
  %8 = add nsw <4 x i32> %7, %broadcast.splat25
  %9 = getelementptr inbounds i32, i32* %res, i32 %index
  %10 = bitcast i32* %9 to <4 x i32>*
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %8, <4 x i32>* %10, i32 4, <4 x i1> %3)
  %index.next = add i32 %index, 4
  %11 = icmp eq i32 %index.next, %n.vec
  br i1 %11, label %for.cond.cleanup, label %vector.body

for.cond.cleanup.loopexit.unr-lcssa:              ; preds = %for.body, %for.body.preheader
  %i.09.unr = phi i32 [ 0, %for.body.preheader ], [ %inc.3, %for.body ]
  %lcmp.mod = icmp eq i32 %xtraiter, 0
  br i1 %lcmp.mod, label %for.cond.cleanup, label %for.body.epil

for.body.epil:                                    ; preds = %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil
  %i.09.epil = phi i32 [ %inc.epil, %for.body.epil ], [ %i.09.unr, %for.cond.cleanup.loopexit.unr-lcssa ]
  %epil.iter = phi i32 [ %epil.iter.sub, %for.body.epil ], [ %xtraiter, %for.cond.cleanup.loopexit.unr-lcssa ]
  %arrayidx.epil = getelementptr inbounds i32, i32* %a, i32 %i.09.epil
  %12 = load i32, i32* %arrayidx.epil, align 4
  %arrayidx1.epil = getelementptr inbounds i32, i32* %b, i32 %i.09.epil
  %13 = load i32, i32* %arrayidx1.epil, align 4
  %mul.epil = mul nsw i32 %13, %12
  %add.epil = add nsw i32 %mul.epil, %c
  %arrayidx2.epil = getelementptr inbounds i32, i32* %res, i32 %i.09.epil
  store i32 %add.epil, i32* %arrayidx2.epil, align 4
  %inc.epil = add nuw i32 %i.09.epil, 1
  %epil.iter.sub = add i32 %epil.iter, -1
  %epil.iter.cmp = icmp eq i32 %epil.iter.sub, 0
  br i1 %epil.iter.cmp, label %for.cond.cleanup, label %for.body.epil

for.cond.cleanup:                                 ; preds = %vector.body, %for.cond.cleanup.loopexit.unr-lcssa, %for.body.epil, %entry
  ret void

for.body:                                         ; preds = %for.body, %for.body.preheader.new
  %i.09 = phi i32 [ 0, %for.body.preheader.new ], [ %inc.3, %for.body ]
  %niter = phi i32 [ %unroll_iter, %for.body.preheader.new ], [ %niter.nsub.3, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %a, i32 %i.09
  %14 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %b, i32 %i.09
  %15 = load i32, i32* %arrayidx1, align 4
  %mul = mul nsw i32 %15, %14
  %add = add nsw i32 %mul, %c
  %arrayidx2 = getelementptr inbounds i32, i32* %res, i32 %i.09
  store i32 %add, i32* %arrayidx2, align 4
  %inc = or i32 %i.09, 1
  %arrayidx.1 = getelementptr inbounds i32, i32* %a, i32 %inc
  %16 = load i32, i32* %arrayidx.1, align 4
  %arrayidx1.1 = getelementptr inbounds i32, i32* %b, i32 %inc
  %17 = load i32, i32* %arrayidx1.1, align 4
  %mul.1 = mul nsw i32 %17, %16
  %add.1 = add nsw i32 %mul.1, %c
  %arrayidx2.1 = getelementptr inbounds i32, i32* %res, i32 %inc
  store i32 %add.1, i32* %arrayidx2.1, align 4
  %inc.1 = or i32 %i.09, 2
  %arrayidx.2 = getelementptr inbounds i32, i32* %a, i32 %inc.1
  %18 = load i32, i32* %arrayidx.2, align 4
  %arrayidx1.2 = getelementptr inbounds i32, i32* %b, i32 %inc.1
  %19 = load i32, i32* %arrayidx1.2, align 4
  %mul.2 = mul nsw i32 %19, %18
  %add.2 = add nsw i32 %mul.2, %c
  %arrayidx2.2 = getelementptr inbounds i32, i32* %res, i32 %inc.1
  store i32 %add.2, i32* %arrayidx2.2, align 4
  %inc.2 = or i32 %i.09, 3
  %arrayidx.3 = getelementptr inbounds i32, i32* %a, i32 %inc.2
  %20 = load i32, i32* %arrayidx.3, align 4
  %arrayidx1.3 = getelementptr inbounds i32, i32* %b, i32 %inc.2
  %21 = load i32, i32* %arrayidx1.3, align 4
  %mul.3 = mul nsw i32 %21, %20
  %add.3 = add nsw i32 %mul.3, %c
  %arrayidx2.3 = getelementptr inbounds i32, i32* %res, i32 %inc.2
  store i32 %add.3, i32* %arrayidx2.3, align 4
  %inc.3 = add nuw i32 %i.09, 4
  %niter.nsub.3 = add i32 %niter, -4
  %niter.ncmp.3 = icmp eq i32 %niter.nsub.3, 0
  br i1 %niter.ncmp.3, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body
}

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 {r7, lr}
; CHECK-NEXT:    cmp r3, #0
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB10_1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.16 lr, r3
; CHECK-NEXT:  .LBB10_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    add.w r12, r12, #8
; CHECK-NEXT:    vldrb.u16 q0, [r1], #8
; CHECK-NEXT:    vldrb.u16 q1, [r2], #8
; CHECK-NEXT:    vmul.i16 q0, q1, q0
; CHECK-NEXT:    vstrh.16 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB10_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, 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
  %1 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %N)

  %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

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

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.vector.reduce.add.v4i32(<4 x i32>)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)