; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -tail-predication=enabled -verify-machineinstrs %s -o - | FileCheck %s

define i32 @add_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB0_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    mov r12, r0
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB0_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    b .LBB0_7
; CHECK-NEXT:  .LBB0_3:
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    b .LBB0_9
; CHECK-NEXT:  .LBB0_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    subs r0, r3, #4
; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    mov r2, r12
; CHECK-NEXT:  .LBB0_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vaddva.u32 r0, q0
; CHECK-NEXT:    le lr, .LBB0_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB0_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
; CHECK-NEXT:  .LBB0_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r2], #4
; CHECK-NEXT:    add r0, r1
; CHECK-NEXT:    le lr, .LBB0_8
; CHECK-NEXT:  .LBB0_9: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %wide.load)
  %3 = add i32 %2, %vec.phi
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 0, %for.body.preheader ], [ %3, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %5 = load i32, i32* %arrayidx, align 4
  %add = add nsw i32 %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %3, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @mul_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: mul_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB1_8
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB1_3
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    b .LBB1_6
; CHECK-NEXT:  .LBB1_3: @ %vector.ph
; CHECK-NEXT:    bic r12, r1, #3
; CHECK-NEXT:    vmov.i32 q0, #0x1
; CHECK-NEXT:    sub.w r3, r12, #4
; CHECK-NEXT:    add.w lr, r2, r3, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB1_4: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vmul.i32 q0, q1, q0
; CHECK-NEXT:    le lr, .LBB1_4
; CHECK-NEXT:  @ %bb.5: @ %middle.block
; CHECK-NEXT:    vmov lr, r3, d1
; CHECK-NEXT:    cmp r12, r1
; CHECK-NEXT:    vmov r2, r4, d0
; CHECK-NEXT:    mul r3, lr, r3
; CHECK-NEXT:    mul r2, r4, r2
; CHECK-NEXT:    mul r2, r3, r2
; CHECK-NEXT:    beq .LBB1_8
; CHECK-NEXT:  .LBB1_6: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r12
; CHECK-NEXT:    add.w r0, r0, r12, lsl #2
; CHECK-NEXT:  .LBB1_7: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    muls r2, r1, r2
; CHECK-NEXT:    le lr, .LBB1_7
; CHECK-NEXT:  .LBB1_8: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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> [ <i32 1, i32 1, i32 1, i32 1>, %vector.ph ], [ %2, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = mul <4 x i32> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 1, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %5 = load i32, i32* %arrayidx, align 4
  %add = mul nsw i32 %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 1, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @and_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: and_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB2_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB2_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r2, #-1
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB2_7
; CHECK-NEXT:  .LBB2_3:
; CHECK-NEXT:    mov.w r2, #-1
; CHECK-NEXT:    b .LBB2_9
; CHECK-NEXT:  .LBB2_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i8 q0, #0xff
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB2_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vand q0, q1, q0
; CHECK-NEXT:    le lr, .LBB2_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vmov lr, r12, d1
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vmov r2, r4, d0
; CHECK-NEXT:    and.w r12, r12, lr
; CHECK-NEXT:    and.w r2, r2, r4
; CHECK-NEXT:    and.w r2, r2, r12
; CHECK-NEXT:    beq .LBB2_9
; CHECK-NEXT:  .LBB2_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB2_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    ands r2, r1
; CHECK-NEXT:    le lr, .LBB2_8
; CHECK-NEXT:  .LBB2_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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> [ <i32 -1, i32 -1, i32 -1, i32 -1>, %vector.ph ], [ %2, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = and <4 x i32> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ -1, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %5 = load i32, i32* %arrayidx, align 4
  %add = and i32 %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ -1, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @or_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: or_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB3_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB3_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB3_7
; CHECK-NEXT:  .LBB3_3:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB3_9
; CHECK-NEXT:  .LBB3_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB3_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vorr q0, q1, q0
; CHECK-NEXT:    le lr, .LBB3_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vmov lr, r12, d1
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vmov r2, r4, d0
; CHECK-NEXT:    orr.w r12, r12, lr
; CHECK-NEXT:    orr.w r2, r2, r4
; CHECK-NEXT:    orr.w r2, r2, r12
; CHECK-NEXT:    beq .LBB3_9
; CHECK-NEXT:  .LBB3_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB3_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    orrs r2, r1
; CHECK-NEXT:    le lr, .LBB3_8
; CHECK-NEXT:  .LBB3_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 ], [ %2, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = or <4 x i32> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 0, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %5 = load i32, i32* %arrayidx, align 4
  %add = or i32 %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @xor_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: xor_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB4_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB4_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB4_7
; CHECK-NEXT:  .LBB4_3:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB4_9
; CHECK-NEXT:  .LBB4_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB4_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    veor q0, q1, q0
; CHECK-NEXT:    le lr, .LBB4_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vmov lr, r12, d1
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vmov r2, r4, d0
; CHECK-NEXT:    eor.w r12, r12, lr
; CHECK-NEXT:    eor.w r2, r2, r4
; CHECK-NEXT:    eor.w r2, r2, r12
; CHECK-NEXT:    beq .LBB4_9
; CHECK-NEXT:  .LBB4_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB4_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    eors r2, r1
; CHECK-NEXT:    le lr, .LBB4_8
; CHECK-NEXT:  .LBB4_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 ], [ %2, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = xor <4 x i32> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 0, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %5 = load i32, i32* %arrayidx, align 4
  %add = xor i32 %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define float @fadd_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: fadd_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB5_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB5_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    vldr s0, .LCPI5_0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB5_7
; CHECK-NEXT:  .LBB5_3:
; CHECK-NEXT:    vldr s0, .LCPI5_0
; CHECK-NEXT:    b .LBB5_9
; CHECK-NEXT:  .LBB5_4: @ %vector.ph
; CHECK-NEXT:    bic r2, r1, #3
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    sub.w r12, r2, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    mov r3, r0
; CHECK-NEXT:  .LBB5_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
; CHECK-NEXT:    vadd.f32 q0, q1, q0
; CHECK-NEXT:    le lr, .LBB5_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    beq .LBB5_9
; CHECK-NEXT:  .LBB5_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r2
; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
; CHECK-NEXT:  .LBB5_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldmia r0!, {s2}
; CHECK-NEXT:    vadd.f32 s0, s2, s0
; CHECK-NEXT:    le lr, .LBB5_8
; CHECK-NEXT:  .LBB5_9: @ %for.cond.cleanup
; CHECK-NEXT:    vmov r0, s0
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:    .p2align 2
; CHECK-NEXT:  @ %bb.10:
; CHECK-NEXT:  .LCPI5_0:
; CHECK-NEXT:    .long 0x00000000 @ float 0
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 float> [ zeroinitializer, %vector.ph ], [ %2, %vector.body ]
  %0 = getelementptr inbounds float, float* %x, i32 %index
  %1 = bitcast float* %0 to <4 x float>*
  %wide.load = load <4 x float>, <4 x float>* %1, align 4
  %2 = fadd fast <4 x float> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 0.000000e+00, <4 x float> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi float [ 0.000000e+00, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi float [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds float, float* %x, i32 %i.08
  %5 = load float, float* %arrayidx, align 4
  %add = fadd fast float %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi float [ 0.000000e+00, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret float %r.0.lcssa
}

define float @fmul_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: fmul_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB6_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB6_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    vmov.f32 s0, #1.000000e+00
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB6_7
; CHECK-NEXT:  .LBB6_3:
; CHECK-NEXT:    vmov.f32 s0, #1.000000e+00
; CHECK-NEXT:    b .LBB6_9
; CHECK-NEXT:  .LBB6_4: @ %vector.ph
; CHECK-NEXT:    bic r2, r1, #3
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    sub.w r12, r2, #4
; CHECK-NEXT:    vmov.f32 q0, #1.000000e+00
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    mov r3, r0
; CHECK-NEXT:  .LBB6_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
; CHECK-NEXT:    vmul.f32 q0, q1, q0
; CHECK-NEXT:    le lr, .LBB6_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vmul.f32 s2, s2, s3
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    vmul.f32 s0, s0, s1
; CHECK-NEXT:    vmul.f32 s0, s0, s2
; CHECK-NEXT:    beq .LBB6_9
; CHECK-NEXT:  .LBB6_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r2
; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
; CHECK-NEXT:  .LBB6_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldmia r0!, {s2}
; CHECK-NEXT:    vmul.f32 s0, s2, s0
; CHECK-NEXT:    le lr, .LBB6_8
; CHECK-NEXT:  .LBB6_9: @ %for.cond.cleanup
; CHECK-NEXT:    vmov r0, s0
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 float> [ <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %vector.ph ], [ %2, %vector.body ]
  %0 = getelementptr inbounds float, float* %x, i32 %index
  %1 = bitcast float* %0 to <4 x float>*
  %wide.load = load <4 x float>, <4 x float>* %1, align 4
  %2 = fmul fast <4 x float> %wide.load, %vec.phi
  %index.next = add i32 %index, 4
  %3 = icmp eq i32 %index.next, %n.vec
  br i1 %3, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %4 = call fast float @llvm.vector.reduce.fmul.f32.v4f32(float 1.000000e+00, <4 x float> %2)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi float [ 1.000000e+00, %for.body.preheader ], [ %4, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi float [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds float, float* %x, i32 %i.08
  %5 = load float, float* %arrayidx, align 4
  %add = fmul fast float %5, %r.07
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi float [ 1.000000e+00, %entry ], [ %4, %middle.block ], [ %add, %for.body ]
  ret float %r.0.lcssa
}

define i32 @smin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: smin_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB7_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB7_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mvn r2, #-2147483648
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB7_7
; CHECK-NEXT:  .LBB7_3:
; CHECK-NEXT:    mvn r2, #-2147483648
; CHECK-NEXT:    b .LBB7_9
; CHECK-NEXT:  .LBB7_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmvn.i32 q0, #0x80000000
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB7_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vmin.s32 q0, q0, q1
; CHECK-NEXT:    le lr, .LBB7_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    mvn r2, #-2147483648
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vminv.s32 r2, q0
; CHECK-NEXT:    beq .LBB7_9
; CHECK-NEXT:  .LBB7_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB7_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    csel r2, r2, r1, lt
; CHECK-NEXT:    le lr, .LBB7_8
; CHECK-NEXT:  .LBB7_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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> [ <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = icmp slt <4 x i32> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x i32> %vec.phi, <4 x i32> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 2147483647, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp slt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 2147483647, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @smin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: smin_i32_inloop:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB8_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    mov r12, r0
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB8_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mvn r0, #-2147483648
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB8_7
; CHECK-NEXT:  .LBB8_3:
; CHECK-NEXT:    mvn r0, #-2147483648
; CHECK-NEXT:    b .LBB8_9
; CHECK-NEXT:  .LBB8_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    subs r0, r3, #4
; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
; CHECK-NEXT:    mvn r0, #-2147483648
; CHECK-NEXT:    mov r2, r12
; CHECK-NEXT:  .LBB8_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vminv.s32 r0, q0
; CHECK-NEXT:    le lr, .LBB8_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB8_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
; CHECK-NEXT:  .LBB8_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r2], #4
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    csel r0, r0, r1, lt
; CHECK-NEXT:    le lr, .LBB8_8
; CHECK-NEXT:  .LBB8_9: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 2147483647, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %l5 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %wide.load)
  %2 = icmp slt i32 %vec.phi, %l5
  %3 = select i1 %2, i32 %vec.phi, i32 %l5
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = phi i32 [ %3, %vector.body ]
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 2147483647, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp slt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 2147483647, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @smax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: smax_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB9_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB9_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r2, #-2147483648
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB9_7
; CHECK-NEXT:  .LBB9_3:
; CHECK-NEXT:    mov.w r2, #-2147483648
; CHECK-NEXT:    b .LBB9_9
; CHECK-NEXT:  .LBB9_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i32 q0, #0x80000000
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB9_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vmax.s32 q0, q0, q1
; CHECK-NEXT:    le lr, .LBB9_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    mov.w r2, #-2147483648
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vmaxv.s32 r2, q0
; CHECK-NEXT:    beq .LBB9_9
; CHECK-NEXT:  .LBB9_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB9_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    csel r2, r2, r1, gt
; CHECK-NEXT:    le lr, .LBB9_8
; CHECK-NEXT:  .LBB9_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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> [ <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = icmp sgt <4 x i32> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x i32> %vec.phi, <4 x i32> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ -2147483648, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp sgt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ -2147483648, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @smax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: smax_i32_inloop:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB10_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    mov r12, r0
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB10_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r0, #-2147483648
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB10_7
; CHECK-NEXT:  .LBB10_3:
; CHECK-NEXT:    mov.w r0, #-2147483648
; CHECK-NEXT:    b .LBB10_9
; CHECK-NEXT:  .LBB10_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    subs r0, r3, #4
; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
; CHECK-NEXT:    mov.w r0, #-2147483648
; CHECK-NEXT:    mov r2, r12
; CHECK-NEXT:  .LBB10_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vmaxv.s32 r0, q0
; CHECK-NEXT:    le lr, .LBB10_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB10_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
; CHECK-NEXT:  .LBB10_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r2], #4
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    csel r0, r0, r1, gt
; CHECK-NEXT:    le lr, .LBB10_8
; CHECK-NEXT:  .LBB10_9: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ -2147483648, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %l5 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %wide.load)
  %2 = icmp sgt i32 %vec.phi, %l5
  %3 = select i1 %2, i32 %vec.phi, i32 %l5
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = phi i32 [ %3, %vector.body ]
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ -2147483648, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp sgt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ -2147483648, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @umin_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: umin_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB11_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB11_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r2, #-1
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB11_7
; CHECK-NEXT:  .LBB11_3:
; CHECK-NEXT:    mov.w r2, #-1
; CHECK-NEXT:    b .LBB11_9
; CHECK-NEXT:  .LBB11_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i8 q0, #0xff
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB11_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vmin.u32 q0, q0, q1
; CHECK-NEXT:    le lr, .LBB11_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    mov.w r2, #-1
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vminv.u32 r2, q0
; CHECK-NEXT:    beq .LBB11_9
; CHECK-NEXT:  .LBB11_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB11_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    csel r2, r2, r1, lo
; CHECK-NEXT:    le lr, .LBB11_8
; CHECK-NEXT:  .LBB11_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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> [ <i32 -1, i32 -1, i32 -1, i32 -1>, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = icmp ult <4 x i32> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x i32> %vec.phi, <4 x i32> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ -1, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp ult i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ -1, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @umin_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: umin_i32_inloop:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB12_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    mov r12, r0
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB12_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    mov.w r0, #-1
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    b .LBB12_7
; CHECK-NEXT:  .LBB12_3:
; CHECK-NEXT:    mov.w r0, #-1
; CHECK-NEXT:    b .LBB12_9
; CHECK-NEXT:  .LBB12_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    subs r0, r3, #4
; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
; CHECK-NEXT:    mov.w r0, #-1
; CHECK-NEXT:    mov r2, r12
; CHECK-NEXT:  .LBB12_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vminv.u32 r0, q0
; CHECK-NEXT:    le lr, .LBB12_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB12_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
; CHECK-NEXT:  .LBB12_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r2], #4
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    csel r0, r0, r1, hi
; CHECK-NEXT:    le lr, .LBB12_8
; CHECK-NEXT:  .LBB12_9: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ -1, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %l5 = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %wide.load)
  %2 = icmp ult i32 %vec.phi, %l5
  %3 = select i1 %2, i32 %vec.phi, i32 %l5
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = phi i32 [ %3, %vector.body ]
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ -1, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp ugt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ -1, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @umax_i32(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: umax_i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB13_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB13_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB13_7
; CHECK-NEXT:  .LBB13_3:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB13_9
; CHECK-NEXT:  .LBB13_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    sub.w r12, r3, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r2, r12, lsr #2
; CHECK-NEXT:    mov r2, r0
; CHECK-NEXT:  .LBB13_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r2], #16
; CHECK-NEXT:    vmax.u32 q0, q0, q1
; CHECK-NEXT:    le lr, .LBB13_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    vmaxv.u32 r2, q0
; CHECK-NEXT:    beq .LBB13_9
; CHECK-NEXT:  .LBB13_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r0, r0, r3, lsl #2
; CHECK-NEXT:  .LBB13_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r0], #4
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    csel r2, r2, r1, hi
; CHECK-NEXT:    le lr, .LBB13_8
; CHECK-NEXT:  .LBB13_9: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %2 = icmp ugt <4 x i32> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x i32> %vec.phi, <4 x i32> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 0, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp ugt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @umax_i32_inloop(i32* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: umax_i32_inloop:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB14_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    mov r12, r0
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB14_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    movs r3, #0
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    b .LBB14_7
; CHECK-NEXT:  .LBB14_3:
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    b .LBB14_9
; CHECK-NEXT:  .LBB14_4: @ %vector.ph
; CHECK-NEXT:    bic r3, r1, #3
; CHECK-NEXT:    movs r2, #1
; CHECK-NEXT:    subs r0, r3, #4
; CHECK-NEXT:    add.w lr, r2, r0, lsr #2
; CHECK-NEXT:    movs r0, #0
; CHECK-NEXT:    mov r2, r12
; CHECK-NEXT:  .LBB14_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vmaxv.u32 r0, q0
; CHECK-NEXT:    le lr, .LBB14_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    cmp r3, r1
; CHECK-NEXT:    it eq
; CHECK-NEXT:    popeq {r7, pc}
; CHECK-NEXT:  .LBB14_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r3
; CHECK-NEXT:    add.w r2, r12, r3, lsl #2
; CHECK-NEXT:  .LBB14_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldr r1, [r2], #4
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    csel r0, r0, r1, hi
; CHECK-NEXT:    le lr, .LBB14_8
; CHECK-NEXT:  .LBB14_9: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
  %l5 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %wide.load)
  %2 = icmp ugt i32 %vec.phi, %l5
  %3 = select i1 %2, i32 %vec.phi, i32 %l5
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = phi i32 [ %3, %vector.body ]
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi i32 [ 0, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi i32 [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %6 = load i32, i32* %arrayidx, align 4
  %c = icmp ugt i32 %r.07, %6
  %add = select i1 %c, i32 %r.07, i32 %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define float @fmin_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: fmin_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB15_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB15_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    vldr s0, .LCPI15_0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB15_7
; CHECK-NEXT:  .LBB15_3:
; CHECK-NEXT:    vldr s0, .LCPI15_0
; CHECK-NEXT:    b .LBB15_9
; CHECK-NEXT:  .LBB15_4: @ %vector.ph
; CHECK-NEXT:    bic r2, r1, #3
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    sub.w r12, r2, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    mov r3, r0
; CHECK-NEXT:  .LBB15_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
; CHECK-NEXT:    vcmp.f32 lt, q0, q1
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    le lr, .LBB15_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vminnm.f32 s2, s2, s3
; CHECK-NEXT:    vminnm.f32 s0, s0, s1
; CHECK-NEXT:    vminnm.f32 s0, s0, s2
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    beq .LBB15_9
; CHECK-NEXT:  .LBB15_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r2
; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
; CHECK-NEXT:  .LBB15_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldmia r0!, {s2}
; CHECK-NEXT:    vcmp.f32 s0, s2
; CHECK-NEXT:    vmrs APSR_nzcv, fpscr
; CHECK-NEXT:    vselge.f32 s0, s2, s0
; CHECK-NEXT:    le lr, .LBB15_8
; CHECK-NEXT:  .LBB15_9: @ %for.cond.cleanup
; CHECK-NEXT:    vmov r0, s0
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:    .p2align 2
; CHECK-NEXT:  @ %bb.10:
; CHECK-NEXT:  .LCPI15_0:
; CHECK-NEXT:    .long 0x00000000 @ float 0
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 float> [ zeroinitializer, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds float, float* %x, i32 %index
  %1 = bitcast float* %0 to <4 x float>*
  %wide.load = load <4 x float>, <4 x float>* %1, align 4
  %2 = fcmp ult <4 x float> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x float> %vec.phi, <4 x float> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi float [ 0.0, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi float [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds float, float* %x, i32 %i.08
  %6 = load float, float* %arrayidx, align 4
  %c = fcmp ult float %r.07, %6
  %add = select i1 %c, float %r.07, float %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi float [ 0.0, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret float %r.0.lcssa
}

define float @fmax_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-LABEL: fmax_f32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cmp r1, #1
; CHECK-NEXT:    blt .LBB16_3
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    cmp r1, #4
; CHECK-NEXT:    bhs .LBB16_4
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    vldr s0, .LCPI16_0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    b .LBB16_7
; CHECK-NEXT:  .LBB16_3:
; CHECK-NEXT:    vldr s0, .LCPI16_0
; CHECK-NEXT:    b .LBB16_9
; CHECK-NEXT:  .LBB16_4: @ %vector.ph
; CHECK-NEXT:    bic r2, r1, #3
; CHECK-NEXT:    movs r3, #1
; CHECK-NEXT:    sub.w r12, r2, #4
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w lr, r3, r12, lsr #2
; CHECK-NEXT:    mov r3, r0
; CHECK-NEXT:  .LBB16_5: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r3], #16
; CHECK-NEXT:    vcmp.f32 lt, q1, q0
; CHECK-NEXT:    vpsel q0, q0, q1
; CHECK-NEXT:    le lr, .LBB16_5
; CHECK-NEXT:  @ %bb.6: @ %middle.block
; CHECK-NEXT:    vmaxnm.f32 s2, s2, s3
; CHECK-NEXT:    vmaxnm.f32 s0, s0, s1
; CHECK-NEXT:    vmaxnm.f32 s0, s0, s2
; CHECK-NEXT:    cmp r2, r1
; CHECK-NEXT:    beq .LBB16_9
; CHECK-NEXT:  .LBB16_7: @ %for.body.preheader1
; CHECK-NEXT:    sub.w lr, r1, r2
; CHECK-NEXT:    add.w r0, r0, r2, lsl #2
; CHECK-NEXT:  .LBB16_8: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldmia r0!, {s2}
; CHECK-NEXT:    vcmp.f32 s2, s0
; CHECK-NEXT:    vmrs APSR_nzcv, fpscr
; CHECK-NEXT:    vselge.f32 s0, s2, s0
; CHECK-NEXT:    le lr, .LBB16_8
; CHECK-NEXT:  .LBB16_9: @ %for.cond.cleanup
; CHECK-NEXT:    vmov r0, s0
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:    .p2align 2
; CHECK-NEXT:  @ %bb.10:
; CHECK-NEXT:  .LCPI16_0:
; CHECK-NEXT:    .long 0x00000000 @ float 0
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %min.iters.check = icmp ult i32 %n, 4
  br i1 %min.iters.check, label %for.body.preheader1, label %vector.ph

vector.ph:                                        ; preds = %for.body.preheader
  %n.vec = and i32 %n, -4
  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 float> [ zeroinitializer, %vector.ph ], [ %3, %vector.body ]
  %0 = getelementptr inbounds float, float* %x, i32 %index
  %1 = bitcast float* %0 to <4 x float>*
  %wide.load = load <4 x float>, <4 x float>* %1, align 4
  %2 = fcmp ugt <4 x float> %vec.phi, %wide.load
  %3 = select <4 x i1> %2, <4 x float> %vec.phi, <4 x float> %wide.load
  %index.next = add i32 %index, 4
  %4 = icmp eq i32 %index.next, %n.vec
  br i1 %4, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %5 = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> %3)
  %cmp.n = icmp eq i32 %n.vec, %n
  br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader1

for.body.preheader1:                              ; preds = %middle.block, %for.body.preheader
  %i.08.ph = phi i32 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
  %r.07.ph = phi float [ 0.0, %for.body.preheader ], [ %5, %middle.block ]
  br label %for.body

for.body:                                         ; preds = %for.body.preheader1, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ %i.08.ph, %for.body.preheader1 ]
  %r.07 = phi float [ %add, %for.body ], [ %r.07.ph, %for.body.preheader1 ]
  %arrayidx = getelementptr inbounds float, float* %x, i32 %i.08
  %6 = load float, float* %arrayidx, align 4
  %c = fcmp ugt float %r.07, %6
  %add = select i1 %c, float %r.07, float %6
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %middle.block, %entry
  %r.0.lcssa = phi float [ 0.0, %entry ], [ %5, %middle.block ], [ %add, %for.body ]
  ret float %r.0.lcssa
}

define i32 @add4i32(i32* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add4i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB17_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB17_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
; CHECK-NEXT:    vaddva.u32 r2, q0
; CHECK-NEXT:    letp lr, .LBB17_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB17_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6.not = icmp eq i32 %n, 0
  br i1 %cmp6.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
  %3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
  %4 = add i32 %3, %vec.phi
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  ret i32 %s.0.lcssa
}

define i32 @mla4i32(i32* noalias nocapture readonly %x, i32* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla4i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB18_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.32 lr, r2
; CHECK-NEXT:  .LBB18_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vmlava.u32 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB18_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB18_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp8.not = icmp eq i32 %n, 0
  br i1 %cmp8.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %7, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %2 = getelementptr inbounds i32, i32* %y, i32 %index
  %3 = bitcast i32* %2 to <4 x i32>*
  %wide.masked.load13 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %3, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %4 = mul nsw <4 x i32> %wide.masked.load13, %wide.masked.load
  %5 = select <4 x i1> %active.lane.mask, <4 x i32> %4, <4 x i32> zeroinitializer
  %6 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %5)
  %7 = add i32 %6, %vec.phi
  %index.next = add i32 %index, 4
  %8 = icmp eq i32 %index.next, %n.vec
  br i1 %8, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %7, %vector.body ]
  ret i32 %s.0.lcssa
}

define i32 @add8i32(i16* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add8i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB19_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.16 lr, r1
; CHECK-NEXT:  .LBB19_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
; CHECK-NEXT:    vaddva.s16 r2, q0
; CHECK-NEXT:    letp lr, .LBB19_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB19_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6.not = icmp eq i32 %n, 0
  br i1 %cmp6.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %5, %vector.body ]
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i16, i16* %x, i32 %index
  %1 = bitcast i16* %0 to <8 x i16>*
  %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %2 = sext <8 x i16> %wide.masked.load to <8 x i32>
  %3 = select <8 x i1> %active.lane.mask, <8 x i32> %2, <8 x i32> zeroinitializer
  %4 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> %3)
  %5 = add i32 %4, %vec.phi
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %5, %vector.body ]
  ret i32 %s.0.lcssa
}

define i32 @mla8i32(i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla8i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB20_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.16 lr, r2
; CHECK-NEXT:  .LBB20_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
; CHECK-NEXT:    vmlava.s16 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB20_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB20_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp9.not = icmp eq i32 %n, 0
  br i1 %cmp9.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %9, %vector.body ]
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i16, i16* %x, i32 %index
  %1 = bitcast i16* %0 to <8 x i16>*
  %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %2 = sext <8 x i16> %wide.masked.load to <8 x i32>
  %3 = getelementptr inbounds i16, i16* %y, i32 %index
  %4 = bitcast i16* %3 to <8 x i16>*
  %wide.masked.load14 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %4, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %5 = sext <8 x i16> %wide.masked.load14 to <8 x i32>
  %6 = mul nsw <8 x i32> %5, %2
  %7 = select <8 x i1> %active.lane.mask, <8 x i32> %6, <8 x i32> zeroinitializer
  %8 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> %7)
  %9 = add i32 %8, %vec.phi
  %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
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %9, %vector.body ]
  ret i32 %s.0.lcssa
}

define i32 @add16i32(i8* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add16i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB21_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.8 lr, r1
; CHECK-NEXT:  .LBB21_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vaddva.u8 r2, q0
; CHECK-NEXT:    letp lr, .LBB21_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB21_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6.not = icmp eq i32 %n, 0
  br i1 %cmp6.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %5, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = zext <16 x i8> %wide.masked.load to <16 x i32>
  %3 = select <16 x i1> %active.lane.mask, <16 x i32> %2, <16 x i32> zeroinitializer
  %4 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %3)
  %5 = add i32 %4, %vec.phi
  %index.next = add i32 %index, 16
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %5, %vector.body ]
  ret i32 %s.0.lcssa
}

define i32 @mla16i32(i8* noalias nocapture readonly %x, i8* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla16i32:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB22_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.8 lr, r2
; CHECK-NEXT:  .LBB22_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vldrb.u8 q1, [r1], #16
; CHECK-NEXT:    vmlava.u8 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB22_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB22_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp9.not = icmp eq i32 %n, 0
  br i1 %cmp9.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %vector.ph ], [ %9, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = zext <16 x i8> %wide.masked.load to <16 x i32>
  %3 = getelementptr inbounds i8, i8* %y, i32 %index
  %4 = bitcast i8* %3 to <16 x i8>*
  %wide.masked.load14 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %4, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %5 = zext <16 x i8> %wide.masked.load14 to <16 x i32>
  %6 = mul nuw nsw <16 x i32> %5, %2
  %7 = select <16 x i1> %active.lane.mask, <16 x i32> %6, <16 x i32> zeroinitializer
  %8 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %7)
  %9 = add i32 %8, %vec.phi
  %index.next = add i32 %index, 16
  %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
  %s.0.lcssa = phi i32 [ 0, %entry ], [ %9, %vector.body ]
  ret i32 %s.0.lcssa
}

define signext i16 @add8i16(i16* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add8i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB23_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.16 lr, r1
; CHECK-NEXT:  .LBB23_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
; CHECK-NEXT:    vaddva.u16 r2, q0
; CHECK-NEXT:    letp lr, .LBB23_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    sxth r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB23_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    sxth r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp8.not = icmp eq i32 %n, 0
  br i1 %cmp8.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i16 [ 0, %vector.ph ], [ %4, %vector.body ]
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i16, i16* %x, i32 %index
  %1 = bitcast i16* %0 to <8 x i16>*
  %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %2 = select <8 x i1> %active.lane.mask, <8 x i16> %wide.masked.load, <8 x i16> zeroinitializer
  %3 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %2)
  %4 = add i16 %3, %vec.phi
  %index.next = add i32 %index, 8
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i16 [ 0, %entry ], [ %4, %vector.body ]
  ret i16 %s.0.lcssa
}

define signext i16 @mla8i16(i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla8i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB24_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.16 lr, r2
; CHECK-NEXT:  .LBB24_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
; CHECK-NEXT:    vmlava.u16 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB24_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    sxth.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB24_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    sxth.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp11.not = icmp eq i32 %n, 0
  br i1 %cmp11.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i16 [ 0, %vector.ph ], [ %7, %vector.body ]
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i16, i16* %x, i32 %index
  %1 = bitcast i16* %0 to <8 x i16>*
  %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %2 = getelementptr inbounds i16, i16* %y, i32 %index
  %3 = bitcast i16* %2 to <8 x i16>*
  %wide.masked.load16 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %3, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %4 = mul <8 x i16> %wide.masked.load16, %wide.masked.load
  %5 = select <8 x i1> %active.lane.mask, <8 x i16> %4, <8 x i16> zeroinitializer
  %6 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %5)
  %7 = add i16 %6, %vec.phi
  %index.next = add i32 %index, 8
  %8 = icmp eq i32 %index.next, %n.vec
  br i1 %8, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i16 [ 0, %entry ], [ %7, %vector.body ]
  ret i16 %s.0.lcssa
}

define signext i16 @add16i16(i8* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add16i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB25_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.8 lr, r1
; CHECK-NEXT:  .LBB25_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vaddva.u8 r2, q0
; CHECK-NEXT:    letp lr, .LBB25_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    sxth r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB25_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    sxth r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp8.not = icmp eq i32 %n, 0
  br i1 %cmp8.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i16 [ 0, %vector.ph ], [ %5, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = zext <16 x i8> %wide.masked.load to <16 x i16>
  %3 = select <16 x i1> %active.lane.mask, <16 x i16> %2, <16 x i16> zeroinitializer
  %4 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> %3)
  %5 = add i16 %4, %vec.phi
  %index.next = add i32 %index, 16
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i16 [ 0, %entry ], [ %5, %vector.body ]
  ret i16 %s.0.lcssa
}

define signext i16 @mla16i16(i8* noalias nocapture readonly %x, i8* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla16i16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB26_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.8 lr, r2
; CHECK-NEXT:  .LBB26_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vldrb.u8 q1, [r1], #16
; CHECK-NEXT:    vmlava.u8 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB26_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    sxth.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB26_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    sxth.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp13.not = icmp eq i32 %n, 0
  br i1 %cmp13.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i16 [ 0, %vector.ph ], [ %9, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = zext <16 x i8> %wide.masked.load to <16 x i16>
  %3 = getelementptr inbounds i8, i8* %y, i32 %index
  %4 = bitcast i8* %3 to <16 x i8>*
  %wide.masked.load18 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %4, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %5 = zext <16 x i8> %wide.masked.load18 to <16 x i16>
  %6 = mul nuw <16 x i16> %5, %2
  %7 = select <16 x i1> %active.lane.mask, <16 x i16> %6, <16 x i16> zeroinitializer
  %8 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> %7)
  %9 = add i16 %8, %vec.phi
  %index.next = add i32 %index, 16
  %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
  %s.0.lcssa = phi i16 [ 0, %entry ], [ %9, %vector.body ]
  ret i16 %s.0.lcssa
}

define zeroext i8 @add16i8(i8* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add16i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB27_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.8 lr, r1
; CHECK-NEXT:  .LBB27_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vaddva.u8 r2, q0
; CHECK-NEXT:    letp lr, .LBB27_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    uxtb r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB27_4:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    uxtb r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp7.not = icmp eq i32 %n, 0
  br i1 %cmp7.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i8 [ 0, %vector.ph ], [ %4, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = select <16 x i1> %active.lane.mask, <16 x i8> %wide.masked.load, <16 x i8> zeroinitializer
  %3 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %2)
  %4 = add i8 %3, %vec.phi
  %index.next = add i32 %index, 16
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i8 [ 0, %entry ], [ %4, %vector.body ]
  ret i8 %s.0.lcssa
}

define zeroext i8 @mla16i8(i8* noalias nocapture readonly %x, i8* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla16i8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB28_4
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    dlstp.8 lr, r2
; CHECK-NEXT:  .LBB28_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r0], #16
; CHECK-NEXT:    vldrb.u8 q1, [r1], #16
; CHECK-NEXT:    vmlava.u8 r12, q1, q0
; CHECK-NEXT:    letp lr, .LBB28_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    uxtb.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:  .LBB28_4:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    uxtb.w r0, r12
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp10.not = icmp eq i32 %n, 0
  br i1 %cmp10.not, label %for.cond.cleanup, label %vector.ph

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 15
  %n.vec = and i32 %n.rnd.up, -16
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i8 [ 0, %vector.ph ], [ %7, %vector.body ]
  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i8, i8* %x, i32 %index
  %1 = bitcast i8* %0 to <16 x i8>*
  %wide.masked.load = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %1, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %2 = getelementptr inbounds i8, i8* %y, i32 %index
  %3 = bitcast i8* %2 to <16 x i8>*
  %wide.masked.load15 = call <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>* %3, i32 1, <16 x i1> %active.lane.mask, <16 x i8> undef)
  %4 = mul <16 x i8> %wide.masked.load15, %wide.masked.load
  %5 = select <16 x i1> %active.lane.mask, <16 x i8> %4, <16 x i8> zeroinitializer
  %6 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %5)
  %7 = add i8 %6, %vec.phi
  %index.next = add i32 %index, 16
  %8 = icmp eq i32 %index.next, %n.vec
  br i1 %8, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i8 [ 0, %entry ], [ %7, %vector.body ]
  ret i8 %s.0.lcssa
}

define i64 @add4i64(i32* noalias nocapture readonly %x, i32 %n) {
; CHECK-LABEL: add4i64:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r1, .LBB29_3
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    mov r3, r2
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB29_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
; CHECK-NEXT:    vaddlva.s32 r2, r3, q0
; CHECK-NEXT:    letp lr, .LBB29_2
; CHECK-NEXT:    b .LBB29_4
; CHECK-NEXT:  .LBB29_3:
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    mov r3, r2
; CHECK-NEXT:  .LBB29_4: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    mov r1, r3
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6.not = icmp eq i32 %n, 0
  br i1 %cmp6.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i64 [ 0, %vector.ph ], [ %5, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %2 = sext <4 x i32> %wide.masked.load to <4 x i64>
  %3 = select <4 x i1> %active.lane.mask, <4 x i64> %2, <4 x i64> zeroinitializer
  %4 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %3)
  %5 = add i64 %4, %vec.phi
  %index.next = add i32 %index, 4
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  %s.0.lcssa = phi i64 [ 0, %entry ], [ %5, %vector.body ]
  ret i64 %s.0.lcssa
}

define i64 @mla4i64(i32* noalias nocapture readonly %x, i32* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla4i64:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB30_3
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:    dlstp.32 lr, r2
; CHECK-NEXT:  .LBB30_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r0], #16
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vmlalva.s32 r12, r3, q1, q0
; CHECK-NEXT:    letp lr, .LBB30_2
; CHECK-NEXT:    b .LBB30_4
; CHECK-NEXT:  .LBB30_3:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:  .LBB30_4: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    mov r1, r3
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp9.not = icmp eq i32 %n, 0
  br i1 %cmp9.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i64 [ 0, %vector.ph ], [ %9, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i32, i32* %x, i32 %index
  %1 = bitcast i32* %0 to <4 x i32>*
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %2 = sext <4 x i32> %wide.masked.load to <4 x i64>
  %3 = getelementptr inbounds i32, i32* %y, i32 %index
  %4 = bitcast i32* %3 to <4 x i32>*
  %wide.masked.load14 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %5 = sext <4 x i32> %wide.masked.load14 to <4 x i64>
  %6 = mul nsw <4 x i64> %5, %2
  %7 = select <4 x i1> %active.lane.mask, <4 x i64> %6, <4 x i64> zeroinitializer
  %8 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> %7)
  %9 = add i64 %8, %vec.phi
  %index.next = add i32 %index, 4
  %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
  %s.0.lcssa = phi i64 [ 0, %entry ], [ %9, %vector.body ]
  ret i64 %s.0.lcssa
}

define i64 @mla8i64(i16* noalias nocapture readonly %x, i16* noalias nocapture readonly %y, i32 %n) {
; CHECK-LABEL: mla8i64:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    cbz r2, .LBB31_3
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:    dlstp.16 lr, r2
; CHECK-NEXT:  .LBB31_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrh.u16 q0, [r0], #16
; CHECK-NEXT:    vldrh.u16 q1, [r1], #16
; CHECK-NEXT:    vmlalva.s16 r12, r3, q1, q0
; CHECK-NEXT:    letp lr, .LBB31_2
; CHECK-NEXT:    b .LBB31_4
; CHECK-NEXT:  .LBB31_3:
; CHECK-NEXT:    mov.w r12, #0
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:  .LBB31_4: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    mov r1, r3
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp9.not = icmp eq i32 %n, 0
  br i1 %cmp9.not, 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
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %vec.phi = phi i64 [ 0, %vector.ph ], [ %9, %vector.body ]
  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
  %0 = getelementptr inbounds i16, i16* %x, i32 %index
  %1 = bitcast i16* %0 to <8 x i16>*
  %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %2 = sext <8 x i16> %wide.masked.load to <8 x i64>
  %3 = getelementptr inbounds i16, i16* %y, i32 %index
  %4 = bitcast i16* %3 to <8 x i16>*
  %wide.masked.load14 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %4, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
  %5 = sext <8 x i16> %wide.masked.load14 to <8 x i64>
  %6 = mul nsw <8 x i64> %5, %2
  %7 = select <8 x i1> %active.lane.mask, <8 x i64> %6, <8 x i64> zeroinitializer
  %8 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> %7)
  %9 = add i64 %8, %vec.phi
  %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
  %s.0.lcssa = phi i64 [ 0, %entry ], [ %9, %vector.body ]
  ret i64 %s.0.lcssa
}

declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32) #1
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #2
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32) #1
declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>) #2
declare i32 @llvm.vector.reduce.add.v8i32(<8 x i32>) #3
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32) #1
declare <16 x i8> @llvm.masked.load.v16i8.p0v16i8(<16 x i8>*, i32 immarg, <16 x i1>, <16 x i8>) #2
declare i32 @llvm.vector.reduce.add.v16i32(<16 x i32>) #3
declare i16 @llvm.vector.reduce.add.v8i16(<8 x i16>) #3
declare i16 @llvm.vector.reduce.add.v16i16(<16 x i16>) #3
declare i8 @llvm.vector.reduce.add.v16i8(<16 x i8>) #3
declare i64 @llvm.vector.reduce.add.v4i64(<4 x i64>) #3
declare i64 @llvm.vector.reduce.add.v8i64(<8 x i64>) #3

declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.mul.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.or.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.xor.v4i32(<4 x i32>)
declare float @llvm.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.vector.reduce.fmul.f32.v4f32(float, <4 x float>)
declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32>)
declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32>)
declare float @llvm.vector.reduce.fmin.v4f32(<4 x float>)
declare float @llvm.vector.reduce.fmax.v4f32(<4 x float>)