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

define dso_local i32 @test_500_504(i32* nocapture readonly %x) {
; CHECK-LABEL: test_500_504:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    mov.w lr, #126
; CHECK-NEXT:    adr r2, .LCPI0_0
; CHECK-NEXT:    vldrw.u32 q0, [r2]
; CHECK-NEXT:    mov.w r2, #500
; CHECK-NEXT:    vdup.32 q1, r2
; CHECK-NEXT:    movs r1, #0
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:  .LBB0_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vadd.i32 q2, q0, r1
; CHECK-NEXT:    vdup.32 q3, r1
; CHECK-NEXT:    vcmp.u32 hi, q3, q2
; CHECK-NEXT:    adds r1, #4
; CHECK-NEXT:    vpnot
; CHECK-NEXT:    vpsttt
; CHECK-NEXT:    vcmpt.u32 hi, q1, q2
; CHECK-NEXT:    vldrwt.u32 q2, [r0], #16
; CHECK-NEXT:    vaddvat.u32 r2, q2
; CHECK-NEXT:    le lr, .LBB0_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.3:
; CHECK-NEXT:  .LCPI0_0:
; CHECK-NEXT:    .long 0 @ 0x0
; CHECK-NEXT:    .long 1 @ 0x1
; CHECK-NEXT:    .long 2 @ 0x2
; CHECK-NEXT:    .long 3 @ 0x3
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 500)
  %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, 504
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body
  ret i32 %4
}

define dso_local i32 @test_501_504(i32* nocapture readonly %x) {
; CHECK-LABEL: test_501_504:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movw r1, #501
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB1_1: @ %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, .LBB1_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 501)
  %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, 504
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body
  ret i32 %4
}

define dso_local i32 @test_502_504(i32* nocapture readonly %x) {
; CHECK-LABEL: test_502_504:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    mov.w r1, #502
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB2_1: @ %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, .LBB2_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 502)
  %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, 504
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body
  ret i32 %4
}

define dso_local i32 @test_503_504(i32* nocapture readonly %x) {
; CHECK-LABEL: test_503_504:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movw r1, #503
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB3_1: @ %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, .LBB3_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 503)
  %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, 504
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body
  ret i32 %4
}

define dso_local i32 @test_504_504(i32* nocapture readonly %x) {
; CHECK-LABEL: test_504_504:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    mov.w r1, #504
; CHECK-NEXT:    movs r2, #0
; CHECK-NEXT:    dlstp.32 lr, r1
; CHECK-NEXT:  .LBB4_1: @ %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, .LBB4_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    mov r0, r2
; CHECK-NEXT:    pop {r7, pc}
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 504)
  %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, 504
  br i1 %5, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body
  ret i32 %4
}

declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)