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

; Check that WLSTP loop is not generated for alignment < 4
; void test1(char* dest, char* src, int n){
;    memcpy(dest, src, n);
; }

declare void @llvm.memcpy.p0.p0.i32(ptr noalias nocapture writeonly, ptr noalias nocapture readonly, i32, i1 immarg)
declare void @llvm.memcpy.p0.p0.i64(ptr noalias nocapture writeonly, ptr noalias nocapture readonly, i64, i1 immarg)
declare void @llvm.memset.p0.i32(ptr nocapture writeonly, i8, i32, i1 immarg)

define void @test1(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n){
; CHECK-LABEL: test1:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    bl __aeabi_memcpy
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 1 %X, ptr align 1 %Y, i32 %n, i1 false)
  ret void
}


; Check that WLSTP loop is generated for alignment >= 4
; void test2(int* restrict X, int* restrict Y, int n){
;     memcpy(X, Y, n);
; }

define void @test2(ptr noalias %X, ptr noalias readonly %Y, i32 %n){
; CHECK-LABEL: test2:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB1_2
; CHECK-NEXT:  .LBB1_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB1_1
; CHECK-NEXT:  .LBB1_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 %n, i1 false)
  ret void
}


; Checks that transform handles some arithmetic on the input arguments.
; void test3(int* restrict X, int* restrict Y, int n)
; {
;     memcpy(X+2, Y+3, (n*2)+10);
; }

define void @test3(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) {
; CHECK-LABEL: test3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movs r3, #10
; CHECK-NEXT:    add.w r2, r3, r2, lsl #1
; CHECK-NEXT:    adds r1, #12
; CHECK-NEXT:    adds r0, #8
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB2_2
; CHECK-NEXT:  .LBB2_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB2_1
; CHECK-NEXT:  .LBB2_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  %add.ptr = getelementptr inbounds i32, ptr %X, i32 2
  %add.ptr1 = getelementptr inbounds i32, ptr %Y, i32 3
  %mul = shl nsw i32 %n, 1
  %add = add nsw i32 %mul, 10
  call void @llvm.memcpy.p0.p0.i32(ptr nonnull align 4 %add.ptr, ptr nonnull align 4 %add.ptr1, i32 %add, i1 false)
  ret void
}


; Checks that transform handles for loops that are implicitly converted to mempcy
; void test4(int* restrict X, int* restrict Y, int n){
;     for(int i = 0; i < n; ++i){
;         X[i] = Y[i];
;     }
; }

define void @test4(ptr noalias %X, ptr noalias readonly %Y, i32 %n) {
; CHECK-LABEL: test4:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:  .LBB3_1: @ %for.body.preheader
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB3_3
; CHECK-NEXT:  .LBB3_2: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB3_2
; CHECK-NEXT:  .LBB3_3: @ %for.body.preheader
; CHECK-NEXT:    pop.w {r7, lr}
; CHECK-NEXT:    bx lr
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 %n, i1 false)
  br label %for.cond.cleanup

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

; Checks that transform can handle > i32 size inputs
define void @test5(ptr noalias %X, ptr noalias %Y, i64 %n){
; CHECK-LABEL: test5:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB4_2
; CHECK-NEXT:  .LBB4_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB4_1
; CHECK-NEXT:  .LBB4_2:
; CHECK-NEXT:    pop {r7, pc}
    call void @llvm.memcpy.p0.p0.i64(ptr align 4 %X, ptr align 4 %Y, i64 %n, i1 false)
    ret void
}

; Checks the transform is applied for constant size inputs below a certain threshold (128 in this case)
define void @test6(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) {
; CHECK-LABEL: test6:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movs r2, #127
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB5_2
; CHECK-NEXT:  .LBB5_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB5_1
; CHECK-NEXT:  .LBB5_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr noundef nonnull align 4 dereferenceable(127) %X, ptr noundef nonnull align 4 dereferenceable(127) %Y, i32 127, i1 false)
  ret void
}

; Checks the transform is NOT applied for constant size inputs above a certain threshold (128 in this case)
define void @test7(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) {
; CHECK-LABEL: test7:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movs r2, #128
; CHECK-NEXT:    bl __aeabi_memcpy4
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 128, i1 false)
  ret void
}

; Checks the transform is NOT applied for constant size inputs below a certain threshold (64 in this case)
define void @test8(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) {
; CHECK-LABEL: test8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    ldm.w r1!, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    stm.w r0!, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    ldm.w r1!, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    stm.w r0!, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    ldm.w r1, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    stm.w r0, {r2, r3, r4, r12, lr}
; CHECK-NEXT:    pop {r4, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 60, i1 false)
  ret void
}

; Checks the transform is NOT applied (regardless of alignment) when optimizations are disabled
define void @test9(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) #0 {
; CHECK-LABEL: test9:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    bl __aeabi_memcpy4
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 %n, i1 false)
  ret void
}

; Checks the transform is NOT applied (regardless of alignment) when optimization for size is on (-Os or -Oz)
define void @test10(ptr noalias nocapture %X, ptr noalias nocapture readonly %Y, i32 %n) #1 {
; CHECK-LABEL: test10:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    bl __aeabi_memcpy4
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 %n, i1 false)
  ret void
}

define void @test11(ptr nocapture %x, ptr nocapture %y, i32 %n) {
; CHECK-LABEL: test11:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp.w r2, #-1
; CHECK-NEXT:    it gt
; CHECK-NEXT:    bxgt lr
; CHECK-NEXT:  .LBB10_1: @ %prehead
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    mov r12, r1
; CHECK-NEXT:    mov r4, r0
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB10_3
; CHECK-NEXT:  .LBB10_2: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r12], #16
; CHECK-NEXT:    vstrb.8 q0, [r4], #16
; CHECK-NEXT:    letp lr, .LBB10_2
; CHECK-NEXT:  .LBB10_3: @ %for.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    ldrb r3, [r0], #1
; CHECK-NEXT:    subs r2, #2
; CHECK-NEXT:    strb r3, [r1], #1
; CHECK-NEXT:    bne .LBB10_3
; CHECK-NEXT:  @ %bb.4:
; CHECK-NEXT:    pop.w {r4, lr}
; CHECK-NEXT:    bx lr
entry:
  %cmp6 = icmp slt i32 %n, 0
  br i1 %cmp6, label %prehead, label %for.cond.cleanup

prehead:                                          ; preds = %entry
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %x, ptr align 4 %y, i32 %n, i1 false)
  br label %for.body

for.body:                                         ; preds = %for.body, %prehead
  %i.09 = phi i32 [ %inc, %for.body ], [ 0, %prehead ]
  %x.addr.08 = phi ptr [ %add.ptr, %for.body ], [ %x, %prehead ]
  %y.addr.07 = phi ptr [ %add.ptr1, %for.body ], [ %y, %prehead ]
  %add.ptr = getelementptr inbounds i8, ptr %x.addr.08, i32 1
  %add.ptr1 = getelementptr inbounds i8, ptr %y.addr.07, i32 1
  %l = load i8, ptr %x.addr.08, align 1
  store i8 %l, ptr %y.addr.07, align 1
  %inc = add nuw nsw i32 %i.09, 2
  %exitcond.not = icmp eq i32 %inc, %n
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body

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

; Check that WLSTP loop is generated for simplest case of align = 1
define void @test12(ptr %X, i8 zeroext %c, i32 %n) {
; CHECK-LABEL: test12:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vdup.8 q0, r1
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB11_2
; CHECK-NEXT:  .LBB11_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB11_1
; CHECK-NEXT:  .LBB11_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memset.p0.i32(ptr align 1 %X, i8 %c, i32 %n, i1 false)
  ret void
}


; Check that WLSTP loop is generated for alignment >= 4
define void @test13(ptr %X, i8 zeroext %c, i32 %n) {
; CHECK-LABEL: test13:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vdup.8 q0, r1
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB12_2
; CHECK-NEXT:  .LBB12_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB12_1
; CHECK-NEXT:  .LBB12_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memset.p0.i32(ptr align 4 %X, i8 %c, i32 %n, i1 false)
  ret void
}

define void @twoloops(ptr %X, i32 %n, i32 %m) {
; CHECK-LABEL: twoloops:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    mov r3, r0
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB13_2
; CHECK-NEXT:  .LBB13_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r3], #16
; CHECK-NEXT:    letp lr, .LBB13_1
; CHECK-NEXT:  .LBB13_2: @ %entry
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB13_4
; CHECK-NEXT:  .LBB13_3: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB13_3
; CHECK-NEXT:  .LBB13_4: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memset.p0.i32(ptr align 4 %X, i8 0, i32 %m, i1 false)
  call void @llvm.memset.p0.i32(ptr align 4 %X, i8 0, i32 %m, i1 false)
  ret void
}


; Checks that transform correctly handles input with some arithmetic on input arguments.
; void test14(int* X, char c, int n)
; {
;     memset(X+2, c, (n*2)+10);
; }

define void @test14(ptr %X, i8 zeroext %c, i32 %n) {
; CHECK-LABEL: test14:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    movs r3, #10
; CHECK-NEXT:    add.w r2, r3, r2, lsl #1
; CHECK-NEXT:    vdup.8 q0, r1
; CHECK-NEXT:    adds r0, #8
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB14_2
; CHECK-NEXT:  .LBB14_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB14_1
; CHECK-NEXT:  .LBB14_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  %add.ptr = getelementptr inbounds i32, ptr %X, i32 2
  %mul = shl nsw i32 %n, 1
  %add = add nsw i32 %mul, 10
  call void @llvm.memset.p0.i32(ptr nonnull align 4 %add.ptr, i8 %c, i32 %add, i1 false)
  ret void
}


; Checks that transform handles for-loops (that get implicitly converted to memset)
; void test15(int* X, char Y, int n){
;     for(int i = 0; i < n; ++i){
;         X[i] = c;
;     }
; }

define void @test15(ptr nocapture %X, i8 zeroext %c, i32 %n) {
; CHECK-LABEL: test15:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r2, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:  .LBB15_1: @ %for.body.preheader
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vdup.8 q0, r1
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB15_3
; CHECK-NEXT:  .LBB15_2: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB15_2
; CHECK-NEXT:  .LBB15_3: @ %for.body.preheader
; CHECK-NEXT:    pop.w {r7, lr}
; CHECK-NEXT:    bx lr
entry:
  %cmp4 = icmp sgt i32 %n, 0
  br i1 %cmp4, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  call void @llvm.memset.p0.i32(ptr align 4 %X, i8 %c, i32 %n, i1 false)
  br label %for.cond.cleanup

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

; Checks that transform handles case with 0 as src value. No difference is expected.
define void @test16(ptr %X, i8 zeroext %c, i32 %n) {
; CHECK-LABEL: test16:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB16_2
; CHECK-NEXT:  .LBB16_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB16_1
; CHECK-NEXT:  .LBB16_2: @ %entry
; CHECK-NEXT:    pop {r7, pc}
entry:
  call void @llvm.memset.p0.i32(ptr align 4 %X, i8 0, i32 %n, i1 false)
  ret void
}

define void @csprlive(ptr noalias %X, ptr noalias readonly %Y, i32 %n) {
; CHECK-LABEL: csprlive:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r7, lr}
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB17_2
; CHECK-NEXT:  .LBB17_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrb.u8 q0, [r1], #16
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB17_1
; CHECK-NEXT:  .LBB17_2: @ %entry
; CHECK-NEXT:    bl other
; CHECK-NEXT:    pop {r7, pc}
entry:
  %cmp6 = icmp sgt i32 %n, 0
  call void @llvm.memcpy.p0.p0.i32(ptr align 4 %X, ptr align 4 %Y, i32 %n, i1 false)
  br i1 %cmp6, label %if, label %else

if:
  call void @other()
  br label %cleanup

else:
  call void @other()
  br label %cleanup

cleanup:
  ret void
}

declare void @other()

@arr_56 = external dso_local local_unnamed_addr global [21 x [16 x [11 x i8]]], align 1
define void @multilooped_exit(i32 %b) {
; CHECK-LABEL: multilooped_exit:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r0, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:  .LBB18_1: @ %loop.preheader
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    mov.w r4, #-1
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    b .LBB18_3
; CHECK-NEXT:  .LBB18_2: @ %loop
; CHECK-NEXT:    @ in Loop: Header=BB18_3 Depth=1
; CHECK-NEXT:    adds r4, #1
; CHECK-NEXT:    cmp.w r4, #1024
; CHECK-NEXT:    bge .LBB18_12
; CHECK-NEXT:  .LBB18_3: @ %loop
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB18_4 Depth 2
; CHECK-NEXT:    @ Child Loop BB18_6 Depth 2
; CHECK-NEXT:    @ Child Loop BB18_8 Depth 2
; CHECK-NEXT:    @ Child Loop BB18_11 Depth 2
; CHECK-NEXT:    movw r3, :lower16:arr_56
; CHECK-NEXT:    add.w r1, r0, #15
; CHECK-NEXT:    movt r3, :upper16:arr_56
; CHECK-NEXT:    lsr.w r12, r1, #4
; CHECK-NEXT:    mov r2, r3
; CHECK-NEXT:    wlstp.8 lr, r0, .LBB18_5
; CHECK-NEXT:  .LBB18_4: @ Parent Loop BB18_3 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vstrb.8 q0, [r2], #16
; CHECK-NEXT:    letp lr, .LBB18_4
; CHECK-NEXT:  .LBB18_5: @ %loop
; CHECK-NEXT:    @ in Loop: Header=BB18_3 Depth=1
; CHECK-NEXT:    mov r2, r3
; CHECK-NEXT:    wlstp.8 lr, r0, .LBB18_7
; CHECK-NEXT:  .LBB18_6: @ Parent Loop BB18_3 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vstrb.8 q0, [r2], #16
; CHECK-NEXT:    letp lr, .LBB18_6
; CHECK-NEXT:  .LBB18_7: @ %loop
; CHECK-NEXT:    @ in Loop: Header=BB18_3 Depth=1
; CHECK-NEXT:    mov r2, r3
; CHECK-NEXT:    wlstp.8 lr, r0, .LBB18_9
; CHECK-NEXT:  .LBB18_8: @ Parent Loop BB18_3 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vstrb.8 q0, [r2], #16
; CHECK-NEXT:    letp lr, .LBB18_8
; CHECK-NEXT:  .LBB18_9: @ %loop
; CHECK-NEXT:    @ in Loop: Header=BB18_3 Depth=1
; CHECK-NEXT:    cmp.w r12, #0
; CHECK-NEXT:    beq .LBB18_2
; CHECK-NEXT:  @ %bb.10: @ %loop
; CHECK-NEXT:    @ in Loop: Header=BB18_3 Depth=1
; CHECK-NEXT:    dlstp.8 lr, r0
; CHECK-NEXT:  .LBB18_11: @ Parent Loop BB18_3 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vstrb.8 q0, [r3], #16
; CHECK-NEXT:    letp lr, .LBB18_11
; CHECK-NEXT:    b .LBB18_2
; CHECK-NEXT:  .LBB18_12:
; CHECK-NEXT:    pop.w {r4, lr}
; CHECK-NEXT:    bx lr
entry:
  %cmp8 = icmp sgt i32 %b, 0
  br i1 %cmp8, label %loop, label %exit

loop:
  %p = phi i32 [ 0, %entry ], [ %inc, %loop ]
  call void @llvm.memset.p0.i32(ptr align 1 getelementptr ([21 x [16 x [11 x i8]]], ptr @arr_56, i32 0, i32 0, i32 undef, i32 0), i8 0, i32 %b, i1 false)
  call void @llvm.memset.p0.i32(ptr align 1 getelementptr ([21 x [16 x [11 x i8]]], ptr @arr_56, i32 0, i32 0, i32 undef, i32 0), i8 0, i32 %b, i1 false)
  call void @llvm.memset.p0.i32(ptr align 1 getelementptr ([21 x [16 x [11 x i8]]], ptr @arr_56, i32 0, i32 0, i32 undef, i32 0), i8 0, i32 %b, i1 false)
  call void @llvm.memset.p0.i32(ptr align 1 getelementptr ([21 x [16 x [11 x i8]]], ptr @arr_56, i32 0, i32 0, i32 undef, i32 0), i8 0, i32 %b, i1 false)
  %inc = add i32 %p, 1
  %c = icmp slt i32 %p, 1024
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

@arr_21 = external dso_local local_unnamed_addr global [17 x [12 x [19 x i16]]], align 2
@arr_20 = external dso_local local_unnamed_addr global [17 x [12 x [19 x i64]]], align 8
@arr_22 = external dso_local local_unnamed_addr global [17 x [12 x [19 x i16]]], align 2
define i32 @reverted(i1 zeroext %b) {
; CHECK-LABEL: reverted:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #12
; CHECK-NEXT:    sub sp, #12
; CHECK-NEXT:    cmp r0, #0
; CHECK-NEXT:    mov.w r1, #11
; CHECK-NEXT:    cinc r1, r1, ne
; CHECK-NEXT:    movs r0, #38
; CHECK-NEXT:    mul r2, r1, r0
; CHECK-NEXT:    str r1, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    movw r0, :lower16:arr_22
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    movt r0, :upper16:arr_22
; CHECK-NEXT:    add.w r1, r2, #15
; CHECK-NEXT:    lsrs r3, r1, #4
; CHECK-NEXT:    strd r3, r2, [sp] @ 8-byte Folded Spill
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB19_2
; CHECK-NEXT:  .LBB19_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q0, [r0], #16
; CHECK-NEXT:    letp lr, .LBB19_1
; CHECK-NEXT:  .LBB19_2: @ %entry
; CHECK-NEXT:    ldr r0, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    movw r6, :lower16:arr_20
; CHECK-NEXT:    movt r6, :upper16:arr_20
; CHECK-NEXT:    add.w r3, r6, #80
; CHECK-NEXT:    dls lr, r0
; CHECK-NEXT:    movw r0, :lower16:arr_21
; CHECK-NEXT:    movt r0, :upper16:arr_21
; CHECK-NEXT:    add.w r5, r0, #36
; CHECK-NEXT:    add.w r11, r6, #128
; CHECK-NEXT:    add.w r7, r6, #112
; CHECK-NEXT:    add.w r2, r6, #96
; CHECK-NEXT:    add.w r4, r6, #64
; CHECK-NEXT:    add.w r0, r6, #48
; CHECK-NEXT:    add.w r1, r6, #32
; CHECK-NEXT:    add.w r12, r6, #16
; CHECK-NEXT:    adr r6, .LCPI19_0
; CHECK-NEXT:    vldrw.u32 q0, [r6]
; CHECK-NEXT:    movw r6, :lower16:arr_20
; CHECK-NEXT:    mov.w r8, #327685
; CHECK-NEXT:    mov.w r9, #5
; CHECK-NEXT:    vmov.i16 q1, #0x5
; CHECK-NEXT:    mov.w r10, #0
; CHECK-NEXT:    movt r6, :upper16:arr_20
; CHECK-NEXT:  .LBB19_3: @ %for.cond8.preheader
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    str r8, [r5, #-4]
; CHECK-NEXT:    vstrh.16 q1, [r5, #-36]
; CHECK-NEXT:    strh.w r9, [r5]
; CHECK-NEXT:    vstrh.16 q1, [r5, #-20]
; CHECK-NEXT:    vstrw.32 q0, [r3]
; CHECK-NEXT:    vstrh.16 q0, [r12], #152
; CHECK-NEXT:    vstrh.16 q0, [r6], #152
; CHECK-NEXT:    vstrh.16 q0, [r1], #152
; CHECK-NEXT:    vstrh.16 q0, [r0], #152
; CHECK-NEXT:    vstrh.16 q0, [r4], #152
; CHECK-NEXT:    vstrh.16 q0, [r2], #152
; CHECK-NEXT:    vstrh.16 q0, [r7], #152
; CHECK-NEXT:    vstrh.16 q0, [r11], #152
; CHECK-NEXT:    strd r9, r10, [r3, #64]
; CHECK-NEXT:    adds r5, #38
; CHECK-NEXT:    adds r3, #152
; CHECK-NEXT:    le lr, .LBB19_3
; CHECK-NEXT:  @ %bb.4: @ %for.cond.cleanup6
; CHECK-NEXT:    movw r0, :lower16:arr_22
; CHECK-NEXT:    ldr r2, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    movt r0, :upper16:arr_22
; CHECK-NEXT:    ldr r3, [sp] @ 4-byte Reload
; CHECK-NEXT:    add.w r0, r0, #1824
; CHECK-NEXT:    vmov.i32 q1, #0x0
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB19_6
; CHECK-NEXT:  .LBB19_5: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q1, [r0], #16
; CHECK-NEXT:    letp lr, .LBB19_5
; CHECK-NEXT:  .LBB19_6: @ %for.cond.cleanup6
; CHECK-NEXT:    movw r6, :lower16:arr_20
; CHECK-NEXT:    movw r0, #7376
; CHECK-NEXT:    movt r6, :upper16:arr_20
; CHECK-NEXT:    adds r3, r6, r0
; CHECK-NEXT:    movw r0, #7408
; CHECK-NEXT:    add.w r12, r6, r0
; CHECK-NEXT:    movw r0, #7344
; CHECK-NEXT:    add.w r9, r6, r0
; CHECK-NEXT:    movw r0, #7312
; CHECK-NEXT:    adds r2, r6, r0
; CHECK-NEXT:    movw r0, :lower16:arr_21
; CHECK-NEXT:    add.w r1, r6, #7424
; CHECK-NEXT:    add.w r7, r6, #7392
; CHECK-NEXT:    add.w r4, r6, #7360
; CHECK-NEXT:    add.w r5, r6, #7328
; CHECK-NEXT:    add.w r8, r6, #7296
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    movt r0, :upper16:arr_21
; CHECK-NEXT:    addw r0, r0, #1860
; CHECK-NEXT:    mov.w r10, #5
; CHECK-NEXT:    dls lr, r6
; CHECK-NEXT:    mov.w r6, #327685
; CHECK-NEXT:    vmov.i16 q1, #0x5
; CHECK-NEXT:    mov.w r11, #0
; CHECK-NEXT:  .LBB19_7: @ %for.cond8.preheader.1
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    str r6, [r0, #-4]
; CHECK-NEXT:    vstrh.16 q1, [r0, #-36]
; CHECK-NEXT:    strh.w r10, [r0]
; CHECK-NEXT:    vstrh.16 q1, [r0, #-20]
; CHECK-NEXT:    vstrw.32 q0, [r3]
; CHECK-NEXT:    vstrh.16 q0, [r2], #152
; CHECK-NEXT:    vstrh.16 q0, [r8], #152
; CHECK-NEXT:    vstrh.16 q0, [r5], #152
; CHECK-NEXT:    vstrh.16 q0, [r9], #152
; CHECK-NEXT:    vstrh.16 q0, [r4], #152
; CHECK-NEXT:    vstrh.16 q0, [r7], #152
; CHECK-NEXT:    vstrh.16 q0, [r12], #152
; CHECK-NEXT:    vstrh.16 q0, [r1], #152
; CHECK-NEXT:    strd r10, r11, [r3, #64]
; CHECK-NEXT:    adds r0, #38
; CHECK-NEXT:    adds r3, #152
; CHECK-NEXT:    le lr, .LBB19_7
; CHECK-NEXT:  @ %bb.8: @ %for.cond.cleanup6.1
; CHECK-NEXT:    movw r0, :lower16:arr_22
; CHECK-NEXT:    ldr r2, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    movt r0, :upper16:arr_22
; CHECK-NEXT:    ldr r3, [sp] @ 4-byte Reload
; CHECK-NEXT:    add.w r0, r0, #3648
; CHECK-NEXT:    vmov.i32 q1, #0x0
; CHECK-NEXT:    wlstp.8 lr, r2, .LBB19_10
; CHECK-NEXT:  .LBB19_9: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q1, [r0], #16
; CHECK-NEXT:    letp lr, .LBB19_9
; CHECK-NEXT:  .LBB19_10: @ %for.cond.cleanup6.1
; CHECK-NEXT:    movw r7, :lower16:arr_20
; CHECK-NEXT:    movw r0, #14672
; CHECK-NEXT:    movt r7, :upper16:arr_20
; CHECK-NEXT:    adds r3, r7, r0
; CHECK-NEXT:    movw r0, #14704
; CHECK-NEXT:    add.w r12, r7, r0
; CHECK-NEXT:    movw r0, #14688
; CHECK-NEXT:    add.w r8, r7, r0
; CHECK-NEXT:    movw r0, #14640
; CHECK-NEXT:    add.w r9, r7, r0
; CHECK-NEXT:    movw r0, #14624
; CHECK-NEXT:    adds r2, r7, r0
; CHECK-NEXT:    movw r0, #14608
; CHECK-NEXT:    movw r1, :lower16:arr_21
; CHECK-NEXT:    add r0, r7
; CHECK-NEXT:    add.w r4, r7, #14720
; CHECK-NEXT:    add.w r5, r7, #14656
; CHECK-NEXT:    add.w r6, r7, #14592
; CHECK-NEXT:    ldr r7, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    movt r1, :upper16:arr_21
; CHECK-NEXT:    addw r1, r1, #3684
; CHECK-NEXT:    mov.w r10, #5
; CHECK-NEXT:    dls lr, r7
; CHECK-NEXT:    mov.w r7, #327685
; CHECK-NEXT:    vmov.i16 q1, #0x5
; CHECK-NEXT:    mov.w r11, #0
; CHECK-NEXT:  .LBB19_11: @ %for.cond8.preheader.2
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    str r7, [r1, #-4]
; CHECK-NEXT:    vstrh.16 q1, [r1, #-36]
; CHECK-NEXT:    strh.w r10, [r1]
; CHECK-NEXT:    vstrh.16 q1, [r1, #-20]
; CHECK-NEXT:    vstrw.32 q0, [r3]
; CHECK-NEXT:    vstrh.16 q0, [r0], #152
; CHECK-NEXT:    vstrh.16 q0, [r6], #152
; CHECK-NEXT:    vstrh.16 q0, [r2], #152
; CHECK-NEXT:    vstrh.16 q0, [r9], #152
; CHECK-NEXT:    vstrh.16 q0, [r5], #152
; CHECK-NEXT:    vstrh.16 q0, [r8], #152
; CHECK-NEXT:    vstrh.16 q0, [r12], #152
; CHECK-NEXT:    vstrh.16 q0, [r4], #152
; CHECK-NEXT:    strd r10, r11, [r3, #64]
; CHECK-NEXT:    adds r1, #38
; CHECK-NEXT:    adds r3, #152
; CHECK-NEXT:    le lr, .LBB19_11
; CHECK-NEXT:  @ %bb.12: @ %for.cond.cleanup6.2
; CHECK-NEXT:    movw r0, :lower16:arr_22
; CHECK-NEXT:    ldrd r2, r1, [sp] @ 8-byte Folded Reload
; CHECK-NEXT:    movt r0, :upper16:arr_22
; CHECK-NEXT:    vmov.i32 q1, #0x0
; CHECK-NEXT:    add.w r0, r0, #5472
; CHECK-NEXT:    wlstp.8 lr, r1, .LBB19_14
; CHECK-NEXT:  .LBB19_13: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vstrb.8 q1, [r0], #16
; CHECK-NEXT:    letp lr, .LBB19_13
; CHECK-NEXT:  .LBB19_14: @ %for.cond.cleanup6.2
; CHECK-NEXT:    movw r2, :lower16:arr_21
; CHECK-NEXT:    movw r1, #5508
; CHECK-NEXT:    movt r2, :upper16:arr_21
; CHECK-NEXT:    movw r7, :lower16:arr_20
; CHECK-NEXT:    add r2, r1
; CHECK-NEXT:    movw r1, #22000
; CHECK-NEXT:    movt r7, :upper16:arr_20
; CHECK-NEXT:    add.w r12, r7, r1
; CHECK-NEXT:    movw r1, #21984
; CHECK-NEXT:    add.w r8, r7, r1
; CHECK-NEXT:    movw r1, #21952
; CHECK-NEXT:    add.w r9, r7, r1
; CHECK-NEXT:    movw r1, #21936
; CHECK-NEXT:    movw r0, #21968
; CHECK-NEXT:    adds r5, r7, r1
; CHECK-NEXT:    movw r1, #21920
; CHECK-NEXT:    movw r3, #21904
; CHECK-NEXT:    adds r4, r7, r3
; CHECK-NEXT:    add r0, r7
; CHECK-NEXT:    add r1, r7
; CHECK-NEXT:    add.w r3, r7, #22016
; CHECK-NEXT:    add.w r6, r7, #21888
; CHECK-NEXT:    ldr r7, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    mov.w r10, #5
; CHECK-NEXT:    vmov.i16 q1, #0x5
; CHECK-NEXT:    mov.w r11, #0
; CHECK-NEXT:    dls lr, r7
; CHECK-NEXT:    mov.w r7, #327685
; CHECK-NEXT:  .LBB19_15: @ %for.cond8.preheader.3
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    str r7, [r2, #-4]
; CHECK-NEXT:    vstrh.16 q1, [r2, #-36]
; CHECK-NEXT:    strh.w r10, [r2]
; CHECK-NEXT:    vstrh.16 q1, [r2, #-20]
; CHECK-NEXT:    vstrw.32 q0, [r0]
; CHECK-NEXT:    vstrh.16 q0, [r4], #152
; CHECK-NEXT:    vstrh.16 q0, [r6], #152
; CHECK-NEXT:    vstrh.16 q0, [r1], #152
; CHECK-NEXT:    vstrh.16 q0, [r5], #152
; CHECK-NEXT:    vstrh.16 q0, [r9], #152
; CHECK-NEXT:    vstrh.16 q0, [r8], #152
; CHECK-NEXT:    vstrh.16 q0, [r12], #152
; CHECK-NEXT:    vstrh.16 q0, [r3], #152
; CHECK-NEXT:    strd r10, r11, [r0, #64]
; CHECK-NEXT:    adds r2, #38
; CHECK-NEXT:    adds r0, #152
; CHECK-NEXT:    le lr, .LBB19_15
; CHECK-NEXT:  @ %bb.16: @ %for.cond.cleanup6.3
; CHECK-NEXT:    add sp, #12
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.17:
; CHECK-NEXT:  .LCPI19_0:
; CHECK-NEXT:    .long 5 @ 0x5
; CHECK-NEXT:    .long 0 @ 0x0
; CHECK-NEXT:    .long 5 @ 0x5
; CHECK-NEXT:    .long 0 @ 0x0
entry:
  %add = select i1 %b, i32 12, i32 11
  %0 = mul nuw nsw i32 %add, 38
  call void @llvm.memset.p0.i32(ptr noundef nonnull align 2 dereferenceable(1) @arr_22, i8 0, i32 %0, i1 false)
  br label %for.cond8.preheader

for.cond8.preheader:                              ; preds = %entry, %for.cond8.preheader
  %d.051 = phi i32 [ 0, %entry ], [ %inc, %for.cond8.preheader ]
  %arrayidx16 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 0, i32 %d.051, i32 0
  %arrayidx21 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 0
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21, align 8
  %arrayidx21.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.2, align 8
  %arrayidx21.4 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 4
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.4, align 8
  %arrayidx21.6 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 6
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.6, align 8
  %arrayidx16.8 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 0, i32 %d.051, i32 8
  %arrayidx21.8 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 8
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.8, align 8
  %arrayidx21.10 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 10
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.10, align 8
  %arrayidx21.12 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 12
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.12, align 8
  %arrayidx21.14 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 14
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.8, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.14, align 8
  %arrayidx16.16 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 0, i32 %d.051, i32 16
  store i16 5, ptr %arrayidx16.16, align 2
  %arrayidx21.16 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 16
  %arrayidx16.17 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 0, i32 %d.051, i32 17
  store i16 5, ptr %arrayidx16.17, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.16, align 8
  %arrayidx16.18 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 0, i32 %d.051, i32 18
  store i16 5, ptr %arrayidx16.18, align 2
  %arrayidx21.18 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 0, i32 %d.051, i32 18
  store i64 5, ptr %arrayidx21.18, align 8
  %inc = add nuw nsw i32 %d.051, 1
  %exitcond.not = icmp eq i32 %inc, %add
  br i1 %exitcond.not, label %for.cond.cleanup6, label %for.cond8.preheader

for.cond.cleanup6:                                ; preds = %for.cond8.preheader
  call void @llvm.memset.p0.i32(ptr noundef nonnull align 2 dereferenceable(1) getelementptr inbounds ([17 x [12 x [19 x i16]]], ptr @arr_22, i32 0, i32 4, i32 0, i32 0), i8 0, i32 %0, i1 false)
  br label %for.cond8.preheader.1

for.cond8.preheader.1:                            ; preds = %for.cond8.preheader.1, %for.cond.cleanup6
  %d.051.1 = phi i32 [ 0, %for.cond.cleanup6 ], [ %inc.1, %for.cond8.preheader.1 ]
  %arrayidx16.1 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 4, i32 %d.051.1, i32 0
  %arrayidx21.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 0
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.1, align 8
  %arrayidx21.2.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.2.1, align 8
  %arrayidx21.4.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 4
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.4.1, align 8
  %arrayidx21.6.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 6
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.1, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.6.1, align 8
  %arrayidx16.8.1 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 4, i32 %d.051.1, i32 8
  %arrayidx21.8.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 8
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.8.1, align 8
  %arrayidx21.10.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 10
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.10.1, align 8
  %arrayidx21.12.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 12
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.12.1, align 8
  %arrayidx21.14.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 14
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.8.1, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.14.1, align 8
  %arrayidx16.16.1 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 4, i32 %d.051.1, i32 16
  store i16 5, ptr %arrayidx16.16.1, align 2
  %arrayidx21.16.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 16
  %arrayidx16.17.1 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 4, i32 %d.051.1, i32 17
  store i16 5, ptr %arrayidx16.17.1, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.16.1, align 8
  %arrayidx16.18.1 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 4, i32 %d.051.1, i32 18
  store i16 5, ptr %arrayidx16.18.1, align 2
  %arrayidx21.18.1 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 4, i32 %d.051.1, i32 18
  store i64 5, ptr %arrayidx21.18.1, align 8
  %inc.1 = add nuw nsw i32 %d.051.1, 1
  %exitcond.not.1 = icmp eq i32 %inc.1, %add
  br i1 %exitcond.not.1, label %for.cond.cleanup6.1, label %for.cond8.preheader.1

for.cond.cleanup6.1:                              ; preds = %for.cond8.preheader.1
  call void @llvm.memset.p0.i32(ptr noundef nonnull align 2 dereferenceable(1) getelementptr inbounds ([17 x [12 x [19 x i16]]], ptr @arr_22, i32 0, i32 8, i32 0, i32 0), i8 0, i32 %0, i1 false)
  br label %for.cond8.preheader.2

for.cond8.preheader.2:                            ; preds = %for.cond8.preheader.2, %for.cond.cleanup6.1
  %d.051.2 = phi i32 [ 0, %for.cond.cleanup6.1 ], [ %inc.2, %for.cond8.preheader.2 ]
  %arrayidx16.2 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 8, i32 %d.051.2, i32 0
  %arrayidx21.254 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 0
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.254, align 8
  %arrayidx21.2.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.2.2, align 8
  %arrayidx21.4.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 4
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.4.2, align 8
  %arrayidx21.6.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 6
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.2, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.6.2, align 8
  %arrayidx16.8.2 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 8, i32 %d.051.2, i32 8
  %arrayidx21.8.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 8
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.8.2, align 8
  %arrayidx21.10.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 10
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.10.2, align 8
  %arrayidx21.12.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 12
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.12.2, align 8
  %arrayidx21.14.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 14
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.8.2, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.14.2, align 8
  %arrayidx16.16.2 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 8, i32 %d.051.2, i32 16
  store i16 5, ptr %arrayidx16.16.2, align 2
  %arrayidx21.16.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 16
  %arrayidx16.17.2 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 8, i32 %d.051.2, i32 17
  store i16 5, ptr %arrayidx16.17.2, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.16.2, align 8
  %arrayidx16.18.2 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 8, i32 %d.051.2, i32 18
  store i16 5, ptr %arrayidx16.18.2, align 2
  %arrayidx21.18.2 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 8, i32 %d.051.2, i32 18
  store i64 5, ptr %arrayidx21.18.2, align 8
  %inc.2 = add nuw nsw i32 %d.051.2, 1
  %exitcond.not.2 = icmp eq i32 %inc.2, %add
  br i1 %exitcond.not.2, label %for.cond.cleanup6.2, label %for.cond8.preheader.2

for.cond.cleanup6.2:                              ; preds = %for.cond8.preheader.2
  call void @llvm.memset.p0.i32(ptr noundef nonnull align 2 dereferenceable(1) getelementptr inbounds ([17 x [12 x [19 x i16]]], ptr @arr_22, i32 0, i32 12, i32 0, i32 0), i8 0, i32 %0, i1 false)
  br label %for.cond8.preheader.3

for.cond8.preheader.3:                            ; preds = %for.cond8.preheader.3, %for.cond.cleanup6.2
  %d.051.3 = phi i32 [ 0, %for.cond.cleanup6.2 ], [ %inc.3, %for.cond8.preheader.3 ]
  %arrayidx16.3 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 12, i32 %d.051.3, i32 0
  %arrayidx21.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 0
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.3, align 8
  %arrayidx21.2.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.2.3, align 8
  %arrayidx21.4.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 4
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.4.3, align 8
  %arrayidx21.6.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 6
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.3, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.6.3, align 8
  %arrayidx16.8.3 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 12, i32 %d.051.3, i32 8
  %arrayidx21.8.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 8
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.8.3, align 8
  %arrayidx21.10.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 10
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.10.3, align 8
  %arrayidx21.12.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 12
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.12.3, align 8
  %arrayidx21.14.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 14
  store <8 x i16> <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>, ptr %arrayidx16.8.3, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.14.3, align 8
  %arrayidx16.16.3 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 12, i32 %d.051.3, i32 16
  store i16 5, ptr %arrayidx16.16.3, align 2
  %arrayidx21.16.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 16
  %arrayidx16.17.3 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 12, i32 %d.051.3, i32 17
  store i16 5, ptr %arrayidx16.17.3, align 2
  store <2 x i64> <i64 5, i64 5>, ptr %arrayidx21.16.3, align 8
  %arrayidx16.18.3 = getelementptr inbounds [17 x [12 x [19 x i16]]], ptr @arr_21, i32 0, i32 12, i32 %d.051.3, i32 18
  store i16 5, ptr %arrayidx16.18.3, align 2
  %arrayidx21.18.3 = getelementptr inbounds [17 x [12 x [19 x i64]]], ptr @arr_20, i32 0, i32 12, i32 %d.051.3, i32 18
  store i64 5, ptr %arrayidx21.18.3, align 8
  %inc.3 = add nuw nsw i32 %d.051.3, 1
  %exitcond.not.3 = icmp eq i32 %inc.3, %add
  br i1 %exitcond.not.3, label %for.cond.cleanup6.3, label %for.cond8.preheader.3

for.cond.cleanup6.3:                              ; preds = %for.cond8.preheader.3
  ret i32 undef
}

attributes #0 = { noinline  optnone }
attributes #1 = { optsize }