; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -p loop-vectorize -force-vector-width=4 -S %s | FileCheck %s

target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Test for https://github.com/llvm/llvm-project/issues/111606.
define ptr @test_interleave_ptradd_with_replicated_op(ptr %m) #0 {
; CHECK-LABEL: define ptr @test_interleave_ptradd_with_replicated_op(
; CHECK-SAME: ptr [[M:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[M]], i64 768
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 8
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[OFFSET_IDX]], 8
; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[OFFSET_IDX]], 16
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[OFFSET_IDX]], 24
; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[OFFSET_IDX]], 32
; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], 40
; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], 48
; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX]], 56
; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[OFFSET_IDX]], 64
; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[OFFSET_IDX]], 72
; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[OFFSET_IDX]], 80
; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[OFFSET_IDX]], 88
; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[OFFSET_IDX]], 96
; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[OFFSET_IDX]], 104
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[OFFSET_IDX]], 112
; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[OFFSET_IDX]], 120
; CHECK-NEXT:    [[NEXT_GEP12:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP0]]
; CHECK-NEXT:    [[NEXT_GEP2:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP1]]
; CHECK-NEXT:    [[NEXT_GEP3:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP2]]
; CHECK-NEXT:    [[NEXT_GEP4:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP3]]
; CHECK-NEXT:    [[NEXT_GEP13:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP4]]
; CHECK-NEXT:    [[NEXT_GEP6:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP5]]
; CHECK-NEXT:    [[NEXT_GEP7:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP6]]
; CHECK-NEXT:    [[NEXT_GEP8:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP7]]
; CHECK-NEXT:    [[NEXT_GEP14:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP8]]
; CHECK-NEXT:    [[NEXT_GEP10:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP9]]
; CHECK-NEXT:    [[NEXT_GEP11:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP10]]
; CHECK-NEXT:    [[NEXT_GEP17:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP11]]
; CHECK-NEXT:    [[NEXT_GEP15:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP12]]
; CHECK-NEXT:    [[NEXT_GEP18:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP13]]
; CHECK-NEXT:    [[NEXT_GEP19:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP14]]
; CHECK-NEXT:    [[NEXT_GEP16:%.*]] = getelementptr i8, ptr [[M]], i64 [[TMP15]]
; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr i8, ptr [[NEXT_GEP12]], i64 4
; CHECK-NEXT:    [[TMP28:%.*]] = getelementptr i8, ptr [[NEXT_GEP13]], i64 4
; CHECK-NEXT:    [[TMP29:%.*]] = getelementptr i8, ptr [[NEXT_GEP14]], i64 4
; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr i8, ptr [[NEXT_GEP15]], i64 4
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr i8, ptr [[TMP27]], i32 -4
; CHECK-NEXT:    [[TMP33:%.*]] = getelementptr i8, ptr [[TMP28]], i32 -4
; CHECK-NEXT:    [[TMP34:%.*]] = getelementptr i8, ptr [[TMP29]], i32 -4
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr i8, ptr [[TMP30]], i32 -4
; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <8 x i32>, ptr [[TMP32]], align 4
; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <8 x i32> [[WIDE_VEC]], <8 x i32> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:    [[STRIDED_VEC17:%.*]] = shufflevector <8 x i32> [[WIDE_VEC]], <8 x i32> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:    [[WIDE_VEC18:%.*]] = load <8 x i32>, ptr [[TMP33]], align 4
; CHECK-NEXT:    [[STRIDED_VEC19:%.*]] = shufflevector <8 x i32> [[WIDE_VEC18]], <8 x i32> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:    [[STRIDED_VEC20:%.*]] = shufflevector <8 x i32> [[WIDE_VEC18]], <8 x i32> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:    [[WIDE_VEC21:%.*]] = load <8 x i32>, ptr [[TMP34]], align 4
; CHECK-NEXT:    [[STRIDED_VEC22:%.*]] = shufflevector <8 x i32> [[WIDE_VEC21]], <8 x i32> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:    [[STRIDED_VEC23:%.*]] = shufflevector <8 x i32> [[WIDE_VEC21]], <8 x i32> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:    [[WIDE_VEC24:%.*]] = load <8 x i32>, ptr [[TMP35]], align 4
; CHECK-NEXT:    [[STRIDED_VEC25:%.*]] = shufflevector <8 x i32> [[WIDE_VEC24]], <8 x i32> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:    [[STRIDED_VEC26:%.*]] = shufflevector <8 x i32> [[WIDE_VEC24]], <8 x i32> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:    [[TMP36:%.*]] = add <4 x i32> [[STRIDED_VEC17]], [[STRIDED_VEC]]
; CHECK-NEXT:    [[TMP37:%.*]] = add <4 x i32> [[STRIDED_VEC20]], [[STRIDED_VEC19]]
; CHECK-NEXT:    [[TMP38:%.*]] = add <4 x i32> [[STRIDED_VEC23]], [[STRIDED_VEC22]]
; CHECK-NEXT:    [[TMP39:%.*]] = add <4 x i32> [[STRIDED_VEC26]], [[STRIDED_VEC25]]
; CHECK-NEXT:    [[TMP40:%.*]] = extractelement <4 x i32> [[TMP36]], i32 0
; CHECK-NEXT:    store i32 [[TMP40]], ptr [[NEXT_GEP12]], align 4
; CHECK-NEXT:    [[TMP41:%.*]] = extractelement <4 x i32> [[TMP36]], i32 1
; CHECK-NEXT:    store i32 [[TMP41]], ptr [[NEXT_GEP2]], align 4
; CHECK-NEXT:    [[TMP42:%.*]] = extractelement <4 x i32> [[TMP36]], i32 2
; CHECK-NEXT:    store i32 [[TMP42]], ptr [[NEXT_GEP3]], align 4
; CHECK-NEXT:    [[TMP43:%.*]] = extractelement <4 x i32> [[TMP36]], i32 3
; CHECK-NEXT:    store i32 [[TMP43]], ptr [[NEXT_GEP4]], align 4
; CHECK-NEXT:    [[TMP44:%.*]] = extractelement <4 x i32> [[TMP37]], i32 0
; CHECK-NEXT:    store i32 [[TMP44]], ptr [[NEXT_GEP13]], align 4
; CHECK-NEXT:    [[TMP45:%.*]] = extractelement <4 x i32> [[TMP37]], i32 1
; CHECK-NEXT:    store i32 [[TMP45]], ptr [[NEXT_GEP6]], align 4
; CHECK-NEXT:    [[TMP46:%.*]] = extractelement <4 x i32> [[TMP37]], i32 2
; CHECK-NEXT:    store i32 [[TMP46]], ptr [[NEXT_GEP7]], align 4
; CHECK-NEXT:    [[TMP47:%.*]] = extractelement <4 x i32> [[TMP37]], i32 3
; CHECK-NEXT:    store i32 [[TMP47]], ptr [[NEXT_GEP8]], align 4
; CHECK-NEXT:    [[TMP48:%.*]] = extractelement <4 x i32> [[TMP38]], i32 0
; CHECK-NEXT:    store i32 [[TMP48]], ptr [[NEXT_GEP14]], align 4
; CHECK-NEXT:    [[TMP49:%.*]] = extractelement <4 x i32> [[TMP38]], i32 1
; CHECK-NEXT:    store i32 [[TMP49]], ptr [[NEXT_GEP10]], align 4
; CHECK-NEXT:    [[TMP50:%.*]] = extractelement <4 x i32> [[TMP38]], i32 2
; CHECK-NEXT:    store i32 [[TMP50]], ptr [[NEXT_GEP11]], align 4
; CHECK-NEXT:    [[TMP51:%.*]] = extractelement <4 x i32> [[TMP38]], i32 3
; CHECK-NEXT:    store i32 [[TMP51]], ptr [[NEXT_GEP17]], align 4
; CHECK-NEXT:    [[TMP52:%.*]] = extractelement <4 x i32> [[TMP39]], i32 0
; CHECK-NEXT:    store i32 [[TMP52]], ptr [[NEXT_GEP15]], align 4
; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <4 x i32> [[TMP39]], i32 1
; CHECK-NEXT:    store i32 [[TMP53]], ptr [[NEXT_GEP18]], align 4
; CHECK-NEXT:    [[TMP54:%.*]] = extractelement <4 x i32> [[TMP39]], i32 2
; CHECK-NEXT:    store i32 [[TMP54]], ptr [[NEXT_GEP19]], align 4
; CHECK-NEXT:    [[TMP55:%.*]] = extractelement <4 x i32> [[TMP39]], i32 3
; CHECK-NEXT:    store i32 [[TMP55]], ptr [[NEXT_GEP16]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT:    [[TMP56:%.*]] = icmp eq i64 [[INDEX_NEXT]], 96
; CHECK-NEXT:    br i1 [[TMP56]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[SCALAR_PH:.*]]
; CHECK:       [[SCALAR_PH]]:
; CHECK-NEXT:    br label %[[LOOP:.*]]
; CHECK:       [[LOOP]]:
; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[IND_END]], %[[SCALAR_PH]] ], [ [[PTR_IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 97, %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT:    [[PTR_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 8
; CHECK-NEXT:    [[P_4:%.*]] = getelementptr i8, ptr [[PTR_IV]], i64 4
; CHECK-NEXT:    [[L_1:%.*]] = load i32, ptr [[P_4]], align 4
; CHECK-NEXT:    [[P_0:%.*]] = getelementptr i8, ptr [[PTR_IV]], i64 0
; CHECK-NEXT:    [[L_2:%.*]] = load i32, ptr [[P_0]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add i32 [[L_1]], [[L_2]]
; CHECK-NEXT:    store i32 [[ADD]], ptr [[PTR_IV]], align 4
; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i32 [[IV]], 100
; CHECK-NEXT:    br i1 [[TOBOOL_NOT]], label %[[EXIT:.*]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    [[P_4_LCSSA:%.*]] = phi ptr [ [[P_4]], %[[LOOP]] ]
; CHECK-NEXT:    ret ptr [[P_4_LCSSA]]
;
entry:
  br label %loop

loop:                                         ; preds = %loop, %entry
  %ptr.iv = phi ptr [ %m, %entry ], [ %ptr.iv.next, %loop ]
  %iv = phi i32 [ 1, %entry ], [ %iv.next, %loop ]
  %ptr.iv.next = getelementptr i8, ptr %ptr.iv, i64 8
  %p.4 = getelementptr i8, ptr %ptr.iv, i64 4
  %l.1 = load i32, ptr %p.4, align 4
  %p.0 = getelementptr i8, ptr %ptr.iv, i64 0
  %l.2 = load i32, ptr %p.0, align 4
  %add = add i32 %l.1, %l.2
  store i32 %add, ptr %ptr.iv, align 4
  %iv.next = add i32 %iv, 1
  %tobool.not = icmp eq i32 %iv, 100
  br i1 %tobool.not, label %exit, label %loop

exit:                       ; preds = %loop
  ret ptr %p.4
}

attributes #0 = { "target-cpu"="znver2" }
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
;.