llvm/llvm/test/Transforms/LoopVectorize/X86/pr81872.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -S -passes=loop-vectorize < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; PR 81872 explains the issue.

; If we vectorize, we have a miscompile where array IV and thereby value stored in (arr[99],
; arr[98]) is calculated incorrectly since disjoint or was only disjoint because
; of dominating conditions. Dropping the disjoint to avoid poison still changes
; the behaviour since now the or is no longer equivalent to the add.
;
define void @test(ptr noundef align 8 dereferenceable_or_null(16) %arr) #0 {
; CHECK-LABEL: define void @test(
; CHECK-SAME: ptr noundef align 8 dereferenceable_or_null(16) [[ARR:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  bb5:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]], !prof [[PROF0:![0-9]+]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 99, i64 98, i64 97, i64 96>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 99, [[INDEX]]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule <4 x i64> [[VEC_IV]], <i64 8, i64 8, i64 8, i64 8>
; CHECK-NEXT:    [[TMP2:%.*]] = and <4 x i64> [[VEC_IND]], <i64 1, i64 1, i64 1, i64 1>
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq <4 x i64> [[TMP2]], zeroinitializer
; CHECK-NEXT:    [[TMP4:%.*]] = select <4 x i1> [[TMP1]], <4 x i1> [[TMP3]], <4 x i1> zeroinitializer
; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[TMP0]], 1
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[ARR]], i64 [[TMP5]]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[TMP6]], i32 0
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 -3
; CHECK-NEXT:    [[REVERSE:%.*]] = shufflevector <4 x i1> [[TMP4]], <4 x i1> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    call void @llvm.masked.store.v4i64.p0(<4 x i64> <i64 1, i64 1, i64 1, i64 1>, ptr [[TMP8]], i32 8, <4 x i1> [[REVERSE]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 -4, i64 -4, i64 -4, i64 -4>
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 12
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !prof [[PROF1:![0-9]+]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[BB6:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 87, [[MIDDLE_BLOCK]] ], [ 99, [[BB5:%.*]] ]
; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
; CHECK:       loop.header:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
; CHECK-NEXT:    [[AND:%.*]] = and i64 [[IV]], 1
; CHECK-NEXT:    [[ICMP17:%.*]] = icmp eq i64 [[AND]], 0
; CHECK-NEXT:    br i1 [[ICMP17]], label [[BB18:%.*]], label [[LOOP_LATCH]], !prof [[PROF5:![0-9]+]]
; CHECK:       bb18:
; CHECK-NEXT:    [[OR:%.*]] = or disjoint i64 [[IV]], 1
; CHECK-NEXT:    [[GETELEMENTPTR19:%.*]] = getelementptr inbounds i64, ptr [[ARR]], i64 [[OR]]
; CHECK-NEXT:    store i64 1, ptr [[GETELEMENTPTR19]], align 8
; CHECK-NEXT:    br label [[LOOP_LATCH]]
; CHECK:       loop.latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nsw i64 [[IV]], -1
; CHECK-NEXT:    [[ICMP22:%.*]] = icmp eq i64 [[IV_NEXT]], 90
; CHECK-NEXT:    br i1 [[ICMP22]], label [[BB6]], label [[LOOP_HEADER]], !prof [[PROF6:![0-9]+]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       bb6:
; CHECK-NEXT:    ret void
;
bb5:
  br label %loop.header

loop.header:                                             ; preds = %loop.latch, %bb8
  %iv = phi i64 [ 99, %bb5 ], [ %iv.next, %loop.latch ]
  %and = and i64 %iv, 1
  %icmp17 = icmp eq i64 %and, 0
  br i1 %icmp17, label %bb18, label %loop.latch, !prof !21

bb18:                                             ; preds = %loop.header
  %or = or disjoint i64 %iv, 1
  %getelementptr19 = getelementptr inbounds i64, ptr %arr, i64 %or
  store i64 1, ptr %getelementptr19, align 8
  br label %loop.latch

loop.latch:                                             ; preds = %bb18, %loop.header
  %iv.next = add nsw i64 %iv, -1
  %icmp22 = icmp eq i64 %iv.next, 90
  br i1 %icmp22, label %bb6, label %loop.header, !prof !22

bb6:
  ret void
}

attributes #0 = {"target-cpu"="haswell" "target-features"="+avx2" }

!4 = !{}
!10 = !{i32 1}
!16 = !{i64 864}
!17 = !{i64 8}
!21 = !{!"branch_weights", i32 1, i32 1}
!22 = !{!"branch_weights", i32 1, i32 95}


;.
; CHECK: [[PROF0]] = !{!"branch_weights", i32 1, i32 127}
; CHECK: [[PROF1]] = !{!"branch_weights", i32 1, i32 23}
; CHECK: [[LOOP2]] = distinct !{[[LOOP2]], [[META3:![0-9]+]], [[META4:![0-9]+]]}
; CHECK: [[META3]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META4]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[PROF5]] = !{!"branch_weights", i32 1, i32 1}
; CHECK: [[PROF6]] = !{!"branch_weights", i32 0, i32 0}
; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META4]], [[META3]]}
;.