llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; A tricky loop:
;
; void loop(int *a, int *b) {
;    for (int i = 0; i < 512; ++i) {
;        a[a[i]] = b[i];
;        a[i] = b[i+1];
;    }
;}

define void @loop(i32* nocapture %a, i32* nocapture %b) nounwind uwtable {
; CHECK-LABEL: @loop(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[IDXPROM3:%.*]] = sext i32 [[TMP1]] to i64
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[IDXPROM3]]
; CHECK-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX4]], align 4
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV_NEXT]]
; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4
; CHECK-NEXT:    store i32 [[TMP2]], i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 512
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
  %1 = load i32, i32* %arrayidx2, align 4
  %idxprom3 = sext i32 %1 to i64
  %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
  store i32 %0, i32* %arrayidx4, align 4
  %indvars.iv.next = add i64 %indvars.iv, 1
  %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
  %2 = load i32, i32* %arrayidx6, align 4
  store i32 %2, i32* %arrayidx2, align 4
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 512
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

; The same loop with parallel loop metadata added to the loop branch
; and the memory instructions.

define void @parallel_loop(i32* nocapture %a, i32* nocapture %b) nounwind uwtable {
; CHECK-LABEL: @parallel_loop(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; 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:    [[TMP0:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP1:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP2:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP0]]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP1]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP2]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP5]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP6]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP7]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP8]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP13:%.*]] = sext i32 [[TMP9]] to i64
; CHECK-NEXT:    [[TMP14:%.*]] = sext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[TMP15:%.*]] = sext i32 [[TMP11]] to i64
; CHECK-NEXT:    [[TMP16:%.*]] = sext i32 [[TMP12]] to i64
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP13]]
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP14]]
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP15]]
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP16]]
; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 0
; CHECK-NEXT:    store i32 [[TMP21]], i32* [[TMP17]], align 4, !llvm.access.group !1
; CHECK-NEXT:    [[TMP22:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 1
; CHECK-NEXT:    store i32 [[TMP22]], i32* [[TMP18]], align 4, !llvm.access.group !1
; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 2
; CHECK-NEXT:    store i32 [[TMP23]], i32* [[TMP19]], align 4, !llvm.access.group !1
; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3
; CHECK-NEXT:    store i32 [[TMP24]], i32* [[TMP20]], align 4, !llvm.access.group !1
; CHECK-NEXT:    [[TMP25:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP25]]
; CHECK-NEXT:    [[TMP27:%.*]] = bitcast i32* [[TMP26]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP27]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[TMP28:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[WIDE_LOAD1]], <4 x i32>* [[TMP28]], align 4, !llvm.access.group !0
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP29:%.*]] = icmp eq i64 [[INDEX_NEXT]], 512
; CHECK-NEXT:    br i1 [[TMP29]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
  %0 = load i32, i32* %arrayidx, align 4, !llvm.access.group !13
  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
  %1 = load i32, i32* %arrayidx2, align 4, !llvm.access.group !13
  %idxprom3 = sext i32 %1 to i64
  %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
  ; This store might have originated from inlining a function with a parallel
  ; loop. Refers to a list with the "original loop reference" (!4) also included.
  store i32 %0, i32* %arrayidx4, align 4, !llvm.access.group !15
  %indvars.iv.next = add i64 %indvars.iv, 1
  %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
  %2 = load i32, i32* %arrayidx6, align 4, !llvm.access.group !13
  store i32 %2, i32* %arrayidx2, align 4, !llvm.access.group !13
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 512
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3

for.end:                                          ; preds = %for.body
  ret void
}

; The same loop with an illegal parallel loop metadata: the memory
; accesses refer to a different loop's identifier.


define void @mixed_metadata(i32* nocapture %a, i32* nocapture %b) nounwind uwtable {
; CHECK-LABEL: @mixed_metadata(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4, !llvm.access.group !7
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4, !llvm.access.group !7
; CHECK-NEXT:    [[IDXPROM3:%.*]] = sext i32 [[TMP1]] to i64
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[IDXPROM3]]
; CHECK-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX4]], align 4, !llvm.access.group !8
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV_NEXT]]
; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4, !llvm.access.group !7
; CHECK-NEXT:    store i32 [[TMP2]], i32* [[ARRAYIDX2]], align 4, !llvm.access.group !7
; CHECK-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 512
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
  %0 = load i32, i32* %arrayidx, align 4, !llvm.access.group !16
  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
  %1 = load i32, i32* %arrayidx2, align 4, !llvm.access.group !16
  %idxprom3 = sext i32 %1 to i64
  %arrayidx4 = getelementptr inbounds i32, i32* %a, i64 %idxprom3
  ; This refers to the loop marked with !7 which we are not in at the moment.
  ; It should prevent detecting as a parallel loop.
  store i32 %0, i32* %arrayidx4, align 4, !llvm.access.group !17
  %indvars.iv.next = add i64 %indvars.iv, 1
  %arrayidx6 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv.next
  %2 = load i32, i32* %arrayidx6, align 4, !llvm.access.group !16
  store i32 %2, i32* %arrayidx2, align 4, !llvm.access.group !16
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 512
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !6

for.end:                                          ; preds = %for.body
  ret void
}

!3 = !{!3, !{!"llvm.loop.parallel_accesses", !13, !15}}
!4 = !{!4, !{!"llvm.loop.parallel_accesses", !14, !15}}
!6 = !{!6, !{!"llvm.loop.parallel_accesses", !16}}
!7 = !{!7, !{!"llvm.loop.parallel_accesses", !17}}
!13 = distinct !{}
!14 = distinct !{}
!15 = distinct !{}
!16 = distinct !{}
!17 = distinct !{}