test/Transforms/LoopDistribute/metadata.ll

; RUN: opt -basicaa -loop-distribute -enable-loop-distribute=0 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_OFF
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute=1 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_ON

; Same loop as in basic.ll.  Check that distribution is enabled/disabled
; properly according to -enable-loop-distribute=0/1 and the
; llvm.loop.distribute.enable metadata.

target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"

; CHECK-LABEL: @explicit_on(
define void @explicit_on(i32* noalias %a,
                         i32* noalias %b,
                         i32* noalias %c,
                         i32* noalias %d,
                         i32* noalias %e) {
entry:
  br label %for.body

; EXPLICIT: for.body.ldist1:

for.body:                                         ; preds = %for.body, %entry
  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]

  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
  %loadA = load i32, i32* %arrayidxA, align 4

  %arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
  %loadB = load i32, i32* %arrayidxB, align 4

  %mulA = mul i32 %loadB, %loadA

  %add = add nuw nsw i64 %ind, 1
  %arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
  store i32 %mulA, i32* %arrayidxA_plus_4, align 4

  %arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
  %loadD = load i32, i32* %arrayidxD, align 4

  %arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
  %loadE = load i32, i32* %arrayidxE, align 4

  %mulC = mul i32 %loadD, %loadE

  %arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
  store i32 %mulC, i32* %arrayidxC, align 4

  %exitcond = icmp eq i64 %add, 20
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0

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

; CHECK-LABEL: @explicit_off(
define void @explicit_off(i32* noalias %a,
                         i32* noalias %b,
                         i32* noalias %c,
                         i32* noalias %d,
                         i32* noalias %e) {
entry:
  br label %for.body

; EXPLICIT-NOT: for.body.ldist1:

for.body:                                         ; preds = %for.body, %entry
  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]

  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
  %loadA = load i32, i32* %arrayidxA, align 4

  %arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
  %loadB = load i32, i32* %arrayidxB, align 4

  %mulA = mul i32 %loadB, %loadA

  %add = add nuw nsw i64 %ind, 1
  %arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
  store i32 %mulA, i32* %arrayidxA_plus_4, align 4

  %arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
  %loadD = load i32, i32* %arrayidxD, align 4

  %arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
  %loadE = load i32, i32* %arrayidxE, align 4

  %mulC = mul i32 %loadD, %loadE

  %arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
  store i32 %mulC, i32* %arrayidxC, align 4

  %exitcond = icmp eq i64 %add, 20
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2

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

; CHECK-LABEL: @default_distribute(
define void @default_distribute(i32* noalias %a,
               i32* noalias %b,
               i32* noalias %c,
               i32* noalias %d,
               i32* noalias %e) {
entry:
  br label %for.body

; Verify the two distributed loops.

; DEFAULT_ON: for.body.ldist1:
; DEFAULT_OFF-NOT: for.body.ldist1:

for.body:                                         ; preds = %for.body, %entry
  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]

  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
  %loadA = load i32, i32* %arrayidxA, align 4

  %arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
  %loadB = load i32, i32* %arrayidxB, align 4

  %mulA = mul i32 %loadB, %loadA

  %add = add nuw nsw i64 %ind, 1
  %arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
  store i32 %mulA, i32* %arrayidxA_plus_4, align 4

  %arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
  %loadD = load i32, i32* %arrayidxD, align 4

  %arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
  %loadE = load i32, i32* %arrayidxE, align 4

  %mulC = mul i32 %loadD, %loadE

  %arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
  store i32 %mulC, i32* %arrayidxC, align 4

  %exitcond = icmp eq i64 %add, 20
  br i1 %exitcond, label %for.end, label %for.body

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

!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.distribute.enable", i1 true}
!2 = distinct !{!2, !3}
!3 = !{!"llvm.loop.distribute.enable", i1 false}