llvm/test/Transforms/LoopDistribute/program-order.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes=loop-distribute -enable-loop-distribute -S -verify-loop-info -verify-dom-info < %s \
; RUN:   | FileCheck %s

; Distributing this loop to avoid the dependence cycle would require to
; reorder S1 and S2 to form the two partitions: {S2} | {S1, S3}.  The analysis
; provided by LoopAccessAnalysis does not allow us to reorder memory
; operations so make sure we bail on this loop.
;
;   for (i = 0; i < n; i++) {
;     S1: d = D[i];
;     S2: A[i + 1] = A[i] * B[i];
;     S3: C[i] = d * E[i];
;   }

define void @f(ptr noalias %a, ptr noalias %b, ptr noalias %c, ptr noalias %d, ptr noalias %e) {
; CHECK-LABEL: define void @f(
; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]], ptr noalias [[D:%.*]], ptr noalias [[E:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    br label %[[FOR_BODY:.*]]
; CHECK:       [[FOR_BODY]]:
; CHECK-NEXT:    [[IND:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[ADD:%.*]], %[[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDXA:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IND]]
; CHECK-NEXT:    [[LOADA:%.*]] = load i32, ptr [[ARRAYIDXA]], align 4
; CHECK-NEXT:    [[ARRAYIDXB:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[IND]]
; CHECK-NEXT:    [[LOADB:%.*]] = load i32, ptr [[ARRAYIDXB]], align 4
; CHECK-NEXT:    [[MULA:%.*]] = mul i32 [[LOADB]], [[LOADA]]
; CHECK-NEXT:    [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[IND]]
; CHECK-NEXT:    [[LOADD:%.*]] = load i32, ptr [[ARRAYIDXD]], align 4
; CHECK-NEXT:    [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT:    [[ARRAYIDXA_PLUS_4:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[ADD]]
; CHECK-NEXT:    store i32 [[MULA]], ptr [[ARRAYIDXA_PLUS_4]], align 4
; CHECK-NEXT:    [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[IND]]
; CHECK-NEXT:    [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, ptr [[E]], i64 [[IND]]
; CHECK-NEXT:    [[LOADE:%.*]] = load i32, ptr [[ARRAYIDXE]], align 4
; CHECK-NEXT:    [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT:    store i32 [[MULC]], ptr [[ARRAYIDXC]], align 4
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], 20
; 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
  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]

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

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

  %mulA = mul i32 %loadB, %loadA

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

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

  %arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind

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

  %mulC = mul i32 %loadD, %loadE

  store i32 %mulC, ptr %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
}