; RUN: opt %loadNPMPolly -aa-pipeline=basic-aa '-passes=print<polly-ast>' -polly-ast-detect-parallel -disable-output < %s | FileCheck %s
;
; This loopnest contains a reduction which imposes the same dependences as the
; accesses to the array A. We need to ensure we do __not__ parallelize anything
; here.
;
; CHECK: #pragma minimal dependence distance: 1
; CHECK-NOT: pragma
; CHECK-NOT: reduction
;
; void AandSum(int *restrict sum, int *restrict A) {
; for (int i = 0; i < 1024; i++) {
; A[i] = A[i] + A[i - 1];
; A[i - 1] = A[i] + A[i - 2];
; *sum += i;
; }
; }
;
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
define void @AandSum(ptr noalias %sum, ptr noalias %A) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%exitcond = icmp ne i32 %i.0, 1024
br i1 %exitcond, label %for.body, label %for.end
for.body: ; preds = %for.cond
%arrayidx = getelementptr inbounds i32, ptr %A, i32 %i.0
%tmp = load i32, ptr %arrayidx, align 4
%sub = add nsw i32 %i.0, -1
%arrayidx1 = getelementptr inbounds i32, ptr %A, i32 %sub
%tmp1 = load i32, ptr %arrayidx1, align 4
%add = add nsw i32 %tmp, %tmp1
%arrayidx2 = getelementptr inbounds i32, ptr %A, i32 %i.0
store i32 %add, ptr %arrayidx2, align 4
%sub4 = add nsw i32 %i.0, -2
%arrayidx5 = getelementptr inbounds i32, ptr %A, i32 %sub4
%tmp2 = load i32, ptr %arrayidx5, align 4
%add6 = add nsw i32 %add, %tmp2
%sub7 = add nsw i32 %i.0, -1
%arrayidx8 = getelementptr inbounds i32, ptr %A, i32 %sub7
store i32 %add6, ptr %arrayidx8, align 4
%tmp3 = load i32, ptr %sum, align 4
%add9 = add nsw i32 %tmp3, %i.0
store i32 %add9, ptr %sum, align 4
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end: ; preds = %for.cond
ret void
}