non-affine-loop-condition-dependent-access_3.ll
3.75 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
; RUN: opt %loadPolly -polly-detect -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=false \
; RUN: -analyze < %s | FileCheck %s --check-prefix=REJECTNONAFFINELOOPS
; RUN: opt %loadPolly -polly-detect -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s --check-prefix=ALLOWNONAFFINELOOPS
; RUN: opt %loadPolly -polly-detect -polly-allow-nonaffine \
; RUN: -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s \
; RUN: --check-prefix=ALLOWNONAFFINELOOPSANDACCESSES
;
; Here we have a non-affine loop (in the context of the loop nest)
; and also a non-affine access (A[k]). While we can always detect the
; innermost loop as a SCoP of depth 1, we have to reject the loop nest if not
; both, non-affine loops as well as non-affine accesses are allowed.
;
; REJECTNONAFFINELOOPS: Valid Region for Scop: bb15 => bb13
; REJECTNONAFFINELOOPS-NOT: Valid
; ALLOWNONAFFINELOOPS: Valid Region for Scop: bb15 => bb13
; ALLOWNONAFFINELOOPS-NOT: Valid
; ALLOWNONAFFINELOOPSANDACCESSES: Valid Region for Scop: bb11 => bb29
;
; void f(int *A) {
; for (int i = 0; i < 1024; i++)
; for (int j = 0; j < 1024; j++)
; for (int k = 0; k < i * j; k++)
; A[k] += A[i] + A[j];
; }
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @f(i32* %A) {
bb:
br label %bb11
bb11: ; preds = %bb28, %bb
%indvars.iv8 = phi i64 [ %indvars.iv.next9, %bb28 ], [ 0, %bb ]
%indvars.iv1 = phi i32 [ %indvars.iv.next2, %bb28 ], [ 0, %bb ]
%exitcond10 = icmp ne i64 %indvars.iv8, 1024
br i1 %exitcond10, label %bb12, label %bb29
bb12: ; preds = %bb11
br label %bb13
bb13: ; preds = %bb26, %bb12
%indvars.iv5 = phi i64 [ %indvars.iv.next6, %bb26 ], [ 0, %bb12 ]
%indvars.iv3 = phi i32 [ %indvars.iv.next4, %bb26 ], [ 0, %bb12 ]
%exitcond7 = icmp ne i64 %indvars.iv5, 1024
br i1 %exitcond7, label %bb14, label %bb27
bb14: ; preds = %bb13
br label %bb15
bb15: ; preds = %bb24, %bb14
%indvars.iv = phi i64 [ %indvars.iv.next, %bb24 ], [ 0, %bb14 ]
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp ne i32 %lftr.wideiv, %indvars.iv3
br i1 %exitcond, label %bb16, label %bb25
bb16: ; preds = %bb15
%tmp = getelementptr inbounds i32, i32* %A, i64 %indvars.iv8
%tmp17 = load i32, i32* %tmp, align 4
%tmp18 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv5
%tmp19 = load i32, i32* %tmp18, align 4
%tmp20 = add nsw i32 %tmp17, %tmp19
%tmp21 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
%tmp22 = load i32, i32* %tmp21, align 4
%tmp23 = add nsw i32 %tmp22, %tmp20
store i32 %tmp23, i32* %tmp21, align 4
br label %bb24
bb24: ; preds = %bb16
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %bb15
bb25: ; preds = %bb15
br label %bb26
bb26: ; preds = %bb25
%indvars.iv.next6 = add nuw nsw i64 %indvars.iv5, 1
%indvars.iv.next4 = add nuw nsw i32 %indvars.iv3, %indvars.iv1
br label %bb13
bb27: ; preds = %bb13
br label %bb28
bb28: ; preds = %bb27
%indvars.iv.next9 = add nuw nsw i64 %indvars.iv8, 1
%indvars.iv.next2 = add nuw nsw i32 %indvars.iv1, 1
br label %bb11
bb29: ; preds = %bb11
ret void
}