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
95
|
/* { dg-do run } */
/* { dg-additional-options "-msse2" { target sse2_runtime } } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
extern void abort ();
int a[1024] __attribute__((aligned (32))) = { 1 };
int b[1024] __attribute__((aligned (32))) = { 1 };
int k, m;
struct U { int u; };
struct V { int v; };
__attribute__((noinline, noclone)) int
foo (int *p)
{
int i, s = 0;
struct U u;
struct V v;
#pragma omp simd aligned(a, p : 32) linear(k: m + 1) \
linear(i) reduction(+:s) lastprivate(u, v)
for (i = 0; i < 1024; i++)
{
int *q = &i;
a[i] *= p[i];
u.u = p[i] + k;
k += m + 1;
v.v = p[i] + k;
s += p[i] + k;
}
if (u.u != 36 + 4 + 3 * 1023 || v.v != 36 + 4 + 3 * 1024 || i != 1024)
abort ();
return s;
}
__attribute__((noinline, noclone)) int
bar (int *p)
{
int i, s = 0;
struct U u;
struct V v;
#pragma omp simd aligned(a, p : 32) linear(k: m + 1) \
reduction(+:s) lastprivate(u, v)
for (i = 0; i < 1024; i++)
{
int *q = &i;
a[i] *= p[i];
u.u = p[i] + k;
k += m + 1;
v.v = p[i] + k;
s += p[i] + k;
}
if (u.u != 36 + 4 + 3 * 1023 || v.v != 36 + 4 + 3 * 1024 || i != 1024)
abort ();
return s;
}
int
main ()
{
#if __SIZEOF_INT__ >= 4
int i;
k = 4;
m = 2;
for (i = 0; i < 1024; i++)
{
a[i] = i - 512;
b[i] = (i - 51) % 39;
}
int s = foo (b);
for (i = 0; i < 1024; i++)
{
if (b[i] != (i - 51) % 39
|| a[i] != (i - 512) * b[i])
abort ();
}
if (k != 4 + 3 * 1024 || s != 1596127)
abort ();
k = 4;
m = 2;
for (i = 0; i < 1024; i++)
{
a[i] = i - 512;
b[i] = (i - 51) % 39;
}
s = bar (b);
for (i = 0; i < 1024; i++)
{
if (b[i] != (i - 51) % 39
|| a[i] != (i - 512) * b[i])
abort ();
}
if (k != 4 + 3 * 1024 || s != 1596127)
abort ();
#endif
return 0;
}
|
