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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
|
/* { dg-do run { target aarch64_sve256_hw } } */
/* { dg-options "-msve-vector-bits=256 -fopenmp -O2" } */
#pragma GCC target "+sve"
#include <arm_sve.h>
#include <omp.h>
static svint32_t __attribute__ ((noipa))
foo (svint32_t *vb, svint32_t *vc, int tn)
{
svint32_t temp = svindex_s32 (tn, 0);
temp = svadd_s32_z (svptrue_b32 (), temp, *vb);
return svadd_s32_z (svptrue_b32 (), temp, *vc);
}
void __attribute__ ((noipa))
lastprivate_sections ()
{
int a[8], b[8], c[8];
svint32_t va, vb, vc;
int i;
#pragma omp parallel for
for (i = 0; i < 8; i++)
{
b[i] = i;
c[i] = i + 1;
}
#pragma omp parallel sections lastprivate (vb, vc) num_threads (2)
{
#pragma omp section
vb = svld1_s32 (svptrue_b32 (), b);
#pragma omp section
vb = svld1_s32 (svptrue_b32 (), b);
vc = svld1_s32 (svptrue_b32 (), c);
}
va = svadd_s32_z (svptrue_b32 (), vb, vc);
svst1_s32 (svptrue_b32 (), a, va);
for (i = 0; i < 8; i++)
if (a[i] != b[i] + c[i])
__builtin_abort ();
}
void __attribute__ ((noipa))
lastprivate_for ()
{
int a[32], b[32], c[32];
int aa[8], bb[8], cc[8];
svint32_t va, vb, vc;
int i, tn;
#pragma omp parallel for
for (i = 0; i < 32; i++)
{
b[i] = i;
c[i] = i + 1;
}
#pragma omp parallel for lastprivate (va, vb, vc, tn)
for (i = 0; i < 4; i++)
{
vb = svld1_s32 (svptrue_b32 (), b + i * 8);
vc = svld1_s32 (svptrue_b32 (), c + i * 8);
tn = i;
va = foo (&vb, &vc, tn);
svst1_s32 (svptrue_b32 (), a + i * 8, va);
}
svst1_s32 (svptrue_b32 (), aa, va);
svst1_s32 (svptrue_b32 (), bb, vb);
svst1_s32 (svptrue_b32 (), cc, vc);
for (i = 0; i < 8; i++)
if (aa[i] != bb[i] + cc[i] + tn)
__builtin_abort ();
for (i = 0; i < 32; i++)
if (a[i] != b[i] + c[i] + i / 8)
__builtin_abort ();
}
void __attribute__ ((noipa))
lastprivate_simd ()
{
int a[64], b[64], c[64];
int aa[8], bb[8], cc[8];
svint32_t va, vb, vc;
int i;
#pragma omp parallel for
for (i = 0; i < 64; i++)
{
b[i] = i;
c[i] = i + 1;
}
#pragma omp simd lastprivate (va, vb, vc)
for (i = 0; i < 8; i++)
{
vb = svld1_s32 (svptrue_b32 (), b + i * 8);
vc = svld1_s32 (svptrue_b32 (), c + i * 8);
va = svadd_s32_z (svptrue_b32 (), vb, vc);
svst1_s32 (svptrue_b32 (), a + i * 8, va);
}
svst1_s32 (svptrue_b32 (), aa, va);
svst1_s32 (svptrue_b32 (), bb, vb);
svst1_s32 (svptrue_b32 (), cc, vc);
for (i = 0; i < 8; i++)
if (aa[i] != bb[i] + cc[i])
__builtin_abort ();
for (i = 0; i < 64; i++)
if (a[i] != b[i] + c[i])
__builtin_abort ();
}
void __attribute__ ((noipa))
lastprivate_distribute ()
{
int a[32], b[32], c[32];
int aa[8], bb[8], cc[8];
svint32_t va, vb, vc;
int i, tn;
#pragma omp parallel for
for (i = 0; i < 32; i++)
{
b[i] = i;
c[i] = i + 1;
}
#pragma omp teams
#pragma omp distribute lastprivate (va, vb, vc, tn)
for (i = 0; i < 4; i++)
{
vb = svld1_s32 (svptrue_b32 (), b + i * 8);
vc = svld1_s32 (svptrue_b32 (), c + i * 8);
tn = i;
va = foo (&vb, &vc, tn);
svst1_s32 (svptrue_b32 (), a + i * 8, va);
}
svst1_s32 (svptrue_b32 (), aa, va);
svst1_s32 (svptrue_b32 (), bb, vb);
svst1_s32 (svptrue_b32 (), cc, vc);
for (i = 0; i < 8; i++)
if (aa[i] != bb[i] + cc[i] + tn)
__builtin_abort ();
for (i = 0; i < 32; i++)
if (a[i] != b[i] + c[i] + i / 8)
__builtin_abort ();
}
int
main ()
{
lastprivate_for ();
lastprivate_sections ();
lastprivate_simd ();
lastprivate_distribute ();
}
|
