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
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
|
/* PR middle-end/106548. */
/* { dg-additional-options "-msse2" { target sse2_runtime } } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
int a[256];
__attribute__((noinline, noclone)) int
f1 (int i)
{
#pragma omp parallel for simd linear (i: 4)
for (int j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f2 (short int i, char k)
{
#pragma omp parallel for simd linear (i: k + 1)
for (long j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f3 (long long int i, long long int k)
{
#pragma omp parallel for simd linear (i: k)
for (short j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) int
f4 (int i)
{
#pragma omp parallel for simd linear (i: 4) schedule(static, 3)
for (int j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f5 (short int i, char k)
{
#pragma omp parallel for simd linear (i: k + 1) schedule(static, 5)
for (long j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f6 (long long int i, long long int k)
{
#pragma omp parallel for simd linear (i: k) schedule(static, 7)
for (short j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) int
f7 (int i)
{
#pragma omp parallel for simd linear (i: 4) schedule(dynamic, 3)
for (int j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f8 (short int i, char k)
{
#pragma omp parallel for simd linear (i: k + 1) schedule(dynamic, 5)
for (long j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f9 (long long int i, long long int k)
{
#pragma omp parallel for simd linear (i: k) schedule(dynamic, 7)
for (short j = 16; j < 64; j++)
{
a[i] = j;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) int
f10 (int i, long step)
{
#pragma omp parallel for simd linear (i: 4)
for (int j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f11 (short int i, char k, char step)
{
#pragma omp parallel for simd linear (i: k + 1)
for (long j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f12 (long long int i, long long int k, int step)
{
#pragma omp parallel for simd linear (i: k)
for (short j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) int
f13 (int i, long long int step)
{
#pragma omp parallel for simd linear (i: 4) schedule(static, 3)
for (int j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f14 (short int i, char k, int step)
{
#pragma omp parallel for simd linear (i: k + 1) schedule(static, 5)
for (long j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f15 (long long int i, long long int k, long int step)
{
#pragma omp parallel for simd linear (i: k) schedule(static, 7)
for (short j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) int
f16 (int i, long long int step)
{
#pragma omp parallel for simd linear (i: 4) schedule(dynamic, 3)
for (int j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) short int
f17 (short int i, char k, int step)
{
#pragma omp parallel for simd linear (i: k + 1) schedule(dynamic, 5)
for (long j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
__attribute__((noinline, noclone)) long long int
f18 (long long int i, long long int k, long int step)
{
#pragma omp parallel for simd linear (i: k) schedule(dynamic, 7)
for (short j = 16; j < 112; j += step)
{
a[i] = j / 2 + 8;
i += 4;
}
return i;
}
int
main ()
{
#define TEST(x) \
if (x != 8 + 48 * 4) \
__builtin_abort (); \
for (int i = 0; i < 256; i++) \
if (a[i] != (((i & 3) == 0 && i >= 8 \
&& i < 8 + 48 * 4) \
? ((i - 8) / 4) + 16 : 0)) \
__builtin_abort (); \
__builtin_memset (a, 0, sizeof (a))
TEST (f1 (8));
TEST (f2 (8, 3));
TEST (f3 (8LL, 4LL));
TEST (f4 (8));
TEST (f5 (8, 3));
TEST (f6 (8LL, 4LL));
TEST (f7 (8));
TEST (f8 (8, 3));
TEST (f9 (8LL, 4LL));
TEST (f10 (8, 2));
TEST (f11 (8, 3, 2));
TEST (f12 (8LL, 4LL, 2));
TEST (f13 (8, 2));
TEST (f14 (8, 3, 2));
TEST (f15 (8LL, 4LL, 2));
TEST (f16 (8, 2));
TEST (f17 (8, 3, 2));
TEST (f18 (8LL, 4LL, 2));
return 0;
}
|
