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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
|
// RUN: %check_clang_tidy -check-suffix=OLDCLOLDAOC %s altera-single-work-item-barrier %t -- -header-filter=.* "--" -cl-std=CL1.2 -c -DOLDCLOLDAOC
// RUN: %check_clang_tidy -check-suffix=NEWCLOLDAOC %s altera-single-work-item-barrier %t -- -header-filter=.* "--" -cl-std=CL2.0 -c -DNEWCLOLDAOC
// RUN: %check_clang_tidy -check-suffix=OLDCLNEWAOC %s altera-single-work-item-barrier %t -- -config='{CheckOptions: [{key: altera-single-work-item-barrier.AOCVersion, value: 1701}]}' -header-filter=.* "--" -cl-std=CL1.2 -c -DOLDCLNEWAOC
// RUN: %check_clang_tidy -check-suffix=NEWCLNEWAOC %s altera-single-work-item-barrier %t -- -config='{CheckOptions: [{key: altera-single-work-item-barrier.AOCVersion, value: 1701}]}' -header-filter=.* "--" -cl-std=CL2.0 -c -DNEWCLNEWAOC
#ifdef OLDCLOLDAOC // OpenCL 1.2 Altera Offline Compiler < 17.1
void __kernel error_barrier_no_id(__global int * foo, int size) {
// CHECK-MESSAGES-OLDCLOLDAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id' does not call 'get_global_id' or 'get_local_id' and will be treated as a single work-item [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-OLDCLOLDAOC: :[[@LINE-1]]:3: note: barrier call is in a single work-item and may error out
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void __kernel success_barrier_global_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void __kernel success_barrier_local_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void __kernel success_barrier_both_ids(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
void success_nokernel_barrier_no_id(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void success_nokernel_barrier_global_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void success_nokernel_barrier_local_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void success_nokernel_barrier_both_ids(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
#endif
#ifdef NEWCLOLDAOC // OpenCL 2.0 Altera Offline Compiler < 17.1
void __kernel error_barrier_no_id(__global int * foo, int size) {
// CHECK-MESSAGES-NEWCLOLDAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id' does not call 'get_global_id' or 'get_local_id' and will be treated as a single work-item [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-NEWCLOLDAOC: :[[@LINE-1]]:3: note: barrier call is in a single work-item and may error out
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void __kernel success_barrier_global_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void __kernel success_barrier_local_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void __kernel success_barrier_both_ids(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
void success_nokernel_barrier_no_id(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void success_nokernel_barrier_global_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void success_nokernel_barrier_local_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void success_nokernel_barrier_both_ids(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
#endif
#ifdef OLDCLNEWAOC // OpenCL 1.2 Altera Offline Compiler >= 17.1
void __kernel error_barrier_no_id(__global int * foo, int size) {
// CHECK-MESSAGES-OLDCLNEWAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id' does not call an ID function and may be a viable single work-item, but will be forced to execute as an NDRange [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-OLDCLNEWAOC: :[[@LINE-1]]:3: note: barrier call will force NDRange execution; if single work-item semantics are desired a mem_fence may be more efficient
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
__attribute__ ((reqd_work_group_size(1,1,1)))
void __kernel error_barrier_no_id_work_group_size(__global int * foo, int size) {
// CHECK-MESSAGES-OLDCLNEWAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id_work_group_size' does not call an ID function and may be a viable single work-item, but will be forced to execute as an NDRange [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-OLDCLNEWAOC: :[[@LINE-1]]:3: note: barrier call will force NDRange execution; if single work-item semantics are desired a mem_fence may be more efficient
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
__attribute__ ((reqd_work_group_size(2,1,1)))
void __kernel success_barrier_no_id_work_group_size(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void __kernel success_barrier_global_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void __kernel success_barrier_local_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void __kernel success_barrier_both_ids(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
void success_nokernel_barrier_no_id(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void success_nokernel_barrier_global_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void success_nokernel_barrier_local_id(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void success_nokernel_barrier_both_ids(__global int * foo, int size) {
barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
#endif
#ifdef NEWCLNEWAOC // OpenCL 2.0 Altera Offline Compiler >= 17.1
void __kernel error_barrier_no_id(__global int * foo, int size) {
// CHECK-MESSAGES-NEWCLNEWAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id' does not call an ID function and may be a viable single work-item, but will be forced to execute as an NDRange [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-NEWCLNEWAOC: :[[@LINE-1]]:3: note: barrier call will force NDRange execution; if single work-item semantics are desired a mem_fence may be more efficient
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
__attribute__ ((reqd_work_group_size(1,1,1)))
void __kernel error_barrier_no_id_work_group_size(__global int * foo, int size) {
// CHECK-MESSAGES-NEWCLNEWAOC: :[[@LINE-1]]:15: warning: kernel function 'error_barrier_no_id_work_group_size' does not call an ID function and may be a viable single work-item, but will be forced to execute as an NDRange [altera-single-work-item-barrier]
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
// CHECK-MESSAGES-NEWCLNEWAOC: :[[@LINE-1]]:3: note: barrier call will force NDRange execution; if single work-item semantics are desired a mem_fence may be more efficient
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
__attribute__ ((reqd_work_group_size(2,1,1)))
void __kernel success_barrier_no_id_work_group_size(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void __kernel success_barrier_global_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void __kernel success_barrier_local_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void __kernel success_barrier_both_ids(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
void success_nokernel_barrier_no_id(__global int * foo, int size) {
for (int j = 0; j < 256; j++) {
for (int i = 256; i < size; i+= 256) {
foo[j] += foo[j+i];
}
}
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
for (int i = 1; i < 256; i++) {
foo[0] += foo[i];
}
}
void success_nokernel_barrier_global_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_global_id(0);
}
void success_nokernel_barrier_local_id(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int tid = get_local_id(0);
}
void success_nokernel_barrier_both_ids(__global int * foo, int size) {
work_group_barrier(CLK_GLOBAL_MEM_FENCE);
int gid = get_global_id(0);
int lid = get_local_id(0);
}
#endif
|
