forked from apache/tvm
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathautotvm_tuning_log_rtx2070.json
300 lines (300 loc) · 197 KB
/
autotvm_tuning_log_rtx2070.json
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
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 3, 416, 416], "float32"], ["TENSOR", [32, 3, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 148370, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 169, 1]], ["tile_rc", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033546979017857147], 0, 2.3427727222442627, 1632429439.4684522], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 416, 416], "float32"], ["TENSOR", [32, 3, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 51245866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 52, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.586410739324411e-05], 0, 2.079979658126831, 1632433719.4716039], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 416, 416], "float32"], ["TENSOR", [64, 32, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 188078037, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00033817767467248915], 0, 1.7674791812896729, 1632435510.984524], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 208, 208], "float32"], ["TENSOR", [32, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40878352, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 13, 16, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.918742086563308e-05], 0, 1.5390434265136719, 1632438669.36732], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 208, 208], "float32"], ["TENSOR", [64, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 504647, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 4, 26, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002490648737166325], 0, 2.7090048789978027, 1632441109.0789561], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 208, 208], "float32"], ["TENSOR", [64, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 110700889, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00027604877972027975], 0, 1.4509353637695312, 1632443509.4313226], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 208, 208], "float32"], ["TENSOR", [128, 64, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37814602, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 13, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00036827713106796114], 0, 1.5102975368499756, 1632446228.7612183], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 104, 104], "float32"], ["TENSOR", [64, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10342797, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 13, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.834998882235529e-05], 0, 1.8878300189971924, 1632447514.8968277], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 104, 104], "float32"], ["TENSOR", [128, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 219108, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 2, 26, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016001715859323157], 0, 2.709181785583496, 1632449276.4336927], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 104, 104], "float32"], ["TENSOR", [128, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 125370743, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 13, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002845219312267658], 0, 2.1770570278167725, 1632451420.5162296], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 104, 104], "float32"], ["TENSOR", [256, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 23715482, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 2, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00041209763220338984], 0, 1.8744757175445557, 1632453050.784338], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 52, 52], "float32"], ["TENSOR", [512, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11738406, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005017961037344399], 0, 2.42246150970459, 1632456036.5287898], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 26, 26], "float32"], ["TENSOR", [1024, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 874699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0016966413820224716], 0, 1.4253714084625244, 1632458680.617533], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1024, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 155780, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 8]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019053876682316117], 0, 2.606387138366699, 1632460914.6867602], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1024, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1064306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004394503618581907], 0, 2.2109992504119873, 1632463259.5314658], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 13, 13], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 128933, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011231993898462972], 0, 1.474869728088379, 1632465553.2298803], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91106, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.7455740480691336e-05], 0, 1.3114264011383057, 1632466859.058276], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 768, 26, 26], "float32"], ["TENSOR", [256, 768, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2597952, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 26, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010452608318890815], 0, 1.565556526184082, 1632468661.3040261], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 26, 26], "float32"], ["TENSOR", [512, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 89062, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 16]], ["tile_x", "sp", [-1, 13, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017492704410701374], 0, 1.8219976425170898, 1632470552.0692384], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 26, 26], "float32"], ["TENSOR", [512, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5727520, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003565263929618768], 0, 1.8599531650543213, 1632473256.2646317], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 26, 26], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190272, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 26, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.783933679753657e-05], 0, 1.3075809478759766, 1632475216.003456], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 26, 26], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1213611, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 26, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.2453610730700685e-05], 0, 1.5335736274719238, 1632477303.1857183], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 52, 52], "float32"], ["TENSOR", [128, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4171976, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 13, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.987621796565389e-05], 0, 1.6942822933197021, 1632479741.4671252], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 52, 52], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9340944, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 26, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.7029334362384235e-05], 0, 1.6811740398406982, 1632481570.6315558], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 52, 52], "float32"], ["TENSOR", [256, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 334268, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 16]], ["tile_x", "sp", [-1, 2, 26, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002012208820375335], 0, 1.5250828266143799, 1632483534.421666], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 52, 52], "float32"], ["TENSOR", [256, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40888749, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029238259344894026], 0, 1.504715919494629, 1632486079.7368813], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 52, 52], "float32"], ["TENSOR", [75, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1945631, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 5, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 26, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.432540938481434e-05], 0, 1.6988091468811035, 1632487609.2994788], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [8, 64, 32], "float32"], ["TENSOR", [8, 64, 32], "float32"], [8, 64, 64]], {}], "config": {"index": 17384, "code_hash": null, "entity": [["tile_y", "sp", [-1, 4, 16]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 64], ["unroll_explicit", "ot", 0]]}, "result": [[2.783180371489391e-06], 0, 1.0794024467468262, 1632088658.108074], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [8, 64, 64], "float32"], ["TENSOR", [8, 32, 64], "float32"], [8, 64, 32]], {}], "config": {"index": 10716, "code_hash": null, "entity": [["tile_y", "sp", [-1, 4, 8]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 32], ["unroll_explicit", "ot", 0]]}, "result": [[3.37969950612436e-06], 0, 1.2455573081970215, 1632089466.9850802], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [1, 64, 256], "float32"], ["TENSOR", [1, 256, 256], "float32"], [1, 64, 256]], {}], "config": {"index": 73212, "code_hash": null, "entity": [["tile_y", "sp", [-1, 4, 8]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 32], ["unroll_explicit", "ot", 1]]}, "result": [[9.29284456433774e-06], 0, 1.1171596050262451, 1632090453.1937106], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [1, 64, 256], "float32"], ["TENSOR", [1, 1024, 256], "float32"], [1, 64, 1024]], {}], "config": {"index": 40794, "code_hash": null, "entity": [["tile_y", "sp", [-1, 2, 32]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 32], ["unroll_explicit", "ot", 0]]}, "result": [[1.9765897431634944e-05], 0, 1.4177889823913574, 1632091410.4895928], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [1, 64, 1024], "float32"], ["TENSOR", [1, 256, 1024], "float32"], [1, 64, 256]], {}], "config": {"index": 74472, "code_hash": null, "entity": [["tile_y", "sp", [-1, 4, 8]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 16], ["unroll_explicit", "ot", 1]]}, "result": [[3.242074472942124e-05], 0, 1.3561878204345703, 1632092399.617349], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [1, 100], "float32"], ["TENSOR", [524288, 100], "float32"], null, "float32"], {}], "config": {"index": 8, "code_hash": null, "entity": [["tile_k", "sp", [-1, 100]]]}, "result": [[0.001399944503816794], 0, 4.2454869747161865, 1630381973.0022857], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 128, 128], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 665027, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 2, 32, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000325942644295302], 0, 2.881211996078491, 1630384092.5707579], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 128, 128], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 154634935, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 16, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008145022783505155], 0, 1.5179941654205322, 1630388064.8182902], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 256, 256], "float32"], ["TENSOR", [64, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1043947, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 2, 32, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008194067554347827], 0, 2.7670726776123047, 1630389800.3414388], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 256, 256], "float32"], ["TENSOR", [64, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 424092080, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 16, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014849934603174601], 0, 3.080049753189087, 1630394736.0459573], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 256, 256], "float32"], ["TENSOR", [3, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 2, 128, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00027143553971119137], 0, 2.4479589462280273, 1630396625.74783], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 256, 256], "float32"], ["TENSOR", [3, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14511747, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 128, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.353992244224421e-05], 0, 1.3810644149780273, 1630399650.3503356], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 256, 256], "float32"], ["TENSOR", [16, 3, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18286804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 64, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.1317437153117864e-06], 0, 1.6320087909698486, 1630401545.6915767], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 128, 128], "float32"], ["TENSOR", [32, 16, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 36070306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 4, 16, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.742233898930284e-05], 0, 1.650618553161621, 1630403155.5529196], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 64, 64], "float32"], ["TENSOR", [64, 32, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37303285, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.856747260380893e-05], 0, 2.6317121982574463, 1630407301.2598958], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 32, 32], "float32"], ["TENSOR", [128, 64, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24316103, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.2067846960556844e-05], 0, 2.847842216491699, 1630411294.2760916], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [1, 32768], "float32"], ["TENSOR", [1, 32768], "float32"], null, "float32"], {}], "config": {"index": 9, "code_hash": null, "entity": [["tile_k", "sp", [-1, 512]]]}, "result": [[5.932951040975998e-06], 0, 1.4032998085021973, 1630411986.7388344], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1, 1], "float32"], [2, 2, 2], 0, [1, 1, 1], "float32"], {}], "config": {"index": 341185, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014959082403965304], 0, 1.696054458618164, 1629904338.576391], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1, 1], "float32"], [2, 2, 2], 0, [1, 1, 1], "float32"], {}], "config": {"index": 247783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010740311775200713], 0, 1.5410511493682861, 1629905817.7427337], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1, 1], "float32"], [2, 2, 2], 0, [1, 1, 1], "float32"], {}], "config": {"index": 66780637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015201736712846349], 0, 2.096114158630371, 1629908619.1053758], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 22283664, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_d", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.5125651016558374e-05], 0, 1.519996166229248, 1629910630.8086412], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 103972137, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.448673288439955e-05], 0, 1.3197848796844482, 1629911908.083578], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 153652, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003480994818181818], 0, 7.442970514297485, 1629914058.1230211], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 708090560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_d", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00036126909566517186], 0, 2.650742530822754, 1629916859.942879], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 73306268, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.360738873994639e-05], 0, 1.2506804466247559, 1629919117.754251], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 65587736, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015446326680040122], 0, 1.2949671745300293, 1629920604.0274003], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 3, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [2, 2, 2], 1, [1, 1, 1], "float32"], {}], "config": {"index": 141776602, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_d", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004265269346289753], 0, 1.8199989795684814, 1629922365.2799358], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 41206616, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.554593471810089e-05], 0, 1.464430332183838, 1629923935.4448922], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 531504, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003483495046082949], 0, 2.475862979888916, 1629925190.604861], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 290049986, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002850636340023613], 0, 2.175903558731079, 1629927083.5056322], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 13273121, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.7472892729439805e-05], 0, 1.5273528099060059, 1629929226.8975885], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 57492627, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010400672641102972], 0, 2.019521951675415, 1629932220.9356678], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 2, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [2, 2, 2], 1, [1, 1, 1], "float32"], {}], "config": {"index": 17594970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004157794293103449], 0, 1.977301836013794, 1629934405.5538595], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 190277, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.141431440936864e-05], 0, 1.4005000591278076, 1629937286.1146924], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 81543, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00025888499312714776], 0, 2.3626890182495117, 1629939144.338135], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 8478414, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002869355219976219], 0, 1.7490770816802979, 1629942104.6037595], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 2892637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.406571648602396e-05], 0, 1.6814355850219727, 1629944014.7774563], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 2056149, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.298626924564797e-05], 0, 1.5123159885406494, 1629946574.4567826], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [2, 2, 2], 1, [1, 1, 1], "float32"], {}], "config": {"index": 1629354, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005796564131274131], 0, 1.9722459316253662, 1629948966.8965082], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 2048, 1, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 227288, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010319489069171648], 0, 1.491898775100708, 1629950717.138206], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 41603, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033830453284671536], 0, 2.742422580718994, 1629952988.662675], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], 1, [1, 1, 1], "float32"], {}], "config": {"index": 1632207, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00041780619064124786], 0, 2.203556776046753, 1629958342.0494118], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1, 1], "float32"], [1, 1, 1], 0, [1, 1, 1], "float32"], {}], "config": {"index": 137337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.2512049148099607e-05], 0, 1.454338550567627, 1629959366.846142], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 1024, 1, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 282887, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 64, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006893117948717949], 0, 2.1110661029815674, 1628163458.2959661], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 2, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 765246, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005890994233333334], 0, 2.3599789142608643, 1628165276.2501752], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 3, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 65350711, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 8]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001089819204819277], 0, 4.2303173542022705, 1628171538.5337417], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 62956729, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016586156330472104], 0, 1.738983154296875, 1628176381.183947], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 3, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 84618513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005448989197707737], 0, 3.207576036453247, 1628179628.8568957], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [8, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 147734, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 7, 16, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0225236618], 0, 10.776888608932495, 1628182826.3356073], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 708090560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_d", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024479823015873016], 0, 3.36167049407959, 1628186591.2029924], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 64, 3, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 153236134, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_d", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006170819136904763], 0, 3.1380715370178223, 1628189171.9368382], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 3, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 120883376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010504613913043478], 0, 4.497891426086426, 1628192862.6946862], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 128, 3, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 288985058, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024285089484536084], 0, 4.331590890884399, 1628198882.8094382], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 2, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 41799869, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003518672121212121], 0, 2.3126463890075684, 1628202431.3765056], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [8, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 2495789, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 7, 16, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.002310015975609756], 0, 2.4003608226776123, 1628205174.9570374], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 289445214, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0017821212574257426], 0, 2.435265302658081, 1628208842.1812413], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 128, 2, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 27353070, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00032955019661733614], 0, 1.8732481002807617, 1628211130.9758208], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 2, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 56418807, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006744936462882097], 0, 2.3656013011932373, 1628212975.4493206], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 2, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 8444571, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013529187387387388], 0, 1.9191310405731201, 1628216762.270795], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 1024, 1, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 2514132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020077317851239666], 0, 2.802685499191284, 1628219086.860853], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [8, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 1325973, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.001453365570093458], 0, 2.514711618423462, 1628220622.9606822], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 17561021, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010163223648648647], 0, 1.8703160285949707, 1628223404.0347831], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 256, 1, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 3552501, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017275209257142858], 0, 1.6910877227783203, 1628225413.275569], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 1024, 1, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 3352177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00033641343049327355], 0, 2.446884870529175, 1628227070.999278], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 1, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 1343142, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0022170504264705884], 0, 2.2527432441711426, 1628230724.3503578], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 2048, 1, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 223821, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003346709142461964], 0, 2.1182615756988525, 1628233154.9007354], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [8, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 118881, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 4, 16, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001274409108108108], 0, 2.9417881965637207, 1628236993.0515275], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 1094370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018749943178294575], 0, 2.403054714202881, 1628239759.06463], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [8, 512, 1, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 312713, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00027561953023255817], 0, 2.187539577484131, 1628243166.685078], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 256, 28, 28], "float32"], ["TENSOR", [256, 1, 5, 5], "float32"], [2, 2], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 200319, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[2.9601451754922343e-05], 0, 2.1863460540771484, 1628127050.6710668], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 128, 56, 56], "float32"], ["TENSOR", [128, 1, 5, 5], "float32"], [2, 2], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1079400, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.1349401143241426e-05], 0, 1.923309564590454, 1628128353.946979], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 320, 56, 56], "float32"], ["TENSOR", [64, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16982278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 5]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002582567911714771], 0, 2.3049774169921875, 1628134017.6590953], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [64, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2881116, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 2, 28, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.702445016865992e-05], 0, 2.389941692352295, 1628135377.989537], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8757407, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.15765366972477e-05], 0, 1.5950675010681152, 1628140620.1800609], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 320, 56, 56], "float32"], ["TENSOR", [128, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 56286557, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 5]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004403553114285714], 0, 2.8777287006378174, 1628143066.7308774], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 128, 56, 56], "float32"], ["TENSOR", [128, 1, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 1036560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 14, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.395786167960481e-05], 0, 2.295018196105957, 1628145196.0280995], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 640, 28, 28], "float32"], ["TENSOR", [128, 640, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7377989, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022166809972552607], 0, 2.2749128341674805, 1628147535.30626], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 128, 28, 28], "float32"], ["TENSOR", [128, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1087320, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.8978725682459995e-05], 0, 2.3193912506103516, 1628149224.6645172], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3730016, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.0972059080228264e-05], 0, 1.4493801593780518, 1628150929.0674286], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 640, 28, 28], "float32"], ["TENSOR", [256, 640, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22816728, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004391617386569873], 0, 2.8127872943878174, 1628152470.0605094], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 256, 28, 28], "float32"], ["TENSOR", [256, 1, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 242559, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.051809323421948e-05], 0, 2.685420513153076, 1628154159.457699], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1280, 14, 14], "float32"], ["TENSOR", [256, 1280, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4077012, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00025459279874213834], 0, 2.6934783458709717, 1628155669.146924], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [8, 256, 14, 14], "float32"], ["TENSOR", [256, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 192443, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[9.023589457114336e-06], 0, 1.8479394912719727, 1628157640.885188], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2091732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.20066189546736e-05], 0, 2.412555694580078, 1628158756.8253434], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 282887, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 64, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006921361054131054], 0, 2.3003246784210205, 1628072758.1050239], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3115269, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005170831407249467], 0, 2.0675415992736816, 1628074487.1437747], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [128, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23322172, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010985279668348953], 0, 1.7817587852478027, 1628084011.4199584], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30174560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00032714281799163183], 0, 2.384423017501831, 1628086656.8532884], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 128, 56, 56], "float32"], ["TENSOR", [128, 4, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 995295480, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[7.200597041984732e-05], 0, 1.9779396057128906, 1628089668.3732355], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 128, 56, 56], "float32"], ["TENSOR", [256, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37266010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003117707071713148], 0, 1.998182773590088, 1628091573.4104843], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 56, 56], "float32"], ["TENSOR", [256, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41490010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006000163117870723], 0, 2.3297810554504395, 1628093762.06509], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 256, 56, 56], "float32"], ["TENSOR", [256, 8, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 293478240, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[8.712689793577981e-05], 0, 2.067061424255371, 1628096127.962], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14104722, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00034884692219679634], 0, 1.9094195365905762, 1628098070.8940258], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 256, 28, 28], "float32"], ["TENSOR", [256, 8, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 359709000, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[5.348114582623509e-05], 0, 2.3457679748535156, 1628100733.343449], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 28, 28], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13827521, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00036279830732860517], 0, 1.903266429901123, 1628102766.487385], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 28, 28], "float32"], ["TENSOR", [512, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15292230, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006770397973568282], 0, 1.9099769592285156, 1628104662.1791315], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 512, 28, 28], "float32"], ["TENSOR", [512, 16, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 231772560, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[6.451336898395722e-05], 0, 1.8730599880218506, 1628106651.0877967], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3352177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00033934853286713286], 0, 2.4890267848968506, 1628108373.3105316], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 512, 14, 14], "float32"], ["TENSOR", [512, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 247849800, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[4.982743231865285e-05], 0, 1.5668716430664062, 1628110284.3981934], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 14, 14], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3918581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003381419381898455], 0, 1.5797171592712402, 1628111875.0313933], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1024, 14, 14], "float32"], ["TENSOR", [1024, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4284661, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006686360526315789], 0, 1.717576026916504, 1628113455.6847277], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 1024, 14, 14], "float32"], ["TENSOR", [1024, 32, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 12323884, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 2, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[6.280987860082305e-05], 0, 1.6873130798339844, 1628115380.3843055], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 2048, 7, 7], "float32"], ["TENSOR", [1024, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 296058, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005813727899761337], 0, 2.176513910293579, 1628118590.1027071], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [8, 1024, 7, 7], "float32"], ["TENSOR", [1024, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 14487007, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 4, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[5.6956668250950575e-05], 0, 2.5400891304016113, 1628120634.3147042], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1024, 7, 7], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 341105, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005417531098654708], 0, 2.520292043685913, 1628125559.878904], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13523488, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000556933864678899], 0, 2.7899837493896484, 1628010943.232412], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25422953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018115990023752967], 0, 2.2872509956359863, 1628017045.363843], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 806294, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 7, 16, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020799305060034305], 0, 3.1382997035980225, 1628021556.0696225], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27186478, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00035210238181818186], 0, 1.2604093551635742, 1628026449.9469278], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33042034, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016550786757038582], 0, 1.8148653507232666, 1628027636.2194831], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 35474002, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000479848712], 0, 2.03600811958313, 1628031917.1829486], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10453229, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017937055238095238], 0, 2.293492555618286, 1628034890.6236284], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [8, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1891057, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 7, 16, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022566900837988827], 0, 1.8688368797302246, 1628036531.824517], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17423193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00032210007203389835], 0, 1.5697014331817627, 1628040609.7701168], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12470290, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001771590905963303], 0, 1.6301791667938232, 1628042707.4093232], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7296666, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004813955466666666], 0, 1.844346284866333, 1628048156.7658014], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2514132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019953364705882352], 0, 2.5706677436828613, 1628050329.3057804], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [8, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 435044, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 4]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00018942720974076982], 0, 1.8311591148376465, 1628052150.985695], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8893866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00036274224999999997], 0, 2.1729300022125244, 1628054417.133234], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3552501, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001714600329171396], 0, 1.5059306621551514, 1628055915.223796], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 252382, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006988947861271676], 0, 1.820629358291626, 1628060058.6754725], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 223770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00033416756449375866], 0, 1.9133450984954834, 1628061871.1778169], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [8, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 382759, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 16]], ["tile_x", "sp", [-1, 2, 16, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020110397333333334], 0, 1.8599557876586914, 1628063708.8853939], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 677250, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006125275265306122], 0, 1.669938325881958, 1628066491.4210167], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [8, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 312713, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00027675146400000004], 0, 2.5085055828094482, 1628068792.9079819], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 32, 224, 224], "float32"], ["TENSOR", [32, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12501104, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 1, 16, 2]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[4.181091725628931e-05], 0, 1.7385523319244385, 1627940298.1713114], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 224, 224], "float32"], ["TENSOR", [16, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25025310, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 32, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.5164189638932495e-05], 0, 1.8780136108398438, 1627943235.86503], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 224, 224], "float32"], ["TENSOR", [96, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160262354, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 56, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.764955657395701e-05], 0, 2.053588390350342, 1627947206.124051], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 96, 224, 224], "float32"], ["TENSOR", [96, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24293472, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 56, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.357640676632573e-05], 0, 2.2565062046051025, 1627949472.1736727], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 96, 112, 112], "float32"], ["TENSOR", [24, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 100767992, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 6]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.3522398670582776e-05], 0, 2.283958911895752, 1627952437.2079084], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 144, 112, 112], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31006150, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 1, 28, 2]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[3.8595344478379685e-05], 0, 1.9066569805145264, 1627954844.121624], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 144, 112, 112], "float32"], ["TENSOR", [24, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99535995, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 8]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 8, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.5518592306571467e-05], 0, 1.6730332374572754, 1627957476.8235772], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 24, 112, 112], "float32"], ["TENSOR", [144, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 132349176, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 4, 28, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.7240995933521925e-05], 0, 1.4264845848083496, 1627960372.8392534], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 144, 112, 112], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12007450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 2, 28, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.5918418997668997e-05], 0, 1.854379415512085, 1627961861.2917902], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 144, 56, 56], "float32"], ["TENSOR", [32, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13471842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.3523714525171954e-05], 0, 1.717620849609375, 1627965414.2157428], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 192, 56, 56], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12026784, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 1, 28, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3691917519218542e-05], 0, 2.1321523189544678, 1627966933.7642572], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 192, 56, 56], "float32"], ["TENSOR", [32, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11290883, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.857162593065305e-05], 0, 1.2802355289459229, 1627969472.8217945], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 56, 56], "float32"], ["TENSOR", [192, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69565903, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3984663593116816e-05], 0, 2.0406546592712402, 1627971089.0871634], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 192, 56, 56], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2926560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.9940534303207915e-06], 0, 1.54085111618042, 1627972523.5203636], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 192, 28, 28], "float32"], ["TENSOR", [64, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4895650, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.2998790406847486e-05], 0, 1.7353224754333496, 1627974939.9426804], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 28, 28], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5195125, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.391642351758794e-05], 0, 1.5475871562957764, 1627977333.141633], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 28, 28], "float32"], ["TENSOR", [384, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7239669, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 6]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.462544704802692e-05], 0, 1.4819557666778564, 1627978766.6317189], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 384, 28, 28], "float32"], ["TENSOR", [384, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4354560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.704299397976175e-06], 0, 1.8865923881530762, 1627980095.4395413], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 28, 28], "float32"], ["TENSOR", [96, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25957468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 3]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.915832251372788e-05], 0, 1.5941276550292969, 1627982346.544235], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 576, 28, 28], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7620480, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.538250928432051e-06], 0, 1.9770903587341309, 1627983654.0111094], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 576, 28, 28], "float32"], ["TENSOR", [96, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25325045, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.2666864984899626e-05], 0, 1.5770540237426758, 1627985831.527787], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 96, 28, 28], "float32"], ["TENSOR", [576, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19412960, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.392474808853119e-05], 0, 1.529926061630249, 1627988170.7023299], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 576, 28, 28], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1009719, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[6.027860446300405e-06], 0, 1.6109349727630615, 1627990006.6840668], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 576, 14, 14], "float32"], ["TENSOR", [160, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6749698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 36]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.460694197492488e-05], 0, 1.6769459247589111, 1627992713.7414572], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 960, 14, 14], "float32"], ["TENSOR", [160, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 671197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 20]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.791267582653499e-05], 0, 1.3421189785003662, 1627994445.968594], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 160, 14, 14], "float32"], ["TENSOR", [960, 160, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6037400, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 15, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 10]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.3518340735668167e-05], 0, 1.52420973777771, 1627996193.452864], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 960, 14, 14], "float32"], ["TENSOR", [960, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1567132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[5.098837165423431e-06], 0, 1.4617102146148682, 1627997545.0918057], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 960, 14, 14], "float32"], ["TENSOR", [320, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12705016, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 10]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.439633109739737e-05], 0, 1.5787391662597656, 1627999105.7856555], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 320, 14, 14], "float32"], ["TENSOR", [1280, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10225440, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 8, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.0628206599713056e-05], 0, 1.503528118133545, 1628000824.8320234], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 341913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014953023368551897], 0, 1.787668228149414, 1626832855.2365348], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 1724048, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001134384493163602], 0, 1.605334758758545, 1626834506.3055696], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1, 1], "float32"], [2, 2, 2], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 54093727, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015127483145363407], 0, 2.105794668197632, 1626836416.5795271], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 37336632, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_d", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.5136793307920373e-05], 0, 1.8463356494903564, 1626841497.583926], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 80831255, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.294127469135802e-05], 0, 1.3222432136535645, 1626845209.9623892], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 330052, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0034816464318181816], 0, 8.696326971054077, 1626847672.2059176], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 633481442, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_d", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004307424927536232], 0, 2.110707998275757, 1626852095.2439368], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 64, 3, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 73306268, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.397683180592993e-05], 0, 1.5550029277801514, 1626856499.3769267], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 3, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 65601656, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000154254394], 0, 1.2664210796356201, 1626858167.1636937], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 3, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 184903282, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004752423948051948], 0, 1.5036439895629883, 1626862445.3746288], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 10491864, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.111977737665463e-05], 0, 1.5816471576690674, 1626867207.958178], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 531577, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003482937615740741], 0, 3.1912665367126465, 1626868412.792674], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 259062387, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_d", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003255131511470985], 0, 1.9981577396392822, 1626870090.4292524], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 128, 2, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 61145121, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.825008492106696e-05], 0, 1.5743095874786377, 1626872985.4592493], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 2, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 57492627, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010453124408092983], 0, 2.1381113529205322, 1626875486.4924114], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 2, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 11806344, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_rd", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004342382679856115], 0, 1.6503088474273682, 1626877692.1350675], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 2517272, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.994674025974026e-05], 0, 1.5024995803833008, 1626880631.3956492], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 81543, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00025805517636986303], 0, 2.543740749359131, 1626881800.8157003], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 17604870, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002677635133037694], 0, 2.0445008277893066, 1626883939.3515148], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 256, 1, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 2892637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.402200099234477e-05], 0, 1.677037239074707, 1626886304.4230554], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 1024, 1, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 197589, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.280987576687117e-05], 0, 1.5181360244750977, 1626888684.8378432], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [2, 2, 2], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 1629354, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005814991397590362], 0, 2.2836945056915283, 1626891049.9751377], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 2048, 1, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 226628, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010316207859888937], 0, 1.5652241706848145, 1626893510.688465], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw_winograd.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 272603, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00033740110986547086], 0, 2.5604734420776367, 1626895702.7466156], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3, 3], "float32"], [1, 1, 1], [1, 1, 1, 1, 1, 1], [1, 1, 1], "float32"], {}], "config": {"index": 1350607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00041811056944444436], 0, 1.7134041786193848, 1626898811.7213461], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv3d_ncdhw.cuda", [["TENSOR", [1, 512, 1, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1, 1], "float32"], [1, 1, 1], [0, 0, 0, 0, 0, 0], [1, 1, 1], "float32"], {}], "config": {"index": 312057, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_d", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_rd", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.254589134720701e-05], 0, 1.547623634338379, 1626900637.2630572], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 32, 56, 56], "float32"], ["TENSOR", [32, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1996120, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.2988153993814652e-06], 0, 1.4635841846466064, 1626769578.7176864], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 56, 56], "float32"], ["TENSOR", [16, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3043913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.1950177777777777e-06], 0, 1.431422233581543, 1626772425.6111925], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 56, 56], "float32"], ["TENSOR", [96, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39227276, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 6]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.27457666989123e-06], 0, 1.7020528316497803, 1626774474.1420712], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 96, 56, 56], "float32"], ["TENSOR", [96, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1592640, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[3.858718777779715e-06], 0, 1.7286641597747803, 1626777204.2141488], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 96, 28, 28], "float32"], ["TENSOR", [24, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8147226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.973299846845985e-06], 0, 1.6392226219177246, 1626779520.4976938], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 144, 28, 28], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3171000, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.215656639168716e-06], 0, 1.387709379196167, 1626780685.18513], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 144, 28, 28], "float32"], ["TENSOR", [24, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10323257, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.967557862258953e-06], 0, 2.1486542224884033, 1626782049.1546593], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 24, 28, 28], "float32"], ["TENSOR", [144, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7524591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 9]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.574770866902997e-06], 0, 1.3514630794525146, 1626784041.2545114], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 144, 28, 28], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 497350, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.7705479902979906e-06], 0, 1.2624905109405518, 1626785336.1245892], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 144, 14, 14], "float32"], ["TENSOR", [32, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 293921, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.6683135837687107e-06], 0, 1.3844048976898193, 1626787258.416458], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 192, 14, 14], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 61824, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.5817201403341854e-06], 0, 1.3784854412078857, 1626788796.6677954], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 192, 14, 14], "float32"], ["TENSOR", [32, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 308240, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.529490981841817e-06], 0, 1.706373691558838, 1626790313.6527674], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 14, 14], "float32"], ["TENSOR", [192, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2451958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 3]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.840961273861274e-06], 0, 1.2444682121276855, 1626791894.1337864], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 192, 14, 14], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29904, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.3266597366202638e-06], 0, 1.3522324562072754, 1626793204.2636414], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 192, 7, 7], "float32"], ["TENSOR", [64, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26227, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.228003258099745e-06], 0, 1.3961050510406494, 1626794499.5188577], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 7, 7], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50419, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.255943779265265e-06], 0, 1.6180460453033447, 1626795832.0919855], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 7, 7], "float32"], ["TENSOR", [384, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143248, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 3]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.5480000772618402e-06], 0, 1.4126369953155518, 1626796996.4956167], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 384, 7, 7], "float32"], ["TENSOR", [384, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27840, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.29731376370029e-06], 0, 1.3405001163482666, 1626798180.6457932], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 7, 7], "float32"], ["TENSOR", [96, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 317284, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.27706182208272e-06], 0, 2.0071144104003906, 1626799349.664607], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 576, 7, 7], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 35372, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 9, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.4316008144427856e-06], 0, 1.1799194812774658, 1626800779.530363], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 576, 7, 7], "float32"], ["TENSOR", [96, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 412708, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3150418514350028e-05], 0, 2.721120595932007, 1626802109.0108218], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 96, 7, 7], "float32"], ["TENSOR", [576, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 438536, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.579141346935758e-06], 0, 1.63499116897583, 1626803278.820766], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 576, 7, 7], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 214292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 9, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.4418611528688686e-06], 0, 1.3576724529266357, 1626804782.4302623], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 576, 4, 4], "float32"], ["TENSOR", [160, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2595082, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 10, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.215395161731706e-06], 0, 2.7732348442077637, 1626806037.3934283], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 960, 4, 4], "float32"], ["TENSOR", [160, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1557950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 5, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 30]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.0170223266180133e-05], 0, 1.9033658504486084, 1626807802.0254574], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 160, 4, 4], "float32"], ["TENSOR", [960, 160, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8945023, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 5]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.194692272053373e-06], 0, 1.922018051147461, 1626809246.167473], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 960, 4, 4], "float32"], ["TENSOR", [960, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 518999, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 60, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.251736003281282e-06], 0, 1.476783275604248, 1626811876.7634873], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 960, 4, 4], "float32"], ["TENSOR", [320, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5260131, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 10, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3587023351251372e-05], 0, 2.318250894546509, 1626813855.6222765], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 320, 4, 4], "float32"], ["TENSOR", [1280, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4940188, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 20, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.1099461440075793e-05], 0, 2.6038742065429688, 1626815433.207924], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [1, 2560], "float32"], ["TENSOR", [2560, 2560], "float32"], null, "float32"], {}], "config": {"index": 14, "code_hash": null, "entity": [["tile_k", "sp", [-1, 256]]]}, "result": [[6.374009691861996e-05], 0, 2.0768020153045654, 1626541706.3913715], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 1, 5, 5], "float32"], [2, 2], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 200310, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[4.185833797679955e-06], 0, 1.6284289360046387, 1626515908.8952615], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 1, 5, 5], "float32"], [2, 2], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1045920, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 28, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.73234189808369e-06], 0, 1.661818265914917, 1626517135.0601795], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 320, 56, 56], "float32"], ["TENSOR", [64, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40052484, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.61615570688663e-05], 0, 1.7532734870910645, 1626521257.6505392], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3008040, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 1, 28, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.999880474981871e-06], 0, 1.9575583934783936, 1626522787.6370182], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 320, 56, 56], "float32"], ["TENSOR", [128, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12501056, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[8.329234164934165e-05], 0, 1.78248929977417, 1626525944.8992922], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 1, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 1042200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.4819309964664305e-06], 0, 3.8896474838256836, 1626527300.4217412], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 640, 28, 28], "float32"], ["TENSOR", [128, 640, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16831019, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 20]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.453021875706215e-05], 0, 1.9410977363586426, 1626529335.4193904], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1089120, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 14, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.1647180117820322e-06], 0, 1.5100455284118652, 1626530594.9945421], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3921748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.2348334075133789e-05], 0, 1.801476001739502, 1626531725.3135374], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 640, 28, 28], "float32"], ["TENSOR", [256, 640, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22552630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 10]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.308724976481656e-05], 0, 1.7175872325897217, 1626533155.0180519], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 1, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 234804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 14, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.639461627296589e-06], 0, 2.0238490104675293, 1626534389.637833], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1280, 14, 14], "float32"], ["TENSOR", [256, 1280, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 241291, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 10]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.032929543378995e-05], 0, 1.4633431434631348, 1626536337.984998], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "depthwise_conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30360, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.8078965810400753e-06], 0, 1.3973054885864258, 1626537853.1437416], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 950597, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.7479116116704637e-05], 0, 1.691641092300415, 1626540606.016297], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 277121, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015003344237918216], 0, 1.7113430500030518, 1626470809.226165], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 250643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010702850419796729], 0, 1.5186004638671875, 1626472148.397674], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4368803, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.884162741882585e-05], 0, 1.5464751720428467, 1626473703.1424558], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41540968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.9191687721009632e-05], 0, 2.131074905395508, 1626475636.8272593], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [128, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14096429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.758993912165573e-05], 0, 1.4738445281982422, 1626478044.7523654], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17168429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.095913381245722e-05], 0, 1.447305679321289, 1626479859.5575686], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 4, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 25486722, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[1.0193841863041719e-05], 0, 2.0286900997161865, 1626484440.8144681], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [256, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46820968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.22145414040426e-05], 0, 2.1269748210906982, 1626486053.71937], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [256, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23588968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.72684414595028e-05], 0, 1.8680100440979004, 1626487456.393536], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [256, 8, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 33108954, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[1.1969048984951015e-05], 0, 1.5389044284820557, 1626490797.8339887], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14355527, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.817245349817365e-05], 0, 1.8578715324401855, 1626492075.3375762], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 8, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 35602068, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[8.852757536688029e-06], 0, 2.025989294052124, 1626494064.0409105], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13878290, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.3827988789237674e-05], 0, 1.9264540672302246, 1626495443.7654123], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [512, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18812281, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001034334256440281], 0, 1.6937673091888428, 1626497207.6904433], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [512, 16, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 12770700, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[1.1065141940085594e-05], 0, 2.445007562637329, 1626500233.3787591], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2675669, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.355944224806203e-05], 0, 1.7359504699707031, 1626502512.1678226], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 6158814, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[9.204861383486041e-06], 0, 2.2560760974884033, 1626504351.0298436], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3188361, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.513420064987815e-05], 0, 1.6758694648742676, 1626505765.1059318], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [1024, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1122876, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012990500107238606], 0, 1.6851868629455566, 1626507134.8757927], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [1024, 32, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 761250, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 0]]}, "result": [[1.2891169910138375e-05], 0, 2.323153018951416, 1626508515.49547], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [1024, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 240565, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014893021052631578], 0, 1.6161813735961914, 1626509985.4288378], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "group_conv2d_nchw.cuda", [["TENSOR", [1, 1024, 7, 7], "float32"], ["TENSOR", [1024, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], 32, "float32"], {}], "config": {"index": 1535394, "code_hash": null, "entity": [["tile_n", "sp", [-1, 1, 1, 1]], ["tile_g", "sp", [-1, 1]], ["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1], ["fuse_yx", "ot", 1]]}, "result": [[1.1638886808342001e-05], 0, 2.2955946922302246, 1626512199.1697915], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 7, 7], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 277113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010217582265591854], 0, 1.59462308883667, 1626513430.9190736], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21282933, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.0667666997088161e-05], 0, 2.304572820663452, 1626423186.1960783], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21688065, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.918416490141763e-05], 0, 1.9900825023651123, 1626424502.5042849], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 153709, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.886236608747753e-05], 0, 2.898927688598633, 1626427867.8366039], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88348115, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.3229421238938047e-05], 0, 2.172410488128662, 1626431478.2044954], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 35791042, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.251772866437045e-05], 0, 1.8278632164001465, 1626438709.7184913], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8574988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.345916648609606e-05], 0, 1.6367971897125244, 1626440166.1230688], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 531577, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.33340865157617e-05], 0, 2.1094250679016113, 1626441346.4326804], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 36073494, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.836500925024343e-05], 0, 2.1619486808776855, 1626443302.382549], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15286341, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.9336621889937494e-05], 0, 1.7637946605682373, 1626444767.0494523], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5808237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013009333747300217], 0, 1.6126878261566162, 1626449033.3008475], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2031512, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.953482186234817e-05], 0, 1.308272361755371, 1626451405.6601372], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 81637, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 8]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.954135932872655e-05], 0, 2.2542731761932373, 1626453219.4659343], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8893530, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.7693830968788e-05], 0, 1.7623140811920166, 1626454598.0289173], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2892637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.3902250986471246e-05], 0, 1.7497470378875732, 1626456330.4298964], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 818861, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002352915395121951], 0, 1.6793508529663086, 1626460457.7294967], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 185488, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010280520366425224], 0, 1.5904998779296875, 1626461876.1348674], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 191526, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 4, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.468694095133952e-05], 0, 1.738861083984375, 1626463568.490281], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 650794, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013172079989065062], 0, 1.9174439907073975, 1626466206.5889864], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 137337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.251552310050361e-05], 0, 1.5863463878631592, 1626468387.2163699], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_large_batch.cuda", [["TENSOR", [64, 1024], "float32"], ["TENSOR", [1024, 1024], "float32"], null, "float32"], {}], "config": {"index": 98127, "code_hash": null, "entity": [["tile_x", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_k", "sp", [-1, 16, 1]]]}, "result": [[0.00012765536826992102], 0, 2.0645174980163574, 1626409412.808597], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [64, 1024], "float32"], ["TENSOR", [1024, 1024], "float32"], null, "float32"], {}], "config": {"index": 5, "code_hash": null, "entity": [["tile_k", "sp", [-1, 32]]]}, "result": [[0.00022610721893491127], 0, 1.111785888671875, 1626410444.289534], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "batch_matmul.cuda", [["TENSOR", [16, 64, 64], "float32"], ["TENSOR", [16, 64, 64], "float32"], [16, 64, 64]], {}], "config": {"index": 19738, "code_hash": null, "entity": [["tile_y", "sp", [-1, 2, 32]], ["tile_x", "sp", [-1, 16, 1]], ["tile_k", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 64], ["unroll_explicit", "ot", 0]]}, "result": [[6.213022904966413e-06], 0, 1.3175175189971924, 1626411851.9340317], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_large_batch.cuda", [["TENSOR", [64, 1024], "float32"], ["TENSOR", [4096, 1024], "float32"], null, "float32"], {}], "config": {"index": 169024, "code_hash": null, "entity": [["tile_x", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_k", "sp", [-1, 16, 1]]]}, "result": [[0.00033621668384401117], 0, 3.9509007930755615, 1626413201.618479], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [64, 1024], "float32"], ["TENSOR", [4096, 1024], "float32"], null, "float32"], {}], "config": {"index": 8, "code_hash": null, "entity": [["tile_k", "sp", [-1, 256]]]}, "result": [[0.0025300651500000004], 0, 1.356475591659546, 1626414498.8889778], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_large_batch.cuda", [["TENSOR", [64, 4096], "float32"], ["TENSOR", [1024, 4096], "float32"], null, "float32"], {}], "config": {"index": 890919, "code_hash": null, "entity": [["tile_x", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_k", "sp", [-1, 2, 8]]]}, "result": [[0.0005015763954802259], 0, 1.7085902690887451, 1626415376.437182], "version": 0.2, "tvm_version": "0.8.dev0"}
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "dense_small_batch.cuda", [["TENSOR", [64, 4096], "float32"], ["TENSOR", [1024, 4096], "float32"], null, "float32"], {}], "config": {"index": 7, "code_hash": null, "entity": [["tile_k", "sp", [-1, 128]]]}, "result": [[0.0025229632], 0, 1.4627528190612793, 1626416502.9665256], "version": 0.2, "tvm_version": "0.8.dev0"}