-
Notifications
You must be signed in to change notification settings - Fork 6
/
Copy pathcenterFace.log
38 lines (38 loc) · 24.4 KB
/
centerFace.log
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
{"input": ["cuda -keys=cuda,gpu -max_num_threads=1024 -model=unknown -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 24, 136, 240], "float32"], ["TENSOR", [10, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25248037, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 2, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 48, 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": [[1.3047658103842386e-05], 0, 1.9858591556549072, 1619090128.935762], "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, 136, 240], "float32"], ["TENSOR", [2, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2219234, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 24, 2]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.23930505952381e-06], 0, 1.7263374328613281, 1619092658.9029145], "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, 68, 120], "float32"], ["TENSOR", [24, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27921461, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 40, 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": [[4.7296050062781e-06], 0, 2.2241098880767822, 1619095332.8846343], "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, 34, 60], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 948360, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 17, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[2.0905719486823856e-05], 0, 2.2631871700286865, 1619098463.924833], "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, 17, 30], "float32"], ["TENSOR", [160, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 711573, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 1]], ["tile_rc", "sp", [-1, 36]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.9829222786238014e-05], 0, 1.4583449363708496, 1619100165.9131207], "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, 17, 30], "float32"], ["TENSOR", [160, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 711449, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.970782551440329e-05], 0, 1.896284818649292, 1619102878.6815524], "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, 17, 30], "float32"], ["TENSOR", [960, 160, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13886353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 10, 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": [[3.7704685595123516e-05], 0, 1.811694860458374, 1619108420.594372], "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, 17, 30], "float32"], ["TENSOR", [960, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1861468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 17, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3033367774013768e-05], 0, 2.0444915294647217, 1619110776.123535], "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, 17, 30], "float32"], ["TENSOR", [320, 960, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3385596, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 10, 1]], ["tile_rc", "sp", [-1, 20]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.369022767648434e-05], 0, 1.6977763175964355, 1619112759.5116324], "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, 17, 30], "float32"], ["TENSOR", [24, 320, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1667257, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 1]], ["tile_rc", "sp", [-1, 80]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.208060752228599e-06], 0, 2.851077079772949, 1619115946.4915922], "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, 136, 240], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19088300, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 30, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[6.796568025362318e-05], 0, 2.07197642326355, 1619118546.1939087], "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, 68, 120], "float32"], ["TENSOR", [32, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17389152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 30, 1]], ["tile_rc", "sp", [-1, 18]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.17696124706343e-05], 0, 1.8953983783721924, 1619121936.4061236], "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, 68, 120], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22696800, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 17]], ["tile_x", "sp", [-1, 2, 60, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.714964770474302e-05], 0, 2.3315036296844482, 1619124136.6685588], "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, 68, 120], "float32"], ["TENSOR", [32, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15236550, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 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": [[2.7704689238905496e-05], 0, 1.974773645401001, 1619126845.7770066], "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, 68, 120], "float32"], ["TENSOR", [192, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39890081, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 60, 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": [[2.7851595938001066e-05], 0, 1.755692720413208, 1619129831.6609602], "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, 68, 120], "float32"], ["TENSOR", [192, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4560192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 4, 15, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.538313814822591e-05], 0, 2.146160364151001, 1619133406.9601288], "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, 34, 60], "float32"], ["TENSOR", [64, 192, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7808072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 20, 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": [[1.4500672235934436e-05], 0, 1.9063498973846436, 1619135935.8192756], "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, 34, 60], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5216420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 10, 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", 0]]}, "result": [[2.8800693707072582e-05], 0, 1.593768835067749, 1619139195.1336563], "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, 34, 60], "float32"], ["TENSOR", [384, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12638229, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 6]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 5, 12, 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": [[2.1986796470253343e-05], 0, 1.6554701328277588, 1619146054.2878928], "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, 34, 60], "float32"], ["TENSOR", [384, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6552057, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 17, 1, 1]], ["tile_x", "sp", [-1, 1, 60, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.1818529242396978e-05], 0, 2.282867193222046, 1619150229.6533096], "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, 34, 60], "float32"], ["TENSOR", [96, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23116838, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 20, 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": [[3.504173986194996e-05], 0, 1.6221210956573486, 1619153356.7909222], "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, 34, 60], "float32"], ["TENSOR", [576, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 138298513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 6, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 3, 20, 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": [[3.996946634246225e-05], 0, 1.8882009983062744, 1619156183.8453841], "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, 34, 60], "float32"], ["TENSOR", [576, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11460960, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 17]], ["tile_x", "sp", [-1, 2, 30, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.101299319727891e-05], 0, 1.9511616230010986, 1619158379.3061266], "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, 34, 60], "float32"], ["TENSOR", [96, 576, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29998177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 20, 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": [[5.0761763689700126e-05], 0, 1.6330413818359375, 1619161678.4774408], "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, 34, 60], "float32"], ["TENSOR", [24, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11326746, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 20, 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": [[5.0493700838729304e-06], 0, 2.084857225418091, 1619164414.7846878], "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, 544, 960], "float32"], ["TENSOR", [32, 3, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 43381310, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 32, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.259844755628775e-05], 0, 2.0576188564300537, 1619168191.4033773], "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, 272, 480], "float32"], ["TENSOR", [32, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 36594992, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 2, 240, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.38191702210159e-05], 0, 2.9549612998962402, 1619172294.0221272], "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, 272, 480], "float32"], ["TENSOR", [16, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 119184299, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 16, 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": [[6.776152641083521e-05], 0, 2.173097610473633, 1619176148.8294299], "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, 272, 480], "float32"], ["TENSOR", [96, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 370424475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 4, 40, 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": [[0.00016151622961373393], 0, 3.037766456604004, 1619180710.0673065], "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, 272, 480], "float32"], ["TENSOR", [96, 1, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 42024192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 5, 16, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017624103991291726], 0, 3.4178011417388916, 1619186320.0145793], "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, 136, 240], "float32"], ["TENSOR", [24, 96, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190617666, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 16, 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": [[4.652422700119474e-05], 0, 2.1412672996520996, 1619192594.899723], "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, 136, 240], "float32"], ["TENSOR", [144, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 724192311, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 12]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 16, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.614139736263736e-05], 0, 2.7007036209106445, 1619198186.1398847], "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, 136, 240], "float32"], ["TENSOR", [144, 1, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 66461150, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 2, 120, 1]], ["auto_unroll_max_step", "ot", 256], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010573737957746478], 0, 2.50951886177063, 1619201874.4961176], "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, 136, 240], "float32"], ["TENSOR", [24, 144, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 276672146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 4]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 4, 20, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.225860936280884e-05], 0, 2.4383678436279297, 1619208458.3871162], "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, 136, 240], "float32"], ["TENSOR", [24, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 133408152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 6]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 48, 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": [[1.8084070159099726e-05], 0, 2.1902265548706055, 1619215682.4869478], "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, 24, 136, 240], "float32"], ["TENSOR", [24, 24, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3805724, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 4, 2]], ["tile_x", "sp", [-1, 2, 60, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00023443220716510906], 0, 3.585075616836548, 1619220859.2236297], "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, 136, 240], "float32"], ["TENSOR", [24, 24, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 319639817, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 3]], ["tile_y", "sp", [-1, 1, 1, 8]], ["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": [[5.686625605786618e-05], 0, 1.7110137939453125, 1619226658.2487266], "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, 136, 240], "float32"], ["TENSOR", [1, 24, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 906560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 120, 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", 0]]}, "result": [[7.852759481005713e-06], 0, 1.971285104751587, 1619230218.5840015], "version": 0.2, "tvm_version": "0.8.dev0"}