Created
July 23, 2019 00:42
-
-
Save ChaiBapchya/37b27d4803e73e0fa5a8bd6e8da11492 to your computer and use it in GitHub Desktop.
CPU Rearrange Ops Benchmark
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"BatchNorm": [ | |
{ | |
"avg_time_backward_BatchNorm": 94.9822, | |
"avg_time_forward_BatchNorm": 67.2517, | |
"inputs": { | |
"beta": [ | |
3 | |
], | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"gamma": [ | |
3 | |
], | |
"moving_mean": [ | |
3 | |
], | |
"moving_var": [ | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 25165.8359 | |
}, | |
{ | |
"avg_time_backward_BatchNorm": 141.3134, | |
"avg_time_forward_BatchNorm": 100.0764, | |
"inputs": { | |
"beta": [ | |
3 | |
], | |
"data": [ | |
32, | |
3, | |
10000, | |
10 | |
], | |
"gamma": [ | |
3 | |
], | |
"moving_mean": [ | |
3 | |
], | |
"moving_var": [ | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 38400.0117 | |
} | |
], | |
"BlockGrad": [ | |
{ | |
"avg_time_forward_BlockGrad": 0.0167, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_BlockGrad": 0.0758, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"Convolution": [ | |
{ | |
"avg_time_backward_Convolution": 17.8374, | |
"avg_time_forward_Convolution": 15.3719, | |
"inputs": { | |
"bias": [ | |
64 | |
], | |
"data": [ | |
32, | |
3, | |
256 | |
], | |
"dilate": [ | |
1 | |
], | |
"kernel": [ | |
3 | |
], | |
"layout": "NCW", | |
"num_filter": 64, | |
"pad": [ | |
0 | |
], | |
"stride": [ | |
1 | |
], | |
"weight": [ | |
64, | |
3, | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2080.7681 | |
} | |
], | |
"Deconvolution": [ | |
{ | |
"avg_time_backward_Deconvolution": 61.8514, | |
"avg_time_forward_Deconvolution": 100.986, | |
"inputs": { | |
"adj": [ | |
0 | |
], | |
"bias": [ | |
64 | |
], | |
"data": [ | |
32, | |
3, | |
256 | |
], | |
"dilate": [ | |
1 | |
], | |
"kernel": [ | |
3 | |
], | |
"layout": "NCW", | |
"no_bias": false, | |
"num_filter": 64, | |
"pad": [ | |
0 | |
], | |
"stride": [ | |
1 | |
], | |
"weight": [ | |
3, | |
64, | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 440545.6875 | |
} | |
], | |
"Dropout": [ | |
{ | |
"avg_time_backward_Dropout": 23.847, | |
"avg_time_forward_Dropout": 245.3539, | |
"inputs": { | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"mode": "always", | |
"p": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 37748.7344 | |
}, | |
{ | |
"avg_time_backward_Dropout": 0.378, | |
"avg_time_forward_Dropout": 4.2056, | |
"inputs": { | |
"data": [ | |
10000, | |
10 | |
], | |
"mode": "always", | |
"p": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 400.0 | |
} | |
], | |
"Flatten": [ | |
{ | |
"avg_time_forward_Flatten": 0.0063, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_Flatten": 0.0526, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"FullyConnected": [ | |
{ | |
"avg_time_backward_FullyConnected": 27.668, | |
"avg_time_forward_FullyConnected": 28.0485, | |
"inputs": { | |
"bias": [ | |
64 | |
], | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"flatten": true, | |
"num_hidden": 64, | |
"weight": [ | |
64, | |
196608 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8.192 | |
}, | |
{ | |
"avg_time_backward_FullyConnected": 102.3403, | |
"avg_time_forward_FullyConnected": 21.3076, | |
"inputs": { | |
"bias": [ | |
64 | |
], | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"flatten": false, | |
"num_hidden": 64, | |
"weight": [ | |
64, | |
256 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 6291.4561 | |
} | |
], | |
"LeakyReLU": [ | |
{ | |
"avg_time_backward_LeakyReLU": 12.4757, | |
"avg_time_forward_LeakyReLU": 10.3453, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
1024, | |
1024 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.1279, | |
"avg_time_forward_LeakyReLU": 0.1123, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
10000, | |
1 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 11.9525, | |
"avg_time_forward_LeakyReLU": 9.8819, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
10000, | |
100 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 12.6311, | |
"avg_time_forward_LeakyReLU": 12.8676, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
1024, | |
1024 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.1965, | |
"avg_time_forward_LeakyReLU": 0.1659, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
10000, | |
1 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 12.1173, | |
"avg_time_forward_LeakyReLU": 12.8783, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
10000, | |
100 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 11.9346, | |
"avg_time_forward_LeakyReLU": 12.7322, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.1213, | |
"avg_time_forward_LeakyReLU": 0.1324, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 11.5088, | |
"avg_time_forward_LeakyReLU": 12.766, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 280.2026, | |
"avg_time_forward_LeakyReLU": 17.1723, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
1024, | |
1024 | |
], | |
"gamma": [ | |
1, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 2.0712, | |
"avg_time_forward_LeakyReLU": 0.2913, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
10000, | |
1 | |
], | |
"gamma": [ | |
1, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 219.4809, | |
"avg_time_forward_LeakyReLU": 16.993, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
10000, | |
100 | |
], | |
"gamma": [ | |
1, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"Pooling": [ | |
{ | |
"avg_time_backward_Pooling": 0.6234, | |
"avg_time_forward_Pooling": 0.5461, | |
"inputs": { | |
"data": [ | |
32, | |
3, | |
256 | |
], | |
"global_pool": 0, | |
"kernel": 3, | |
"pad": 1, | |
"pool_type": "avg", | |
"stride": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 49.152 | |
} | |
], | |
"abs": [ | |
{ | |
"avg_time_backward_abs": 0.0113, | |
"avg_time_forward_abs": 0.0113, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_abs": 2.8999, | |
"avg_time_forward_abs": 0.8214, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arccos": [ | |
{ | |
"avg_time_backward_arccos": 0.0119, | |
"avg_time_forward_arccos": 0.0149, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arccos": 2.1233, | |
"avg_time_forward_arccos": 4.1234, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arccosh": [ | |
{ | |
"avg_time_backward_arccosh": 0.0098, | |
"avg_time_forward_arccosh": 0.0102, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arccosh": 1.8048, | |
"avg_time_forward_arccosh": 1.6185, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arcsin": [ | |
{ | |
"avg_time_backward_arcsin": 0.0093, | |
"avg_time_forward_arcsin": 0.01, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arcsin": 1.8121, | |
"avg_time_forward_arcsin": 3.9668, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arcsinh": [ | |
{ | |
"avg_time_backward_arcsinh": 0.0094, | |
"avg_time_forward_arcsinh": 0.01, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arcsinh": 1.994, | |
"avg_time_forward_arcsinh": 2.4176, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arctan": [ | |
{ | |
"avg_time_backward_arctan": 0.0101, | |
"avg_time_forward_arctan": 0.0103, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arctan": 1.61, | |
"avg_time_forward_arctan": 2.6599, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arctanh": [ | |
{ | |
"avg_time_backward_arctanh": 0.0089, | |
"avg_time_forward_arctanh": 0.0107, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_arctanh": 1.5818, | |
"avg_time_forward_arctanh": 3.3453, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"argmax": [ | |
{ | |
"avg_time_forward_argmax": 0.0227, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_argmax": 14.7732, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"argmax_channel": [ | |
{ | |
"avg_time_forward_argmax_channel": 0.0082, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.032 | |
}, | |
{ | |
"avg_time_forward_argmax_channel": 3.3033, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
} | |
], | |
"argmin": [ | |
{ | |
"avg_time_forward_argmin": 0.0208, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_argmin": 14.3713, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"argsort": [ | |
{ | |
"avg_time_forward_argsort": 0.0397, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_argsort": 87.1471, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 6350.0 | |
} | |
], | |
"batch_dot": [ | |
{ | |
"avg_time_backward_batch_dot": 1203.4496, | |
"avg_time_forward_batch_dot": 650.7618, | |
"inputs": { | |
"lhs": [ | |
32, | |
1024, | |
1024 | |
], | |
"rhs": [ | |
32, | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 134217.7344 | |
}, | |
{ | |
"avg_time_backward_batch_dot": 51.0916, | |
"avg_time_forward_batch_dot": 37.0182, | |
"inputs": { | |
"lhs": [ | |
32, | |
1000, | |
10 | |
], | |
"rhs": [ | |
32, | |
1000, | |
10 | |
], | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 128000.0 | |
}, | |
{ | |
"avg_time_backward_batch_dot": 1.8586, | |
"avg_time_forward_batch_dot": 0.9606, | |
"inputs": { | |
"lhs": [ | |
32, | |
1000, | |
1 | |
], | |
"rhs": [ | |
32, | |
100, | |
1000 | |
], | |
"transpose_a": true, | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 12.8 | |
} | |
], | |
"broadcast_add": [ | |
{ | |
"avg_time_backward_broadcast_add": 0.0118, | |
"avg_time_forward_broadcast_add": 0.0134, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_div": [ | |
{ | |
"avg_time_backward_broadcast_div": 0.0144, | |
"avg_time_forward_broadcast_div": 0.0133, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_equal": [ | |
{ | |
"avg_time_forward_broadcast_equal": 0.0118, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_greater": [ | |
{ | |
"avg_time_forward_broadcast_greater": 0.0134, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_greater_equal": [ | |
{ | |
"avg_time_forward_broadcast_greater_equal": 0.0081, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_hypot": [ | |
{ | |
"avg_time_backward_broadcast_hypot": 0.0117, | |
"avg_time_forward_broadcast_hypot": 0.0115, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_lesser": [ | |
{ | |
"avg_time_forward_broadcast_lesser": 0.0095, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_lesser_equal": [ | |
{ | |
"avg_time_forward_broadcast_lesser_equal": 0.0135, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_logical_and": [ | |
{ | |
"avg_time_forward_broadcast_logical_and": 0.0109, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_logical_or": [ | |
{ | |
"avg_time_forward_broadcast_logical_or": 0.0106, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_logical_xor": [ | |
{ | |
"avg_time_forward_broadcast_logical_xor": 0.0122, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_maximum": [ | |
{ | |
"avg_time_backward_broadcast_maximum": 0.0118, | |
"avg_time_forward_broadcast_maximum": 0.0116, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_minimum": [ | |
{ | |
"avg_time_backward_broadcast_minimum": 0.0131, | |
"avg_time_forward_broadcast_minimum": 0.0117, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_minus": [ | |
{ | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_mod": [ | |
{ | |
"avg_time_backward_broadcast_mod": 0.0119, | |
"avg_time_forward_broadcast_mod": 0.0123, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_mul": [ | |
{ | |
"avg_time_backward_broadcast_mul": 0.0128, | |
"avg_time_forward_broadcast_mul": 0.0123, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_not_equal": [ | |
{ | |
"avg_time_forward_broadcast_not_equal": 0.0121, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_plus": [ | |
{ | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_power": [ | |
{ | |
"avg_time_backward_broadcast_power": 0.0139, | |
"avg_time_forward_broadcast_power": 0.0114, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"broadcast_sub": [ | |
{ | |
"avg_time_backward_broadcast_sub": 0.0101, | |
"avg_time_forward_broadcast_sub": 0.0131, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"cbrt": [ | |
{ | |
"avg_time_backward_cbrt": 0.0098, | |
"avg_time_forward_cbrt": 0.0115, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_cbrt": 1.5544, | |
"avg_time_forward_cbrt": 2.752, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"ceil": [ | |
{ | |
"avg_time_forward_ceil": 0.0097, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_ceil": 0.8094, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"cos": [ | |
{ | |
"avg_time_backward_cos": 0.0095, | |
"avg_time_forward_cos": 0.0118, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_cos": 4.0973, | |
"avg_time_forward_cos": 3.5927, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"cosh": [ | |
{ | |
"avg_time_backward_cosh": 0.0116, | |
"avg_time_forward_cosh": 0.0104, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_cosh": 2.681, | |
"avg_time_forward_cosh": 2.1182, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"degrees": [ | |
{ | |
"avg_time_backward_degrees": 0.0094, | |
"avg_time_forward_degrees": 0.01, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_degrees": 1.0236, | |
"avg_time_forward_degrees": 0.8857, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"depth_to_space": [ | |
{ | |
"avg_time_forward_depth_to_space": 0.0191, | |
"inputs": { | |
"block_size": 2, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_depth_to_space": 19.0879, | |
"inputs": { | |
"block_size": 5, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"dot": [ | |
{ | |
"avg_time_backward_dot": 39.6793, | |
"avg_time_forward_dot": 17.9421, | |
"inputs": { | |
"lhs": [ | |
1024, | |
1024 | |
], | |
"rhs": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_backward_dot": 2.1502, | |
"avg_time_forward_dot": 1.4198, | |
"inputs": { | |
"lhs": [ | |
1000, | |
10 | |
], | |
"rhs": [ | |
1000, | |
10 | |
], | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
}, | |
{ | |
"avg_time_backward_dot": 0.0844, | |
"avg_time_forward_dot": 0.0395, | |
"inputs": { | |
"lhs": [ | |
1000, | |
1 | |
], | |
"rhs": [ | |
100, | |
1000 | |
], | |
"transpose_a": true, | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.4 | |
} | |
], | |
"elemwise_add": [ | |
{ | |
"avg_time_forward_elemwise_add": 0.0088, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"elemwise_div": [ | |
{ | |
"avg_time_forward_elemwise_div": 0.0079, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"elemwise_mul": [ | |
{ | |
"avg_time_forward_elemwise_mul": 0.0109, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"elemwise_sub": [ | |
{ | |
"avg_time_forward_elemwise_sub": 0.0111, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.024 | |
} | |
], | |
"erf": [ | |
{ | |
"avg_time_backward_erf": 0.0128, | |
"avg_time_forward_erf": 0.014, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_erf": 3.454, | |
"avg_time_forward_erf": 7.1123, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"erfinv": [ | |
{ | |
"avg_time_backward_erfinv": 0.0129, | |
"avg_time_forward_erfinv": 0.0126, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_erfinv": 23.6023, | |
"avg_time_forward_erfinv": 18.5274, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"exp": [ | |
{ | |
"avg_time_forward_exp": 0.0113, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_exp": 2.268, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"expm1": [ | |
{ | |
"avg_time_backward_expm1": 0.0138, | |
"avg_time_forward_expm1": 0.0122, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_expm1": 2.4229, | |
"avg_time_forward_expm1": 2.1422, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"fix": [ | |
{ | |
"avg_time_forward_fix": 0.0107, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_fix": 3.6694, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"flatten": [ | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"flip": [ | |
{ | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"floor": [ | |
{ | |
"avg_time_forward_floor": 0.0122, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_floor": 0.8038, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"gamma": [ | |
{ | |
"avg_time_backward_gamma": 0.0145, | |
"avg_time_forward_gamma": 0.0108, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_gamma": 35.8976, | |
"avg_time_forward_gamma": 8.5454, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"gammaln": [ | |
{ | |
"avg_time_backward_gammaln": 0.0141, | |
"avg_time_forward_gammaln": 0.013, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_gammaln": 35.0018, | |
"avg_time_forward_gammaln": 13.5399, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"hard_sigmoid": [ | |
{ | |
"avg_time_backward_hard_sigmoid": 6.6356, | |
"avg_time_forward_hard_sigmoid": 7.6101, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_hard_sigmoid": 0.0676, | |
"avg_time_forward_hard_sigmoid": 0.0833, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_backward_hard_sigmoid": 6.2974, | |
"avg_time_forward_hard_sigmoid": 7.7274, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"identity": [ | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"log": [ | |
{ | |
"avg_time_backward_log": 0.0106, | |
"avg_time_forward_log": 0.0136, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_log": 1.2821, | |
"avg_time_forward_log": 3.089, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log10": [ | |
{ | |
"avg_time_backward_log10": 0.0097, | |
"avg_time_forward_log10": 0.0119, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_log10": 1.1498, | |
"avg_time_forward_log10": 3.1409, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log1p": [ | |
{ | |
"avg_time_backward_log1p": 0.0091, | |
"avg_time_forward_log1p": 0.0106, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_log1p": 1.6733, | |
"avg_time_forward_log1p": 4.0004, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"log2": [ | |
{ | |
"avg_time_backward_log2": 0.0126, | |
"avg_time_forward_log2": 0.0158, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_log2": 1.258, | |
"avg_time_forward_log2": 3.3976, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"log_softmax": [ | |
{ | |
"avg_time_backward_log_softmax": 14.3768, | |
"avg_time_forward_log_softmax": 21.2158, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
1024, | |
1024 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_log_softmax": 0.2962, | |
"avg_time_forward_log_softmax": 0.4249, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
1 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_log_softmax": 14.1877, | |
"avg_time_forward_log_softmax": 21.9005, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
100 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"logical_not": [ | |
{ | |
"avg_time_forward_logical_not": 0.013, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_logical_not": 0.9521, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"make_loss": [ | |
{ | |
"avg_time_forward_make_loss": 0.0069, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_make_loss": 0.0573, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"max": [ | |
{ | |
"avg_time_backward_max": 0.0247, | |
"avg_time_forward_max": 0.0461, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_max": 71.4833, | |
"avg_time_forward_max": 44.0928, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"max_axis": [ | |
{ | |
"avg_time_forward_max": 0.0248, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_max": 43.8067, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"mean": [ | |
{ | |
"avg_time_backward_mean": 0.0488, | |
"avg_time_forward_mean": 0.0464, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_mean": 37.2893, | |
"avg_time_forward_mean": 37.3751, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"min": [ | |
{ | |
"avg_time_backward_min": 0.0217, | |
"avg_time_forward_min": 0.0365, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_min": 55.9278, | |
"avg_time_forward_min": 39.1448, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"min_axis": [ | |
{ | |
"avg_time_forward_min": 0.0251, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_min": 39.4352, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"nanprod": [ | |
{ | |
"avg_time_backward_nanprod": 0.0251, | |
"avg_time_forward_nanprod": 0.0287, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_nanprod": 60.2467, | |
"avg_time_forward_nanprod": 34.0136, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"nansum": [ | |
{ | |
"avg_time_backward_nansum": 0.0224, | |
"avg_time_forward_nansum": 0.0332, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_nansum": 53.7117, | |
"avg_time_forward_nansum": 34.9494, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"negative": [ | |
{ | |
"avg_time_forward_negative": 0.0091, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_negative": 0.6697, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"ones_like": [ | |
{ | |
"avg_time_forward_ones_like": 0.0133, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_ones_like": 0.5136, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"prod": [ | |
{ | |
"avg_time_backward_prod": 0.0251, | |
"avg_time_forward_prod": 0.0432, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_prod": 53.6272, | |
"avg_time_forward_prod": 34.9464, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"radians": [ | |
{ | |
"avg_time_backward_radians": 0.0123, | |
"avg_time_forward_radians": 0.017, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_radians": 1.0693, | |
"avg_time_forward_radians": 0.9844, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"random_exponential": [ | |
{ | |
"avg_time_forward__random_exponential": 62.3242, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_exponential": 0.629, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_exponential": 59.3457, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_gamma": [ | |
{ | |
"avg_time_forward__random_gamma": 267.2349, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_gamma": 2.4606, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_gamma": 245.6321, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_generalized_negative_binomial": [ | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 366.2596, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 3.6017, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 363.0028, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_negative_binomial": [ | |
{ | |
"avg_time_forward__random_negative_binomial": 311.1194, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_negative_binomial": 2.8999, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_negative_binomial": 288.6107, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_normal": [ | |
{ | |
"avg_time_forward__random_normal": 163.0979, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_normal": 2.1105, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_normal": 150.4169, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_poisson": [ | |
{ | |
"avg_time_forward__random_poisson": 129.2493, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_poisson": 1.1549, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_poisson": 131.6929, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_randint": [ | |
{ | |
"avg_time_forward__random_randint": 67.0276, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_randint": 0.6413, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_randint": 74.8244, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_uniform": [ | |
{ | |
"avg_time_forward__random_uniform": 55.1974, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_uniform": 0.5707, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_uniform": 47.0119, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"rcbrt": [ | |
{ | |
"avg_time_backward_rcbrt": 0.0126, | |
"avg_time_forward_rcbrt": 0.0142, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_rcbrt": 4.0681, | |
"avg_time_forward_rcbrt": 3.3188, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"reciprocal": [ | |
{ | |
"avg_time_backward_reciprocal": 0.0154, | |
"avg_time_forward_reciprocal": 0.0149, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_reciprocal": 1.7098, | |
"avg_time_forward_reciprocal": 0.9189, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"relu": [ | |
{ | |
"avg_time_backward_relu": 0.0122, | |
"avg_time_forward_relu": 0.0116, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_relu": 2.0481, | |
"avg_time_forward_relu": 2.7827, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"rint": [ | |
{ | |
"avg_time_forward_rint": 0.0095, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_rint": 3.8602, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"round": [ | |
{ | |
"avg_time_forward_round": 0.0102, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_round": 3.5915, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"rsqrt": [ | |
{ | |
"avg_time_backward_rsqrt": 0.0122, | |
"avg_time_forward_rsqrt": 0.0124, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_rsqrt": 1.6019, | |
"avg_time_forward_rsqrt": 0.9993, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sample_exponential": [ | |
{ | |
"avg_time_forward__sample_exponential": 138.3763, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_exponential": 1.7019, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_exponential": 127.6174, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_gamma": [ | |
{ | |
"avg_time_forward__sample_gamma": 544.3638, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"beta": [ | |
1.0, | |
0.7 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_gamma": 5.506, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"beta": [ | |
1.0, | |
0.7 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_gamma": 534.553, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"beta": [ | |
1.0, | |
0.7 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_generalized_negative_binomial": [ | |
{ | |
"avg_time_forward__sample_generalized_negative_binomial": 649.4515, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_generalized_negative_binomial": 6.5389, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_generalized_negative_binomial": 687.5925, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_negative_binomial": [ | |
{ | |
"avg_time_forward__sample_negative_binomial": 1406.4028, | |
"inputs": { | |
"k": [ | |
20, | |
49 | |
], | |
"p": [ | |
0.4, | |
0.77 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_negative_binomial": 13.2211, | |
"inputs": { | |
"k": [ | |
20, | |
49 | |
], | |
"p": [ | |
0.4, | |
0.77 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_negative_binomial": 1268.1676, | |
"inputs": { | |
"k": [ | |
20, | |
49 | |
], | |
"p": [ | |
0.4, | |
0.77 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"sample_normal": [ | |
{ | |
"avg_time_forward__sample_normal": 324.7289, | |
"inputs": { | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
], | |
"sigma": [ | |
1.0, | |
3.7 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_normal": 2.9569, | |
"inputs": { | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
], | |
"sigma": [ | |
1.0, | |
3.7 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_normal": 316.1108, | |
"inputs": { | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
], | |
"sigma": [ | |
1.0, | |
3.7 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_poisson": [ | |
{ | |
"avg_time_forward__sample_poisson": 1582.3153, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_poisson": 17.3791, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_poisson": 2343.8877, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_uniform": [ | |
{ | |
"avg_time_forward__sample_uniform": 463.6894, | |
"inputs": { | |
"high": [ | |
1.0, | |
3.7 | |
], | |
"low": [ | |
0.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_uniform": 3.5304, | |
"inputs": { | |
"high": [ | |
1.0, | |
3.7 | |
], | |
"low": [ | |
0.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_uniform": 467.4507, | |
"inputs": { | |
"high": [ | |
1.0, | |
3.7 | |
], | |
"low": [ | |
0.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"shuffle": [ | |
{ | |
"avg_time_forward__shuffle": 0.0073, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward__shuffle": 0.1382, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1149.808 | |
} | |
], | |
"sigmoid": [ | |
{ | |
"avg_time_backward_sigmoid": 0.0118, | |
"avg_time_forward_sigmoid": 0.0131, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sigmoid": 1.4157, | |
"avg_time_forward_sigmoid": 2.3267, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sign": [ | |
{ | |
"avg_time_backward_sign": 0.0104, | |
"avg_time_forward_sign": 0.0105, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sign": 0.9569, | |
"avg_time_forward_sign": 2.4026, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sin": [ | |
{ | |
"avg_time_backward_sin": 0.0117, | |
"avg_time_forward_sin": 0.0128, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sin": 4.0611, | |
"avg_time_forward_sin": 3.6394, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sinh": [ | |
{ | |
"avg_time_backward_sinh": 0.0101, | |
"avg_time_forward_sinh": 0.0123, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sinh": 2.565, | |
"avg_time_forward_sinh": 2.3061, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"size_array": [ | |
{ | |
"avg_time_forward_size_array": 0.0095, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.008 | |
}, | |
{ | |
"avg_time_forward_size_array": 0.0067, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.008 | |
} | |
], | |
"softmax": [ | |
{ | |
"avg_time_backward_softmax": 8.8548, | |
"avg_time_forward_softmax": 24.5564, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
1024, | |
1024 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_backward_softmax": 0.3006, | |
"avg_time_forward_softmax": 0.3366, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
1 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_backward_softmax": 8.3591, | |
"avg_time_forward_softmax": 23.35, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
100 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"softsign": [ | |
{ | |
"avg_time_backward_softsign": 0.0103, | |
"avg_time_forward_softsign": 0.0106, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_softsign": 1.7234, | |
"avg_time_forward_softsign": 0.9921, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sort": [ | |
{ | |
"avg_time_forward_sort": 0.0363, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.192 | |
}, | |
{ | |
"avg_time_forward_sort": 105.4341, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1500.0 | |
} | |
], | |
"space_to_depth": [ | |
{ | |
"avg_time_forward_space_to_depth": 0.0194, | |
"inputs": { | |
"block_size": 2, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_space_to_depth": 21.3816, | |
"inputs": { | |
"block_size": 5, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sqrt": [ | |
{ | |
"avg_time_backward_sqrt": 0.0104, | |
"avg_time_forward_sqrt": 0.0107, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sqrt": 1.2696, | |
"avg_time_forward_sqrt": 0.8824, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"square": [ | |
{ | |
"avg_time_backward_square": 0.013, | |
"avg_time_forward_square": 0.0112, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_square": 1.6997, | |
"avg_time_forward_square": 1.3684, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"stop_gradient": [ | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"sum": [ | |
{ | |
"avg_time_backward_sum": 0.0208, | |
"avg_time_forward_sum": 0.0293, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_sum": 24.1291, | |
"avg_time_forward_sum": 31.6291, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"sum_axis": [ | |
{ | |
"avg_time_forward_sum": 0.023, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_sum": 37.1857, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"swapaxes": [ | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 0, | |
"dim2": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 1, | |
"dim2": 2 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 2, | |
"dim2": 3 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 3, | |
"dim2": 0 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
} | |
], | |
"tan": [ | |
{ | |
"avg_time_backward_tan": 0.0102, | |
"avg_time_forward_tan": 0.0123, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_tan": 1.7956, | |
"avg_time_forward_tan": 4.2917, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"tanh": [ | |
{ | |
"avg_time_backward_tanh": 0.0142, | |
"avg_time_forward_tanh": 0.0136, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_tanh": 1.5235, | |
"avg_time_forward_tanh": 2.7717, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"topk": [ | |
{ | |
"avg_time_forward_topk": 0.0685, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"k": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_topk": 21.7366, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
], | |
"k": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"transpose": [ | |
{ | |
"avg_time_forward_transpose": 0.0213, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_transpose": 20.4937, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"trunc": [ | |
{ | |
"avg_time_forward_trunc": 0.0096, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_trunc": 0.822, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"zeros_like": [ | |
{ | |
"avg_time_forward_zeros_like": 0.0106, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_zeros_like": 0.5962, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment