Created
July 22, 2019 21:24
-
-
Save ChaiBapchya/51b6c7c2346959f3f72aa1b702eb002d to your computer and use it in GitHub Desktop.
GPU 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": 8.1367, | |
"avg_time_forward_BatchNorm": 7.7976, | |
"inputs": { | |
"beta": [ | |
3 | |
], | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"gamma": [ | |
3 | |
], | |
"moving_mean": [ | |
3 | |
], | |
"moving_var": [ | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 12582.9238 | |
}, | |
{ | |
"avg_time_backward_BatchNorm": 13.9439, | |
"avg_time_forward_BatchNorm": 14.4524, | |
"inputs": { | |
"beta": [ | |
3 | |
], | |
"data": [ | |
32, | |
3, | |
10000, | |
10 | |
], | |
"gamma": [ | |
3 | |
], | |
"moving_mean": [ | |
3 | |
], | |
"moving_var": [ | |
3 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 19200.0117 | |
} | |
], | |
"BlockGrad": [ | |
{ | |
"avg_time_forward_BlockGrad": 0.0185, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_BlockGrad": 0.2685, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"Convolution": [ | |
{ | |
"avg_time_backward_Convolution": 0.9606, | |
"avg_time_forward_Convolution": 0.4483, | |
"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": 1.9013, | |
"avg_time_forward_Deconvolution": 2.0321, | |
"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": 2217221.5 | |
} | |
], | |
"Dropout": [ | |
{ | |
"avg_time_backward_Dropout": 0.7963, | |
"avg_time_forward_Dropout": 2.1278, | |
"inputs": { | |
"data": [ | |
32, | |
3, | |
256, | |
256 | |
], | |
"mode": "always", | |
"p": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 37748.7344 | |
}, | |
{ | |
"avg_time_backward_Dropout": 0.0401, | |
"avg_time_forward_Dropout": 0.0733, | |
"inputs": { | |
"data": [ | |
10000, | |
10 | |
], | |
"mode": "always", | |
"p": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 400.0 | |
} | |
], | |
"Flatten": [ | |
{ | |
"avg_time_forward_Flatten": 0.0417, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_Flatten": 0.0844, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2999.8081 | |
} | |
], | |
"FullyConnected": [ | |
{ | |
"avg_time_backward_FullyConnected": 3.3788, | |
"avg_time_forward_FullyConnected": 1.1843, | |
"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": 3.0802, | |
"avg_time_forward_FullyConnected": 1.1615, | |
"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": 0.048, | |
"avg_time_forward_LeakyReLU": 0.2521, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
1024, | |
1024 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.0373, | |
"avg_time_forward_LeakyReLU": 0.0837, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
10000, | |
1 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.0707, | |
"avg_time_forward_LeakyReLU": 0.2693, | |
"inputs": { | |
"act_type": "leaky", | |
"data": [ | |
10000, | |
100 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.2646, | |
"avg_time_forward_LeakyReLU": 0.6806, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
1024, | |
1024 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.0683, | |
"avg_time_forward_LeakyReLU": 0.042, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
10000, | |
1 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.2553, | |
"avg_time_forward_LeakyReLU": 0.6471, | |
"inputs": { | |
"act_type": "elu", | |
"data": [ | |
10000, | |
100 | |
], | |
"slope": 0.1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.2618, | |
"avg_time_forward_LeakyReLU": 0.6833, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.064, | |
"avg_time_forward_LeakyReLU": 0.0419, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.305, | |
"avg_time_forward_LeakyReLU": 0.7337, | |
"inputs": { | |
"act_type": "selu", | |
"data": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 1.8924, | |
"avg_time_forward_LeakyReLU": 0.3514, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
1024, | |
1024 | |
], | |
"gamma": [ | |
1, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 0.2093, | |
"avg_time_forward_LeakyReLU": 0.0472, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
10000, | |
1 | |
], | |
"gamma": [ | |
1, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_LeakyReLU": 2.0529, | |
"avg_time_forward_LeakyReLU": 0.3499, | |
"inputs": { | |
"act_type": "prelu", | |
"data": [ | |
10000, | |
100 | |
], | |
"gamma": [ | |
1, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"Pooling": [ | |
{ | |
"avg_time_backward_Pooling": 0.2981, | |
"avg_time_forward_Pooling": 0.2439, | |
"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": 0.0094, | |
"avg_time_forward_abs": 0.0109, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_abs": 0.0905, | |
"avg_time_forward_abs": 0.0347, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"arccos": [ | |
{ | |
"avg_time_backward_arccos": 0.0057, | |
"avg_time_forward_arccos": 0.0066, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arccos": 0.1304, | |
"avg_time_forward_arccos": 0.2009, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arccosh": [ | |
{ | |
"avg_time_backward_arccosh": 0.0053, | |
"avg_time_forward_arccosh": 0.006, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arccosh": 0.1703, | |
"avg_time_forward_arccosh": 0.1721, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arcsin": [ | |
{ | |
"avg_time_backward_arcsin": 0.0056, | |
"avg_time_forward_arcsin": 0.0063, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arcsin": 0.1338, | |
"avg_time_forward_arcsin": 0.1878, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arcsinh": [ | |
{ | |
"avg_time_backward_arcsinh": 0.0059, | |
"avg_time_forward_arcsinh": 0.0073, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arcsinh": 0.1161, | |
"avg_time_forward_arcsinh": 0.3591, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arctan": [ | |
{ | |
"avg_time_backward_arctan": 0.0056, | |
"avg_time_forward_arctan": 0.0069, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arctan": 0.0246, | |
"avg_time_forward_arctan": 0.2209, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"arctanh": [ | |
{ | |
"avg_time_backward_arctanh": 0.0061, | |
"avg_time_forward_arctanh": 0.0076, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_arctanh": 0.026, | |
"avg_time_forward_arctanh": 0.3264, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"argmax": [ | |
{ | |
"avg_time_forward_argmax": 0.0426, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_argmax": 2.8347, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"argmax_channel": [ | |
{ | |
"avg_time_forward_argmax_channel": 0.0228, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.016 | |
}, | |
{ | |
"avg_time_forward_argmax_channel": 0.3162, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
} | |
], | |
"argmin": [ | |
{ | |
"avg_time_forward_argmin": 0.042, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_argmin": 3.0053, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"argsort": [ | |
{ | |
"avg_time_forward_argsort": 0.087, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_argsort": 6.8466, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 5000.0 | |
} | |
], | |
"batch_dot": [ | |
{ | |
"avg_time_backward_batch_dot": 149.3427, | |
"avg_time_forward_batch_dot": 106.4045, | |
"inputs": { | |
"lhs": [ | |
32, | |
1024, | |
1024 | |
], | |
"rhs": [ | |
32, | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 134217.7344 | |
}, | |
{ | |
"avg_time_backward_batch_dot": 11.2007, | |
"avg_time_forward_batch_dot": 26.5575, | |
"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": 1.6701, | |
"avg_time_forward_batch_dot": 0.785, | |
"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": 0.0185, | |
"avg_time_forward_broadcast_add": 0.0233, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_div": [ | |
{ | |
"avg_time_backward_broadcast_div": 0.0185, | |
"avg_time_forward_broadcast_div": 0.0221, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_equal": [ | |
{ | |
"avg_time_forward_broadcast_equal": 0.0209, | |
"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": 0.0212, | |
"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_equal": [ | |
{ | |
"avg_time_forward_broadcast_greater_equal": 0.0212, | |
"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": 0.019, | |
"avg_time_forward_broadcast_hypot": 0.021, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_lesser": [ | |
{ | |
"avg_time_forward_broadcast_lesser": 0.0203, | |
"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": 0.0202, | |
"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": 0.0211, | |
"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_or": [ | |
{ | |
"avg_time_forward_broadcast_logical_or": 0.0203, | |
"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": 0.0203, | |
"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": 0.0184, | |
"avg_time_forward_broadcast_maximum": 0.0218, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_minimum": [ | |
{ | |
"avg_time_backward_broadcast_minimum": 0.0187, | |
"avg_time_forward_broadcast_minimum": 0.0218, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"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": 0.0192, | |
"avg_time_forward_broadcast_mod": 0.0214, | |
"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": 0.0181, | |
"avg_time_forward_broadcast_mul": 0.0207, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_not_equal": [ | |
{ | |
"avg_time_forward_broadcast_not_equal": 0.021, | |
"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": 0.0211, | |
"avg_time_forward_broadcast_power": 0.0229, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"broadcast_sub": [ | |
{ | |
"avg_time_backward_broadcast_sub": 0.0164, | |
"avg_time_forward_broadcast_sub": 0.0208, | |
"inputs": { | |
"lhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
], | |
"rhs": [ | |
[ | |
1024, | |
1024 | |
], | |
[ | |
10000, | |
10 | |
], | |
[ | |
10000, | |
1 | |
] | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.012 | |
} | |
], | |
"cbrt": [ | |
{ | |
"avg_time_backward_cbrt": 0.0066, | |
"avg_time_forward_cbrt": 0.0086, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_cbrt": 0.0263, | |
"avg_time_forward_cbrt": 0.3478, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"ceil": [ | |
{ | |
"avg_time_forward_ceil": 0.0075, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_ceil": 0.0526, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"cos": [ | |
{ | |
"avg_time_backward_cos": 0.0102, | |
"avg_time_forward_cos": 0.015, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_backward_cos": 0.1431, | |
"avg_time_forward_cos": 0.1528, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"cosh": [ | |
{ | |
"avg_time_backward_cosh": 0.0088, | |
"avg_time_forward_cosh": 0.0098, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_cosh": 0.3968, | |
"avg_time_forward_cosh": 0.2262, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"degrees": [ | |
{ | |
"avg_time_backward_degrees": 0.0078, | |
"avg_time_forward_degrees": 0.0094, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_degrees": 0.0279, | |
"avg_time_forward_degrees": 0.0336, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"depth_to_space": [ | |
{ | |
"avg_time_forward_depth_to_space": 0.0572, | |
"inputs": { | |
"block_size": 2, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_depth_to_space": 0.2995, | |
"inputs": { | |
"block_size": 5, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"dot": [ | |
{ | |
"avg_time_backward_dot": 4.6965, | |
"avg_time_forward_dot": 2.1797, | |
"inputs": { | |
"lhs": [ | |
1024, | |
1024 | |
], | |
"rhs": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_backward_dot": 0.2805, | |
"avg_time_forward_dot": 0.2318, | |
"inputs": { | |
"lhs": [ | |
1000, | |
10 | |
], | |
"rhs": [ | |
1000, | |
10 | |
], | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
}, | |
{ | |
"avg_time_backward_dot": 0.0636, | |
"avg_time_forward_dot": 0.0426, | |
"inputs": { | |
"lhs": [ | |
1000, | |
1 | |
], | |
"rhs": [ | |
100, | |
1000 | |
], | |
"transpose_a": true, | |
"transpose_b": true | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.2 | |
} | |
], | |
"elemwise_add": [ | |
{ | |
"avg_time_forward_elemwise_add": 0.065, | |
"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": 0.0207, | |
"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": 0.0207, | |
"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": 0.0202, | |
"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": 0.0096, | |
"avg_time_forward_erf": 0.0115, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_erf": 0.2008, | |
"avg_time_forward_erf": 0.2392, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"erfinv": [ | |
{ | |
"avg_time_backward_erfinv": 0.0126, | |
"avg_time_forward_erfinv": 0.0133, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_erfinv": 1.0105, | |
"avg_time_forward_erfinv": 0.8444, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"exp": [ | |
{ | |
"avg_time_forward_exp": 0.0103, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_exp": 0.1793, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"expm1": [ | |
{ | |
"avg_time_backward_expm1": 0.0099, | |
"avg_time_forward_expm1": 0.0118, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_expm1": 0.1738, | |
"avg_time_forward_expm1": 0.2601, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"fix": [ | |
{ | |
"avg_time_forward_fix": 0.0103, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_fix": 0.1071, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"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": 500.0 | |
} | |
], | |
"flip": [ | |
{ | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"floor": [ | |
{ | |
"avg_time_forward_floor": 0.0104, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_floor": 0.0567, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"gamma": [ | |
{ | |
"avg_time_backward_gamma": 0.0137, | |
"avg_time_forward_gamma": 0.0141, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_gamma": 1.7096, | |
"avg_time_forward_gamma": 0.9531, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"gammaln": [ | |
{ | |
"avg_time_backward_gammaln": 0.0131, | |
"avg_time_forward_gammaln": 0.0232, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_gammaln": 0.8162, | |
"avg_time_forward_gammaln": 5.6172, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"hard_sigmoid": [ | |
{ | |
"avg_time_backward_hard_sigmoid": 0.0995, | |
"avg_time_forward_hard_sigmoid": 0.1108, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_hard_sigmoid": 0.0396, | |
"avg_time_forward_hard_sigmoid": 0.0408, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_hard_sigmoid": 0.0973, | |
"avg_time_forward_hard_sigmoid": 0.1065, | |
"inputs": { | |
"alpha": 0.25, | |
"beta": 0.5, | |
"data": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"identity": [ | |
{ | |
"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": 500.0 | |
} | |
], | |
"log": [ | |
{ | |
"avg_time_backward_log": 0.0137, | |
"avg_time_forward_log": 0.0173, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_log": 0.0349, | |
"avg_time_forward_log": 0.273, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log10": [ | |
{ | |
"avg_time_backward_log10": 0.0126, | |
"avg_time_forward_log10": 0.0163, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_log10": 0.0365, | |
"avg_time_forward_log10": 0.2972, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log1p": [ | |
{ | |
"avg_time_backward_log1p": 0.0124, | |
"avg_time_forward_log1p": 0.0161, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_log1p": 0.0322, | |
"avg_time_forward_log1p": 0.2573, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log2": [ | |
{ | |
"avg_time_backward_log2": 0.0124, | |
"avg_time_forward_log2": 0.0162, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_log2": 0.0328, | |
"avg_time_forward_log2": 0.2235, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"log_softmax": [ | |
{ | |
"avg_time_backward_log_softmax": 0.568, | |
"avg_time_forward_log_softmax": 1.1603, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
1024, | |
1024 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_log_softmax": 0.0425, | |
"avg_time_forward_log_softmax": 0.1011, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
1 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_log_softmax": 0.7549, | |
"avg_time_forward_log_softmax": 1.5429, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
100 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"logical_not": [ | |
{ | |
"avg_time_forward_logical_not": 0.0155, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_logical_not": 0.0585, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"make_loss": [ | |
{ | |
"avg_time_forward_make_loss": 0.0133, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_make_loss": 0.1157, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"max": [ | |
{ | |
"avg_time_backward_max": 0.0443, | |
"avg_time_forward_max": 0.0447, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_max": 0.2285, | |
"avg_time_forward_max": 0.1594, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"max_axis": [ | |
{ | |
"avg_time_forward_max": 0.041, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_max": 0.1561, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 100.0 | |
} | |
], | |
"mean": [ | |
{ | |
"avg_time_backward_mean": 0.0562, | |
"avg_time_forward_mean": 0.0622, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_mean": 0.5514, | |
"avg_time_forward_mean": 0.1861, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"min": [ | |
{ | |
"avg_time_backward_min": 0.0396, | |
"avg_time_forward_min": 0.0454, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_min": 0.2247, | |
"avg_time_forward_min": 0.1539, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"min_axis": [ | |
{ | |
"avg_time_forward_min": 0.0427, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_min": 0.1487, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"nanprod": [ | |
{ | |
"avg_time_backward_nanprod": 0.0383, | |
"avg_time_forward_nanprod": 0.0442, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_nanprod": 0.2085, | |
"avg_time_forward_nanprod": 0.1424, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"nansum": [ | |
{ | |
"avg_time_backward_nansum": 0.0408, | |
"avg_time_forward_nansum": 0.043, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_nansum": 0.2022, | |
"avg_time_forward_nansum": 0.1654, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"negative": [ | |
{ | |
"avg_time_forward_negative": 0.0141, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_negative": 0.0796, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"ones_like": [ | |
{ | |
"avg_time_forward_ones_like": 0.0136, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_ones_like": 0.0568, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"prod": [ | |
{ | |
"avg_time_backward_prod": 0.0398, | |
"avg_time_forward_prod": 0.0444, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_prod": 0.2135, | |
"avg_time_forward_prod": 0.1441, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"radians": [ | |
{ | |
"avg_time_backward_radians": 0.012, | |
"avg_time_forward_radians": 0.0144, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_radians": 0.0344, | |
"avg_time_forward_radians": 0.0399, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"random_exponential": [ | |
{ | |
"avg_time_forward__random_exponential": 2.3103, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_forward__random_exponential": 0.0564, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_exponential": 2.6538, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"random_gamma": [ | |
{ | |
"avg_time_forward__random_gamma": 6.9311, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_gamma": 0.1145, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_gamma": 6.5866, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_generalized_negative_binomial": [ | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 9.668, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 0.128, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__random_generalized_negative_binomial": 6.1451, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"random_negative_binomial": [ | |
{ | |
"avg_time_forward__random_negative_binomial": 5.0987, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_forward__random_negative_binomial": 0.0894, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_negative_binomial": 4.9121, | |
"inputs": { | |
"k": 1, | |
"p": 1, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"random_normal": [ | |
{ | |
"avg_time_forward__random_normal": 2.4695, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_normal": 0.0586, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_normal": 2.4081, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_poisson": [ | |
{ | |
"avg_time_forward__random_poisson": 2.0722, | |
"inputs": { | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_poisson": 0.0547, | |
"inputs": { | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_poisson": 2.0156, | |
"inputs": { | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"random_randint": [ | |
{ | |
"avg_time_forward__random_randint": 1.4471, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_randint": 0.0405, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_randint": 1.3344, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"random_uniform": [ | |
{ | |
"avg_time_forward__random_uniform": 0.5761, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__random_uniform": 0.0464, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_forward__random_uniform": 0.3409, | |
"inputs": { | |
"high": 5, | |
"low": 0, | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"rcbrt": [ | |
{ | |
"avg_time_backward_rcbrt": 0.0158, | |
"avg_time_forward_rcbrt": 0.0188, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_rcbrt": 0.4048, | |
"avg_time_forward_rcbrt": 0.4439, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"reciprocal": [ | |
{ | |
"avg_time_backward_reciprocal": 0.0134, | |
"avg_time_forward_reciprocal": 0.0166, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_reciprocal": 0.0353, | |
"avg_time_forward_reciprocal": 0.0406, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"relu": [ | |
{ | |
"avg_time_backward_relu": 0.0153, | |
"avg_time_forward_relu": 0.0188, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_relu": 0.0462, | |
"avg_time_forward_relu": 0.0466, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"rint": [ | |
{ | |
"avg_time_forward_rint": 0.0195, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_rint": 0.1472, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"round": [ | |
{ | |
"avg_time_forward_round": 0.0177, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_round": 0.1421, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 1000.0 | |
} | |
], | |
"rsqrt": [ | |
{ | |
"avg_time_backward_rsqrt": 0.0133, | |
"avg_time_forward_rsqrt": 0.0171, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_rsqrt": 0.1854, | |
"avg_time_forward_rsqrt": 0.1757, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sample_exponential": [ | |
{ | |
"avg_time_forward__sample_exponential": 3.093, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_exponential": 0.0856, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_exponential": 4.4416, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_gamma": [ | |
{ | |
"avg_time_forward__sample_gamma": 12.9143, | |
"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": 0.2091, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"beta": [ | |
1.0, | |
0.7 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__sample_gamma": 13.4562, | |
"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": 28.2741, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_generalized_negative_binomial": 0.3184, | |
"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": 27.1992, | |
"inputs": { | |
"alpha": [ | |
0.0, | |
2.5 | |
], | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4000.0 | |
} | |
], | |
"sample_negative_binomial": [ | |
{ | |
"avg_time_forward__sample_negative_binomial": 364.558, | |
"inputs": { | |
"k": [ | |
20, | |
49 | |
], | |
"p": [ | |
0.4, | |
0.77 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_negative_binomial": 3.4774, | |
"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": 342.8267, | |
"inputs": { | |
"k": [ | |
20, | |
49 | |
], | |
"p": [ | |
0.4, | |
0.77 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_normal": [ | |
{ | |
"avg_time_forward__sample_normal": 3.4717, | |
"inputs": { | |
"mu": [ | |
2.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
], | |
"sigma": [ | |
1.0, | |
3.7 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_normal": 0.0877, | |
"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": 4.637, | |
"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": 7.9577, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8388.6084 | |
}, | |
{ | |
"avg_time_forward__sample_poisson": 0.1218, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 80.0 | |
}, | |
{ | |
"avg_time_forward__sample_poisson": 6.4888, | |
"inputs": { | |
"lam": [ | |
1.0, | |
8.5 | |
], | |
"shape": [ | |
10000, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 8000.0 | |
} | |
], | |
"sample_uniform": [ | |
{ | |
"avg_time_forward__sample_uniform": 0.6759, | |
"inputs": { | |
"high": [ | |
1.0, | |
3.7 | |
], | |
"low": [ | |
0.0, | |
2.5 | |
], | |
"shape": [ | |
1024, | |
1024 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 4194.3042 | |
}, | |
{ | |
"avg_time_forward__sample_uniform": 0.0577, | |
"inputs": { | |
"high": [ | |
1.0, | |
3.7 | |
], | |
"low": [ | |
0.0, | |
2.5 | |
], | |
"shape": [ | |
10000, | |
1 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 40.0 | |
}, | |
{ | |
"avg_time_forward__sample_uniform": 1.1853, | |
"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": 0.0144, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward__shuffle": 0.2553, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sigmoid": [ | |
{ | |
"avg_time_backward_sigmoid": 0.0133, | |
"avg_time_forward_sigmoid": 0.0165, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sigmoid": 0.0322, | |
"avg_time_forward_sigmoid": 0.1964, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sign": [ | |
{ | |
"avg_time_backward_sign": 0.012, | |
"avg_time_forward_sign": 0.0154, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sign": 0.0356, | |
"avg_time_forward_sign": 0.0762, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sin": [ | |
{ | |
"avg_time_backward_sin": 0.0157, | |
"avg_time_forward_sin": 0.0197, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sin": 0.1633, | |
"avg_time_forward_sin": 0.1614, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sinh": [ | |
{ | |
"avg_time_backward_sinh": 0.0145, | |
"avg_time_forward_sinh": 0.0184, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sinh": 0.2366, | |
"avg_time_forward_sinh": 0.3828, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"size_array": [ | |
{ | |
"avg_time_forward_size_array": 0.0145, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.004 | |
}, | |
{ | |
"avg_time_forward_size_array": 0.0143, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.008 | |
} | |
], | |
"softmax": [ | |
{ | |
"avg_time_backward_softmax": 0.1024, | |
"avg_time_forward_softmax": 1.1571, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
1024, | |
1024 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2097.1521 | |
}, | |
{ | |
"avg_time_backward_softmax": 0.0385, | |
"avg_time_forward_softmax": 0.0491, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
1 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 20.0 | |
}, | |
{ | |
"avg_time_backward_softmax": 0.1032, | |
"avg_time_forward_softmax": 1.1213, | |
"inputs": { | |
"axis": -1, | |
"data": [ | |
10000, | |
100 | |
], | |
"temperature": 0.5 | |
}, | |
"max_storage_mem_alloc_cpu/0": 2000.0 | |
} | |
], | |
"softsign": [ | |
{ | |
"avg_time_backward_softsign": 0.0122, | |
"avg_time_forward_softsign": 0.0153, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_softsign": 0.0357, | |
"avg_time_forward_softsign": 0.0421, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sort": [ | |
{ | |
"avg_time_forward_sort": 0.1222, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.192 | |
}, | |
{ | |
"avg_time_forward_sort": 7.0136, | |
"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": 0.0588, | |
"inputs": { | |
"block_size": 2, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_space_to_depth": 0.305, | |
"inputs": { | |
"block_size": 5, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"sqrt": [ | |
{ | |
"avg_time_backward_sqrt": 0.0148, | |
"avg_time_forward_sqrt": 0.0191, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sqrt": 0.0352, | |
"avg_time_forward_sqrt": 0.2198, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"square": [ | |
{ | |
"avg_time_backward_square": 0.0139, | |
"avg_time_forward_square": 0.0174, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_square": 0.0375, | |
"avg_time_forward_square": 0.0431, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"stop_gradient": [ | |
{ | |
"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": 500.0 | |
} | |
], | |
"sum": [ | |
{ | |
"avg_time_backward_sum": 0.0318, | |
"avg_time_forward_sum": 0.0374, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_sum": 0.2916, | |
"avg_time_forward_sum": 0.1418, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"sum_axis": [ | |
{ | |
"avg_time_forward_sum": 0.0467, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_sum": 0.1572, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"swapaxes": [ | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 0, | |
"dim2": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 1, | |
"dim2": 2 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 2, | |
"dim2": 3 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"dim1": 3, | |
"dim2": 0 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
} | |
], | |
"tan": [ | |
{ | |
"avg_time_backward_tan": 0.0181, | |
"avg_time_forward_tan": 0.0235, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_tan": 0.0322, | |
"avg_time_forward_tan": 0.2816, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"tanh": [ | |
{ | |
"avg_time_backward_tanh": 0.0192, | |
"avg_time_forward_tanh": 0.0238, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_backward_tanh": 0.032, | |
"avg_time_forward_tanh": 0.3171, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"topk": [ | |
{ | |
"avg_time_forward_topk": 0.1038, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
], | |
"k": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.128 | |
}, | |
{ | |
"avg_time_forward_topk": 6.2361, | |
"inputs": { | |
"axis": 0, | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
], | |
"k": 1 | |
}, | |
"max_storage_mem_alloc_cpu/0": 50.0 | |
} | |
], | |
"transpose": [ | |
{ | |
"avg_time_forward_transpose": 0.0237, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_transpose": 0.0551, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"trunc": [ | |
{ | |
"avg_time_forward_trunc": 0.018, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_trunc": 0.088, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
], | |
"zeros_like": [ | |
{ | |
"avg_time_forward_zeros_like": 0.0205, | |
"inputs": { | |
"data": [ | |
1, | |
4, | |
2, | |
4 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 0.064 | |
}, | |
{ | |
"avg_time_forward_zeros_like": 0.0498, | |
"inputs": { | |
"data": [ | |
10, | |
25, | |
10, | |
100 | |
] | |
}, | |
"max_storage_mem_alloc_cpu/0": 500.0 | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment