Skip to content

Instantly share code, notes, and snippets.

@connorgoggins

connorgoggins/int64_tensor_flag_small_all_ops_cpu_5_warmup_5_runs.md Secret

Created February 28, 2020 23:04
Show Gist options
  • Save connorgoggins/4d8f74a3ee89e93abf689e5fdfcecc7e to your computer and use it in GitHub Desktop.
Save connorgoggins/4d8f74a3ee89e93abf689e5fdfcecc7e to your computer and use it in GitHub Desktop.
Download ZIP
Raw
int64_tensor_flag_small_all_ops_cpu_5_warmup_5_runs.md

Runtime Features

  1. BLAS_APPLE : ✖ BLAS_APPLE
  2. BLAS_ATLAS : ✖ BLAS_ATLAS
  3. BLAS_MKL : ✖ BLAS_MKL
  4. BLAS_OPEN : ✔ BLAS_OPEN
  5. CAFFE : ✖ CAFFE
  6. CPU_AVX : ✔ CPU_AVX
  7. CPU_AVX2 : ✖ CPU_AVX2
  8. CPU_SSE : ✔ CPU_SSE
  9. CPU_SSE2 : ✔ CPU_SSE2
  10. CPU_SSE3 : ✔ CPU_SSE3
  11. CPU_SSE4A : ✖ CPU_SSE4A
  12. CPU_SSE4_1 : ✔ CPU_SSE4_1
  13. CPU_SSE4_2 : ✔ CPU_SSE4_2
  14. CUDA : ✖ CUDA
  15. CUDA_RTC : ✖ CUDA_RTC
  16. CUDNN : ✖ CUDNN
  17. CXX14 : ✖ CXX14
  18. DEBUG : ✔ DEBUG
  19. DIST_KVSTORE : ✖ DIST_KVSTORE
  20. F16C : ✔ F16C
  21. INT64_TENSOR_SIZE : ✔ INT64_TENSOR_SIZE
  22. JEMALLOC : ✖ JEMALLOC
  23. LAPACK : ✔ LAPACK
  24. MKLDNN : ✖ MKLDNN
  25. NCCL : ✖ NCCL
  26. OPENCV : ✖ OPENCV
  27. OPENMP : ✔ OPENMP
  28. PROFILER : ✖ PROFILER
  29. SIGNAL_HANDLER : ✖ SIGNAL_HANDLER
  30. SSE : ✖ SSE
  31. TENSORRT : ✖ TENSORRT
  32. TVM_OP : ✖ TVM_OP

Benchmark Results

Operator Inputs Max Mem Usage (Storage) (Bytes) Avg Forward Time (ms) Avg. Backward Time (ms)
Activation {'data': (1024, 1024), 'act_type': 'relu'} 2384978.25 0.7228 0.865
Activation {'data': (1024, 1024), 'act_type': 'sigmoid'} 2389172.5 1.0898 0.5484
Activation {'data': (1024, 1024), 'act_type': 'softrelu'} 2393366.75 2.2916 1.4594
Activation {'data': (1024, 1024), 'act_type': 'softsign'} 2397561.25 0.3866 0.673
Activation {'data': (1024, 1024), 'act_type': 'tanh'} 2401755.5 2.7828 0.635
BatchNorm {'data': (32, 3, 256, 256), 'gamma': (3,), 'beta': (3,), 'moving_mean': (3,), 'moving_var': (3,), 'eps': 1e-08, 'axis': 1} 681461.125 115.42 63.3374
BatchNorm {'data': (32, 3, 10000, 10), 'gamma': (3,), 'beta': (3,), 'moving_mean': (3,), 'moving_var': (3,), 'eps': 1e-08, 'axis': 1} 719861.125 201.6882 110.1308
BilinearSampler {'data': (32, 2, 256, 256), 'grid': (32, 2, 256, 256)} 16777.2168 316.345 344.09
BlockGrad {'data': (1024, 1024)} 4194.3042 0.3772 ---
BlockGrad {'data': (10000, 1)} 20.0 0.0464 ---
BlockGrad {'data': (10000, 100)} 2000.0 0.3654 ---
CTCLoss {'data': (1024, 100, 100), 'label': (100, 100)} 2774390.5 79.762 ---
Convolution {'data': (32, 3, 64, 64), 'weight': (1, 3, 3, 3), 'bias': (1,), 'kernel': (3, 3), 'stride': (1, 1), 'dilate': (1, 1), 'pad': (0, 0), 'num_filter': 1, 'layout': 'NCHW'} 2630710.25 21.6526 46.2242
Correlation {'data1': (32, 3, 256, 256), 'data2': (32, 3, 256, 256), 'kernel_size': 3, 'max_displacement': 2, 'stride1': 2, 'stride2': 2} 806192.75 36433.4375 66967.7266
Correlation {'data1': (32, 3, 10000, 10), 'data2': (32, 3, 10000, 10), 'kernel_size': 3, 'max_displacement': 2, 'stride1': 2, 'stride2': 2} 821940.0625 25530.0332 43059.7461
Custom {'args': [(1024, 1024)], 'op_type': 'CustomAddOne'} 3090566.0 0.0156 0.024
Custom {'args': [(10000, 1)], 'op_type': 'CustomAddOne'} 3090566.0 0.0152 0.0242
Custom {'args': [(10000, 10)], 'op_type': 'CustomAddOne'} 3090566.0 0.015 0.0236
Deconvolution {'data': (32, 3, 64, 64), 'weight': (3, 1, 3, 3), 'bias': (1,), 'kernel': (3, 3), 'stride': (1, 1), 'pad': (0, 0), 'num_filter': 1, 'no_bias': False, 'layout': 'NCHW'} 2733708.75 45.7484 50.2232
Dropout {'data': (32, 3, 256, 256), 'p': 1, 'mode': 'always', 'axes': [0, 1]} 872533.8125 6.0944 5.1082
Dropout {'data': (10000, 10), 'p': 1, 'mode': 'always', 'axes': [0, 1]} 860350.9375 0.2554 0.2298
ElementWiseSum {'args': (1024, 1024)} 2097.1521 0.263 ---
Embedding {'data': (1024, 1024), 'weight': (3, 4), 'input_dim': 3, 'output_dim': 4, 'dtype': 'float32', 'sparse_grad': False} 885516.75 0.7202 ---
Embedding {'data': (10000, 1), 'weight': (3, 4), 'input_dim': 3, 'output_dim': 4, 'dtype': 'int32', 'sparse_grad': False} 877288.125 0.0738 ---
Embedding {'data': (10000, 100), 'weight': (3, 4), 'input_dim': 3, 'output_dim': 4, 'dtype': 'float32', 'sparse_grad': False} 893208.125 0.8232 ---
FullyConnected {'data': (32, 3, 256, 256), 'weight': (64, 196608), 'bias': (64,), 'num_hidden': 64, 'flatten': True} 885224.5 1.834 4.1142
FullyConnected {'data': (32, 3, 10000, 10), 'weight': (64, 10), 'bias': (64,), 'num_hidden': 64, 'flatten': False} 1130984.5 73.6848 227.4092
GridGenerator {'data': (32, 2, 256, 256), 'transform_type': 'warp', 'target_shape': (256, 6)} 8650.752 53.4568 37.5954
GridGenerator {'data': (256, 6), 'transform_type': 'affine', 'target_shape': (256, 6)} 1582.08 0.7358 0.233
GroupNorm {'data': (32, 3, 256, 256), 'gamma': (1,), 'beta': (1,), 'num_groups': 1, 'eps': 1e-08} 1181316.375 56.5254 772.9122
GroupNorm {'data': (32, 10, 10000, 10), 'gamma': (10,), 'beta': (10,), 'num_groups': 10, 'eps': 1e-08} 1431097.125 367.3502 1481.5076
InstanceNorm {'data': (32, 3, 256, 256), 'gamma': (3,), 'beta': (3,), 'eps': 1e-08} 1417429.625 75.6394 946.3446
InstanceNorm {'data': (32, 3, 10000, 10), 'gamma': (3,), 'beta': (3,), 'eps': 1e-08} 1455830.0 114.426 1387.3988
L2Normalization {'data': (32, 3, 256, 256), 'eps': 1e-08, 'mode': 'channel'} 1514550.25 98.5754 70.6352
L2Normalization {'data': (32, 3, 256, 256), 'eps': 1e-08, 'mode': 'instance'} 1539716.125 389.3556 37.6872
L2Normalization {'data': (32, 3, 256, 256), 'eps': 1e-08, 'mode': 'spatial'} 1564882.125 254.9056 54.3488
LRN {'data': (32, 3, 256, 256), 'alpha': 0.001, 'beta': 0.2, 'nsize': 3} 1640379.625 55.5114 106.595
LRN {'data': (32, 3, 10000, 10), 'alpha': 0.001, 'beta': 0.2, 'nsize': 3} 1697979.625 75.2792 151.8046
LayerNorm {'data': (32, 3, 256, 256), 'gamma': (32,), 'beta': (32,), 'axis': 0, 'eps': 1e-08} 1749884.125 70.3072 110.3524
LayerNorm {'data': (32, 3, 10000, 10), 'gamma': (32,), 'beta': (32,), 'axis': 0, 'eps': 1e-08} 1788697.625 94.5508 135.7664
LeakyReLU {'data': (1024, 1024), 'act_type': 'leaky'} 2408047.0 0.6562 0.8422
LeakyReLU {'data': (1024, 1024), 'act_type': 'elu'} 2412241.25 1.1406 0.8146
LeakyReLU {'data': (1024, 1024), 'act_type': 'selu'} 2416435.5 1.1348 0.7706
LeakyReLU {'data': (1024, 1024), 'act_type': 'gelu'} 2420629.75 1.276 2.518
LinearRegressionOutput {'data': (32, 3, 256, 256), 'label': (32, 3, 256, 256), 'grad_scale': 0.5} 1813863.5 1.671 ---
LinearRegressionOutput {'data': (32, 3, 10000, 10), 'label': (32, 3, 10000, 10), 'grad_scale': 0.5} 1852263.5 5.7176 ---
LogisticRegressionOutput {'data': (32, 3, 256, 256), 'label': (32, 3, 256, 256), 'grad_scale': 0.5} 1858229.375 6.4698 ---
LogisticRegressionOutput {'data': (32, 3, 10000, 10), 'label': (32, 3, 10000, 10), 'grad_scale': 0.5} 1896629.375 12.3032 ---
MAERegressionOutput {'data': (32, 3, 256, 256), 'label': (32, 3, 256, 256), 'grad_scale': 0.5} 1902595.125 1.2198 ---
MAERegressionOutput {'data': (32, 3, 10000, 10), 'label': (32, 3, 10000, 10), 'grad_scale': 0.5} 1940995.125 5.4376 ---
MakeLoss {'data': (1024, 1024), 'grad_scale': 0.5, 'normalization': 'batch'} 2760202.0 0.8252 0.533
MakeLoss {'data': (10000, 1), 'grad_scale': 0.5, 'normalization': 'batch'} 2758144.75 0.0852 0.0522
MakeLoss {'data': (10000, 100), 'grad_scale': 0.5, 'normalization': 'batch'} 2762124.75 0.7328 0.536
Pooling {'data': (32, 3, 64, 64), 'kernel': (3, 3), 'pool_type': 'sum', 'global_pool': 1, 'stride': (1, 1), 'pad': (0, 0)} 2613117.0 2.1902 4.168
RNN {'data': (1024, 4, 4), 'parameters': (21,), 'state': (1, 4, 1), 'mode': 'gru', 'state_size': 1, 'num_layers': 1} 631129.4375 4.9598 13.34
ROIPooling {'data': (32, 3, 64, 64), 'rois': (32, 5), 'pooled_size': (2, 2), 'spatial_scale': 0.5} 2613129.25 0.2276 0.2412
SVMOutput {'data': (32, 3, 256, 256), 'label': (32, 3, 256), 'margin': 0.5, 'regularization_coefficient': 0.5} 1959543.875 15.6004 626.5028
SVMOutput {'data': (32, 3, 10000, 10), 'label': (32, 3, 10000), 'margin': 0.5, 'regularization_coefficient': 0.5} 1985361.0 34.6542 989.042
SequenceLast {'data': (1024, 1024), 'axis': 0} 3090572.25 0.0806 ---
SequenceLast {'data': (10000, 1), 'axis': 0} 3090570.25 0.0662 ---
SequenceLast {'data': (10000, 100), 'axis': 0} 3090570.5 0.07 ---
SequenceMask {'data': (1024, 1024), 'axis': 0} 3098959.0 0.8606 0.8282
SequenceMask {'data': (10000, 1), 'axis': 0} 3098999.0 0.141 0.076
SequenceMask {'data': (10000, 100), 'axis': 0} 3102979.0 0.7812 0.8404
SequenceReverse {'data': (1024, 1024), 'axis': 0} 3111367.5 3.2912 3.4404
SequenceReverse {'data': (10000, 1), 'axis': 0} 3111407.5 0.08 0.068
SequenceReverse {'data': (10000, 100), 'axis': 0} 3115407.5 3.7258 3.6228
Softmax {'data': (1024, 1024), 'label': (1024, 1024), 'grad_scale': 0.5, 'normalization': 'batch'} 2426921.25 1.896 ---
Softmax {'data': (10000, 1), 'label': (10000, 1), 'grad_scale': 0.5, 'normalization': 'batch'} 2424864.25 0.0936 ---
Softmax {'data': (10000, 100), 'label': (10000, 100), 'grad_scale': 0.5, 'normalization': 'batch'} 2428844.25 1.8644 ---
SoftmaxActivation {'data': (1024, 1024)} 2435232.75 1.8788 5.9668
SoftmaxActivation {'data': (10000, 1)} 2435272.75 0.0892 0.137
SoftmaxActivation {'data': (10000, 100)} 2439272.75 1.836 5.7544
SoftmaxOutput {'data': (32, 3, 256, 256), 'label': (32, 3, 256), 'grad_scale': 0.5, 'normalization': 'batch'} 2003909.75 11.9566 20.0664
SoftmaxOutput {'data': (32, 3, 10000, 10), 'label': (32, 3, 10000), 'grad_scale': 0.5, 'normalization': 'batch'} 2029726.75 21.7382 32.387
SpatialTransformer {'data': (32, 3, 256, 6), 'loc': (32, 6), 'target_shape': (32, 6), 'transform_type': 'affine', 'sampler_type': 'bilinear'} 2010730.25 1.6454 1.7422
SpatialTransformer {'data': (256, 3, 10000, 6), 'loc': (256, 6), 'target_shape': (256, 6), 'transform_type': 'affine', 'sampler_type': 'bilinear'} 2017063.25 93.8736 123.4996
UpSampling {'args': (32, 3, 256, 256), 'scale': 2, 'sample_type': 'nearest'} 3029126.0 56.0206 14.326
UpSampling {'args': (32, 3, 10000, 1), 'scale': 4, 'sample_type': 'nearest'} 3090566.0 31.3164 4.368
abs {'data': (1024, 1024)} 2097.1521 0.3822 0.7348
abs {'data': (10000, 1)} 20.0 0.0594 0.047
abs {'data': (10000, 100)} 2000.0 0.3562 3.898
adam_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mean': (1024, 1024), 'var': (1024, 1024), 'lr': 0.1, 'beta1': 0.1, 'beta2': 0.1, 'epsilon': 1e-08, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0} 2637001.75 1.4958 ---
adam_update {'weight': (10000, 1), 'grad': (10000, 1), 'mean': (10000, 1), 'var': (10000, 1), 'lr': 0.5, 'beta1': 0.5, 'beta2': 0.5, 'epsilon': 1e-08, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0} 2634944.5 0.072 ---
adam_update {'weight': (10000, 100), 'grad': (10000, 100), 'mean': (10000, 100), 'var': (10000, 100), 'lr': 0.9, 'beta1': 0.9, 'beta2': 0.9, 'epsilon': 1e-08, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0} 2638924.5 1.691 ---
add_n {'args': [(1024, 1024)]} 2827799.5 0.0852 ---
add_n {'args': [(10000, 1)]} 2827799.5 0.0908 ---
add_n {'args': [(10000, 10)]} 2827799.5 0.088 ---
all_finite {'data': (1024, 1024)} 3115407.5 0.513 ---
all_finite {'data': (10000, 1)} 3115407.5 0.0512 ---
all_finite {'data': (10000, 100)} 3115407.5 0.4422 ---
amp_cast {'data': (1024, 1024), 'dtype': 'float32'} 4194.3042 10.4834 10.5186
amp_cast {'data': (10000, 1), 'dtype': 'int32'} 40.0 0.1928 0.1788
amp_cast {'data': (10000, 100), 'dtype': 'float32'} 4000.0 13.9772 13.9576
amp_multicast {'args': [(1024, 1024)], 'num_outputs': 1} 0.004 0.2156 0.2026
amp_multicast {'args': [(10000, 1)], 'num_outputs': 1} 0.004 0.2292 0.181
arccos {'data': (1024, 1024)} 2097.1521 1.6562 1.3386
arccos {'data': (10000, 1)} 20.0 0.1452 0.1288
arccos {'data': (10000, 100)} 2000.0 8.8986 5.639
arccosh {'data': (1024, 1024)} 2097.1521 1.1394 1.3064
arccosh {'data': (10000, 1)} 20.0 0.0616 0.069
arccosh {'data': (10000, 100)} 2000.0 0.9422 1.1244
arcsin {'data': (1024, 1024)} 2097.1521 1.2086 0.9062
arcsin {'data': (10000, 1)} 20.0 0.077 0.085
arcsin {'data': (10000, 100)} 2000.0 0.9846 0.7116
arcsinh {'data': (1024, 1024)} 2097.1521 1.6842 0.555
arcsinh {'data': (10000, 1)} 20.0 0.1352 0.0658
arcsinh {'data': (10000, 100)} 2000.0 1.583 0.4958
arctan {'data': (1024, 1024)} 2097.1521 1.1826 0.3882
arctan {'data': (10000, 1)} 20.0 0.0782 0.063
arctan {'data': (10000, 100)} 2000.0 1.1172 0.3486
arctanh {'data': (1024, 1024)} 2097.1521 1.545 0.453
arctanh {'data': (10000, 1)} 20.0 0.0818 0.0614
arctanh {'data': (10000, 100)} 2000.0 1.4678 0.3426
argmax {'data': (1024, 1024), 'axis': 0} 587563.5625 64.056 ---
argmax {'data': (10000, 1), 'axis': 0} 587561.5 0.5038 ---
argmax {'data': (10000, 100), 'axis': 0} 587561.875 47.991 ---
argmax_channel {'data': (1024, 1024)} 2.048 1.1966 ---
argmax_channel {'data': (10000, 1)} 20.0 0.1198 ---
argmax_channel {'data': (10000, 100)} 20.0 1.1084 ---
argmin {'data': (1024, 1024), 'axis': 0} 587565.8125 65.7178 ---
argmin {'data': (10000, 1), 'axis': 0} 587563.75 0.4894 ---
argmin {'data': (10000, 100), 'axis': 0} 587564.125 48.31 ---
argsort {'data': (1024, 1024), 'axis': 0, 'dtype': 'float32'} 593855.4375 139.7702 ---
argsort {'data': (10000, 1), 'axis': 0, 'dtype': 'int32'} 591798.25 4.1624 ---
argsort {'data': (10000, 100), 'axis': 0, 'dtype': 'float32'} 595778.25 139.1118 ---
batch_dot {'lhs': (32, 1024, 1024), 'rhs': (32, 1024, 1024)} 134217.7344 108.0773 ---
batch_dot {'lhs': (32, 1000, 10), 'rhs': (32, 1000, 10), 'transpose_b': True} 128000.0 29.1314 ---
batch_dot {'lhs': (32, 1000, 1), 'rhs': (32, 100, 1000), 'transpose_a': True, 'transpose_b': True} 6.4 1.0532 ---
broadcast_add {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3246 0.462
broadcast_add {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1634 0.2326
broadcast_add {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0758 0.0672
broadcast_div {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.352 0.7318
broadcast_div {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1008 0.1728
broadcast_div {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0806 0.0774
broadcast_equal {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.364 ---
broadcast_equal {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1016 ---
broadcast_equal {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.072 ---
broadcast_greater {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.5948 ---
broadcast_greater {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1164 ---
broadcast_greater {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0752 ---
broadcast_greater_equal {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.545 ---
broadcast_greater_equal {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.119 ---
broadcast_greater_equal {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.073 ---
broadcast_hypot {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.7428 1.1842
broadcast_hypot {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.133 0.2014
broadcast_hypot {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0782 0.0878
broadcast_lesser {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.5408 ---
broadcast_lesser {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.118 ---
broadcast_lesser {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0726 ---
broadcast_lesser_equal {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.5238 ---
broadcast_lesser_equal {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.117 ---
broadcast_lesser_equal {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0736 ---
broadcast_logical_and {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3152 ---
broadcast_logical_and {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0986 ---
broadcast_logical_and {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0886 ---
broadcast_logical_or {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.2852 ---
broadcast_logical_or {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0962 ---
broadcast_logical_or {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0728 ---
broadcast_logical_xor {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.353 ---
broadcast_logical_xor {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1 ---
broadcast_logical_xor {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0738 ---
broadcast_maximum {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.6752 1.1148
broadcast_maximum {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.129 0.1938
broadcast_maximum {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0778 0.08
broadcast_minimum {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.6984 1.1264
broadcast_minimum {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1392 0.1816
broadcast_minimum {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0792 0.0796
broadcast_minus {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.2866 ---
broadcast_minus {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0958 ---
broadcast_minus {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0708 ---
broadcast_mod {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 1.927 0.614
broadcast_mod {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.261 0.1556
broadcast_mod {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.091 0.0774
broadcast_mul {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3386 0.6104
broadcast_mul {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.098 0.138
broadcast_mul {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.076 0.0768
broadcast_not_equal {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3224 ---
broadcast_not_equal {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1526 ---
broadcast_not_equal {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0732 ---
broadcast_plus {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.2888 ---
broadcast_plus {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0956 ---
broadcast_plus {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0732 ---
broadcast_power {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 2.3882 4.8424
broadcast_power {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.3156 0.5312
broadcast_power {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0988 0.1278
broadcast_sub {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3428 0.3946
broadcast_sub {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1146 0.1008
broadcast_sub {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0756 0.067
cast {'data': (1024, 1024), 'dtype': 'float32'} 2097.1521 --- 9.0584
cast {'data': (10000, 1), 'dtype': 'int32'} 20.0 --- 0.1752
cast {'data': (10000, 100), 'dtype': 'float32'} 2000.0 --- 9.3458
cast_storage {'data': (1024, 1024), 'stype': 'default'} 3121699.0 0.3788 ---
cast_storage {'data': (10000, 1), 'stype': 'csr'} 3119802.0 0.1914 ---
cast_storage {'data': (10000, 100), 'stype': 'row_sparse'} 3123782.0 1.4672 ---
cbrt {'data': (1024, 1024)} 2097.1521 1.75 0.568
cbrt {'data': (10000, 1)} 20.0 0.1388 0.1018
cbrt {'data': (10000, 100)} 2000.0 1.6354 0.531
ceil {'data': (1024, 1024)} 2097.1521 0.4062 ---
ceil {'data': (10000, 1)} 20.0 0.0482 ---
ceil {'data': (10000, 100)} 2000.0 0.3962 ---
choose_element_0index {'data': (1024, 1024), 'index': (1, 1024), 'axis': 0} 2.048 0.0712 ---
choose_element_0index {'data': (10000, 1), 'index': (1, 1), 'axis': 0} 0.002 0.0664 ---
choose_element_0index {'data': (10000, 100), 'index': (1, 100), 'axis': 0} 0.2 0.0676 ---
clip {'data': (1024, 1024), 'a_min': 0.1, 'a_max': 0.9} 3130130.5 0.6922 0.7268
clip {'data': (10000, 1), 'a_min': 0.1, 'a_max': 0.9} 3130170.5 0.0574 0.0464
clip {'data': (10000, 100), 'a_min': 0.1, 'a_max': 0.9} 3134150.5 0.6488 0.6738
col2im {'data': (32, 64, 256), 'output_size': (64, 16, 1), 'kernel': (1, 1, 1), 'stride': (2, 2, 2)} 2029646.125 166.2192 162.1108
col2im {'data': (32, 64, 256), 'output_size': (32, 8, 1), 'kernel': (1, 1, 1), 'stride': (1, 1, 1)} 2031743.25 175.4904 155.4888
cos {'data': (1024, 1024)} 2097.1521 0.9848 1.1088
cos {'data': (10000, 1)} 20.0 0.0616 0.0554
cos {'data': (10000, 100)} 2000.0 0.9174 1.0262
cosh {'data': (1024, 1024)} 2097.1521 1.2668 2.0346
cosh {'data': (10000, 1)} 20.0 0.1184 0.0736
cosh {'data': (10000, 100)} 2000.0 1.1884 1.8682
ctc_loss {'data': (1024, 100, 100), 'label': (100, 100)} 2821565.25 85.396 ---
cumsum {'a': (1024, 1024), 'axis': 0, 'dtype': 'float32'} 3140442.0 0.997 ---
cumsum {'a': (1024, 1024), 'axis': 0, 'dtype': 'int32'} 3142539.25 1.0286 ---
cumsum {'a': (1024, 1024), 'axis': 0, 'dtype': 'float32'} 3144636.25 1.024 ---
degrees {'data': (1024, 1024)} 2097.1521 0.4248 0.439
degrees {'data': (10000, 1)} 20.0 0.0746 0.0662
degrees {'data': (10000, 100)} 2000.0 0.3282 0.3908
depth_to_space {'data': (1, 4, 2, 4), 'block_size': 2} 600037.0625 0.0542 ---
depth_to_space {'data': (10, 25, 10, 100), 'block_size': 5} 601037.0 1.5644 ---
dot {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 2.3748 5.0332
dot {'lhs': (1000, 10), 'rhs': (1000, 10), 'transpose_b': True} 2000.0 0.284 0.3936
dot {'lhs': (1000, 1), 'rhs': (100, 1000), 'transpose_a': True, 'transpose_b': True} 0.2 0.2288 0.1886
elemwise_add {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.2972 ---
elemwise_add {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0982 ---
elemwise_add {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.1844 ---
elemwise_div {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.296 ---
elemwise_div {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1128 ---
elemwise_div {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0862 ---
elemwise_mul {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.304 ---
elemwise_mul {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.0918 ---
elemwise_mul {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.071 ---
elemwise_sub {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.3036 ---
elemwise_sub {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.224 ---
elemwise_sub {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.078 ---
erf {'data': (1024, 1024)} 2097.1521 1.1984 0.8734
erf {'data': (10000, 1)} 20.0 0.0782 0.0616
erf {'data': (10000, 100)} 2000.0 1.1964 0.8418
erfinv {'data': (1024, 1024)} 2097.1521 4.2082 1.4468
erfinv {'data': (10000, 1)} 20.0 0.0902 0.0522
erfinv {'data': (10000, 100)} 2000.0 4.0388 1.3642
exp {'data': (1024, 1024)} 2097.1521 1.4502 ---
exp {'data': (10000, 1)} 20.0 0.082 ---
exp {'data': (10000, 100)} 2000.0 1.2132 ---
expm1 {'data': (1024, 1024)} 2097.1521 1.4518 1.1002
expm1 {'data': (10000, 1)} 20.0 0.0636 0.0932
expm1 {'data': (10000, 100)} 2000.0 1.3678 1.046
fill_element_0index {'lhs': (1024, 1024), 'mhs': (1024,), 'rhs': (1024,)} 3148830.5 0.7684 ---
fill_element_0index {'lhs': (10000, 1), 'mhs': (10000,), 'rhs': (10000,)} 3146773.5 0.0364 ---
fill_element_0index {'lhs': (10000, 100), 'mhs': (10000,), 'rhs': (10000,)} 3150753.5 0.7308 ---
fix {'data': (1024, 1024)} 2097.1521 0.9952 ---
fix {'data': (10000, 1)} 20.0 0.059 ---
fix {'data': (10000, 100)} 2000.0 0.9328 ---
flatten {'data': (1024, 1024)} 2097.1521 0.3774 ---
flatten {'data': (10000, 1)} 20.0 0.0404 ---
flatten {'data': (10000, 100)} 2000.0 0.389 ---
flip {'data': (1024, 1024), 'axis': 0} 606828.4375 2.9712 ---
flip {'data': (10000, 1), 'axis': 0} 604771.3125 0.085 ---
flip {'data': (10000, 100), 'axis': 0} 608751.3125 2.8574 ---
floor {'data': (1024, 1024)} 2097.1521 0.3952 ---
floor {'data': (10000, 1)} 20.0 0.046 ---
floor {'data': (10000, 100)} 2000.0 0.3772 ---
ftml_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'd': (1024, 1024), 'v': (1024, 1024), 'z': (1024, 1024), 'lr': 0.1, 'beta1': 0.1, 'beta2': 0.1, 'epsilon': 1e-08, 't': 1, 'wd': 0.1, 'rescale_grad': 0.4, 'clip_grad': -1.0} 2643216.0 2.788 ---
ftml_update {'weight': (10000, 1), 'grad': (10000, 1), 'd': (10000, 1), 'v': (10000, 1), 'z': (10000, 1), 'lr': 0.5, 'beta1': 0.5, 'beta2': 0.5, 'epsilon': 1e-08, 't': 1, 'wd': 0.5, 'rescale_grad': 0.4, 'clip_grad': -1.0} 2641158.75 0.1028 ---
ftml_update {'weight': (10000, 100), 'grad': (10000, 100), 'd': (10000, 100), 'v': (10000, 100), 'z': (10000, 100), 'lr': 0.9, 'beta1': 0.9, 'beta2': 0.9, 'epsilon': 1e-08, 't': 1, 'wd': 0.9, 'rescale_grad': 0.4, 'clip_grad': -1.0} 2645138.75 2.9468 ---
ftrl_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'z': (1024, 1024), 'n': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4} 2649430.25 3.4112 ---
ftrl_update {'weight': (10000, 1), 'grad': (10000, 1), 'z': (10000, 1), 'n': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4} 2647373.0 0.173 ---
ftrl_update {'weight': (10000, 100), 'grad': (10000, 100), 'z': (10000, 100), 'n': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4} 2651353.0 3.2252 ---
gamma {'data': (1024, 1024)} 2097.1521 4.0916 9.2046
gamma {'data': (10000, 1)} 20.0 0.0986 0.132
gamma {'data': (10000, 100)} 2000.0 3.8948 8.7606
gammaln {'data': (1024, 1024)} 2097.1521 33.7642 5.6866
gammaln {'data': (10000, 1)} 20.0 0.3732 0.0958
gammaln {'data': (10000, 100)} 2000.0 32.1908 5.3906
gather_nd {'data': (1024, 1024), 'indices': (1, 1)} 617589.0 0.0622 ---
gather_nd {'data': (10000, 1), 'indices': (1, 1)} 617587.0 0.0592 ---
gather_nd {'data': (10000, 100), 'indices': (1, 1)} 617587.375 0.0586 ---
hard_sigmoid {'data': (1024, 1024)} 2447661.25 0.529 0.5338
hard_sigmoid {'data': (10000, 1)} 2447701.25 0.0678 0.0586
hard_sigmoid {'data': (10000, 100)} 2451701.25 0.5096 0.5496
identity {'data': (1024, 1024)} 2097.1521 0.3722 ---
identity {'data': (10000, 1)} 20.0 0.0402 ---
identity {'data': (10000, 100)} 2000.0 0.3758 ---
im2col {'data': (32, 3, 256, 256), 'kernel': (3,), 'stride': (1,), 'dilate': (1,), 'pad': (1,)} 2031137.125 7.9486 7.9328
im2col {'data': (32, 3, 10000, 10), 'kernel': (3, 3), 'stride': (1, 1), 'dilate': (1, 1), 'pad': (1, 1)} 2376589.75 723.5026 640.7732
khatri_rao {'args': [(32, 32), (32, 32)]} 0.008 0.1252 ---
khatri_rao {'args': [(64, 64), (64, 64)]} 0.008 0.121 ---
lamb_update_phase1 {'weight': (1024, 1024), 'grad': (1024, 1024), 'mean': (1024, 1024), 'var': (1024, 1024), 'beta1': 0.1, 'beta2': 0.1, 'epsilon': 1e-08, 't': 1, 'wd': 0.1, 'rescale_grad': 0.4} 2651450.25 2.1784 ---
lamb_update_phase1 {'weight': (10000, 1), 'grad': (10000, 1), 'mean': (10000, 1), 'var': (10000, 1), 'beta1': 0.5, 'beta2': 0.5, 'epsilon': 1e-08, 't': 1, 'wd': 0.5, 'rescale_grad': 0.4} 2651490.25 0.0866 ---
lamb_update_phase1 {'weight': (10000, 100), 'grad': (10000, 100), 'mean': (10000, 100), 'var': (10000, 100), 'beta1': 0.9, 'beta2': 0.9, 'epsilon': 1e-08, 't': 1, 'wd': 0.9, 'rescale_grad': 0.4} 2655470.25 2.496 ---
lamb_update_phase2 {'weight': (1024, 1024), 'g': (1024, 1024), 'r1': (1, 1024), 'r2': (1, 1024), 'lr': 0.1} 2659761.75 0.7232 ---
lamb_update_phase2 {'weight': (10000, 1), 'g': (10000, 1), 'r1': (1, 1), 'r2': (1, 1), 'lr': 0.5} 2657704.5 0.1018 ---
lamb_update_phase2 {'weight': (10000, 100), 'g': (10000, 100), 'r1': (1, 100), 'r2': (1, 100), 'lr': 0.9} 2661684.5 0.7038 ---
linalg_det {'A': (1024, 1024)} 3175943.5 5.9172 19.5508
linalg_extractdiag {'A': (1024, 1024)} 3175951.5 0.0566 0.2288
linalg_extracttrian {'A': (1024, 1024)} 3180150.0 1.1282 1.216
linalg_gelqf {'A': (1024, 1024)} 3192733.0 27.5024 ---
linalg_gemm {'A': (1024, 1024), 'B': (1024, 1024), 'C': (1024, 1024), 'axis': 0} 3196927.25 3.2726 5.8474
linalg_gemm2 {'A': (1024, 1024), 'B': (1024, 1024), 'axis': 0} 3205315.75 2.257 4.7474
linalg_inverse {'A': (1024, 1024)} 3213704.5 13.4066 5.2376
linalg_makediag {'A': (1024, 1024)} 11803639.0 528.0402 9.9892
linalg_maketrian {'A': (1024, 1035)} 11820228.0 3.2908 2.8376
linalg_potrf {'A': [[1, 0], [0, 1]]} 3171745.0 0.0538 ---
linalg_potrf {'A': [[2, -1, 0], [-1, 2, -1], [0, -1, 2]]} 3171745.0 0.0516 ---
linalg_potri {'A': (1024, 1024)} 11828616.0 11.3698 7.07
linalg_slogdet {'A': (1024, 1024)} 11832815.0 6.5328 ---
linalg_sumlogdiag {'A': (1024, 1024)} 11832815.0 0.1038 0.9028
linalg_syrk {'A': (1024, 1024)} 11841203.0 3.2556 4.3508
linalg_trmm {'A': (1024, 1024), 'B': (1024, 1024)} 11849592.0 2.3468 4.6616
linalg_trsm {'A': (1024, 1024), 'B': (1024, 1024)} 11857981.0 2.0618 4.5612
log {'data': (1024, 1024)} 2097.1521 1.2138 0.4834
log {'data': (10000, 1)} 20.0 0.0674 0.0482
log {'data': (10000, 100)} 2000.0 1.1498 0.4456
log10 {'data': (1024, 1024)} 2097.1521 1.3328 0.4118
log10 {'data': (10000, 1)} 20.0 0.0642 0.0466
log10 {'data': (10000, 100)} 2000.0 1.2618 0.4046
log1p {'data': (1024, 1024)} 2097.1521 1.398 0.473
log1p {'data': (10000, 1)} 20.0 0.0612 0.0478
log1p {'data': (10000, 100)} 2000.0 1.3154 0.4492
log2 {'data': (1024, 1024)} 2097.1521 2.9748 2.0772
log2 {'data': (10000, 1)} 20.0 0.132 0.1216
log2 {'data': (10000, 100)} 2000.0 1.9858 1.2906
log_softmax {'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'} 2452847.0 4.536 3.4868
log_softmax {'data': (10000, 1), 'axis': 0, 'dtype': 'float32'} 2451838.5 0.654 0.4032
log_softmax {'data': (10000, 100), 'axis': 0, 'dtype': 'float64'} 2459838.5 4.3886 4.1634
logical_not {'data': (1024, 1024)} 2097.1521 0.3424 ---
logical_not {'data': (10000, 1)} 20.0 0.0492 ---
logical_not {'data': (10000, 100)} 2000.0 0.3182 ---
make_loss {'data': (1024, 1024)} 2097.1521 0.3642 ---
make_loss {'data': (10000, 1)} 20.0 0.0408 ---
make_loss {'data': (10000, 100)} 2000.0 0.4446 ---
max {'data': (1024, 1024), 'axis': 0} 587490.0625 3.3924 5.2954
max {'data': (10000, 1), 'axis': 0} 587490.0625 0.8132 0.11
max {'data': (10000, 100), 'axis': 0} 587490.5 3.9074 5.5152
max_axis {'data': (1024, 1024), 'axis': 0} 587496.625 3.3214 ---
max_axis {'data': (10000, 1), 'axis': 0} 587494.5625 0.8142 ---
max_axis {'data': (10000, 100), 'axis': 0} 587495.0 3.8072 ---
mean {'data': (1024, 1024), 'axis': 0} 587503.0 3.8338 20.7358
mean {'data': (10000, 1), 'axis': 0} 587503.0 0.6252 0.2456
mean {'data': (10000, 100), 'axis': 0} 587503.375 3.3154 19.4032
min {'data': (1024, 1024), 'axis': 0} 587511.5625 3.3796 5.4618
min {'data': (10000, 1), 'axis': 0} 587511.5625 0.8098 0.1218
min {'data': (10000, 100), 'axis': 0} 587512.0 3.8844 5.1848
min_axis {'data': (1024, 1024), 'axis': 0} 587518.125 3.3462 ---
min_axis {'data': (10000, 1), 'axis': 0} 587516.0625 0.7914 ---
min_axis {'data': (10000, 100), 'axis': 0} 587516.5 3.8136 ---
moments {'data': (1024, 1024), 'axes': [0, 1]} 11857981.0 117.5186 ---
moments {'data': (10000, 1), 'axes': [0, 1]} 11857981.0 1.3184 ---
moments {'data': (10000, 100), 'axes': [0, 1]} 11857981.0 128.3984 ---
mp_nag_mom_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'weight32': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4} 2665976.0 1.2092 ---
mp_nag_mom_update {'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'weight32': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4} 2663918.75 0.0652 ---
mp_nag_mom_update {'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'weight32': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4} 2667898.75 1.1104 ---
mp_sgd_mom_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'weight32': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0} 2672190.25 0.9882 ---
mp_sgd_mom_update {'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'weight32': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0} 2670133.25 0.0678 ---
mp_sgd_mom_update {'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'weight32': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0} 2674113.25 0.9142 ---
mp_sgd_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'weight32': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0} 2678404.5 0.7132 ---
mp_sgd_update {'weight': (10000, 1), 'grad': (10000, 1), 'weight32': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0} 2676347.5 0.0616 ---
mp_sgd_update {'weight': (10000, 100), 'grad': (10000, 100), 'weight32': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0} 2680327.5 0.688 ---
multi_all_finite {'args': [(1024, 1024)], 'num_arrays': 1} 2827799.5 0.0698 ---
multi_all_finite {'args': [(10000, 1)], 'num_arrays': 1} 2827799.5 0.0626 ---
multi_all_finite {'args': [(10000, 10)], 'num_arrays': 1} 2827799.5 0.0576 ---
multi_lars {'lrs': (1024, 1024), 'weights_sum_sq': (1024, 1024), 'grads_sum_sq': (1024, 1024), 'wds': (1024, 1024), 'eta': 0.5, 'eps': 1e-08, 'rescale_grad': 0.4} 3155045.0 1.324 ---
multi_lars {'lrs': (10000, 1), 'weights_sum_sq': (10000, 1), 'grads_sum_sq': (10000, 1), 'wds': (10000, 1), 'eta': 0.5, 'eps': 1e-08, 'rescale_grad': 0.4} 3152987.75 0.0646 ---
multi_lars {'lrs': (10000, 100), 'weights_sum_sq': (10000, 100), 'grads_sum_sq': (10000, 100), 'wds': (10000, 100), 'eta': 0.5, 'eps': 1e-08, 'rescale_grad': 0.4} 3156967.75 1.2024 ---
multi_mp_sgd_mom_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'args3': '<NDArray 5x5 @cpu(0)>', 'lrs': 0.1, 'wds': 0.2, 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0735 ---
multi_mp_sgd_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'lrs': 0.1, 'wds': 0.2, 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.05 ---
multi_sgd_mom_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'lrs': 0.1, 'wds': 0.2, 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0649 ---
multi_sgd_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'lrs': 0.1, 'wds': 0.2, 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.049 ---
multi_sum_sq {'args': [(1024, 1024)], 'num_arrays': 1} 2827799.5 0.0626 ---
multi_sum_sq {'args': [(10000, 1)], 'num_arrays': 1} 2827799.5 0.0496 ---
multi_sum_sq {'args': [(10000, 10)], 'num_arrays': 1} 2827799.5 0.0678 ---
nag_mom_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4} 2684619.0 1.0912 ---
nag_mom_update {'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4} 2682561.75 0.0634 ---
nag_mom_update {'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4} 2686541.75 0.9898 ---
nanprod {'data': (1024, 1024), 'axis': 0} 587520.375 3.7316 5.61
nanprod {'data': (10000, 1), 'axis': 0} 587520.375 0.862 0.1084
nanprod {'data': (10000, 100), 'axis': 0} 587520.75 4.0956 5.4066
nansum {'data': (1024, 1024), 'axis': 0} 587528.9375 3.633 5.6082
nansum {'data': (10000, 1), 'axis': 0} 587529.0 0.8506 0.1206
nansum {'data': (10000, 100), 'axis': 0} 587529.375 3.648 5.2664
negative {'data': (1024, 1024)} 2097.1521 0.3028 ---
negative {'data': (10000, 1)} 20.0 0.0574 ---
negative {'data': (10000, 100)} 2000.0 0.2932 ---
norm {'data': (1024, 1024), 'axis': 0} 587537.5625 3.726 5.2912
norm {'data': (10000, 1), 'axis': 0} 587537.5625 0.8956 0.1078
norm {'data': (10000, 100), 'axis': 0} 587537.9375 3.8384 5.1258
one_hot {'indices': (1, 1), 'depth': 0, 'dtype': 'float32'} --- 0.0294 ---
one_hot {'indices': (1, 1), 'depth': 0, 'dtype': 'int32'} --- 0.0306 ---
one_hot {'indices': (1, 1), 'depth': 0, 'dtype': 'float32'} --- 0.0298 ---
ones_like {'data': (1024, 1024)} 2097.1521 0.19 ---
ones_like {'data': (10000, 1)} 20.0 0.0458 ---
ones_like {'data': (10000, 100)} 2000.0 0.186 ---
pick {'data': (1024, 1024), 'index': (1, 1024), 'axis': 0} 617593.3125 0.0746 9.2106
pick {'data': (10000, 1), 'index': (1, 1), 'axis': 0} 617591.25 0.068 0.1952
pick {'data': (10000, 100), 'index': (1, 100), 'axis': 0} 617591.6875 0.071 8.7896
preloaded_multi_mp_sgd_mom_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'args3': '<NDArray 5x5 @cpu(0)>', 'args4': '<NDArray 1 @cpu(0)>', 'args5': '<NDArray 1 @cpu(0)>', 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0583 ---
preloaded_multi_mp_sgd_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'args3': '<NDArray 1 @cpu(0)>', 'args4': '<NDArray 1 @cpu(0)>', 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0474 ---
preloaded_multi_sgd_mom_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args2': '<NDArray 5x5 @cpu(0)>', 'args3': '<NDArray 1 @cpu(0)>', 'args4': '<NDArray 1 @cpu(0)>', 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0479 ---
preloaded_multi_sgd_update {'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'args4': '<NDArray 1 @cpu(0)>', 'args5': '<NDArray 1 @cpu(0)>', 'out': '<NDArray 5x5 @cpu(0)>'} --- 0.0515 ---
prod {'data': (1024, 1024), 'axis': 0} 587546.1875 3.291 5.398
prod {'data': (10000, 1), 'axis': 0} 587546.1875 0.7594 0.1114
prod {'data': (10000, 100), 'axis': 0} 587546.5625 3.7298 5.253
radians {'data': (1024, 1024)} 2097.1521 0.3608 0.4092
radians {'data': (10000, 1)} 20.0 0.0566 0.0502
radians {'data': (10000, 100)} 2000.0 0.3328 0.4018
random_exponential {'shape': (1024, 1024), 'dtype': 'float16'} 1048.576 12.9418 ---
random_exponential {'shape': (10000, 1), 'dtype': 'float32'} 20.0 0.2164 ---
random_exponential {'shape': (10000, 100), 'dtype': 'float64'} 4000.0 12.127 ---
random_gamma {'shape': (1024, 1024), 'dtype': 'float16'} 1048.576 39.3618 ---
random_gamma {'shape': (10000, 1), 'dtype': 'float32'} 20.0 0.4488 ---
random_gamma {'shape': (10000, 100), 'dtype': 'float64'} 4837.3179 46.6734 ---
random_generalized_negative_binomial {'shape': (1024, 1024), 'dtype': 'float16'} 3983.0459 44.0244 ---
random_generalized_negative_binomial {'shape': (10000, 1), 'dtype': 'float32'} 2974.47 0.5508 ---
random_generalized_negative_binomial {'shape': (10000, 100), 'dtype': 'float64'} 10954.4697 41.6416 ---
random_negative_binomial {'k': 1, 'p': 1, 'shape': (1024, 1024), 'dtype': 'float16'} 10100.1982 35.816 ---
random_negative_binomial {'k': 1, 'p': 1, 'shape': (10000, 1), 'dtype': 'float32'} 9091.6221 0.4622 ---
random_negative_binomial {'k': 1, 'p': 1, 'shape': (10000, 100), 'dtype': 'float64'} 17071.6211 33.9036 ---
random_normal {'shape': (1024, 1024), 'dtype': 'float16'} 16217.3496 20.4122 ---
random_normal {'shape': (10000, 1), 'dtype': 'float32'} 15208.7744 0.2602 ---
random_normal {'shape': (10000, 100), 'dtype': 'float64'} 23188.7734 19.3882 ---
random_pdf_dirichlet {'sample': (2,), 'alpha': [0.0, 2.5]} 19188.7793 0.0716 ---
random_pdf_exponential {'sample': (2,), 'lam': [1.0, 8.5]} 19188.7891 0.07 ---
random_pdf_gamma {'sample': (2,), 'alpha': [0.0, 2.5], 'beta': [1.0, 0.7]} 19188.7988 0.0744 ---
random_pdf_generalized_negative_binomial {'sample': (2,), 'mu': [2.0, 2.5], 'alpha': [0.0, 2.5]} 19188.8066 0.0744 ---
random_pdf_negative_binomial {'sample': (2,), 'k': [20, 49], 'p': [0.4, 0.77]} 19188.8145 0.0744 ---
random_pdf_normal {'sample': (2,), 'mu': [2.0, 2.5], 'sigma': [1.0, 3.7]} 19188.8223 0.0732 ---
random_pdf_poisson {'sample': (2,), 'lam': [1.0, 8.5]} 19188.8301 0.1466 ---
random_pdf_uniform {'sample': (2,), 'low': [0.0, 2.5], 'high': [1.0, 3.7]} 19188.8379 0.0706 ---
random_poisson {'shape': (1024, 1024), 'dtype': 'float16'} 22334.5625 14.8466 ---
random_poisson {'shape': (10000, 1), 'dtype': 'float32'} 21325.9863 0.2366 ---
random_poisson {'shape': (10000, 100), 'dtype': 'float64'} 29305.9863 14.1912 ---
random_randint {'low': 0, 'high': 5, 'shape': (1024, 1024), 'dtype': 'int32'} 31597.4414 3.1232 ---
random_randint {'low': 0, 'high': 5, 'shape': (10000, 1), 'dtype': 'int64'} 29580.2891 0.1406 ---
random_randint {'low': 0, 'high': 5, 'shape': (10000, 100), 'dtype': 'int32'} 33540.2891 3.0268 ---
random_uniform {'low': 0, 'high': 5, 'shape': (1024, 1024), 'dtype': 'float16'} 34686.0195 8.9082 ---
random_uniform {'low': 0, 'high': 5, 'shape': (10000, 1), 'dtype': 'float32'} 33677.4414 0.1992 ---
random_uniform {'low': 0, 'high': 5, 'shape': (10000, 100), 'dtype': 'float64'} 41657.4414 8.2722 ---
ravel_multi_index {'data': (2, 1024), 'shape': (1024, 1024)} 617597.625 0.0718 ---
ravel_multi_index {'data': (2, 1024), 'shape': (10000, 1)} 617599.6875 0.0724 ---
ravel_multi_index {'data': (2, 1024), 'shape': (10000, 100)} 617601.6875 0.0714 ---
rcbrt {'data': (1024, 1024)} 2097.1521 1.836 1.8906
rcbrt {'data': (10000, 1)} 20.0 0.0786 0.0912
rcbrt {'data': (10000, 100)} 2000.0 1.6758 1.7738
reciprocal {'data': (1024, 1024)} 2097.1521 0.3438 0.5528
reciprocal {'data': (10000, 1)} 20.0 0.0534 0.047
reciprocal {'data': (10000, 100)} 2000.0 0.3366 0.5098
relu {'data': (1024, 1024)} 2097.1521 0.7492 0.8506
relu {'data': (10000, 1)} 20.0 0.0568 0.0552
relu {'data': (10000, 100)} 2000.0 0.6692 0.779
reset_arrays {'args': [(1024, 1024)], 'num_arrays': 1} --- 0.0384 ---
reset_arrays {'args': [(10000, 1)], 'num_arrays': 1} --- 0.0362 ---
reset_arrays {'args': [(10000, 10)], 'num_arrays': 1} --- 0.0342 ---
reshape_like {'lhs': (1024, 1024), 'rhs': (1024, 1024)} 2097.1521 0.4662 ---
reshape_like {'lhs': (10000, 10), 'rhs': (10000, 10)} 200.0 0.1112 ---
reshape_like {'lhs': (10000, 1), 'rhs': (10000, 1)} 20.0 0.0642 ---
rint {'data': (1024, 1024)} 2097.1521 0.9964 ---
rint {'data': (10000, 1)} 20.0 0.0598 ---
rint {'data': (10000, 100)} 2000.0 0.9402 ---
rmsprop_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'n': (1024, 1024), 'lr': 0.1, 'gamma1': 0.1, 'epsilon': 1e-08, 'wd': 0.1, 'rescale_grad': 0.4} 2690833.25 1.4616 ---
rmsprop_update {'weight': (10000, 1), 'grad': (10000, 1), 'n': (10000, 1), 'lr': 0.5, 'gamma1': 0.5, 'epsilon': 1e-08, 'wd': 0.5, 'rescale_grad': 0.4} 2688776.0 0.07 ---
rmsprop_update {'weight': (10000, 100), 'grad': (10000, 100), 'n': (10000, 100), 'lr': 0.9, 'gamma1': 0.9, 'epsilon': 1e-08, 'wd': 0.9, 'rescale_grad': 0.4} 2692756.0 1.608 ---
rmspropalex_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'n': (1024, 1024), 'g': (1024, 1024), 'delta': (1024, 1024), 'lr': 0.1, 'gamma1': 0.1, 'gamma2': 0.1, 'epsilon': 1e-08, 'wd': 0.1, 'rescale_grad': 0.4} 2694950.5 2.069 ---
rmspropalex_update {'weight': (10000, 1), 'grad': (10000, 1), 'n': (10000, 1), 'g': (10000, 1), 'delta': (10000, 1), 'lr': 0.5, 'gamma1': 0.5, 'gamma2': 0.5, 'epsilon': 1e-08, 'wd': 0.5, 'rescale_grad': 0.4} 2692893.25 0.0808 ---
rmspropalex_update {'weight': (10000, 100), 'grad': (10000, 100), 'n': (10000, 100), 'g': (10000, 100), 'delta': (10000, 100), 'lr': 0.9, 'gamma1': 0.9, 'gamma2': 0.9, 'epsilon': 1e-08, 'wd': 0.9, 'rescale_grad': 0.4} 2696873.25 1.9606 ---
round {'data': (1024, 1024)} 4194.3042 0.8192 ---
round {'data': (10000, 1)} 20.0 0.0792 ---
round {'data': (10000, 100)} 2000.0 0.8664 ---
rsqrt {'data': (1024, 1024)} 2097.1521 0.8992 1.0464
rsqrt {'data': (10000, 1)} 20.0 0.0598 0.0612
rsqrt {'data': (10000, 100)} 2000.0 0.914 1.16
sample_exponential {'lam': [1.0, 8.5], 'shape': (1024, 1024), 'dtype': 'float16'} 43948.8984 18.9886 ---
sample_exponential {'lam': [1.0, 8.5], 'shape': (10000, 1), 'dtype': 'float32'} 41931.7461 0.2754 ---
sample_exponential {'lam': [1.0, 8.5], 'shape': (10000, 100), 'dtype': 'float64'} 57891.7461 17.5774 ---
sample_gamma {'alpha': [0.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'beta': [1.0, 0.7]} 56183.2031 72.7822 ---
sample_gamma {'alpha': [0.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'beta': [1.0, 0.7]} 54126.0508 1.0362 ---
sample_gamma {'alpha': [0.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'beta': [1.0, 0.7]} 70126.0469 77.2066 ---
sample_generalized_negative_binomial {'mu': [2.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'alpha': [0.0, 2.5]} 68417.5078 132.5426 ---
sample_generalized_negative_binomial {'mu': [2.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'alpha': [0.0, 2.5]} 66400.3516 1.4492 ---
sample_generalized_negative_binomial {'mu': [2.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'alpha': [0.0, 2.5]} 82360.3516 157.3978 ---
sample_multinomial {'data': (32, 32), 'shape': (1024, 1024), 'dtype': 'float16'} 443459.0938 6482.2856 ---
sample_multinomial {'data': (32, 32), 'shape': (10000, 1), 'dtype': 'float32'} 411184.6875 60.138 ---
sample_multinomial {'data': (32, 32), 'shape': (10000, 100), 'dtype': 'float64'} 666544.6875 6201.6147 ---
sample_negative_binomial {'k': [20, 49], 'shape': (1024, 1024), 'dtype': 'float16', 'p': [0.4, 0.77]} 544836.125 583.3652 ---
sample_negative_binomial {'k': [20, 49], 'shape': (10000, 1), 'dtype': 'float32', 'p': [0.4, 0.77]} 542819.0 5.7008 ---
sample_negative_binomial {'k': [20, 49], 'shape': (10000, 100), 'dtype': 'float64', 'p': [0.4, 0.77]} 558779.0 555.5234 ---
sample_normal {'mu': [2.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'sigma': [1.0, 3.7]} 557070.4375 56.7754 ---
sample_normal {'mu': [2.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'sigma': [1.0, 3.7]} 555053.3125 0.68 ---
sample_normal {'mu': [2.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'sigma': [1.0, 3.7]} 571013.3125 49.8232 ---
sample_poisson {'lam': [1.0, 8.5], 'shape': (1024, 1024), 'dtype': 'float16'} 569304.75 143.0912 ---
sample_poisson {'lam': [1.0, 8.5], 'shape': (10000, 1), 'dtype': 'float32'} 567287.5625 1.5108 ---
sample_poisson {'lam': [1.0, 8.5], 'shape': (10000, 100), 'dtype': 'float64'} 583247.5625 126.2726 ---
sample_uniform {'low': [0.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'high': [1.0, 3.7]} 581539.0625 24.4044 ---
sample_uniform {'low': [0.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'high': [1.0, 3.7]} 579521.875 0.2776 ---
sample_uniform {'low': [0.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'high': [1.0, 3.7]} 595481.875 22.6432 ---
sgd_mom_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0} 2701164.75 0.7962 ---
sgd_mom_update {'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0} 2699107.5 0.0606 ---
sgd_mom_update {'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0} 2703087.5 0.749 ---
sgd_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0} 2707379.0 0.5756 ---
sgd_update {'weight': (10000, 1), 'grad': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0} 2705321.75 0.0546 ---
sgd_update {'weight': (10000, 100), 'grad': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0} 2709301.75 0.5606 ---
shape_array {'data': (1024, 1024)} 0.008 0.0524 ---
shape_array {'data': (10000, 1)} 0.008 0.0536 ---
shape_array {'data': (10000, 100)} 0.008 0.0528 ---
shuffle {'data': (1024, 1024)} 2097.1521 1.027 ---
shuffle {'data': (10000, 1)} 20.0 0.8646 ---
shuffle {'data': (10000, 100)} 2000.0 1.714 ---
sigmoid {'data': (1024, 1024)} 2097.1521 0.9368 0.3078
sigmoid {'data': (10000, 1)} 20.0 0.0746 0.0608
sigmoid {'data': (10000, 100)} 2000.0 0.8692 0.2952
sign {'data': (1024, 1024)} 2097.1521 0.5408 0.2894
sign {'data': (10000, 1)} 20.0 0.07 0.0602
sign {'data': (10000, 100)} 2000.0 0.5158 0.2646
signsgd_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4} 2713593.25 0.634 ---
signsgd_update {'weight': (10000, 1), 'grad': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4} 2711536.25 0.053 ---
signsgd_update {'weight': (10000, 100), 'grad': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4} 2715516.25 0.5916 ---
signum_update {'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4} 2719807.5 0.9946 ---
signum_update {'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4} 2717750.5 0.0678 ---
signum_update {'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4} 2721730.5 0.9248 ---
sin {'data': (1024, 1024)} 2097.1521 0.8578 0.738
sin {'data': (10000, 1)} 20.0 0.0736 0.0648
sin {'data': (10000, 100)} 2000.0 0.8424 0.7242
sinh {'data': (1024, 1024)} 2097.1521 1.635 0.9536
sinh {'data': (10000, 1)} 20.0 0.0824 0.0674
sinh {'data': (10000, 100)} 2000.0 1.581 0.925
size_array {'data': (1024, 1024)} 0.004 0.0562 ---
size_array {'data': (10000, 1)} 0.004 0.055 ---
size_array {'data': (10000, 100)} 0.004 0.0548 ---
slice {'data': (1024, 1024), 'begin': 0, 'end': 1} 617607.875 0.115 0.2404
slice {'data': (10000, 1), 'begin': 0, 'end': 1} 617607.875 0.0692 0.058
slice {'data': (10000, 100), 'begin': 0, 'end': 1} 617608.25 0.0734 0.202
slice_axis {'data': (1024, 1024), 'axis': 0, 'begin': 0, 'end': 1} 617616.4375 0.1322 0.6256
slice_axis {'data': (10000, 1), 'axis': 0, 'begin': 0, 'end': 1} 617616.4375 0.0546 0.0558
slice_axis {'data': (10000, 100), 'axis': 0, 'begin': 0, 'end': 1} 617616.875 0.0622 0.5092
slice_like {'data': (1024, 1024), 'shape_like': (100, 100), 'axes': [0, 1]} 617696.875 0.0962 0.2756
slice_like {'data': (10000, 1), 'shape_like': (10, 1), 'axes': [0, 1]} 617696.875 0.0856 0.0704
slice_like {'data': (10000, 100), 'shape_like': (100, 10), 'axes': [0, 1]} 617700.875 0.0822 0.2112
smooth_l1 {'data': (1024, 1024)} 2827856.5 0.9642 1.0984
smooth_l1 {'data': (10000, 1)} 2825799.5 0.058 0.0666
smooth_l1 {'data': (10000, 100)} 2829799.5 0.9352 0.995
softmax {'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'} 2462984.25 4.9242 4.9294
softmax {'data': (10000, 1), 'axis': 0, 'dtype': 'float32'} 2461975.75 0.6576 0.2452
softmax {'data': (10000, 100), 'axis': 0, 'dtype': 'float64'} 2469975.75 5.29 4.056
softmax_cross_entropy {'data': (1024, 1024), 'label': (1024,)} 2827799.5 2.0616 ---
softmin {'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'} 2473121.5 4.7208 4.697
softmin {'data': (10000, 1), 'axis': 0, 'dtype': 'float32'} 2473161.5 0.677 0.2462
softmin {'data': (10000, 100), 'axis': 0, 'dtype': 'float64'} 2481161.5 4.3982 4.0266
softsign {'data': (1024, 1024)} 2097.1521 0.3686 0.4132
softsign {'data': (10000, 1)} 20.0 0.0684 0.0622
softsign {'data': (10000, 100)} 2000.0 0.3358 0.3952
sort {'data': (1024, 1024), 'axis': 0} 604264.0 186.6978 ---
sort {'data': (10000, 1), 'axis': 0} 598052.5625 4.414 ---
sort {'data': (10000, 100), 'axis': 0} 606032.5625 133.1322 ---
space_to_depth {'data': (1, 4, 2, 4), 'block_size': 2} 606751.5 0.1712 ---
space_to_depth {'data': (10, 25, 10, 100), 'block_size': 5} 607751.4375 2.5286 ---
sqrt {'data': (1024, 1024)} 2097.1521 1.0564 0.3612
sqrt {'data': (10000, 1)} 20.0 0.2086 0.0882
sqrt {'data': (10000, 100)} 2000.0 0.7928 0.2664
square {'data': (1024, 1024)} 2097.1521 0.3532 0.3282
square {'data': (10000, 1)} 20.0 0.069 0.061
square {'data': (10000, 100)} 2000.0 0.3334 0.3196
squeeze {'data': (1, 1024, 1024), 'axis': 0} 3163356.25 0.4602 0.6294
squeeze {'data': (32, 1, 256, 256), 'axis': 1} 3171745.0 1.2596 1.0216
stop_gradient {'data': (1024, 1024)} 2097.1521 0.3934 ---
stop_gradient {'data': (10000, 1)} 20.0 0.0638 ---
stop_gradient {'data': (10000, 100)} 2000.0 0.4262 ---
sum {'data': (1024, 1024), 'axis': 0} 587554.75 3.785 5.28
sum {'data': (10000, 1), 'axis': 0} 587554.75 0.9076 0.0968
sum {'data': (10000, 100), 'axis': 0} 587555.1875 3.8986 4.9982
sum_axis {'data': (1024, 1024), 'axis': 0} 587561.3125 3.8026 ---
sum_axis {'data': (10000, 1), 'axis': 0} 587559.25 0.9064 ---
sum_axis {'data': (10000, 100), 'axis': 0} 587559.625 3.8454 ---
swapaxes {'data': (1024, 1024), 'dim1': 0, 'dim2': 1} 611445.75 5.7426 ---
swapaxes {'data': (10000, 1), 'dim1': 0, 'dim2': 1} 609388.5625 0.1074 ---
swapaxes {'data': (10000, 100), 'dim1': 0, 'dim2': 1} 613368.5625 5.3814 ---
take {'a': (1024, 1024), 'indices': (1, 1), 'axis': 0} 617709.0625 0.0578 0.5558
tan {'data': (1024, 1024)} 2097.1521 1.3864 0.3176
tan {'data': (10000, 1)} 20.0 0.079 0.0662
tan {'data': (10000, 100)} 2000.0 1.305 0.3012
tanh {'data': (1024, 1024)} 2097.1521 1.52 0.3584
tanh {'data': (10000, 1)} 20.0 0.0826 0.0596
tanh {'data': (10000, 100)} 2000.0 1.4784 0.315
topk {'data': (1024, 1024), 'axis': 0, 'k': 1, 'dtype': 'float32'} 600038.6875 125.058 ---
topk {'data': (10000, 1), 'axis': 0, 'k': 1, 'dtype': 'int32'} 600036.6875 1.3998 ---
topk {'data': (10000, 100), 'axis': 0, 'k': 1, 'dtype': 'float32'} 600037.0625 115.3784 ---
transpose {'data': (1024, 1024), 'axes': [0, 1]} 617660.0 0.407 ---
transpose {'data': (10000, 1), 'axes': [0, 1]} 615602.875 0.0782 ---
transpose {'data': (10000, 100), 'axes': [0, 1]} 619582.875 1.0166 ---
trunc {'data': (1024, 1024)} 2097.1521 0.513 ---
trunc {'data': (10000, 1)} 20.0 0.0678 ---
trunc {'data': (10000, 100)} 2000.0 0.5132 ---
where {'condition': (1024,), 'x': (1024, 1024), 'y': (1024, 1024)} 626097.6875 0.8682 1.5826
where {'condition': (10000,), 'x': (10000, 1), 'y': (10000, 1)} 626137.6875 0.0738 0.059
where {'condition': (10000,), 'x': (10000, 100), 'y': (10000, 100)} 630137.6875 0.8326 1.5166
zeros_like {'data': (1024, 1024)} 2097.1521 0.1942 ---
zeros_like {'data': (10000, 1)} 20.0 0.0604 ---
zeros_like {'data': (10000, 100)} 2000.0 0.1856 ---
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment