connorgoggins/spatialtransformer_all_gpu_5_warmup_5_runs.md Secret

## spatialtransformer_all_gpu_5_warmup_5_runs.md

      
    Raw
  

              spatialtransformer_all_gpu_5_warmup_5_runs.md
            
          
    Runtime Features


BLAS_APPLE : ✖ BLAS_APPLE
BLAS_ATLAS : ✖ BLAS_ATLAS
BLAS_MKL : ✖ BLAS_MKL
BLAS_OPEN : ✔ BLAS_OPEN
CAFFE : ✖ CAFFE
CPU_AVX : ✔ CPU_AVX
CPU_AVX2 : ✖ CPU_AVX2
CPU_SSE : ✔ CPU_SSE
CPU_SSE2 : ✔ CPU_SSE2
CPU_SSE3 : ✔ CPU_SSE3
CPU_SSE4A : ✖ CPU_SSE4A
CPU_SSE4_1 : ✔ CPU_SSE4_1
CPU_SSE4_2 : ✔ CPU_SSE4_2
CUDA : ✖ CUDA
CUDA_RTC : ✖ CUDA_RTC
CUDNN : ✖ CUDNN
CXX14 : ✖ CXX14
DEBUG : ✖ DEBUG
DIST_KVSTORE : ✖ DIST_KVSTORE
F16C : ✔ F16C
INT64_TENSOR_SIZE : ✔ INT64_TENSOR_SIZE
JEMALLOC : ✖ JEMALLOC
LAPACK : ✔ LAPACK
MKLDNN : ✖ MKLDNN
NCCL : ✖ NCCL
OPENCV : ✖ OPENCV
OPENMP : ✔ OPENMP
PROFILER : ✖ PROFILER
SIGNAL_HANDLER : ✖ SIGNAL_HANDLER
SSE : ✖ SSE
TENSORRT : ✖ TENSORRT
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'}
366488.4062
0.0612
0.1002


Activation
{'data': (1024, 1024), 'act_type': 'sigmoid'}
368585.5625
0.6748
0.056


Activation
{'data': (1024, 1024), 'act_type': 'softrelu'}
370682.7188
1.7744
0.9588


Activation
{'data': (1024, 1024), 'act_type': 'softsign'}
372779.8438
0.0532
0.0534


Activation
{'data': (1024, 1024), 'act_type': 'tanh'}
374877.0
1.4206
0.0676


BatchNorm
{'data': (32, 3, 256, 256), 'gamma': (3,), 'beta': (3,), 'moving_mean': (3,), 'moving_var': (3,)}
353579.875
14.6506
8.1104


BatchNorm
{'data': (32, 3, 10000, 10), 'gamma': (3,), 'beta': (3,), 'moving_mean': (3,), 'moving_var': (3,)}
379396.9688
17.5304
13.6382


BilinearSampler
{'data': (32, 2, 256, 256), 'grid': (32, 2, 256, 256)}
16777.2168
100.6782
119.2164


BlockGrad
{'data': (1024, 1024)}
2097.1521
0.3224
---


BlockGrad
{'data': (10000, 1)}
20.0
0.011
---


BlockGrad
{'data': (10000, 100)}
2000.0
0.3918
---


CTCLoss
{'data': (1024, 100, 100), 'label': (100, 100)}
2663714.0
51.9336
---


Convolution
{'data': (32, 3, 64, 64), 'weight': (64, 3, 3, 3), 'bias': (64,), 'kernel': (3, 3), 'stride': (1, 1), 'dilate': (1, 1), 'pad': (0, 0), 'num_filter': 64, 'layout': 'NCHW'}
1341985.625
7.8122
13.3234


Custom
{'args': [(1024, 1024)], 'op_type': 'CustomAddOne'}
2787046.25
0.0055
0.0072


Custom
{'args': [(10000, 1)], 'op_type': 'CustomAddOne'}
2787046.25
0.005
0.0062


Custom
{'args': [(10000, 10)], 'op_type': 'CustomAddOne'}
2787046.25
0.0056
0.0058


Deconvolution
{'data': (32, 3, 64, 64), 'weight': (3, 64, 3, 3), 'bias': (64,), 'kernel': (3, 3), 'stride': (1, 1), 'dilate': (1, 1), 'pad': (0, 0), 'num_filter': 64, 'no_bias': False, 'layout': 'NCHW'}
2661075.75
306.0796
108.6012


Dropout
{'data': (32, 3, 256, 256), 'p': 0.5, 'mode': 'always'}
327814.0312
5.224
0.984


Dropout
{'data': (10000, 10), 'p': 0.5, 'mode': 'always'}
315831.125
0.0802
0.02


ElementWiseSum
{'args': (1024, 1024)}
2097.1521
0.0872
---


FullyConnected
{'data': (32, 3, 256, 256), 'num_hidden': 64, 'weight': (64, 196608), 'bias': (64,), 'flatten': True}
261757.8438
1.9692
3.9592


FullyConnected
{'data': (32, 3, 256, 256), 'num_hidden': 64, 'weight': (64, 256), 'bias': (64,), 'flatten': False}
268045.1875
9.1298
7.3656


GridGenerator
{'data': (32, 2, 256, 256), 'transform_type': 'warp', 'target_shape': (256, 6)}
8650.752
32.7878
28.4014


GridGenerator
{'data': (256, 6), 'transform_type': 'affine', 'target_shape': (256, 6)}
1582.08
0.4452
0.3376


LeakyReLU
{'data': (1024, 1024), 'act_type': 'leaky'}
379071.3125
0.2542
0.0532


LeakyReLU
{'data': (1024, 1024), 'act_type': 'elu'}
381168.4688
0.6718
0.3506


LeakyReLU
{'data': (1024, 1024), 'act_type': 'selu'}
383265.625
0.6952
0.267


LeakyReLU
{'data': (1024, 1024), 'act_type': 'gelu'}
385362.7812
0.7508
1.7076


MakeLoss
{'data': (1024, 1024)}
2649525.5
0.0254
0.0166


MakeLoss
{'data': (10000, 1)}
2647468.25
0.017
0.0678


MakeLoss
{'data': (10000, 100)}
2651448.25
0.0372
0.0178


Pooling
{'data': (32, 3, 64, 64), 'kernel': (3, 3), 'pool_type': 'sum', 'global_pool': 1, 'stride': (1, 1), 'pad': (0, 0)}
499384.1562
0.4854
0.266


ROIPooling
{'data': (32, 3, 64, 64), 'rois': (32, 5), 'pooled_size': (2, 2), 'spatial_scale': 0.5}
499391.625
0.1358
0.0284


SequenceLast
{'data': (1024, 1024), 'axis': 0}
2787052.5
0.0212
---


SequenceLast
{'data': (10000, 1), 'axis': 0}
2787050.5
0.015
---


SequenceLast
{'data': (10000, 100), 'axis': 0}
2787050.75
0.0172
---


SequenceMask
{'data': (1024, 1024), 'axis': 0}
2793342.0
0.236
0.2312


SequenceMask
{'data': (10000, 1), 'axis': 0}
2791285.0
0.0182
0.0144


SequenceMask
{'data': (10000, 100), 'axis': 0}
2795265.0
1.1988
0.2206


SequenceReverse
{'data': (1024, 1024), 'axis': 0}
2799556.25
2.413
2.5898


SequenceReverse
{'data': (10000, 1), 'axis': 0}
2797499.25
0.114
0.027


SequenceReverse
{'data': (10000, 100), 'axis': 0}
2801479.25
2.1198
2.227


Softmax
{'data': (1024, 1024), 'label': (1024, 1024)}
389557.0625
0.7084
---


Softmax
{'data': (10000, 1), 'label': (10000, 1)}
387499.9375
0.0212
---


Softmax
{'data': (10000, 100), 'label': (10000, 100)}
391479.9375
0.677
---


SoftmaxActivation
{'data': (1024, 1024)}
395771.375
0.722
2.5686


SoftmaxActivation
{'data': (10000, 1)}
393714.2188
0.018
0.0458


SoftmaxActivation
{'data': (10000, 100)}
397694.2188
0.6598
2.4262


UpSampling
{'args': (32, 3, 256, 256), 'scale': 2, 'sample_type': 'nearest'}
2806658.0
20.4806
3.576


UpSampling
{'args': (32, 3, 10000, 1), 'scale': 4, 'sample_type': 'nearest'}
2817766.25
15.3894
2.4824


abs
{'data': (1024, 1024)}
2097.1521
0.0412
0.4446


abs
{'data': (10000, 1)}
20.0
0.0706
0.0114


abs
{'data': (10000, 100)}
2000.0
0.0396
0.3768


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}
1332532.125
0.4328
---


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}
1330475.0
0.071
---


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}
1334455.0
0.7548
---


add_n
{'args': [(1024, 1024)]}
2655663.0
0.0086
---


add_n
{'args': [(10000, 1)]}
2655663.0
0.0082
---


add_n
{'args': [(10000, 10)]}
2655663.0
0.021
---


all_finite
{'data': (1024, 1024)}
2799479.25
0.0584
---


all_finite
{'data': (10000, 1)}
2799479.25
0.0154
---


all_finite
{'data': (10000, 100)}
2799479.25
0.058
---


amp_cast
{'data': (1024, 1024), 'dtype': 'float32'}
2097.1521
0.3822
0.7264


amp_cast
{'data': (10000, 1), 'dtype': 'int32'}
20.0
0.0178
0.0156


amp_cast
{'data': (10000, 100), 'dtype': 'float32'}
2000.0
0.4632
0.718


amp_multicast
{'args': [(1024, 1024)], 'num_outputs': 1}
0.004
0.1494
0.2182


amp_multicast
{'args': [(10000, 1)], 'num_outputs': 1}
0.004
0.2058
0.1646


arccos
{'data': (1024, 1024)}
2097.1521
0.7754
0.5562


arccos
{'data': (10000, 1)}
20.0
0.019
0.0138


arccos
{'data': (10000, 100)}
2000.0
0.7388
0.473


arccosh
{'data': (1024, 1024)}
2097.1521
0.6592
0.679


arccosh
{'data': (10000, 1)}
20.0
0.0184
0.0164


arccosh
{'data': (10000, 100)}
2000.0
0.6574
0.6262


arcsin
{'data': (1024, 1024)}
2097.1521
0.7198
0.5258


arcsin
{'data': (10000, 1)}
20.0
0.0172
0.0136


arcsin
{'data': (10000, 100)}
2000.0
0.7036
0.478


arcsinh
{'data': (1024, 1024)}
2097.1521
1.506
0.4308


arcsinh
{'data': (10000, 1)}
20.0
0.0236
0.0144


arcsinh
{'data': (10000, 100)}
2000.0
1.393
0.412


arctan
{'data': (1024, 1024)}
2097.1521
1.1018
0.0558


arctan
{'data': (10000, 1)}
20.0
0.0234
0.0142


arctan
{'data': (10000, 100)}
2000.0
0.8488
0.053


arctanh
{'data': (1024, 1024)}
2097.1521
1.3018
0.059


arctanh
{'data': (10000, 1)}
20.0
0.026
0.0148


arctanh
{'data': (10000, 100)}
2000.0
1.2358
0.0554


argmax
{'data': (1024, 1024), 'axis': 0}
225478.4375
28.4932
---


argmax
{'data': (10000, 1), 'axis': 0}
225476.3906
0.2746
---


argmax
{'data': (10000, 100), 'axis': 0}
225476.7969
20.8574
---


argmax_channel
{'data': (1024, 1024)}
2.048
0.6618
---


argmax_channel
{'data': (10000, 1)}
20.0
0.2182
---


argmax_channel
{'data': (10000, 100)}
20.0
0.7302
---


argmin
{'data': (1024, 1024), 'axis': 0}
225482.7344
27.1264
---


argmin
{'data': (10000, 1), 'axis': 0}
225480.6875
0.1894
---


argmin
{'data': (10000, 100), 'axis': 0}
225481.0938
22.1958
---


argsort
{'data': (1024, 1024), 'axis': 0, 'dtype': 'float32'}
231772.3438
65.4412
---


argsort
{'data': (10000, 1), 'axis': 0, 'dtype': 'int32'}
229715.2031
1.3666
---


argsort
{'data': (10000, 100), 'axis': 0, 'dtype': 'float32'}
233695.2031
61.1342
---


batch_dot
{'lhs': (32, 1024, 1024), 'rhs': (32, 1024, 1024)}
67108.8672
67.6699
---


batch_dot
{'lhs': (32, 1000, 10), 'rhs': (32, 1000, 10), 'transpose_b': True}
64000.0
28.2041
---


batch_dot
{'lhs': (32, 1000, 1), 'rhs': (32, 100, 1000), 'transpose_a': True, 'transpose_b': True}
6.4
0.5757
---


broadcast_add
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0496
0.0616


broadcast_add
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0208
0.016


broadcast_add
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0132
0.0142


broadcast_div
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0484
0.0966


broadcast_div
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.029
0.023


broadcast_div
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0138
0.017


broadcast_equal
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0456
---


broadcast_equal
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0162
---


broadcast_equal
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.013
---


broadcast_greater
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0452
---


broadcast_greater
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.016
---


broadcast_greater
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0134
---


broadcast_greater_equal
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0456
---


broadcast_greater_equal
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.071
---


broadcast_greater_equal
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0116
---


broadcast_hypot
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.4212
0.935


broadcast_hypot
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.052
0.1026


broadcast_hypot
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.016
0.0228


broadcast_lesser
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0448
---


broadcast_lesser
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.1598
---


broadcast_lesser
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0112
---


broadcast_lesser_equal
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0444
---


broadcast_lesser_equal
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0134
---


broadcast_lesser_equal
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0112
---


broadcast_logical_and
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0472
---


broadcast_logical_and
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0152
---


broadcast_logical_and
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.012
---


broadcast_logical_or
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.049
---


broadcast_logical_or
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0148
---


broadcast_logical_or
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0118
---


broadcast_logical_xor
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.1372
---


broadcast_logical_xor
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.023
---


broadcast_logical_xor
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0124
---


broadcast_maximum
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.066
0.1162


broadcast_maximum
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0184
0.0206


broadcast_maximum
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0132
0.0166


broadcast_minimum
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0658
0.1048


broadcast_minimum
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0184
0.0218


broadcast_minimum
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0136
0.0224


broadcast_minus
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.048
---


broadcast_minus
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0188
---


broadcast_minus
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0134
---


broadcast_mod
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
2.0048
0.1652


broadcast_mod
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.2156
0.0288


broadcast_mod
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0306
0.0182


broadcast_mul
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.048
0.0916


broadcast_mul
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.015
0.0188


broadcast_mul
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.083
0.0162


broadcast_not_equal
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0474
---


broadcast_not_equal
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0176
---


broadcast_not_equal
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0122
---


broadcast_plus
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0472
---


broadcast_plus
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0152
---


broadcast_plus
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0124
---


broadcast_power
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
2.452
5.6488


broadcast_power
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.2396
0.5526


broadcast_power
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0362
0.0694


broadcast_sub
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.049
0.0602


broadcast_sub
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0158
0.015


broadcast_sub
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0132
0.0134


cast
{'data': (1024, 1024), 'dtype': 'float32'}
2097.1521
---
0.6986


cast
{'data': (10000, 1), 'dtype': 'int32'}
20.0
---
0.016


cast
{'data': (10000, 100), 'dtype': 'float32'}
2000.0
---
0.6988


cast_storage
{'data': (1024, 1024), 'stype': 'default'}
2805770.75
0.3338
---


cast_storage
{'data': (10000, 1), 'stype': 'csr'}
2803813.5
1.7382
---


cast_storage
{'data': (10000, 100), 'stype': 'row_sparse'}
2805853.5
0.8246
---


cbrt
{'data': (1024, 1024)}
2097.1521
1.3416
0.0564


cbrt
{'data': (10000, 1)}
20.0
0.0826
0.0108


cbrt
{'data': (10000, 100)}
2000.0
1.4136
0.0636


ceil
{'data': (1024, 1024)}
2097.1521
0.158
---


ceil
{'data': (10000, 1)}
20.0
0.0106
---


ceil
{'data': (10000, 100)}
2000.0
5.2406
---


choose_element_0index
{'data': (1024, 1024), 'index': (1, 1024), 'axis': 0}
2.048
0.013
---


choose_element_0index
{'data': (10000, 1), 'index': (1, 1), 'axis': 0}
0.002
0.01
---


choose_element_0index
{'data': (10000, 100), 'index': (1, 100), 'axis': 0}
0.2
0.0106
---


clip
{'data': (1024, 1024), 'a_min': 0.1, 'a_max': 0.9}
2812105.0
0.1434
0.272


clip
{'data': (10000, 1), 'a_min': 0.1, 'a_max': 0.9}
2810047.75
0.0106
0.0094


clip
{'data': (10000, 100), 'a_min': 0.1, 'a_max': 0.9}
2814027.75
0.1488
0.2476


cos
{'data': (1024, 1024)}
2097.1521
0.4746
0.533


cos
{'data': (10000, 1)}
20.0
0.0262
0.0222


cos
{'data': (10000, 100)}
2000.0
0.6506
0.6954


cosh
{'data': (1024, 1024)}
2097.1521
0.9284
1.6436


cosh
{'data': (10000, 1)}
20.0
0.026
0.029


cosh
{'data': (10000, 100)}
2000.0
0.834
1.5324


ctc_loss
{'data': (1024, 100, 100), 'label': (100, 100)}
2690408.75
56.6516
---


cumsum
{'a': (1024, 1024), 'axis': 0, 'dtype': 'float32'}
2818319.25
1.271
---


cumsum
{'a': (1024, 1024), 'axis': 0, 'dtype': 'int32'}
2820416.5
1.2022
---


cumsum
{'a': (1024, 1024), 'axis': 0, 'dtype': 'float32'}
2822513.5
1.2452
---


degrees
{'data': (1024, 1024)}
2097.1521
0.0462
0.0384


degrees
{'data': (10000, 1)}
20.0
0.0126
0.012


degrees
{'data': (10000, 100)}
2000.0
0.061
0.036


depth_to_space
{'data': (1, 4, 2, 4), 'block_size': 2}
237913.9844
0.02
---


depth_to_space
{'data': (10, 25, 10, 100), 'block_size': 5}
238913.9219
1.1982
---


dot
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
2.3594
5.0956


dot
{'lhs': (1000, 10), 'rhs': (1000, 10), 'transpose_b': True}
2000.0
0.2376
0.3486


dot
{'lhs': (1000, 1), 'rhs': (100, 1000), 'transpose_a': True, 'transpose_b': True}
0.2
0.496
0.3552


elemwise_add
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0462
---


elemwise_add
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.09
---


elemwise_add
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0128
---


elemwise_div
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0464
---


elemwise_div
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0134
---


elemwise_div
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0112
---


elemwise_mul
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.048
---


elemwise_mul
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.015
---


elemwise_mul
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.012
---


elemwise_sub
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.0444
---


elemwise_sub
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0142
---


elemwise_sub
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0128
---


erf
{'data': (1024, 1024)}
2097.1521
0.911
0.778


erf
{'data': (10000, 1)}
20.0
0.0218
0.0184


erf
{'data': (10000, 100)}
2000.0
0.8886
0.7576


erfinv
{'data': (1024, 1024)}
2097.1521
4.0932
0.8178


erfinv
{'data': (10000, 1)}
20.0
0.0548
0.0782


erfinv
{'data': (10000, 100)}
2000.0
3.4034
0.7242


exp
{'data': (1024, 1024)}
2097.1521
0.5958
---


exp
{'data': (10000, 1)}
20.0
0.0206
---


exp
{'data': (10000, 100)}
2000.0
0.5546
---


expm1
{'data': (1024, 1024)}
2097.1521
0.998
0.635


expm1
{'data': (10000, 1)}
20.0
0.0792
0.0172


expm1
{'data': (10000, 100)}
2000.0
0.952
0.6044


fill_element_0index
{'lhs': (1024, 1024), 'mhs': (1024,), 'rhs': (1024,)}
2826707.75
0.0784
---


fill_element_0index
{'lhs': (10000, 1), 'mhs': (10000,), 'rhs': (10000,)}
2824650.75
0.0124
---


fill_element_0index
{'lhs': (10000, 100), 'mhs': (10000,), 'rhs': (10000,)}
2828630.75
0.078
---


fix
{'data': (1024, 1024)}
2097.1521
0.3086
---


fix
{'data': (10000, 1)}
20.0
0.0174
---


fix
{'data': (10000, 100)}
2000.0
0.3006
---


flatten
{'data': (1024, 1024)}
2097.1521
0.4218
---


flatten
{'data': (10000, 1)}
20.0
0.016
---


flatten
{'data': (10000, 100)}
2000.0
0.4934
---


flip
{'data': (1024, 1024), 'axis': 0}
242608.2344
1.201
---


flip
{'data': (10000, 1), 'axis': 0}
242628.2344
0.025
---


flip
{'data': (10000, 100), 'axis': 0}
244628.2344
1.173
---


floor
{'data': (1024, 1024)}
2097.1521
0.123
---


floor
{'data': (10000, 1)}
20.0
0.0124
---


floor
{'data': (10000, 100)}
2000.0
0.1232
---


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}
1334552.125
1.5026
---


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}
1334592.125
0.0418
---


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}
1338572.125
1.8204
---


ftrl_update
{'weight': (1024, 1024), 'grad': (1024, 1024), 'z': (1024, 1024), 'n': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4}
1342863.625
1.6096
---


ftrl_update
{'weight': (10000, 1), 'grad': (10000, 1), 'z': (10000, 1), 'n': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4}
1340806.375
0.0344
---


ftrl_update
{'weight': (10000, 100), 'grad': (10000, 100), 'z': (10000, 100), 'n': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4}
1344786.375
1.7374
---


gamma
{'data': (1024, 1024)}
2097.1521
4.523
8.283


gamma
{'data': (10000, 1)}
20.0
0.0658
0.0816


gamma
{'data': (10000, 100)}
2000.0
3.684
6.9538


gammaln
{'data': (1024, 1024)}
2097.1521
22.1688
3.6534


gammaln
{'data': (10000, 1)}
20.0
0.2214
0.0528


gammaln
{'data': (10000, 100)}
2000.0
21.1138
3.1828


gather_nd
{'data': (1024, 1024), 'indices': (1, 1)}
255465.8906
0.0248
---


gather_nd
{'data': (10000, 1), 'indices': (1, 1)}
255463.8438
0.0222
---


gather_nd
{'data': (10000, 100), 'indices': (1, 1)}
255464.25
0.035
---


hard_sigmoid
{'data': (1024, 1024)}
401985.6875
0.0962
0.1264


hard_sigmoid
{'data': (10000, 1)}
399928.5312
0.011
0.0108


hard_sigmoid
{'data': (10000, 100)}
403908.5312
0.0902
0.099


identity
{'data': (1024, 1024)}
2097.1521
0.3702
---


identity
{'data': (10000, 1)}
20.0
0.0124
---


identity
{'data': (10000, 100)}
2000.0
0.4864
---


khatri_rao
{'args': [(32, 32), (32, 32)]}
0.008
0.0162
---


khatri_rao
{'args': [(64, 64), (64, 64)]}
0.008
0.0124
---


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}
1349077.875
0.6448
---


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}
1347020.75
0.0678
---


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}
1351000.75
1.3144
---


lamb_update_phase2
{'weight': (1024, 1024), 'g': (1024, 1024), 'r1': (1, 1024), 'r2': (1, 1024), 'lr': 0.1}
1355292.125
0.2024
---


lamb_update_phase2
{'weight': (10000, 1), 'g': (10000, 1), 'r1': (1, 1), 'r2': (1, 1), 'lr': 0.5}
1353235.0
0.014
---


lamb_update_phase2
{'weight': (10000, 100), 'g': (10000, 100), 'r1': (1, 100), 'r2': (1, 100), 'lr': 0.9}
1357215.0
0.1996
---


linalg_det
{'A': (1024, 1024)}
2843332.75
6.273
14.2136


linalg_extractdiag
{'A': (1024, 1024)}
2841239.75
0.0122
0.0246


linalg_extracttrian
{'A': (1024, 1024)}
2844386.5
0.4962
0.4698


linalg_gelqf
{'A': (1024, 1024)}
2855919.75
27.4016
---


linalg_gemm
{'A': (1024, 1024), 'B': (1024, 1024), 'C': (1024, 1024), 'axis': 0}
2858017.0
2.182
4.914


linalg_gemm2
{'A': (1024, 1024), 'B': (1024, 1024), 'axis': 0}
2862211.25
1.232
2.9446


linalg_inverse
{'A': (1024, 1024)}
2866405.75
14.0604
5.3512


linalg_makediag
{'A': (1024, 1024)}
9306759.0
510.868
10.3234


linalg_maketrian
{'A': (1024, 1035)}
7171717.5
2.8278
2.6514


linalg_potrf
{'A': [[1, 0], [0, 1]]}
2841233.75
0.011
---


linalg_potrf
{'A': [[2, -1, 0], [-1, 2, -1], [0, -1, 2]]}
2841233.75
0.0102
---


linalg_potri
{'A': (1024, 1024)}
7178009.0
11.0338
7.3288


linalg_slogdet
{'A': (1024, 1024)}
7180108.0
5.2206
---


linalg_sumlogdiag
{'A': (1024, 1024)}
7180108.0
0.0622
0.4224


linalg_syrk
{'A': (1024, 1024)}
7186399.5
2.6536
4.3462


linalg_trmm
{'A': (1024, 1024), 'B': (1024, 1024)}
7194788.0
3.055
6.9746


linalg_trsm
{'A': (1024, 1024), 'B': (1024, 1024)}
7198982.5
2.7888
6.965


log
{'data': (1024, 1024)}
2097.1521
0.8582
0.114


log
{'data': (10000, 1)}
20.0
0.0186
0.0106


log
{'data': (10000, 100)}
2000.0
0.773
0.0496


log10
{'data': (1024, 1024)}
2097.1521
0.9688
0.0516


log10
{'data': (10000, 1)}
20.0
0.0242
0.012


log10
{'data': (10000, 100)}
2000.0
1.012
0.0538


log1p
{'data': (1024, 1024)}
2097.1521
0.9614
0.0502


log1p
{'data': (10000, 1)}
20.0
0.0194
0.011


log1p
{'data': (10000, 100)}
2000.0
0.9288
0.0504


log2
{'data': (1024, 1024)}
2097.1521
0.7932
0.0666


log2
{'data': (10000, 1)}
20.0
0.0224
0.0102


log2
{'data': (10000, 100)}
2000.0
0.7478
0.0488


log_softmax
{'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'}
405054.25
3.0146
1.8958


log_softmax
{'data': (10000, 1), 'axis': 0, 'dtype': 'float32'}
404045.6875
0.4254
0.222


log_softmax
{'data': (10000, 100), 'axis': 0, 'dtype': 'float64'}
412025.6875
4.3692
3.8542


logical_not
{'data': (1024, 1024)}
2097.1521
0.0384
---


logical_not
{'data': (10000, 1)}
20.0
0.0102
---


logical_not
{'data': (10000, 100)}
2000.0
0.0568
---


make_loss
{'data': (1024, 1024)}
2097.1521
0.3632
---


make_loss
{'data': (10000, 1)}
20.0
0.0142
---


make_loss
{'data': (10000, 100)}
2000.0
0.456
---


max
{'data': (1024, 1024), 'axis': 0}
225433.0156
1.1784
0.9798


max
{'data': (10000, 1), 'axis': 0}
225430.9688
0.3048
0.021


max
{'data': (10000, 100), 'axis': 0}
225431.3594
1.257
0.9096


max_axis
{'data': (1024, 1024), 'axis': 0}
225437.3125
1.0052
---


max_axis
{'data': (10000, 1), 'axis': 0}
225435.2656
0.248
---


max_axis
{'data': (10000, 100), 'axis': 0}
225435.6562
1.1448
---


mean
{'data': (1024, 1024), 'axis': 0}
225441.6094
1.192
1.6202


mean
{'data': (10000, 1), 'axis': 0}
225439.5625
0.339
0.0298


mean
{'data': (10000, 100), 'axis': 0}
225439.9531
1.2318
1.4816


min
{'data': (1024, 1024), 'axis': 0}
225445.9062
1.097
0.9514


min
{'data': (10000, 1), 'axis': 0}
225443.8594
0.3134
0.0212


min
{'data': (10000, 100), 'axis': 0}
225444.2656
1.208
0.9864


min_axis
{'data': (1024, 1024), 'axis': 0}
225450.2031
1.0054
---


min_axis
{'data': (10000, 1), 'axis': 0}
225448.1562
0.2446
---


min_axis
{'data': (10000, 100), 'axis': 0}
225448.5625
1.1444
---


moments
{'data': (1024, 1024), 'axes': [0, 1]}
7196885.5
51.8952
---


moments
{'data': (10000, 1), 'axes': [0, 1]}
7196885.5
0.5656
---


moments
{'data': (10000, 100), 'axes': [0, 1]}
7196885.5
52.1542
---


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}
1361506.5
0.3314
---


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}
1359449.375
0.0208
---


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}
1363429.375
0.2442
---


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}
1367720.75
0.1882
---


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}
1365663.625
0.0178
---


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}
1369643.625
0.1814
---


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}
1373935.125
0.174
---


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}
1371878.0
0.0158
---


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}
1375858.0
0.1712
---


multi_all_finite
{'args': [(1024, 1024)], 'num_arrays': 1}
2655663.0
0.0708
---


multi_all_finite
{'args': [(10000, 1)], 'num_arrays': 1}
2655663.0
0.0588
---


multi_all_finite
{'args': [(10000, 10)], 'num_arrays': 1}
2655663.0
0.0604
---


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}
2832922.25
4.0508
---


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}
2830865.0
0.074
---


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}
2834845.0
0.9
---


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)>'}
---
0.0135
---


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)>'}
---
0.0148
---


multi_sgd_update
{'args0': '<NDArray 5x5 @cpu(0)>', 'args1': '<NDArray 5x5 @cpu(0)>', 'lrs': 0.1, 'wds': 0.2, 'out': '<NDArray 5x5 @cpu(0)>'}
---
0.036
---


multi_sum_sq
{'args': [(1024, 1024)], 'num_arrays': 1}
2655663.0
0.0088
---


multi_sum_sq
{'args': [(10000, 1)], 'num_arrays': 1}
2655663.0
0.008
---


multi_sum_sq
{'args': [(10000, 10)], 'num_arrays': 1}
2655663.0
0.0078
---


nag_mom_update
{'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4}
1380149.375
0.274
---


nag_mom_update
{'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4}
1378092.25
0.0172
---


nag_mom_update
{'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4}
1382072.25
0.2622
---


nanprod
{'data': (1024, 1024), 'axis': 0}
225454.5
1.2514
0.9976


nanprod
{'data': (10000, 1), 'axis': 0}
225452.4531
0.301
0.0212


nanprod
{'data': (10000, 100), 'axis': 0}
225452.8594
1.2488
0.9458


nansum
{'data': (1024, 1024), 'axis': 0}
225458.7969
1.201
1.0496


nansum
{'data': (10000, 1), 'axis': 0}
225456.75
0.3112
0.0216


nansum
{'data': (10000, 100), 'axis': 0}
225457.1562
1.2022
0.8632


negative
{'data': (1024, 1024)}
2097.1521
0.0402
---


negative
{'data': (10000, 1)}
20.0
0.0326
---


negative
{'data': (10000, 100)}
2000.0
0.0602
---


norm
{'data': (1024, 1024), 'axis': 0}
225463.0938
1.9666
1.4628


norm
{'data': (10000, 1), 'axis': 0}
225461.0469
0.3276
0.0254


norm
{'data': (10000, 100), 'axis': 0}
225461.4531
1.3678
1.3804


one_hot
{'indices': (1, 1), 'depth': 0, 'dtype': 'float32'}
---
0.008
---


one_hot
{'indices': (1, 1), 'depth': 0, 'dtype': 'int32'}
---
0.008
---


one_hot
{'indices': (1, 1), 'depth': 0, 'dtype': 'float32'}
---
0.0078
---


ones_like
{'data': (1024, 1024)}
2097.1521
0.0376
---


ones_like
{'data': (10000, 1)}
20.0
0.0176
---


ones_like
{'data': (10000, 100)}
2000.0
0.0436
---


pick
{'data': (1024, 1024), 'index': (1, 1024), 'axis': 0}
255470.1875
0.0192
0.2586


pick
{'data': (10000, 1), 'index': (1, 1), 'axis': 0}
255468.1406
0.0158
0.0196


pick
{'data': (10000, 100), 'index': (1, 100), 'axis': 0}
255468.5469
0.0168
0.2888


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)>'}
---
0.017
---


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)>'}
---
0.0153
---


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)>'}
---
0.015
---


prod
{'data': (1024, 1024), 'axis': 0}
225467.3906
1.7888
1.4696


prod
{'data': (10000, 1), 'axis': 0}
225465.3438
0.2978
0.0252


prod
{'data': (10000, 100), 'axis': 0}
225465.75
1.4932
1.4082


radians
{'data': (1024, 1024)}
2097.1521
0.0478
0.0406


radians
{'data': (10000, 1)}
20.0
0.0154
0.0136


radians
{'data': (10000, 100)}
2000.0
0.053
0.039


random_exponential
{'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
2.8246
---


random_exponential
{'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0456
---


random_exponential
{'shape': (10000, 100), 'dtype': 'float64'}
4000.0
2.6586
---


random_gamma
{'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
7.3196
---


random_gamma
{'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0824
---


random_gamma
{'shape': (10000, 100), 'dtype': 'float64'}
4000.0
8.7672
---


random_generalized_negative_binomial
{'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
11.67
---


random_generalized_negative_binomial
{'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.1076
---


random_generalized_negative_binomial
{'shape': (10000, 100), 'dtype': 'float64'}
4000.0
10.1344
---


random_negative_binomial
{'k': 1, 'p': 1, 'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
8.5006
---


random_negative_binomial
{'k': 1, 'p': 1, 'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0944
---


random_negative_binomial
{'k': 1, 'p': 1, 'shape': (10000, 100), 'dtype': 'float64'}
4000.0
8.1284
---


random_normal
{'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
4.2624
---


random_normal
{'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0392
---


random_normal
{'shape': (10000, 100), 'dtype': 'float64'}
4000.0
4.4492
---


random_pdf_dirichlet
{'sample': (2,), 'alpha': [0.0, 2.5]}
0.002
0.009
---


random_pdf_exponential
{'sample': (2,), 'lam': [1.0, 8.5]}
0.004
0.0094
---


random_pdf_gamma
{'sample': (2,), 'alpha': [0.0, 2.5], 'beta': [1.0, 0.7]}
0.004
0.0122
---


random_pdf_generalized_negative_binomial
{'sample': (2,), 'mu': [2.0, 2.5], 'alpha': [0.0, 2.5]}
0.004
0.012
---


random_pdf_negative_binomial
{'sample': (2,), 'k': [20, 49], 'p': [0.4, 0.77]}
0.004
0.0124
---


random_pdf_normal
{'sample': (2,), 'mu': [2.0, 2.5], 'sigma': [1.0, 3.7]}
0.004
0.012
---


random_pdf_poisson
{'sample': (2,), 'lam': [1.0, 8.5]}
0.004
0.0122
---


random_pdf_uniform
{'sample': (2,), 'low': [0.0, 2.5], 'high': [1.0, 3.7]}
0.004
0.0126
---


random_poisson
{'shape': (1024, 1024), 'dtype': 'float16'}
1048.576
2.5328
---


random_poisson
{'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0348
---


random_poisson
{'shape': (10000, 100), 'dtype': 'float64'}
4000.0
2.2502
---


random_randint
{'low': 0, 'high': 5, 'shape': (1024, 1024), 'dtype': 'int32'}
2097.1521
1.7264
---


random_randint
{'low': 0, 'high': 5, 'shape': (10000, 1), 'dtype': 'int64'}
40.0
0.0282
---


random_randint
{'low': 0, 'high': 5, 'shape': (10000, 100), 'dtype': 'int32'}
2000.0
1.6516
---


random_uniform
{'low': 0, 'high': 5, 'shape': (1024, 1024), 'dtype': 'float16'}
2097.1521
1.4548
---


random_uniform
{'low': 0, 'high': 5, 'shape': (10000, 1), 'dtype': 'float32'}
20.0
0.0336
---


random_uniform
{'low': 0, 'high': 5, 'shape': (10000, 100), 'dtype': 'float64'}
8000.0
1.6414
---


ravel_multi_index
{'data': (2, 1024), 'shape': (1024, 1024)}
255474.4844
0.0172
---


ravel_multi_index
{'data': (2, 1024), 'shape': (10000, 1)}
255476.5312
0.0168
---


ravel_multi_index
{'data': (2, 1024), 'shape': (10000, 100)}
255478.5938
0.0182
---


rcbrt
{'data': (1024, 1024)}
2097.1521
1.4202
1.507


rcbrt
{'data': (10000, 1)}
20.0
0.0256
0.0246


rcbrt
{'data': (10000, 100)}
2000.0
1.2624
1.3266


reciprocal
{'data': (1024, 1024)}
2097.1521
0.0528
0.0528


reciprocal
{'data': (10000, 1)}
20.0
0.0168
0.0122


reciprocal
{'data': (10000, 100)}
2000.0
0.051
0.0504


relu
{'data': (1024, 1024)}
2097.1521
0.0712
0.1052


relu
{'data': (10000, 1)}
20.0
0.0118
0.0118


relu
{'data': (10000, 100)}
2000.0
0.0634
0.092


reset_arrays
{'args': [(1024, 1024)], 'num_arrays': 1}
---
0.005
---


reset_arrays
{'args': [(10000, 1)], 'num_arrays': 1}
---
0.0032
---


reset_arrays
{'args': [(10000, 10)], 'num_arrays': 1}
---
0.003
---


reshape_like
{'lhs': (1024, 1024), 'rhs': (1024, 1024)}
2097.1521
0.3992
---


reshape_like
{'lhs': (10000, 10), 'rhs': (10000, 10)}
200.0
0.0536
---


reshape_like
{'lhs': (10000, 1), 'rhs': (10000, 1)}
20.0
0.0104
---


rint
{'data': (1024, 1024)}
2097.1521
0.2502
---


rint
{'data': (10000, 1)}
20.0
0.0124
---


rint
{'data': (10000, 100)}
2000.0
0.2364
---


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}
1386363.75
0.4028
---


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}
1384306.5
0.0232
---


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}
1388286.5
0.8
---


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}
1392578.0
0.5422
---


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}
1390520.875
0.0378
---


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}
1394500.875
0.804
---


round
{'data': (1024, 1024)}
2097.1521
0.3482
---


round
{'data': (10000, 1)}
20.0
0.0146
---


round
{'data': (10000, 100)}
2000.0
0.4528
---


rsqrt
{'data': (1024, 1024)}
2097.1521
0.6472
0.6758


rsqrt
{'data': (10000, 1)}
20.0
0.0184
0.0156


rsqrt
{'data': (10000, 100)}
2000.0
0.601
0.654


sample_exponential
{'lam': [1.0, 8.5], 'shape': (1024, 1024), 'dtype': 'float16'}
2097.1521
6.1304
---


sample_exponential
{'lam': [1.0, 8.5], 'shape': (10000, 1), 'dtype': 'float32'}
40.0
0.0698
---


sample_exponential
{'lam': [1.0, 8.5], 'shape': (10000, 100), 'dtype': 'float64'}
16000.0
5.2318
---


sample_gamma
{'alpha': [0.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'beta': [1.0, 0.7]}
2097.1521
18.391
---


sample_gamma
{'alpha': [0.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'beta': [1.0, 0.7]}
40.0
0.2092
---


sample_gamma
{'alpha': [0.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'beta': [1.0, 0.7]}
8000.0
21.4558
---


sample_generalized_negative_binomial
{'mu': [2.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'alpha': [0.0, 2.5]}
2097.1521
35.7084
---


sample_generalized_negative_binomial
{'mu': [2.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'alpha': [0.0, 2.5]}
40.0
0.435
---


sample_generalized_negative_binomial
{'mu': [2.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'alpha': [0.0, 2.5]}
8000.0
34.1968
---


sample_multinomial
{'data': (32, 32), 'shape': (1024, 1024), 'dtype': 'float16'}
81404.0781
257.0554
---


sample_multinomial
{'data': (32, 32), 'shape': (10000, 1), 'dtype': 'float32'}
49129.6484
1.7624
---


sample_multinomial
{'data': (32, 32), 'shape': (10000, 100), 'dtype': 'float64'}
304489.6562
171.6686
---


sample_negative_binomial
{'k': [20, 49], 'shape': (1024, 1024), 'dtype': 'float16', 'p': [0.4, 0.77]}
182781.1094
299.2208
---


sample_negative_binomial
{'k': [20, 49], 'shape': (10000, 1), 'dtype': 'float32', 'p': [0.4, 0.77]}
180763.9531
2.8592
---


sample_negative_binomial
{'k': [20, 49], 'shape': (10000, 100), 'dtype': 'float64', 'p': [0.4, 0.77]}
196723.9531
284.7328
---


sample_normal
{'mu': [2.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'sigma': [1.0, 3.7]}
195015.4062
6.015
---


sample_normal
{'mu': [2.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'sigma': [1.0, 3.7]}
192998.2656
0.0668
---


sample_normal
{'mu': [2.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'sigma': [1.0, 3.7]}
208958.2656
5.7466
---


sample_poisson
{'lam': [1.0, 8.5], 'shape': (1024, 1024), 'dtype': 'float16'}
207249.7188
6.8382
---


sample_poisson
{'lam': [1.0, 8.5], 'shape': (10000, 1), 'dtype': 'float32'}
205232.5625
0.087
---


sample_poisson
{'lam': [1.0, 8.5], 'shape': (10000, 100), 'dtype': 'float64'}
221192.5625
6.6176
---


sample_uniform
{'low': [0.0, 2.5], 'shape': (1024, 1024), 'dtype': 'float16', 'high': [1.0, 3.7]}
219484.0156
1.6996
---


sample_uniform
{'low': [0.0, 2.5], 'shape': (10000, 1), 'dtype': 'float32', 'high': [1.0, 3.7]}
217466.8594
0.038
---


sample_uniform
{'low': [0.0, 2.5], 'shape': (10000, 100), 'dtype': 'float64', 'high': [1.0, 3.7]}
233426.8594
1.4822
---


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}
1398792.25
0.1456
---


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}
1396735.125
0.013
---


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}
1400715.125
0.1264
---


sgd_update
{'weight': (1024, 1024), 'grad': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4, 'lazy_update': 0}
1405006.625
0.0944
---


sgd_update
{'weight': (10000, 1), 'grad': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4, 'lazy_update': 0}
1402949.5
0.0164
---


sgd_update
{'weight': (10000, 100), 'grad': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4, 'lazy_update': 0}
1406929.5
0.0902
---


shape_array
{'data': (1024, 1024)}
0.008
0.008
---


shape_array
{'data': (10000, 1)}
0.008
0.005
---


shape_array
{'data': (10000, 100)}
0.008
0.005
---


shuffle
{'data': (1024, 1024)}
2097.1521
1.0618
---


shuffle
{'data': (10000, 1)}
20.0
0.573
---


shuffle
{'data': (10000, 100)}
2000.0
1.6734
---


sigmoid
{'data': (1024, 1024)}
2097.1521
0.688
0.0498


sigmoid
{'data': (10000, 1)}
20.0
0.0198
0.011


sigmoid
{'data': (10000, 100)}
2000.0
0.6562
0.049


sign
{'data': (1024, 1024)}
2097.1521
0.2382
0.0394


sign
{'data': (10000, 1)}
20.0
0.0124
0.0114


sign
{'data': (10000, 100)}
2000.0
0.2266
0.0346


signsgd_update
{'weight': (1024, 1024), 'grad': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4}
1411220.875
0.124
---


signsgd_update
{'weight': (10000, 1), 'grad': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4}
1409163.75
0.0126
---


signsgd_update
{'weight': (10000, 100), 'grad': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4}
1413143.75
0.1178
---


signum_update
{'weight': (1024, 1024), 'grad': (1024, 1024), 'mom': (1024, 1024), 'lr': 0.1, 'wd': 0.1, 'rescale_grad': 0.4}
1417435.25
0.3168
---


signum_update
{'weight': (10000, 1), 'grad': (10000, 1), 'mom': (10000, 1), 'lr': 0.5, 'wd': 0.5, 'rescale_grad': 0.4}
1415378.125
0.021
---


signum_update
{'weight': (10000, 100), 'grad': (10000, 100), 'mom': (10000, 100), 'lr': 0.9, 'wd': 0.9, 'rescale_grad': 0.4}
1419358.125
0.292
---


sin
{'data': (1024, 1024)}
2097.1521
0.4764
0.485


sin
{'data': (10000, 1)}
20.0
0.0146
0.0134


sin
{'data': (10000, 100)}
2000.0
0.4518
0.474


sinh
{'data': (1024, 1024)}
2097.1521
1.4904
0.9036


sinh
{'data': (10000, 1)}
20.0
0.0244
0.018


sinh
{'data': (10000, 100)}
2000.0
1.424
0.8778


size_array
{'data': (1024, 1024)}
0.004
0.0062
---


size_array
{'data': (10000, 1)}
0.004
0.0056
---


size_array
{'data': (10000, 100)}
0.004
0.0062
---


slice
{'data': (1024, 1024), 'begin': 0, 'end': 1}
255482.6875
0.017
0.025


slice
{'data': (10000, 1), 'begin': 0, 'end': 1}
255480.6406
0.0156
0.0108


slice
{'data': (10000, 100), 'begin': 0, 'end': 1}
255481.0312
0.0142
0.0288


slice_axis
{'data': (1024, 1024), 'axis': 0, 'begin': 0, 'end': 1}
255486.9844
0.0128
0.0254


slice_axis
{'data': (10000, 1), 'axis': 0, 'begin': 0, 'end': 1}
255484.9375
0.0124
0.0158


slice_axis
{'data': (10000, 100), 'axis': 0, 'begin': 0, 'end': 1}
255485.3281
0.0126
0.0268


slice_like
{'data': (1024, 1024), 'shape_like': (100, 100), 'axes': [0, 1]}
255545.1406
0.0158
0.036


slice_like
{'data': (10000, 1), 'shape_like': (10, 1), 'axes': [0, 1]}
255525.1719
0.0148
0.0164


slice_like
{'data': (10000, 100), 'shape_like': (100, 10), 'axes': [0, 1]}
255529.1562
0.0152
0.0312


smooth_l1
{'data': (1024, 1024)}
2655740.0
0.2966
0.219


smooth_l1
{'data': (10000, 1)}
2653683.0
0.013
0.0102


smooth_l1
{'data': (10000, 100)}
2657663.0
0.2484
0.204


softmax
{'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'}
411171.4062
3.2496
1.7626


softmax
{'data': (10000, 1), 'axis': 0, 'dtype': 'float32'}
410162.8438
0.3944
0.034


softmax
{'data': (10000, 100), 'axis': 0, 'dtype': 'float64'}
418142.8438
4.4234
1.9228


softmax_cross_entropy
{'data': (1024, 1024), 'label': (1024,)}
2655663.0
0.5932
---


softmin
{'data': (1024, 1024), 'axis': 0, 'dtype': 'float16'}
417288.5625
3.3336
1.7892


softmin
{'data': (10000, 1), 'axis': 0, 'dtype': 'float32'}
416280.0
0.4106
0.0374


softmin
{'data': (10000, 100), 'axis': 0, 'dtype': 'float64'}
424260.0
4.5022
1.982


softsign
{'data': (1024, 1024)}
2097.1521
0.0452
0.0466


softsign
{'data': (10000, 1)}
20.0
0.0114
0.0104


softsign
{'data': (10000, 100)}
2000.0
0.1784
0.097


sort
{'data': (1024, 1024), 'axis': 0}
242180.9531
66.2036
---


sort
{'data': (10000, 1), 'axis': 0}
235969.5
1.4408
---


sort
{'data': (10000, 100), 'axis': 0}
243909.5
63.1696
---


space_to_depth
{'data': (1, 4, 2, 4), 'block_size': 2}
244628.2969
0.017
---


space_to_depth
{'data': (10, 25, 10, 100), 'block_size': 5}
245128.2969
0.8904
---


sqrt
{'data': (1024, 1024)}
2097.1521
0.6336
0.0488


sqrt
{'data': (10000, 1)}
20.0
0.0216
0.0098


sqrt
{'data': (10000, 100)}
2000.0
0.6446
0.1016


square
{'data': (1024, 1024)}
2097.1521
0.0366
0.0438


square
{'data': (10000, 1)}
20.0
0.0142
0.012


square
{'data': (10000, 100)}
2000.0
0.0456
0.0474


squeeze
{'data': (1, 1024, 1024), 'axis': 0}
2839136.5
0.4142
0.625


squeeze
{'data': (32, 1, 256, 256), 'axis': 1}
2845428.0
1.314
1.165


stop_gradient
{'data': (1024, 1024)}
2097.1521
0.3286
---


stop_gradient
{'data': (10000, 1)}
20.0
0.0116
---


stop_gradient
{'data': (10000, 100)}
2000.0
0.3582
---


sum
{'data': (1024, 1024), 'axis': 0}
225471.8906
1.8752
1.4526


sum
{'data': (10000, 1), 'axis': 0}
225469.8438
0.369
0.0228


sum
{'data': (10000, 100), 'axis': 0}
225470.25
1.7088
1.3704


sum_axis
{'data': (1024, 1024), 'axis': 0}
225474.1406
1.9974
---


sum_axis
{'data': (10000, 1), 'axis': 0}
225474.1406
0.3746
---


sum_axis
{'data': (10000, 100), 'axis': 0}
225474.3438
1.7386
---


swapaxes
{'data': (1024, 1024), 'dim1': 0, 'dim2': 1}
247225.4531
3.0952
---


swapaxes
{'data': (10000, 1), 'dim1': 0, 'dim2': 1}
247265.4531
0.0416
---


swapaxes
{'data': (10000, 100), 'dim1': 0, 'dim2': 1}
251245.4531
1.9396
---


take
{'a': (1024, 1024), 'indices': (1, 1), 'axis': 0}
255533.2969
0.0142
0.0332


tan
{'data': (1024, 1024)}
2097.1521
1.1422
0.0506


tan
{'data': (10000, 1)}
20.0
0.019
0.01


tan
{'data': (10000, 100)}
2000.0
1.0806
0.0492


tanh
{'data': (1024, 1024)}
2097.1521
1.3942
0.0494


tanh
{'data': (10000, 1)}
40.0
0.0642
0.0092


tanh
{'data': (10000, 100)}
4000.0
1.339
0.0582


topk
{'data': (1024, 1024), 'axis': 0, 'k': 1, 'dtype': 'float32'}
237915.6406
67.2932
---


topk
{'data': (10000, 1), 'axis': 0, 'k': 1, 'dtype': 'int32'}
237913.5938
0.5962
---


topk
{'data': (10000, 100), 'axis': 0, 'k': 1, 'dtype': 'float32'}
237914.0
55.9822
---


transpose
{'data': (1024, 1024), 'axes': [0, 1]}
255536.9062
0.3544
---


transpose
{'data': (10000, 1), 'axes': [0, 1]}
253479.75
0.0162
---


transpose
{'data': (10000, 100), 'axes': [0, 1]}
257459.75
0.3684
---


trunc
{'data': (1024, 1024)}
2097.1521
0.2564
---


trunc
{'data': (10000, 1)}
20.0
0.0124
---


trunc
{'data': (10000, 100)}
2000.0
0.2468
---


where
{'condition': (1024,), 'x': (1024, 1024), 'y': (1024, 1024)}
261822.7031
0.586
1.0934


where
{'condition': (10000,), 'x': (10000, 1), 'y': (10000, 1)}
259765.5469
0.0264
0.0226


where
{'condition': (10000,), 'x': (10000, 100), 'y': (10000, 100)}
263745.5625
0.5384
1.065


zeros_like
{'data': (1024, 1024)}
2097.1521
0.0236
---


zeros_like
{'data': (10000, 1)}
20.0
0.0098
---


zeros_like
{'data': (10000, 100)}
2000.0
0.0276
---