size,operation,boundary,mode,device,round,ms
256,scale,computed,gpu_shared,d0,0,2.697911
256,scale,computed,gpu_copy,d1,0,3.285523
256,scale,computed,gpu_shared,d1,0,1.013462
256,scale,computed,gpu_copy,i0,0,1.174532
256,scale,computed,gpu_shared,i0,0,0.798693
256,scale,computed,cpu,cpu,0,8.563548
256,scale,computed,gpu_copy,d0,0,2.561448
256,scale,computed,gpu_copy,d1,1,2.166064
256,scale,computed,gpu_shared,d1,1,0.867652
256,scale,computed,gpu_copy,i0,1,1.008964
256,scale,computed,gpu_shared,i0,1,0.849708
256,scale,computed,cpu,cpu,1,8.095278
256,scale,computed,gpu_copy,d0,1,2.000075
256,scale,computed,gpu_shared,d0,1,2.299712
256,scale,computed,gpu_shared,d1,2,1.618056
256,scale,computed,gpu_copy,i0,2,1.282632
256,scale,computed,gpu_shared,i0,2,1.29212
256,scale,computed,cpu,cpu,2,8.686957
256,scale,computed,gpu_copy,d0,2,1.957175
256,scale,computed,gpu_shared,d0,2,0.822127
256,scale,computed,gpu_copy,d1,2,1.665634
256,scale,computed,gpu_copy,i0,3,1.086228
256,scale,computed,gpu_shared,i0,3,0.752999
256,scale,computed,cpu,cpu,3,9.985218
256,scale,computed,gpu_copy,d0,3,2.053975
256,scale,computed,gpu_shared,d0,3,0.871168
256,scale,computed,gpu_copy,d1,3,1.536976
256,scale,computed,gpu_shared,d1,3,0.920219
256,scale,computed,gpu_shared,i0,4,1.338777
256,scale,computed,cpu,cpu,4,8.036298
256,scale,computed,gpu_copy,d0,4,9.145749
256,scale,computed,gpu_shared,d0,4,1.53987
256,scale,computed,gpu_copy,d1,4,1.672447
256,scale,computed,gpu_shared,d1,4,0.90952
256,scale,computed,gpu_copy,i0,4,1.112868
256,scale,computed,cpu,cpu,5,8.139209
256,scale,computed,gpu_copy,d0,5,2.568021
256,scale,computed,gpu_shared,d0,5,2.391041
256,scale,computed,gpu_copy,d1,5,1.934894
256,scale,computed,gpu_shared,d1,5,1.000509
256,scale,computed,gpu_copy,i0,5,1.473647
256,scale,computed,gpu_shared,i0,5,1.354856
256,scale,computed,gpu_copy,d0,6,7.024789
256,scale,computed,gpu_shared,d0,6,1.783713
256,scale,computed,gpu_copy,d1,6,1.645957
256,scale,computed,gpu_shared,d1,6,0.972837
256,scale,computed,gpu_copy,i0,6,1.108279
256,scale,computed,gpu_shared,i0,6,1.261573
256,scale,computed,cpu,cpu,6,8.718475
256,scale,computed,gpu_shared,d0,7,1.83529
256,scale,computed,gpu_copy,d1,7,1.932029
256,scale,computed,gpu_shared,d1,7,0.983828
256,scale,computed,gpu_copy,i0,7,0.983397
256,scale,computed,gpu_shared,i0,7,0.891537
256,scale,computed,cpu,cpu,7,8.153516
256,scale,computed,gpu_copy,d0,7,2.743426
256,scale,computed,gpu_copy,d1,8,1.783924
256,scale,computed,gpu_shared,d1,8,0.94726
256,scale,computed,gpu_copy,i0,8,0.934495
256,scale,computed,gpu_shared,i0,8,0.867451
256,scale,computed,cpu,cpu,8,8.157383
256,scale,computed,gpu_copy,d0,8,1.630068
256,scale,computed,gpu_shared,d0,8,1.551952
256,scale,computed,gpu_shared,d1,9,1.261544
256,scale,computed,gpu_copy,i0,9,1.12482
256,scale,computed,gpu_shared,i0,9,0.704318
256,scale,computed,cpu,cpu,9,7.802383
256,scale,computed,gpu_copy,d0,9,2.849153
256,scale,computed,gpu_shared,d0,9,1.161758
256,scale,computed,gpu_copy,d1,9,2.021786
256,scale,nu_readback,gpu_shared,d0,0,25.088543
256,scale,nu_readback,gpu_copy,d1,0,19.021804
256,scale,nu_readback,gpu_shared,d1,0,17.805996
256,scale,nu_readback,gpu_copy,i0,0,23.64956
256,scale,nu_readback,gpu_shared,i0,0,18.451145
256,scale,nu_readback,cpu,cpu,0,11.333783
256,scale,nu_readback,gpu_copy,d0,0,19.397662
256,scale,nu_readback,gpu_copy,d1,1,20.032882
256,scale,nu_readback,gpu_shared,d1,1,27.48776
256,scale,nu_readback,gpu_copy,i0,1,26.558714
256,scale,nu_readback,gpu_shared,i0,1,23.129304
256,scale,nu_readback,cpu,cpu,1,12.253762
256,scale,nu_readback,gpu_copy,d0,1,46.278375
256,scale,nu_readback,gpu_shared,d0,1,34.302659
256,scale,nu_readback,gpu_shared,d1,2,20.151282
256,scale,nu_readback,gpu_copy,i0,2,27.070926
256,scale,nu_readback,gpu_shared,i0,2,20.707555
256,scale,nu_readback,cpu,cpu,2,11.962411
256,scale,nu_readback,gpu_copy,d0,2,21.241016
256,scale,nu_readback,gpu_shared,d0,2,29.894621
256,scale,nu_readback,gpu_copy,d1,2,19.387093
256,scale,nu_readback,gpu_copy,i0,3,23.316021
256,scale,nu_readback,gpu_shared,i0,3,19.613252
256,scale,nu_readback,cpu,cpu,3,11.521792
256,scale,nu_readback,gpu_copy,d0,3,22.057834
256,scale,nu_readback,gpu_shared,d0,3,33.019867
256,scale,nu_readback,gpu_copy,d1,3,21.537066
256,scale,nu_readback,gpu_shared,d1,3,19.450261
256,scale,nu_readback,gpu_shared,i0,4,24.055705
256,scale,nu_readback,cpu,cpu,4,10.526423
256,scale,nu_readback,gpu_copy,d0,4,20.910342
256,scale,nu_readback,gpu_shared,d0,4,33.345391
256,scale,nu_readback,gpu_copy,d1,4,20.23616
256,scale,nu_readback,gpu_shared,d1,4,19.504791
256,scale,nu_readback,gpu_copy,i0,4,25.143325
256,scale,nu_readback,cpu,cpu,5,11.578929
256,scale,nu_readback,gpu_copy,d0,5,26.306025
256,scale,nu_readback,gpu_shared,d0,5,29.391837
256,scale,nu_readback,gpu_copy,d1,5,20.422776
256,scale,nu_readback,gpu_shared,d1,5,19.266108
256,scale,nu_readback,gpu_copy,i0,5,24.342417
256,scale,nu_readback,gpu_shared,i0,5,22.816793
256,scale,nu_readback,gpu_copy,d0,6,35.282259
256,scale,nu_readback,gpu_shared,d0,6,24.724227
256,scale,nu_readback,gpu_copy,d1,6,27.763012
256,scale,nu_readback,gpu_shared,d1,6,21.117006
256,scale,nu_readback,gpu_copy,i0,6,23.731232
256,scale,nu_readback,gpu_shared,i0,6,18.849774
256,scale,nu_readback,cpu,cpu,6,12.522371
256,scale,nu_readback,gpu_shared,d0,7,31.410978
256,scale,nu_readback,gpu_copy,d1,7,27.348431
256,scale,nu_readback,gpu_shared,d1,7,22.283512
256,scale,nu_readback,gpu_copy,i0,7,21.490129
256,scale,nu_readback,gpu_shared,i0,7,17.632684
256,scale,nu_readback,cpu,cpu,7,10.831721
256,scale,nu_readback,gpu_copy,d0,7,23.915465
256,scale,nu_readback,gpu_copy,d1,8,27.174809
256,scale,nu_readback,gpu_shared,d1,8,20.772556
256,scale,nu_readback,gpu_copy,i0,8,24.8603
256,scale,nu_readback,gpu_shared,i0,8,19.378898
256,scale,nu_readback,cpu,cpu,8,12.324763
256,scale,nu_readback,gpu_copy,d0,8,35.112063
256,scale,nu_readback,gpu_shared,d0,8,32.379767
256,scale,nu_readback,gpu_shared,d1,9,21.495639
256,scale,nu_readback,gpu_copy,i0,9,24.454326
256,scale,nu_readback,gpu_shared,i0,9,20.7313
256,scale,nu_readback,cpu,cpu,9,11.300411
256,scale,nu_readback,gpu_copy,d0,9,27.405427
256,scale,nu_readback,gpu_shared,d0,9,32.28975
256,scale,nu_readback,gpu_copy,d1,9,21.545833
256,multiply,computed,gpu_shared,d0,0,8.036268
256,multiply,computed,gpu_copy,d1,0,8.95258
256,multiply,computed,gpu_shared,d1,0,6.338374
256,multiply,computed,gpu_copy,i0,0,8.948232
256,multiply,computed,gpu_shared,i0,0,4.871228
256,multiply,computed,cpu,cpu,0,17.648483
256,multiply,computed,gpu_copy,d0,0,11.985834
256,multiply,computed,gpu_copy,d1,1,7.069502
256,multiply,computed,gpu_shared,d1,1,6.312796
256,multiply,computed,gpu_copy,i0,1,9.06522
256,multiply,computed,gpu_shared,i0,1,4.767536
256,multiply,computed,cpu,cpu,1,18.57316
256,multiply,computed,gpu_copy,d0,1,9.325853
256,multiply,computed,gpu_shared,d0,1,3.964765
256,multiply,computed,gpu_shared,d1,2,6.224683
256,multiply,computed,gpu_copy,i0,2,7.239047
256,multiply,computed,gpu_shared,i0,2,4.994768
256,multiply,computed,cpu,cpu,2,20.740496
256,multiply,computed,gpu_copy,d0,2,14.207672
256,multiply,computed,gpu_shared,d0,2,13.665654
256,multiply,computed,gpu_copy,d1,2,7.19214
256,multiply,computed,gpu_copy,i0,3,8.933264
256,multiply,computed,gpu_shared,i0,3,4.921392
256,multiply,computed,cpu,cpu,3,19.0682
256,multiply,computed,gpu_copy,d0,3,14.466994
256,multiply,computed,gpu_shared,d0,3,13.449824
256,multiply,computed,gpu_copy,d1,3,6.127062
256,multiply,computed,gpu_shared,d1,3,6.317495
256,multiply,computed,gpu_shared,i0,4,8.152163
256,multiply,computed,cpu,cpu,4,17.025687
256,multiply,computed,gpu_copy,d0,4,12.157533
256,multiply,computed,gpu_shared,d0,4,12.743943
256,multiply,computed,gpu_copy,d1,4,7.68193
256,multiply,computed,gpu_shared,d1,4,6.2074
256,multiply,computed,gpu_copy,i0,4,9.301228
256,multiply,computed,cpu,cpu,5,18.059827
256,multiply,computed,gpu_copy,d0,5,5.499886
256,multiply,computed,gpu_shared,d0,5,13.489808
256,multiply,computed,gpu_copy,d1,5,6.675821
256,multiply,computed,gpu_shared,d1,5,6.377987
256,multiply,computed,gpu_copy,i0,5,9.332486
256,multiply,computed,gpu_shared,i0,5,4.890755
256,multiply,computed,gpu_copy,d0,6,8.674042
256,multiply,computed,gpu_shared,d0,6,13.987533
256,multiply,computed,gpu_copy,d1,6,5.123818
256,multiply,computed,gpu_shared,d1,6,4.971063
256,multiply,computed,gpu_copy,i0,6,5.419036
256,multiply,computed,gpu_shared,i0,6,4.802411
256,multiply,computed,cpu,cpu,6,17.448391
256,multiply,computed,gpu_shared,d0,7,7.518466
256,multiply,computed,gpu_copy,d1,7,4.946268
256,multiply,computed,gpu_shared,d1,7,5.038569
256,multiply,computed,gpu_copy,i0,7,5.455714
256,multiply,computed,gpu_shared,i0,7,4.821025
256,multiply,computed,cpu,cpu,7,17.082292
256,multiply,computed,gpu_copy,d0,7,10.62685
256,multiply,computed,gpu_copy,d1,8,6.270909
256,multiply,computed,gpu_shared,d1,8,5.249812
256,multiply,computed,gpu_copy,i0,8,5.649955
256,multiply,computed,gpu_shared,i0,8,4.820083
256,multiply,computed,cpu,cpu,8,15.991245
256,multiply,computed,gpu_copy,d0,8,4.499047
256,multiply,computed,gpu_shared,d0,8,6.63239
256,multiply,computed,gpu_shared,d1,9,5.500808
256,multiply,computed,gpu_copy,i0,9,5.540331
256,multiply,computed,gpu_shared,i0,9,4.998805
256,multiply,computed,cpu,cpu,9,17.881465
256,multiply,computed,gpu_copy,d0,9,4.361622
256,multiply,computed,gpu_shared,d0,9,3.492037
256,multiply,computed,gpu_copy,d1,9,6.14752
256,multiply,nu_readback,gpu_shared,d0,0,27.901248
256,multiply,nu_readback,gpu_copy,d1,0,27.893083
256,multiply,nu_readback,gpu_shared,d1,0,25.46889
256,multiply,nu_readback,gpu_copy,i0,0,28.929849
256,multiply,nu_readback,gpu_shared,i0,0,28.158797
256,multiply,nu_readback,cpu,cpu,0,22.134286
256,multiply,nu_readback,gpu_copy,d0,0,45.004849
256,multiply,nu_readback,gpu_copy,d1,1,26.566939
256,multiply,nu_readback,gpu_shared,d1,1,23.714531
256,multiply,nu_readback,gpu_copy,i0,1,27.098998
256,multiply,nu_readback,gpu_shared,i0,1,23.199665
256,multiply,nu_readback,cpu,cpu,1,22.870273
256,multiply,nu_readback,gpu_copy,d0,1,28.841335
256,multiply,nu_readback,gpu_shared,d0,1,33.486282
256,multiply,nu_readback,gpu_shared,d1,2,24.72555
256,multiply,nu_readback,gpu_copy,i0,2,27.168157
256,multiply,nu_readback,gpu_shared,i0,2,23.71425
256,multiply,nu_readback,cpu,cpu,2,21.91047
256,multiply,nu_readback,gpu_copy,d0,2,35.865563
256,multiply,nu_readback,gpu_shared,d0,2,28.239326
256,multiply,nu_readback,gpu_copy,d1,2,25.975441
256,multiply,nu_readback,gpu_copy,i0,3,27.3211
256,multiply,nu_readback,gpu_shared,i0,3,25.647712
256,multiply,nu_readback,cpu,cpu,3,20.494399
256,multiply,nu_readback,gpu_copy,d0,3,32.992274
256,multiply,nu_readback,gpu_shared,d0,3,30.704416
256,multiply,nu_readback,gpu_copy,d1,3,27.407921
256,multiply,nu_readback,gpu_shared,d1,3,28.409712
256,multiply,nu_readback,gpu_shared,i0,4,27.45021
256,multiply,nu_readback,cpu,cpu,4,23.014671
256,multiply,nu_readback,gpu_copy,d0,4,33.283355
256,multiply,nu_readback,gpu_shared,d0,4,20.429599
256,multiply,nu_readback,gpu_copy,d1,4,24.183091
256,multiply,nu_readback,gpu_shared,d1,4,24.643006
256,multiply,nu_readback,gpu_copy,i0,4,30.903526
256,multiply,nu_readback,cpu,cpu,5,21.073926
256,multiply,nu_readback,gpu_copy,d0,5,32.669776
256,multiply,nu_readback,gpu_shared,d0,5,35.248476
256,multiply,nu_readback,gpu_copy,d1,5,25.890753
256,multiply,nu_readback,gpu_shared,d1,5,24.319155
256,multiply,nu_readback,gpu_copy,i0,5,27.314238
256,multiply,nu_readback,gpu_shared,i0,5,25.556483
256,multiply,nu_readback,gpu_copy,d0,6,32.302052
256,multiply,nu_readback,gpu_shared,d0,6,33.416593
256,multiply,nu_readback,gpu_copy,d1,6,23.862035
256,multiply,nu_readback,gpu_shared,d1,6,26.027126
256,multiply,nu_readback,gpu_copy,i0,6,27.603475
256,multiply,nu_readback,gpu_shared,i0,6,22.411621
256,multiply,nu_readback,cpu,cpu,6,23.286085
256,multiply,nu_readback,gpu_shared,d0,7,23.146215
256,multiply,nu_readback,gpu_copy,d1,7,25.003856
256,multiply,nu_readback,gpu_shared,d1,7,25.105995
256,multiply,nu_readback,gpu_copy,i0,7,29.63553
256,multiply,nu_readback,gpu_shared,i0,7,23.384488
256,multiply,nu_readback,cpu,cpu,7,20.09106
256,multiply,nu_readback,gpu_copy,d0,7,27.11584
256,multiply,nu_readback,gpu_copy,d1,8,30.230684
256,multiply,nu_readback,gpu_shared,d1,8,23.156084
256,multiply,nu_readback,gpu_copy,i0,8,27.316381
256,multiply,nu_readback,gpu_shared,i0,8,23.928769
256,multiply,nu_readback,cpu,cpu,8,19.887984
256,multiply,nu_readback,gpu_copy,d0,8,26.921869
256,multiply,nu_readback,gpu_shared,d0,8,30.522167
256,multiply,nu_readback,gpu_shared,d1,9,29.481834
256,multiply,nu_readback,gpu_copy,i0,9,28.271145
256,multiply,nu_readback,gpu_shared,i0,9,23.228609
256,multiply,nu_readback,cpu,cpu,9,20.384726
256,multiply,nu_readback,gpu_copy,d0,9,32.082455
256,multiply,nu_readback,gpu_shared,d0,9,28.832978
256,multiply,nu_readback,gpu_copy,d1,9,24.258742
512,scale,computed,gpu_shared,d0,0,13.358764
512,scale,computed,gpu_copy,d1,0,2.847439
512,scale,computed,gpu_shared,d1,0,1.633765
512,scale,computed,gpu_copy,i0,0,5.293173
512,scale,computed,gpu_shared,i0,0,0.995048
512,scale,computed,cpu,cpu,0,28.865859
512,scale,computed,gpu_copy,d0,0,14.351148
512,scale,computed,gpu_copy,d1,1,3.039005
512,scale,computed,gpu_shared,d1,1,1.476193
512,scale,computed,gpu_copy,i0,1,5.050191
512,scale,computed,gpu_shared,i0,1,1.655786
512,scale,computed,cpu,cpu,1,30.742506
512,scale,computed,gpu_copy,d0,1,17.034171
512,scale,computed,gpu_shared,d0,1,13.093772
512,scale,computed,gpu_shared,d1,2,2.456213
512,scale,computed,gpu_copy,i0,2,5.167629
512,scale,computed,gpu_shared,i0,2,1.442901
512,scale,computed,cpu,cpu,2,28.710501
512,scale,computed,gpu_copy,d0,2,16.488088
512,scale,computed,gpu_shared,d0,2,2.217529
512,scale,computed,gpu_copy,d1,2,2.707018
512,scale,computed,gpu_copy,i0,3,5.338877
512,scale,computed,gpu_shared,i0,3,1.607556
512,scale,computed,cpu,cpu,3,31.024149
512,scale,computed,gpu_copy,d0,3,12.809004
512,scale,computed,gpu_shared,d0,3,1.683538
512,scale,computed,gpu_copy,d1,3,3.007086
512,scale,computed,gpu_shared,d1,3,2.007239
512,scale,computed,gpu_shared,i0,4,4.223646
512,scale,computed,cpu,cpu,4,32.354119
512,scale,computed,gpu_copy,d0,4,15.283069
512,scale,computed,gpu_shared,d0,4,5.28118
512,scale,computed,gpu_copy,d1,4,3.025109
512,scale,computed,gpu_shared,d1,4,2.026364
512,scale,computed,gpu_copy,i0,4,5.807899
512,scale,computed,cpu,cpu,5,28.236831
512,scale,computed,gpu_copy,d0,5,2.036653
512,scale,computed,gpu_shared,d0,5,1.163992
512,scale,computed,gpu_copy,d1,5,2.673436
512,scale,computed,gpu_shared,d1,5,1.476022
512,scale,computed,gpu_copy,i0,5,1.306366
512,scale,computed,gpu_shared,i0,5,0.922624
512,scale,computed,gpu_copy,d0,6,7.830385
512,scale,computed,gpu_shared,d0,6,1.782642
512,scale,computed,gpu_copy,d1,6,3.008188
512,scale,computed,gpu_shared,d1,6,1.697323
512,scale,computed,gpu_copy,i0,6,1.303872
512,scale,computed,gpu_shared,i0,6,0.870648
512,scale,computed,cpu,cpu,6,30.428713
512,scale,computed,gpu_shared,d0,7,1.974638
512,scale,computed,gpu_copy,d1,7,2.773582
512,scale,computed,gpu_shared,d1,7,1.778835
512,scale,computed,gpu_copy,i0,7,1.86282
512,scale,computed,gpu_shared,i0,7,1.389952
512,scale,computed,cpu,cpu,7,30.637921
512,scale,computed,gpu_copy,d0,7,16.108673
512,scale,computed,gpu_copy,d1,8,3.479143
512,scale,computed,gpu_shared,d1,8,1.643753
512,scale,computed,gpu_copy,i0,8,4.989939
512,scale,computed,gpu_shared,i0,8,1.123787
512,scale,computed,cpu,cpu,8,28.781433
512,scale,computed,gpu_copy,d0,8,16.395445
512,scale,computed,gpu_shared,d0,8,13.94827
512,scale,computed,gpu_shared,d1,9,3.813164
512,scale,computed,gpu_copy,i0,9,4.819903
512,scale,computed,gpu_shared,i0,9,1.04988
512,scale,computed,cpu,cpu,9,29.368032
512,scale,computed,gpu_copy,d0,9,4.868354
512,scale,computed,gpu_shared,d0,9,12.197217
512,scale,computed,gpu_copy,d1,9,3.222285
512,scale,nu_readback,gpu_shared,d0,0,82.972826
512,scale,nu_readback,gpu_copy,d1,0,78.645307
512,scale,nu_readback,gpu_shared,d1,0,74.87234
512,scale,nu_readback,gpu_copy,i0,0,79.250762
512,scale,nu_readback,gpu_shared,i0,0,77.695814
512,scale,nu_readback,cpu,cpu,0,41.205441
512,scale,nu_readback,gpu_copy,d0,0,98.140221
512,scale,nu_readback,gpu_copy,d1,1,82.103442
512,scale,nu_readback,gpu_shared,d1,1,73.913508
512,scale,nu_readback,gpu_copy,i0,1,79.380253
512,scale,nu_readback,gpu_shared,i0,1,77.10683
512,scale,nu_readback,cpu,cpu,1,39.956281
512,scale,nu_readback,gpu_copy,d0,1,106.33882
512,scale,nu_readback,gpu_shared,d0,1,85.460557
512,scale,nu_readback,gpu_shared,d1,2,76.818695
512,scale,nu_readback,gpu_copy,i0,2,83.745461
512,scale,nu_readback,gpu_shared,i0,2,75.624747
512,scale,nu_readback,cpu,cpu,2,40.810287
512,scale,nu_readback,gpu_copy,d0,2,82.661258
512,scale,nu_readback,gpu_shared,d0,2,88.177745
512,scale,nu_readback,gpu_copy,d1,2,90.337867
512,scale,nu_readback,gpu_copy,i0,3,89.766907
512,scale,nu_readback,gpu_shared,i0,3,76.639672
512,scale,nu_readback,cpu,cpu,3,42.12508
512,scale,nu_readback,gpu_copy,d0,3,94.157272
512,scale,nu_readback,gpu_shared,d0,3,86.430038
512,scale,nu_readback,gpu_copy,d1,3,87.638784
512,scale,nu_readback,gpu_shared,d1,3,84.483863
512,scale,nu_readback,gpu_shared,i0,4,82.514876
512,scale,nu_readback,cpu,cpu,4,38.110452
512,scale,nu_readback,gpu_copy,d0,4,79.12029
512,scale,nu_readback,gpu_shared,d0,4,92.624184
512,scale,nu_readback,gpu_copy,d1,4,80.7139
512,scale,nu_readback,gpu_shared,d1,4,78.369265
512,scale,nu_readback,gpu_copy,i0,4,81.670267
512,scale,nu_readback,cpu,cpu,5,44.727623
512,scale,nu_readback,gpu_copy,d0,5,93.665639
512,scale,nu_readback,gpu_shared,d0,5,89.075883
512,scale,nu_readback,gpu_copy,d1,5,81.698719
512,scale,nu_readback,gpu_shared,d1,5,76.402822
512,scale,nu_readback,gpu_copy,i0,5,84.352339
512,scale,nu_readback,gpu_shared,i0,5,89.737282
512,scale,nu_readback,gpu_copy,d0,6,103.984577
512,scale,nu_readback,gpu_shared,d0,6,88.249618
512,scale,nu_readback,gpu_copy,d1,6,77.691416
512,scale,nu_readback,gpu_shared,d1,6,77.533021
512,scale,nu_readback,gpu_copy,i0,6,74.380686
512,scale,nu_readback,gpu_shared,i0,6,79.025254
512,scale,nu_readback,cpu,cpu,6,41.859836
512,scale,nu_readback,gpu_shared,d0,7,74.085407
512,scale,nu_readback,gpu_copy,d1,7,75.248829
512,scale,nu_readback,gpu_shared,d1,7,70.912634
512,scale,nu_readback,gpu_copy,i0,7,83.027879
512,scale,nu_readback,gpu_shared,i0,7,83.450744
512,scale,nu_readback,cpu,cpu,7,40.595959
512,scale,nu_readback,gpu_copy,d0,7,88.069384
512,scale,nu_readback,gpu_copy,d1,8,76.188905
512,scale,nu_readback,gpu_shared,d1,8,75.585644
512,scale,nu_readback,gpu_copy,i0,8,81.023716
512,scale,nu_readback,gpu_shared,i0,8,77.98454
512,scale,nu_readback,cpu,cpu,8,41.878391
512,scale,nu_readback,gpu_copy,d0,8,89.8495
512,scale,nu_readback,gpu_shared,d0,8,87.930726
512,scale,nu_readback,gpu_shared,d1,9,78.250825
512,scale,nu_readback,gpu_copy,i0,9,80.617811
512,scale,nu_readback,gpu_shared,i0,9,78.707122
512,scale,nu_readback,cpu,cpu,9,41.761945
512,scale,nu_readback,gpu_copy,d0,9,79.962023
512,scale,nu_readback,gpu_shared,d0,9,72.881862
512,scale,nu_readback,gpu_copy,d1,9,85.891638
512,multiply,computed,gpu_shared,d0,0,8.489339
512,multiply,computed,gpu_copy,d1,0,12.063659
512,multiply,computed,gpu_shared,d1,0,6.432419
512,multiply,computed,gpu_copy,i0,0,17.629667
512,multiply,computed,gpu_shared,i0,0,13.542867
512,multiply,computed,cpu,cpu,0,69.625292
512,multiply,computed,gpu_copy,d0,0,27.443918
512,multiply,computed,gpu_copy,d1,1,10.132502
512,multiply,computed,gpu_shared,d1,1,10.014773
512,multiply,computed,gpu_copy,i0,1,19.220333
512,multiply,computed,gpu_shared,i0,1,14.149052
512,multiply,computed,cpu,cpu,1,70.169844
512,multiply,computed,gpu_copy,d0,1,21.137534
512,multiply,computed,gpu_shared,d0,1,4.725447
512,multiply,computed,gpu_shared,d1,2,8.069539
512,multiply,computed,gpu_copy,i0,2,20.243914
512,multiply,computed,gpu_shared,i0,2,13.651599
512,multiply,computed,cpu,cpu,2,64.766127
512,multiply,computed,gpu_copy,d0,2,27.942835
512,multiply,computed,gpu_shared,d0,2,14.940312
512,multiply,computed,gpu_copy,d1,2,9.823728
512,multiply,computed,gpu_copy,i0,3,18.465691
512,multiply,computed,gpu_shared,i0,3,13.767263
512,multiply,computed,cpu,cpu,3,66.132775
512,multiply,computed,gpu_copy,d0,3,27.288289
512,multiply,computed,gpu_shared,d0,3,17.940656
512,multiply,computed,gpu_copy,d1,3,8.62403
512,multiply,computed,gpu_shared,d1,3,8.374036
512,multiply,computed,gpu_shared,i0,4,16.520628
512,multiply,computed,cpu,cpu,4,67.425597
512,multiply,computed,gpu_copy,d0,4,7.826088
512,multiply,computed,gpu_shared,d0,4,16.595376
512,multiply,computed,gpu_copy,d1,4,9.436299
512,multiply,computed,gpu_shared,d1,4,8.472909
512,multiply,computed,gpu_copy,i0,4,17.858623
512,multiply,computed,cpu,cpu,5,64.894275
512,multiply,computed,gpu_copy,d0,5,35.647848
512,multiply,computed,gpu_shared,d0,5,14.963516
512,multiply,computed,gpu_copy,d1,5,9.474189
512,multiply,computed,gpu_shared,d1,5,7.960086
512,multiply,computed,gpu_copy,i0,5,19.469356
512,multiply,computed,gpu_shared,i0,5,13.408207
512,multiply,computed,gpu_copy,d0,6,20.432464
512,multiply,computed,gpu_shared,d0,6,17.396054
512,multiply,computed,gpu_copy,d1,6,10.077018
512,multiply,computed,gpu_shared,d1,6,8.046718
512,multiply,computed,gpu_copy,i0,6,17.459472
512,multiply,computed,gpu_shared,i0,6,13.301799
512,multiply,computed,cpu,cpu,6,72.213861
512,multiply,computed,gpu_shared,d0,7,16.610455
512,multiply,computed,gpu_copy,d1,7,9.507781
512,multiply,computed,gpu_shared,d1,7,7.583657
512,multiply,computed,gpu_copy,i0,7,17.506829
512,multiply,computed,gpu_shared,i0,7,13.688607
512,multiply,computed,cpu,cpu,7,66.17802
512,multiply,computed,gpu_copy,d0,7,19.377274
512,multiply,computed,gpu_copy,d1,8,9.411763
512,multiply,computed,gpu_shared,d1,8,7.592473
512,multiply,computed,gpu_copy,i0,8,17.783673
512,multiply,computed,gpu_shared,i0,8,13.676204
512,multiply,computed,cpu,cpu,8,77.250296
512,multiply,computed,gpu_copy,d0,8,19.7305
512,multiply,computed,gpu_shared,d0,8,16.503866
512,multiply,computed,gpu_shared,d1,9,7.49358
512,multiply,computed,gpu_copy,i0,9,17.812568
512,multiply,computed,gpu_shared,i0,9,13.506639
512,multiply,computed,cpu,cpu,9,68.810208
512,multiply,computed,gpu_copy,d0,9,28.638057
512,multiply,computed,gpu_shared,d0,9,14.475749
512,multiply,computed,gpu_copy,d1,9,9.904879
512,multiply,nu_readback,gpu_shared,d0,0,96.505253
512,multiply,nu_readback,gpu_copy,d1,0,85.718406
512,multiply,nu_readback,gpu_shared,d1,0,84.629083
512,multiply,nu_readback,gpu_copy,i0,0,88.27266
512,multiply,nu_readback,gpu_shared,i0,0,88.443588
512,multiply,nu_readback,cpu,cpu,0,78.758157
512,multiply,nu_readback,gpu_copy,d0,0,118.972918
512,multiply,nu_readback,gpu_copy,d1,1,88.539015
512,multiply,nu_readback,gpu_shared,d1,1,85.272968
512,multiply,nu_readback,gpu_copy,i0,1,90.919357
512,multiply,nu_readback,gpu_shared,i0,1,88.301765
512,multiply,nu_readback,cpu,cpu,1,79.356688
512,multiply,nu_readback,gpu_copy,d0,1,84.516583
512,multiply,nu_readback,gpu_shared,d0,1,108.419665
512,multiply,nu_readback,gpu_shared,d1,2,79.632108
512,multiply,nu_readback,gpu_copy,i0,2,94.553889
512,multiply,nu_readback,gpu_shared,i0,2,93.155471
512,multiply,nu_readback,cpu,cpu,2,78.074838
512,multiply,nu_readback,gpu_copy,d0,2,120.580634
512,multiply,nu_readback,gpu_shared,d0,2,93.080001
512,multiply,nu_readback,gpu_copy,d1,2,83.675481
512,multiply,nu_readback,gpu_copy,i0,3,89.059011
512,multiply,nu_readback,gpu_shared,i0,3,93.040828
512,multiply,nu_readback,cpu,cpu,3,80.116751
512,multiply,nu_readback,gpu_copy,d0,3,115.858653
512,multiply,nu_readback,gpu_shared,d0,3,97.769762
512,multiply,nu_readback,gpu_copy,d1,3,87.144595
512,multiply,nu_readback,gpu_shared,d1,3,81.576472
512,multiply,nu_readback,gpu_shared,i0,4,89.834772
512,multiply,nu_readback,cpu,cpu,4,81.615224
512,multiply,nu_readback,gpu_copy,d0,4,101.213589
512,multiply,nu_readback,gpu_shared,d0,4,92.180509
512,multiply,nu_readback,gpu_copy,d1,4,90.678029
512,multiply,nu_readback,gpu_shared,d1,4,88.180429
512,multiply,nu_readback,gpu_copy,i0,4,93.406787
512,multiply,nu_readback,cpu,cpu,5,89.009078
512,multiply,nu_readback,gpu_copy,d0,5,97.158046
512,multiply,nu_readback,gpu_shared,d0,5,100.195428
512,multiply,nu_readback,gpu_copy,d1,5,82.074897
512,multiply,nu_readback,gpu_shared,d1,5,79.905027
512,multiply,nu_readback,gpu_copy,i0,5,96.059264
512,multiply,nu_readback,gpu_shared,i0,5,97.44592
512,multiply,nu_readback,gpu_copy,d0,6,86.381367
512,multiply,nu_readback,gpu_shared,d0,6,82.395343
512,multiply,nu_readback,gpu_copy,d1,6,93.788005
512,multiply,nu_readback,gpu_shared,d1,6,89.459886
512,multiply,nu_readback,gpu_copy,i0,6,98.979228
512,multiply,nu_readback,gpu_shared,i0,6,91.172808
512,multiply,nu_readback,cpu,cpu,6,80.48275
512,multiply,nu_readback,gpu_shared,d0,7,86.460855
512,multiply,nu_readback,gpu_copy,d1,7,93.123811
512,multiply,nu_readback,gpu_shared,d1,7,87.138494
512,multiply,nu_readback,gpu_copy,i0,7,90.542356
512,multiply,nu_readback,gpu_shared,i0,7,100.044006
512,multiply,nu_readback,cpu,cpu,7,78.191074
512,multiply,nu_readback,gpu_copy,d0,7,103.217772
512,multiply,nu_readback,gpu_copy,d1,8,79.097707
512,multiply,nu_readback,gpu_shared,d1,8,88.42298
512,multiply,nu_readback,gpu_copy,i0,8,94.314043
512,multiply,nu_readback,gpu_shared,i0,8,89.67749
512,multiply,nu_readback,cpu,cpu,8,82.817998
512,multiply,nu_readback,gpu_copy,d0,8,95.867348
512,multiply,nu_readback,gpu_shared,d0,8,93.269072
512,multiply,nu_readback,gpu_shared,d1,9,81.332929
512,multiply,nu_readback,gpu_copy,i0,9,94.116535
512,multiply,nu_readback,gpu_shared,i0,9,90.094565
512,multiply,nu_readback,cpu,cpu,9,80.279362
512,multiply,nu_readback,gpu_copy,d0,9,94.351402
512,multiply,nu_readback,gpu_shared,d0,9,89.115296
512,multiply,nu_readback,gpu_copy,d1,9,86.399491
1024,scale,computed,gpu_shared,d0,0,15.229249
1024,scale,computed,gpu_copy,d1,0,7.153918
1024,scale,computed,gpu_shared,d1,0,5.883038
1024,scale,computed,gpu_copy,i0,0,6.842581
1024,scale,computed,gpu_shared,i0,0,2.404697
1024,scale,computed,cpu,cpu,0,107.221378
1024,scale,computed,gpu_copy,d0,0,30.694737
1024,scale,computed,gpu_copy,d1,1,8.179714
1024,scale,computed,gpu_shared,d1,1,4.857623
1024,scale,computed,gpu_copy,i0,1,6.254538
1024,scale,computed,gpu_shared,i0,1,2.420206
1024,scale,computed,cpu,cpu,1,111.44821
1024,scale,computed,gpu_copy,d0,1,19.888673
1024,scale,computed,gpu_shared,d0,1,6.373429
1024,scale,computed,gpu_shared,d1,2,5.462427
1024,scale,computed,gpu_copy,i0,2,6.327544
1024,scale,computed,gpu_shared,i0,2,2.082228
1024,scale,computed,cpu,cpu,2,107.517357
1024,scale,computed,gpu_copy,d0,2,25.285148
1024,scale,computed,gpu_shared,d0,2,7.293538
1024,scale,computed,gpu_copy,d1,2,6.738798
1024,scale,computed,gpu_copy,i0,3,6.622932
1024,scale,computed,gpu_shared,i0,3,2.284674
1024,scale,computed,cpu,cpu,3,107.606463
1024,scale,computed,gpu_copy,d0,3,3.793657
1024,scale,computed,gpu_shared,d0,3,17.885774
1024,scale,computed,gpu_copy,d1,3,8.456799
1024,scale,computed,gpu_shared,d1,3,4.903478
1024,scale,computed,gpu_shared,i0,4,6.270538
1024,scale,computed,cpu,cpu,4,113.320096
1024,scale,computed,gpu_copy,d0,4,21.479649
1024,scale,computed,gpu_shared,d0,4,14.331111
1024,scale,computed,gpu_copy,d1,4,6.908253
1024,scale,computed,gpu_shared,d1,4,5.611874
1024,scale,computed,gpu_copy,i0,4,7.53168
1024,scale,computed,cpu,cpu,5,113.803714
1024,scale,computed,gpu_copy,d0,5,17.863733
1024,scale,computed,gpu_shared,d0,5,4.771032
1024,scale,computed,gpu_copy,d1,5,6.488873
1024,scale,computed,gpu_shared,d1,5,7.906787
1024,scale,computed,gpu_copy,i0,5,6.640545
1024,scale,computed,gpu_shared,i0,5,2.577909
1024,scale,computed,gpu_copy,d0,6,22.587738
1024,scale,computed,gpu_shared,d0,6,12.801589
1024,scale,computed,gpu_copy,d1,6,6.519561
1024,scale,computed,gpu_shared,d1,6,4.52234
1024,scale,computed,gpu_copy,i0,6,5.647691
1024,scale,computed,gpu_shared,i0,6,1.60432
1024,scale,computed,cpu,cpu,6,105.031801
1024,scale,computed,gpu_shared,d0,7,14.161355
1024,scale,computed,gpu_copy,d1,7,6.38455
1024,scale,computed,gpu_shared,d1,7,4.723664
1024,scale,computed,gpu_copy,i0,7,6.412161
1024,scale,computed,gpu_shared,i0,7,3.054905
1024,scale,computed,cpu,cpu,7,108.889546
1024,scale,computed,gpu_copy,d0,7,26.296717
1024,scale,computed,gpu_copy,d1,8,7.957441
1024,scale,computed,gpu_shared,d1,8,4.762546
1024,scale,computed,gpu_copy,i0,8,6.612152
1024,scale,computed,gpu_shared,i0,8,2.234741
1024,scale,computed,cpu,cpu,8,106.560941
1024,scale,computed,gpu_copy,d0,8,12.836916
1024,scale,computed,gpu_shared,d0,8,13.05506
1024,scale,computed,gpu_shared,d1,9,5.083402
1024,scale,computed,gpu_copy,i0,9,6.261921
1024,scale,computed,gpu_shared,i0,9,2.590102
1024,scale,computed,cpu,cpu,9,109.025228
1024,scale,computed,gpu_copy,d0,9,9.762284
1024,scale,computed,gpu_shared,d0,9,13.199459
1024,scale,computed,gpu_copy,d1,9,6.758033
1024,scale,nu_readback,gpu_shared,d0,0,358.790856
1024,scale,nu_readback,gpu_copy,d1,0,310.118346
1024,scale,nu_readback,gpu_shared,d1,0,305.608638
1024,scale,nu_readback,gpu_copy,i0,0,303.304709
1024,scale,nu_readback,gpu_shared,i0,0,319.002718
1024,scale,nu_readback,cpu,cpu,0,156.130628
1024,scale,nu_readback,gpu_copy,d0,0,322.968024
1024,scale,nu_readback,gpu_copy,d1,1,303.279983
1024,scale,nu_readback,gpu_shared,d1,1,309.274448
1024,scale,nu_readback,gpu_copy,i0,1,331.862626
1024,scale,nu_readback,gpu_shared,i0,1,342.056611
1024,scale,nu_readback,cpu,cpu,1,165.925883
1024,scale,nu_readback,gpu_copy,d0,1,355.371265
1024,scale,nu_readback,gpu_shared,d0,1,338.209705
1024,scale,nu_readback,gpu_shared,d1,2,320.466036
1024,scale,nu_readback,gpu_copy,i0,2,337.098703
1024,scale,nu_readback,gpu_shared,i0,2,343.336328
1024,scale,nu_readback,cpu,cpu,2,181.236703
1024,scale,nu_readback,gpu_copy,d0,2,338.424995
1024,scale,nu_readback,gpu_shared,d0,2,360.304668
1024,scale,nu_readback,gpu_copy,d1,2,355.954967
1024,scale,nu_readback,gpu_copy,i0,3,354.35706
1024,scale,nu_readback,gpu_shared,i0,3,339.054895
1024,scale,nu_readback,cpu,cpu,3,177.216696
1024,scale,nu_readback,gpu_copy,d0,3,353.621473
1024,scale,nu_readback,gpu_shared,d0,3,360.372523
1024,scale,nu_readback,gpu_copy,d1,3,378.852411
1024,scale,nu_readback,gpu_shared,d1,3,335.939889
1024,scale,nu_readback,gpu_shared,i0,4,310.972641
1024,scale,nu_readback,cpu,cpu,4,165.530699
1024,scale,nu_readback,gpu_copy,d0,4,372.1769
1024,scale,nu_readback,gpu_shared,d0,4,390.659762
1024,scale,nu_readback,gpu_copy,d1,4,364.953872
1024,scale,nu_readback,gpu_shared,d1,4,396.092263
1024,scale,nu_readback,gpu_copy,i0,4,347.266017
1024,scale,nu_readback,cpu,cpu,5,197.53157
1024,scale,nu_readback,gpu_copy,d0,5,354.175863
1024,scale,nu_readback,gpu_shared,d0,5,345.065198
1024,scale,nu_readback,gpu_copy,d1,5,328.892467
1024,scale,nu_readback,gpu_shared,d1,5,325.065378
1024,scale,nu_readback,gpu_copy,i0,5,317.580865
1024,scale,nu_readback,gpu_shared,i0,5,312.4099
1024,scale,nu_readback,gpu_copy,d0,6,341.192375
1024,scale,nu_readback,gpu_shared,d0,6,333.704455
1024,scale,nu_readback,gpu_copy,d1,6,312.133386
1024,scale,nu_readback,gpu_shared,d1,6,321.127543
1024,scale,nu_readback,gpu_copy,i0,6,348.693467
1024,scale,nu_readback,gpu_shared,i0,6,358.554075
1024,scale,nu_readback,cpu,cpu,6,173.804366
1024,scale,nu_readback,gpu_shared,d0,7,333.805142
1024,scale,nu_readback,gpu_copy,d1,7,328.772334
1024,scale,nu_readback,gpu_shared,d1,7,312.541896
1024,scale,nu_readback,gpu_copy,i0,7,319.419
1024,scale,nu_readback,gpu_shared,i0,7,301.161305
1024,scale,nu_readback,cpu,cpu,7,164.285455
1024,scale,nu_readback,gpu_copy,d0,7,306.915794
1024,scale,nu_readback,gpu_copy,d1,8,312.535092
1024,scale,nu_readback,gpu_shared,d1,8,297.044769
1024,scale,nu_readback,gpu_copy,i0,8,306.636365
1024,scale,nu_readback,gpu_shared,i0,8,300.788693
1024,scale,nu_readback,cpu,cpu,8,162.227502
1024,scale,nu_readback,gpu_copy,d0,8,318.221094
1024,scale,nu_readback,gpu_shared,d0,8,328.829319
1024,scale,nu_readback,gpu_shared,d1,9,308.398598
1024,scale,nu_readback,gpu_copy,i0,9,306.131537
1024,scale,nu_readback,gpu_shared,i0,9,300.863942
1024,scale,nu_readback,cpu,cpu,9,158.197647
1024,scale,nu_readback,gpu_copy,d0,9,314.290472
1024,scale,nu_readback,gpu_shared,d0,9,311.791019
1024,scale,nu_readback,gpu_copy,d1,9,298.689223
1024,multiply,computed,gpu_shared,d0,0,14.595792
1024,multiply,computed,gpu_copy,d1,0,30.171946
1024,multiply,computed,gpu_shared,d1,0,22.440644
1024,multiply,computed,gpu_copy,i0,0,69.348527
1024,multiply,computed,gpu_shared,i0,0,40.165518
1024,multiply,computed,cpu,cpu,0,249.370131
1024,multiply,computed,gpu_copy,d0,0,36.045294
1024,multiply,computed,gpu_copy,d1,1,30.286698
1024,multiply,computed,gpu_shared,d1,1,22.184588
1024,multiply,computed,gpu_copy,i0,1,69.669753
1024,multiply,computed,gpu_shared,i0,1,41.209457
1024,multiply,computed,cpu,cpu,1,253.498029
1024,multiply,computed,gpu_copy,d0,1,33.073195
1024,multiply,computed,gpu_shared,d0,1,22.468626
1024,multiply,computed,gpu_shared,d1,2,25.998773
1024,multiply,computed,gpu_copy,i0,2,69.076531
1024,multiply,computed,gpu_shared,i0,2,41.50154
1024,multiply,computed,cpu,cpu,2,281.515151
1024,multiply,computed,gpu_copy,d0,2,30.996587
1024,multiply,computed,gpu_shared,d0,2,21.734071
1024,multiply,computed,gpu_copy,d1,2,30.365866
1024,multiply,computed,gpu_copy,i0,3,69.939644
1024,multiply,computed,gpu_shared,i0,3,43.004182
1024,multiply,computed,cpu,cpu,3,267.345009
1024,multiply,computed,gpu_copy,d0,3,34.645995
1024,multiply,computed,gpu_shared,d0,3,23.754374
1024,multiply,computed,gpu_copy,d1,3,30.705928
1024,multiply,computed,gpu_shared,d1,3,23.430242
1024,multiply,computed,gpu_shared,i0,4,67.887132
1024,multiply,computed,cpu,cpu,4,273.270646
1024,multiply,computed,gpu_copy,d0,4,38.281299
1024,multiply,computed,gpu_shared,d0,4,23.852777
1024,multiply,computed,gpu_copy,d1,4,31.290293
1024,multiply,computed,gpu_shared,d1,4,21.807328
1024,multiply,computed,gpu_copy,i0,4,68.876579
1024,multiply,computed,cpu,cpu,5,276.886754
1024,multiply,computed,gpu_copy,d0,5,40.444446
1024,multiply,computed,gpu_shared,d0,5,23.834894
1024,multiply,computed,gpu_copy,d1,5,31.877894
1024,multiply,computed,gpu_shared,d1,5,22.114068
1024,multiply,computed,gpu_copy,i0,5,70.048788
1024,multiply,computed,gpu_shared,i0,5,41.814061
1024,multiply,computed,gpu_copy,d0,6,26.638462
1024,multiply,computed,gpu_shared,d0,6,23.469035
1024,multiply,computed,gpu_copy,d1,6,30.641217
1024,multiply,computed,gpu_shared,d1,6,23.693491
1024,multiply,computed,gpu_copy,i0,6,69.122737
1024,multiply,computed,gpu_shared,i0,6,41.365337
1024,multiply,computed,cpu,cpu,6,279.150408
1024,multiply,computed,gpu_shared,d0,7,19.593235
1024,multiply,computed,gpu_copy,d1,7,30.925465
1024,multiply,computed,gpu_shared,d1,7,23.564782
1024,multiply,computed,gpu_copy,i0,7,68.834812
1024,multiply,computed,gpu_shared,i0,7,41.131392
1024,multiply,computed,cpu,cpu,7,270.568687
1024,multiply,computed,gpu_copy,d0,7,27.912218
1024,multiply,computed,gpu_copy,d1,8,30.522817
1024,multiply,computed,gpu_shared,d1,8,24.36562
1024,multiply,computed,gpu_copy,i0,8,68.522402
1024,multiply,computed,gpu_shared,i0,8,41.262706
1024,multiply,computed,cpu,cpu,8,283.027159
1024,multiply,computed,gpu_copy,d0,8,35.931664
1024,multiply,computed,gpu_shared,d0,8,21.815212
1024,multiply,computed,gpu_shared,d1,9,25.961183
1024,multiply,computed,gpu_copy,i0,9,69.155578
1024,multiply,computed,gpu_shared,i0,9,42.222038
1024,multiply,computed,cpu,cpu,9,281.171993
1024,multiply,computed,gpu_copy,d0,9,32.55412
1024,multiply,computed,gpu_shared,d0,9,22.878026
1024,multiply,computed,gpu_copy,d1,9,30.938359
1024,multiply,nu_readback,gpu_shared,d0,0,323.806717
1024,multiply,nu_readback,gpu_copy,d1,0,326.825775
1024,multiply,nu_readback,gpu_shared,d1,0,339.855869
1024,multiply,nu_readback,gpu_copy,i0,0,396.5776
1024,multiply,nu_readback,gpu_shared,i0,0,384.296808
1024,multiply,nu_readback,cpu,cpu,0,325.823504
1024,multiply,nu_readback,gpu_copy,d0,0,345.388726
1024,multiply,nu_readback,gpu_copy,d1,1,348.267883
1024,multiply,nu_readback,gpu_shared,d1,1,359.556052
1024,multiply,nu_readback,gpu_copy,i0,1,368.38402
1024,multiply,nu_readback,gpu_shared,i0,1,373.831418
1024,multiply,nu_readback,cpu,cpu,1,331.951646
1024,multiply,nu_readback,gpu_copy,d0,1,354.225761
1024,multiply,nu_readback,gpu_shared,d0,1,331.126994
1024,multiply,nu_readback,gpu_shared,d1,2,344.461884
1024,multiply,nu_readback,gpu_copy,i0,2,374.019186
1024,multiply,nu_readback,gpu_shared,i0,2,369.522304
1024,multiply,nu_readback,cpu,cpu,2,313.584899
1024,multiply,nu_readback,gpu_copy,d0,2,329.577075
1024,multiply,nu_readback,gpu_shared,d0,2,315.656657
1024,multiply,nu_readback,gpu_copy,d1,2,331.736526
1024,multiply,nu_readback,gpu_copy,i0,3,360.968225
1024,multiply,nu_readback,gpu_shared,i0,3,358.277606
1024,multiply,nu_readback,cpu,cpu,3,305.293697
1024,multiply,nu_readback,gpu_copy,d0,3,344.586655
1024,multiply,nu_readback,gpu_shared,d0,3,323.106405
1024,multiply,nu_readback,gpu_copy,d1,3,337.40252
1024,multiply,nu_readback,gpu_shared,d1,3,322.010108
1024,multiply,nu_readback,gpu_shared,i0,4,373.280274
1024,multiply,nu_readback,cpu,cpu,4,320.333303
1024,multiply,nu_readback,gpu_copy,d0,4,354.201384
1024,multiply,nu_readback,gpu_shared,d0,4,322.580578
1024,multiply,nu_readback,gpu_copy,d1,4,329.776164
1024,multiply,nu_readback,gpu_shared,d1,4,309.303566
1024,multiply,nu_readback,gpu_copy,i0,4,354.278497
1024,multiply,nu_readback,cpu,cpu,5,315.790736
1024,multiply,nu_readback,gpu_copy,d0,5,319.903084
1024,multiply,nu_readback,gpu_shared,d0,5,314.774458
1024,multiply,nu_readback,gpu_copy,d1,5,329.173895
1024,multiply,nu_readback,gpu_shared,d1,5,336.728848
1024,multiply,nu_readback,gpu_copy,i0,5,361.431614
1024,multiply,nu_readback,gpu_shared,i0,5,378.517821
1024,multiply,nu_readback,gpu_copy,d0,6,333.542479
1024,multiply,nu_readback,gpu_shared,d0,6,346.670445
1024,multiply,nu_readback,gpu_copy,d1,6,339.110121
1024,multiply,nu_readback,gpu_shared,d1,6,342.105374
1024,multiply,nu_readback,gpu_copy,i0,6,361.983479
1024,multiply,nu_readback,gpu_shared,i0,6,374.912915
1024,multiply,nu_readback,cpu,cpu,6,330.927491
1024,multiply,nu_readback,gpu_shared,d0,7,330.605273
1024,multiply,nu_readback,gpu_copy,d1,7,325.811177
1024,multiply,nu_readback,gpu_shared,d1,7,320.119995
1024,multiply,nu_readback,gpu_copy,i0,7,357.967598
1024,multiply,nu_readback,gpu_shared,i0,7,370.744351
1024,multiply,nu_readback,cpu,cpu,7,333.989118
1024,multiply,nu_readback,gpu_copy,d0,7,359.829527
1024,multiply,nu_readback,gpu_copy,d1,8,348.39079
1024,multiply,nu_readback,gpu_shared,d1,8,325.486775
1024,multiply,nu_readback,gpu_copy,i0,8,354.104313
1024,multiply,nu_readback,gpu_shared,i0,8,359.533336
1024,multiply,nu_readback,cpu,cpu,8,324.396781
1024,multiply,nu_readback,gpu_copy,d0,8,362.33498
1024,multiply,nu_readback,gpu_shared,d0,8,341.485933
1024,multiply,nu_readback,gpu_shared,d1,9,339.52452
1024,multiply,nu_readback,gpu_copy,i0,9,376.198452
1024,multiply,nu_readback,gpu_shared,i0,9,376.412279
1024,multiply,nu_readback,cpu,cpu,9,327.166505
1024,multiply,nu_readback,gpu_copy,d0,9,344.106591
1024,multiply,nu_readback,gpu_shared,d0,9,352.847307
1024,multiply,nu_readback,gpu_copy,d1,9,320.519066