size,operation,boundary,mode,device,round,ms
256,scale,computed,gpu_shared,d0,0,3.491699
256,scale,computed,gpu_copy,d1,0,2.735046
256,scale,computed,gpu_shared,d1,0,1.345417
256,scale,computed,gpu_copy,i0,0,1.452986
256,scale,computed,gpu_shared,i0,0,0.942589
256,scale,computed,cpu,cpu,0,7.112949
256,scale,computed,gpu_copy,d0,0,2.766203
256,scale,computed,gpu_copy,d1,1,1.515192
256,scale,computed,gpu_shared,d1,1,0.948711
256,scale,computed,gpu_copy,i0,1,1.068413
256,scale,computed,gpu_shared,i0,1,0.690692
256,scale,computed,cpu,cpu,1,7.604681
256,scale,computed,gpu_copy,d0,1,1.642398
256,scale,computed,gpu_shared,d0,1,0.759669
256,scale,computed,gpu_shared,d1,2,1.173848
256,scale,computed,gpu_copy,i0,2,1.001799
256,scale,computed,gpu_shared,i0,2,0.818569
256,scale,computed,cpu,cpu,2,7.213676
256,scale,computed,gpu_copy,d0,2,1.623152
256,scale,computed,gpu_shared,d0,2,0.782773
256,scale,computed,gpu_copy,d1,2,1.602754
256,scale,computed,gpu_copy,i0,3,1.058243
256,scale,computed,gpu_shared,i0,3,0.65728
256,scale,computed,cpu,cpu,3,9.058289
256,scale,computed,gpu_copy,d0,3,3.469017
256,scale,computed,gpu_shared,d0,3,1.46527
256,scale,computed,gpu_copy,d1,3,2.520146
256,scale,computed,gpu_shared,d1,3,1.07785
256,scale,computed,gpu_shared,i0,4,0.804954
256,scale,computed,cpu,cpu,4,7.902164
256,scale,computed,gpu_copy,d0,4,9.670125
256,scale,computed,gpu_shared,d0,4,1.560806
256,scale,computed,gpu_copy,d1,4,2.289077
256,scale,computed,gpu_shared,d1,4,1.467704
256,scale,computed,gpu_copy,i0,4,1.515812
256,scale,computed,cpu,cpu,5,8.522725
256,scale,computed,gpu_copy,d0,5,28.355298
256,scale,computed,gpu_shared,d0,5,15.17037
256,scale,computed,gpu_copy,d1,5,2.215622
256,scale,computed,gpu_shared,d1,5,1.888985
256,scale,computed,gpu_copy,i0,5,4.563358
256,scale,computed,gpu_shared,i0,5,1.003702
256,scale,computed,gpu_copy,d0,6,13.849971
256,scale,computed,gpu_shared,d0,6,10.763553
256,scale,computed,gpu_copy,d1,6,2.716721
256,scale,computed,gpu_shared,d1,6,0.911061
256,scale,computed,gpu_copy,i0,6,1.106744
256,scale,computed,gpu_shared,i0,6,1.406309
256,scale,computed,cpu,cpu,6,8.059676
256,scale,computed,gpu_shared,d0,7,12.907882
256,scale,computed,gpu_copy,d1,7,1.85902
256,scale,computed,gpu_shared,d1,7,0.784175
256,scale,computed,gpu_copy,i0,7,1.102626
256,scale,computed,gpu_shared,i0,7,0.853624
256,scale,computed,cpu,cpu,7,9.536476
256,scale,computed,gpu_copy,d0,7,17.970687
256,scale,computed,gpu_copy,d1,8,2.741979
256,scale,computed,gpu_shared,d1,8,3.898535
256,scale,computed,gpu_copy,i0,8,3.221598
256,scale,computed,gpu_shared,i0,8,1.612762
256,scale,computed,cpu,cpu,8,8.756078
256,scale,computed,gpu_copy,d0,8,20.47819
256,scale,computed,gpu_shared,d0,8,4.684402
256,scale,computed,gpu_shared,d1,9,1.759686
256,scale,computed,gpu_copy,i0,9,1.583038
256,scale,computed,gpu_shared,i0,9,1.363069
256,scale,computed,cpu,cpu,9,7.591518
256,scale,computed,gpu_copy,d0,9,16.202526
256,scale,computed,gpu_shared,d0,9,12.067623
256,scale,computed,gpu_copy,d1,9,3.333005
256,scale,nu_readback,gpu_shared,d0,0,22.516322
256,scale,nu_readback,gpu_copy,d1,0,20.207819
256,scale,nu_readback,gpu_shared,d1,0,20.053091
256,scale,nu_readback,gpu_copy,i0,0,24.027727
256,scale,nu_readback,gpu_shared,i0,0,20.460207
256,scale,nu_readback,cpu,cpu,0,10.891231
256,scale,nu_readback,gpu_copy,d0,0,50.297444
256,scale,nu_readback,gpu_copy,d1,1,24.75722
256,scale,nu_readback,gpu_shared,d1,1,20.284982
256,scale,nu_readback,gpu_copy,i0,1,23.385706
256,scale,nu_readback,gpu_shared,i0,1,18.9913
256,scale,nu_readback,cpu,cpu,1,12.051203
256,scale,nu_readback,gpu_copy,d0,1,39.640779
256,scale,nu_readback,gpu_shared,d0,1,27.110477
256,scale,nu_readback,gpu_shared,d1,2,20.331388
256,scale,nu_readback,gpu_copy,i0,2,26.840797
256,scale,nu_readback,gpu_shared,i0,2,22.383156
256,scale,nu_readback,cpu,cpu,2,11.064932
256,scale,nu_readback,gpu_copy,d0,2,32.761513
256,scale,nu_readback,gpu_shared,d0,2,35.600322
256,scale,nu_readback,gpu_copy,d1,2,19.231807
256,scale,nu_readback,gpu_copy,i0,3,22.894323
256,scale,nu_readback,gpu_shared,i0,3,20.344051
256,scale,nu_readback,cpu,cpu,3,10.716486
256,scale,nu_readback,gpu_copy,d0,3,28.525052
256,scale,nu_readback,gpu_shared,d0,3,29.524707
256,scale,nu_readback,gpu_copy,d1,3,19.35163
256,scale,nu_readback,gpu_shared,d1,3,19.489275
256,scale,nu_readback,gpu_shared,i0,4,22.646203
256,scale,nu_readback,cpu,cpu,4,10.520682
256,scale,nu_readback,gpu_copy,d0,4,47.111912
256,scale,nu_readback,gpu_shared,d0,4,33.656224
256,scale,nu_readback,gpu_copy,d1,4,23.526366
256,scale,nu_readback,gpu_shared,d1,4,20.410395
256,scale,nu_readback,gpu_copy,i0,4,24.687351
256,scale,nu_readback,cpu,cpu,5,11.632796
256,scale,nu_readback,gpu_copy,d0,5,48.481474
256,scale,nu_readback,gpu_shared,d0,5,43.425522
256,scale,nu_readback,gpu_copy,d1,5,22.079942
256,scale,nu_readback,gpu_shared,d1,5,23.150018
256,scale,nu_readback,gpu_copy,i0,5,25.595286
256,scale,nu_readback,gpu_shared,i0,5,23.954261
256,scale,nu_readback,gpu_copy,d0,6,28.867768
256,scale,nu_readback,gpu_shared,d0,6,29.359931
256,scale,nu_readback,gpu_copy,d1,6,21.13521
256,scale,nu_readback,gpu_shared,d1,6,19.36767
256,scale,nu_readback,gpu_copy,i0,6,23.599612
256,scale,nu_readback,gpu_shared,i0,6,22.336288
256,scale,nu_readback,cpu,cpu,6,10.397163
256,scale,nu_readback,gpu_shared,d0,7,21.750431
256,scale,nu_readback,gpu_copy,d1,7,19.235935
256,scale,nu_readback,gpu_shared,d1,7,18.467368
256,scale,nu_readback,gpu_copy,i0,7,24.510112
256,scale,nu_readback,gpu_shared,i0,7,20.687198
256,scale,nu_readback,cpu,cpu,7,9.860868
256,scale,nu_readback,gpu_copy,d0,7,56.139745
256,scale,nu_readback,gpu_copy,d1,8,26.547052
256,scale,nu_readback,gpu_shared,d1,8,21.511969
256,scale,nu_readback,gpu_copy,i0,8,24.454669
256,scale,nu_readback,gpu_shared,i0,8,19.868669
256,scale,nu_readback,cpu,cpu,8,10.997477
256,scale,nu_readback,gpu_copy,d0,8,45.335046
256,scale,nu_readback,gpu_shared,d0,8,43.691235
256,scale,nu_readback,gpu_shared,d1,9,21.938019
256,scale,nu_readback,gpu_copy,i0,9,24.693282
256,scale,nu_readback,gpu_shared,i0,9,19.320321
256,scale,nu_readback,cpu,cpu,9,10.840256
256,scale,nu_readback,gpu_copy,d0,9,42.946093
256,scale,nu_readback,gpu_shared,d0,9,32.958078
256,scale,nu_readback,gpu_copy,d1,9,20.221003
256,multiply,computed,gpu_shared,d0,0,12.267925
256,multiply,computed,gpu_copy,d1,0,6.823843
256,multiply,computed,gpu_shared,d1,0,5.737116
256,multiply,computed,gpu_copy,i0,0,9.059521
256,multiply,computed,gpu_shared,i0,0,4.914309
256,multiply,computed,cpu,cpu,0,17.165312
256,multiply,computed,gpu_copy,d0,0,20.253714
256,multiply,computed,gpu_copy,d1,1,8.18604
256,multiply,computed,gpu_shared,d1,1,5.941826
256,multiply,computed,gpu_copy,i0,1,9.328971
256,multiply,computed,gpu_shared,i0,1,4.927775
256,multiply,computed,cpu,cpu,1,16.821575
256,multiply,computed,gpu_copy,d0,1,9.384324
256,multiply,computed,gpu_shared,d0,1,13.605276
256,multiply,computed,gpu_shared,d1,2,5.423875
256,multiply,computed,gpu_copy,i0,2,8.813194
256,multiply,computed,gpu_shared,i0,2,5.613868
256,multiply,computed,cpu,cpu,2,19.525713
256,multiply,computed,gpu_copy,d0,2,27.254575
256,multiply,computed,gpu_shared,d0,2,3.589571
256,multiply,computed,gpu_copy,d1,2,5.34023
256,multiply,computed,gpu_copy,i0,3,8.339615
256,multiply,computed,gpu_shared,i0,3,4.318173
256,multiply,computed,cpu,cpu,3,15.696778
256,multiply,computed,gpu_copy,d0,3,3.88533
256,multiply,computed,gpu_shared,d0,3,3.530782
256,multiply,computed,gpu_copy,d1,3,5.645696
256,multiply,computed,gpu_shared,d1,3,4.47299
256,multiply,computed,gpu_shared,i0,4,5.041435
256,multiply,computed,cpu,cpu,4,16.457689
256,multiply,computed,gpu_copy,d0,4,9.784897
256,multiply,computed,gpu_shared,d0,4,4.212016
256,multiply,computed,gpu_copy,d1,4,6.130617
256,multiply,computed,gpu_shared,d1,4,5.149846
256,multiply,computed,gpu_copy,i0,4,8.504401
256,multiply,computed,cpu,cpu,5,16.948771
256,multiply,computed,gpu_copy,d0,5,32.547326
256,multiply,computed,gpu_shared,d0,5,14.357452
256,multiply,computed,gpu_copy,d1,5,6.710653
256,multiply,computed,gpu_shared,d1,5,4.964853
256,multiply,computed,gpu_copy,i0,5,9.042019
256,multiply,computed,gpu_shared,i0,5,5.092219
256,multiply,computed,gpu_copy,d0,6,24.108868
256,multiply,computed,gpu_shared,d0,6,12.760038
256,multiply,computed,gpu_copy,d1,6,5.468307
256,multiply,computed,gpu_shared,d1,6,5.210329
256,multiply,computed,gpu_copy,i0,6,9.004609
256,multiply,computed,gpu_shared,i0,6,5.374163
256,multiply,computed,cpu,cpu,6,17.086446
256,multiply,computed,gpu_shared,d0,7,14.815272
256,multiply,computed,gpu_copy,d1,7,6.501375
256,multiply,computed,gpu_shared,d1,7,4.614513
256,multiply,computed,gpu_copy,i0,7,8.539146
256,multiply,computed,gpu_shared,i0,7,5.004417
256,multiply,computed,cpu,cpu,7,18.977325
256,multiply,computed,gpu_copy,d0,7,29.506072
256,multiply,computed,gpu_copy,d1,8,5.985748
256,multiply,computed,gpu_shared,d1,8,5.099633
256,multiply,computed,gpu_copy,i0,8,9.548678
256,multiply,computed,gpu_shared,i0,8,5.105915
256,multiply,computed,cpu,cpu,8,17.331021
256,multiply,computed,gpu_copy,d0,8,30.621242
256,multiply,computed,gpu_shared,d0,8,3.601383
256,multiply,computed,gpu_shared,d1,9,4.589135
256,multiply,computed,gpu_copy,i0,9,8.689174
256,multiply,computed,gpu_shared,i0,9,5.241376
256,multiply,computed,cpu,cpu,9,17.259938
256,multiply,computed,gpu_copy,d0,9,13.842457
256,multiply,computed,gpu_shared,d0,9,14.458019
256,multiply,computed,gpu_copy,d1,9,5.136642
256,multiply,nu_readback,gpu_shared,d0,0,33.369702
256,multiply,nu_readback,gpu_copy,d1,0,28.385754
256,multiply,nu_readback,gpu_shared,d1,0,25.006243
256,multiply,nu_readback,gpu_copy,i0,0,30.984826
256,multiply,nu_readback,gpu_shared,i0,0,31.585391
256,multiply,nu_readback,cpu,cpu,0,19.80998
256,multiply,nu_readback,gpu_copy,d0,0,40.74581
256,multiply,nu_readback,gpu_copy,d1,1,24.005275
256,multiply,nu_readback,gpu_shared,d1,1,30.225728
256,multiply,nu_readback,gpu_copy,i0,1,26.747494
256,multiply,nu_readback,gpu_shared,i0,1,24.033898
256,multiply,nu_readback,cpu,cpu,1,19.152009
256,multiply,nu_readback,gpu_copy,d0,1,26.347692
256,multiply,nu_readback,gpu_shared,d0,1,19.599149
256,multiply,nu_readback,gpu_shared,d1,2,23.347294
256,multiply,nu_readback,gpu_copy,i0,2,26.451404
256,multiply,nu_readback,gpu_shared,i0,2,26.04513
256,multiply,nu_readback,cpu,cpu,2,19.208785
256,multiply,nu_readback,gpu_copy,d0,2,63.240262
256,multiply,nu_readback,gpu_shared,d0,2,35.355517
256,multiply,nu_readback,gpu_copy,d1,2,25.786309
256,multiply,nu_readback,gpu_copy,i0,3,28.017591
256,multiply,nu_readback,gpu_shared,i0,3,27.827257
256,multiply,nu_readback,cpu,cpu,3,21.725896
256,multiply,nu_readback,gpu_copy,d0,3,55.622776
256,multiply,nu_readback,gpu_shared,d0,3,28.02253
256,multiply,nu_readback,gpu_copy,d1,3,24.276519
256,multiply,nu_readback,gpu_shared,d1,3,25.019287
256,multiply,nu_readback,gpu_shared,i0,4,29.264404
256,multiply,nu_readback,cpu,cpu,4,22.153278
256,multiply,nu_readback,gpu_copy,d0,4,47.653248
256,multiply,nu_readback,gpu_shared,d0,4,31.84848
256,multiply,nu_readback,gpu_copy,d1,4,23.275601
256,multiply,nu_readback,gpu_shared,d1,4,22.52027
256,multiply,nu_readback,gpu_copy,i0,4,26.289694
256,multiply,nu_readback,cpu,cpu,5,18.740666
256,multiply,nu_readback,gpu_copy,d0,5,35.995615
256,multiply,nu_readback,gpu_shared,d0,5,49.032677
256,multiply,nu_readback,gpu_copy,d1,5,26.328477
256,multiply,nu_readback,gpu_shared,d1,5,25.371199
256,multiply,nu_readback,gpu_copy,i0,5,27.431784
256,multiply,nu_readback,gpu_shared,i0,5,23.568826
256,multiply,nu_readback,gpu_copy,d0,6,53.885432
256,multiply,nu_readback,gpu_shared,d0,6,38.232846
256,multiply,nu_readback,gpu_copy,d1,6,25.562495
256,multiply,nu_readback,gpu_shared,d1,6,25.088816
256,multiply,nu_readback,gpu_copy,i0,6,28.322726
256,multiply,nu_readback,gpu_shared,i0,6,23.302341
256,multiply,nu_readback,cpu,cpu,6,21.343967
256,multiply,nu_readback,gpu_shared,d0,7,24.602364
256,multiply,nu_readback,gpu_copy,d1,7,25.740415
256,multiply,nu_readback,gpu_shared,d1,7,24.649611
256,multiply,nu_readback,gpu_copy,i0,7,27.59681
256,multiply,nu_readback,gpu_shared,i0,7,23.739171
256,multiply,nu_readback,cpu,cpu,7,20.173165
256,multiply,nu_readback,gpu_copy,d0,7,24.139955
256,multiply,nu_readback,gpu_copy,d1,8,26.360646
256,multiply,nu_readback,gpu_shared,d1,8,23.640107
256,multiply,nu_readback,gpu_copy,i0,8,26.86401
256,multiply,nu_readback,gpu_shared,i0,8,22.818853
256,multiply,nu_readback,cpu,cpu,8,20.034256
256,multiply,nu_readback,gpu_copy,d0,8,65.050831
256,multiply,nu_readback,gpu_shared,d0,8,39.132156
256,multiply,nu_readback,gpu_shared,d1,9,24.617953
256,multiply,nu_readback,gpu_copy,i0,9,29.191609
256,multiply,nu_readback,gpu_shared,i0,9,23.8461
256,multiply,nu_readback,cpu,cpu,9,19.535921
256,multiply,nu_readback,gpu_copy,d0,9,42.424535
256,multiply,nu_readback,gpu_shared,d0,9,32.235658
256,multiply,nu_readback,gpu_copy,d1,9,24.911216
512,scale,computed,gpu_shared,d0,0,11.002216
512,scale,computed,gpu_copy,d1,0,3.140518
512,scale,computed,gpu_shared,d1,0,1.441936
512,scale,computed,gpu_copy,i0,0,4.714489
512,scale,computed,gpu_shared,i0,0,0.915088
512,scale,computed,cpu,cpu,0,27.44048
512,scale,computed,gpu_copy,d0,0,2.019337
512,scale,computed,gpu_copy,d1,1,2.808662
512,scale,computed,gpu_shared,d1,1,1.459138
512,scale,computed,gpu_copy,i0,1,1.140926
512,scale,computed,gpu_shared,i0,1,0.947468
512,scale,computed,cpu,cpu,1,27.172513
512,scale,computed,gpu_copy,d0,1,2.173022
512,scale,computed,gpu_shared,d0,1,3.028079
512,scale,computed,gpu_shared,d1,2,2.077996
512,scale,computed,gpu_copy,i0,2,1.387495
512,scale,computed,gpu_shared,i0,2,0.821354
512,scale,computed,cpu,cpu,2,28.824488
512,scale,computed,gpu_copy,d0,2,27.884404
512,scale,computed,gpu_shared,d0,2,7.143316
512,scale,computed,gpu_copy,d1,2,6.334715
512,scale,computed,gpu_copy,i0,3,5.516797
512,scale,computed,gpu_shared,i0,3,1.405729
512,scale,computed,cpu,cpu,3,28.856818
512,scale,computed,gpu_copy,d0,3,20.389867
512,scale,computed,gpu_shared,d0,3,13.173997
512,scale,computed,gpu_copy,d1,3,3.822894
512,scale,computed,gpu_shared,d1,3,1.727586
512,scale,computed,gpu_shared,i0,4,4.464574
512,scale,computed,cpu,cpu,4,27.834041
512,scale,computed,gpu_copy,d0,4,19.730864
512,scale,computed,gpu_shared,d0,4,4.855079
512,scale,computed,gpu_copy,d1,4,3.468657
512,scale,computed,gpu_shared,d1,4,2.325145
512,scale,computed,gpu_copy,i0,4,5.457296
512,scale,computed,cpu,cpu,5,28.361319
512,scale,computed,gpu_copy,d0,5,15.970856
512,scale,computed,gpu_shared,d0,5,12.787329
512,scale,computed,gpu_copy,d1,5,3.526344
512,scale,computed,gpu_shared,d1,5,1.705245
512,scale,computed,gpu_copy,i0,5,5.529751
512,scale,computed,gpu_shared,i0,5,1.69169
512,scale,computed,gpu_copy,d0,6,15.529998
512,scale,computed,gpu_shared,d0,6,4.939967
512,scale,computed,gpu_copy,d1,6,3.124368
512,scale,computed,gpu_shared,d1,6,2.156962
512,scale,computed,gpu_copy,i0,6,1.911207
512,scale,computed,gpu_shared,i0,6,1.505053
512,scale,computed,cpu,cpu,6,28.792419
512,scale,computed,gpu_shared,d0,7,3.21206
512,scale,computed,gpu_copy,d1,7,3.008493
512,scale,computed,gpu_shared,d1,7,1.431697
512,scale,computed,gpu_copy,i0,7,1.393416
512,scale,computed,gpu_shared,i0,7,0.831914
512,scale,computed,cpu,cpu,7,28.731125
512,scale,computed,gpu_copy,d0,7,11.304768
512,scale,computed,gpu_copy,d1,8,3.053556
512,scale,computed,gpu_shared,d1,8,1.947514
512,scale,computed,gpu_copy,i0,8,4.95761
512,scale,computed,gpu_shared,i0,8,1.404707
512,scale,computed,cpu,cpu,8,30.633966
512,scale,computed,gpu_copy,d0,8,8.189096
512,scale,computed,gpu_shared,d0,8,4.051969
512,scale,computed,gpu_shared,d1,9,2.05271
512,scale,computed,gpu_copy,i0,9,5.473627
512,scale,computed,gpu_shared,i0,9,0.976392
512,scale,computed,cpu,cpu,9,31.294552
512,scale,computed,gpu_copy,d0,9,19.932508
512,scale,computed,gpu_shared,d0,9,2.418869
512,scale,computed,gpu_copy,d1,9,3.220917
512,scale,nu_readback,gpu_shared,d0,0,93.088089
512,scale,nu_readback,gpu_copy,d1,0,80.10629
512,scale,nu_readback,gpu_shared,d1,0,78.480793
512,scale,nu_readback,gpu_copy,i0,0,78.974739
512,scale,nu_readback,gpu_shared,i0,0,80.716081
512,scale,nu_readback,cpu,cpu,0,41.396137
512,scale,nu_readback,gpu_copy,d0,0,103.475754
512,scale,nu_readback,gpu_copy,d1,1,77.792967
512,scale,nu_readback,gpu_shared,d1,1,76.546414
512,scale,nu_readback,gpu_copy,i0,1,79.494905
512,scale,nu_readback,gpu_shared,i0,1,76.919245
512,scale,nu_readback,cpu,cpu,1,37.24864
512,scale,nu_readback,gpu_copy,d0,1,77.314308
512,scale,nu_readback,gpu_shared,d0,1,95.612854
512,scale,nu_readback,gpu_shared,d1,2,79.333265
512,scale,nu_readback,gpu_copy,i0,2,81.063725
512,scale,nu_readback,gpu_shared,i0,2,78.800907
512,scale,nu_readback,cpu,cpu,2,40.431055
512,scale,nu_readback,gpu_copy,d0,2,84.80056
512,scale,nu_readback,gpu_shared,d0,2,85.643133
512,scale,nu_readback,gpu_copy,d1,2,74.926678
512,scale,nu_readback,gpu_copy,i0,3,90.048348
512,scale,nu_readback,gpu_shared,i0,3,80.576902
512,scale,nu_readback,cpu,cpu,3,41.750756
512,scale,nu_readback,gpu_copy,d0,3,99.005289
512,scale,nu_readback,gpu_shared,d0,3,93.786014
512,scale,nu_readback,gpu_copy,d1,3,77.398504
512,scale,nu_readback,gpu_shared,d1,3,75.179386
512,scale,nu_readback,gpu_shared,i0,4,79.571317
512,scale,nu_readback,cpu,cpu,4,39.483568
512,scale,nu_readback,gpu_copy,d0,4,110.399833
512,scale,nu_readback,gpu_shared,d0,4,97.31896
512,scale,nu_readback,gpu_copy,d1,4,84.575722
512,scale,nu_readback,gpu_shared,d1,4,78.576641
512,scale,nu_readback,gpu_copy,i0,4,88.036305
512,scale,nu_readback,cpu,cpu,5,38.371324
512,scale,nu_readback,gpu_copy,d0,5,76.07592
512,scale,nu_readback,gpu_shared,d0,5,110.435299
512,scale,nu_readback,gpu_copy,d1,5,75.521882
512,scale,nu_readback,gpu_shared,d1,5,83.129369
512,scale,nu_readback,gpu_copy,i0,5,77.566055
512,scale,nu_readback,gpu_shared,i0,5,76.034694
512,scale,nu_readback,gpu_copy,d0,6,83.249843
512,scale,nu_readback,gpu_shared,d0,6,76.09174
512,scale,nu_readback,gpu_copy,d1,6,78.687056
512,scale,nu_readback,gpu_shared,d1,6,76.371679
512,scale,nu_readback,gpu_copy,i0,6,78.603551
512,scale,nu_readback,gpu_shared,i0,6,84.619645
512,scale,nu_readback,cpu,cpu,6,41.12815
512,scale,nu_readback,gpu_shared,d0,7,76.352323
512,scale,nu_readback,gpu_copy,d1,7,77.574472
512,scale,nu_readback,gpu_shared,d1,7,71.961626
512,scale,nu_readback,gpu_copy,i0,7,80.406136
512,scale,nu_readback,gpu_shared,i0,7,77.71424
512,scale,nu_readback,cpu,cpu,7,41.460786
512,scale,nu_readback,gpu_copy,d0,7,104.516366
512,scale,nu_readback,gpu_copy,d1,8,79.279425
512,scale,nu_readback,gpu_shared,d1,8,80.157715
512,scale,nu_readback,gpu_copy,i0,8,76.649324
512,scale,nu_readback,gpu_shared,i0,8,76.00013
512,scale,nu_readback,cpu,cpu,8,37.740343
512,scale,nu_readback,gpu_copy,d0,8,82.120367
512,scale,nu_readback,gpu_shared,d0,8,99.871998
512,scale,nu_readback,gpu_shared,d1,9,78.318903
512,scale,nu_readback,gpu_copy,i0,9,78.883771
512,scale,nu_readback,gpu_shared,i0,9,79.487321
512,scale,nu_readback,cpu,cpu,9,41.657853
512,scale,nu_readback,gpu_copy,d0,9,85.371189
512,scale,nu_readback,gpu_shared,d0,9,78.864114
512,scale,nu_readback,gpu_copy,d1,9,75.237064
512,multiply,computed,gpu_shared,d0,0,5.331854
512,multiply,computed,gpu_copy,d1,0,11.98542
512,multiply,computed,gpu_shared,d1,0,9.215501
512,multiply,computed,gpu_copy,i0,0,17.912359
512,multiply,computed,gpu_shared,i0,0,13.790801
512,multiply,computed,cpu,cpu,0,61.792486
512,multiply,computed,gpu_copy,d0,0,35.673558
512,multiply,computed,gpu_copy,d1,1,12.599761
512,multiply,computed,gpu_shared,d1,1,8.960638
512,multiply,computed,gpu_copy,i0,1,17.549205
512,multiply,computed,gpu_shared,i0,1,13.723677
512,multiply,computed,cpu,cpu,1,67.546873
512,multiply,computed,gpu_copy,d0,1,28.804231
512,multiply,computed,gpu_shared,d0,1,13.830425
512,multiply,computed,gpu_shared,d1,2,9.73265
512,multiply,computed,gpu_copy,i0,2,17.762361
512,multiply,computed,gpu_shared,i0,2,13.694802
512,multiply,computed,cpu,cpu,2,68.739216
512,multiply,computed,gpu_copy,d0,2,23.550491
512,multiply,computed,gpu_shared,d0,2,16.052669
512,multiply,computed,gpu_copy,d1,2,12.12511
512,multiply,computed,gpu_copy,i0,3,17.840847
512,multiply,computed,gpu_shared,i0,3,13.65537
512,multiply,computed,cpu,cpu,3,61.964815
512,multiply,computed,gpu_copy,d0,3,9.896835
512,multiply,computed,gpu_shared,d0,3,6.561446
512,multiply,computed,gpu_copy,d1,3,11.130965
512,multiply,computed,gpu_shared,d1,3,9.61398
512,multiply,computed,gpu_shared,i0,4,16.529222
512,multiply,computed,cpu,cpu,4,64.92613
512,multiply,computed,gpu_copy,d0,4,40.990575
512,multiply,computed,gpu_shared,d0,4,17.641768
512,multiply,computed,gpu_copy,d1,4,11.838758
512,multiply,computed,gpu_shared,d1,4,9.736648
512,multiply,computed,gpu_copy,i0,4,18.429419
512,multiply,computed,cpu,cpu,5,64.620123
512,multiply,computed,gpu_copy,d0,5,31.526793
512,multiply,computed,gpu_shared,d0,5,8.274675
512,multiply,computed,gpu_copy,d1,5,12.353734
512,multiply,computed,gpu_shared,d1,5,9.312009
512,multiply,computed,gpu_copy,i0,5,17.885389
512,multiply,computed,gpu_shared,i0,5,13.724808
512,multiply,computed,gpu_copy,d0,6,29.319497
512,multiply,computed,gpu_shared,d0,6,5.25431
512,multiply,computed,gpu_copy,d1,6,11.79101
512,multiply,computed,gpu_shared,d1,6,10.030183
512,multiply,computed,gpu_copy,i0,6,18.378785
512,multiply,computed,gpu_shared,i0,6,13.694862
512,multiply,computed,cpu,cpu,6,65.615059
512,multiply,computed,gpu_shared,d0,7,9.986511
512,multiply,computed,gpu_copy,d1,7,11.488289
512,multiply,computed,gpu_shared,d1,7,9.50619
512,multiply,computed,gpu_copy,i0,7,17.566487
512,multiply,computed,gpu_shared,i0,7,13.665419
512,multiply,computed,cpu,cpu,7,65.654502
512,multiply,computed,gpu_copy,d0,7,5.141741
512,multiply,computed,gpu_copy,d1,8,11.768618
512,multiply,computed,gpu_shared,d1,8,9.415271
512,multiply,computed,gpu_copy,i0,8,17.244961
512,multiply,computed,gpu_shared,i0,8,13.764393
512,multiply,computed,cpu,cpu,8,61.353281
512,multiply,computed,gpu_copy,d0,8,42.356139
512,multiply,computed,gpu_shared,d0,8,8.020974
512,multiply,computed,gpu_shared,d1,9,11.739354
512,multiply,computed,gpu_copy,i0,9,17.721324
512,multiply,computed,gpu_shared,i0,9,13.731361
512,multiply,computed,cpu,cpu,9,61.96175
512,multiply,computed,gpu_copy,d0,9,29.442205
512,multiply,computed,gpu_shared,d0,9,13.941761
512,multiply,computed,gpu_copy,d1,9,12.272734
512,multiply,nu_readback,gpu_shared,d0,0,92.777704
512,multiply,nu_readback,gpu_copy,d1,0,87.951798
512,multiply,nu_readback,gpu_shared,d1,0,80.344362
512,multiply,nu_readback,gpu_copy,i0,0,97.210399
512,multiply,nu_readback,gpu_shared,i0,0,92.039073
512,multiply,nu_readback,cpu,cpu,0,76.909538
512,multiply,nu_readback,gpu_copy,d0,0,119.233376
512,multiply,nu_readback,gpu_copy,d1,1,87.436452
512,multiply,nu_readback,gpu_shared,d1,1,84.91301
512,multiply,nu_readback,gpu_copy,i0,1,88.603659
512,multiply,nu_readback,gpu_shared,i0,1,91.276618
512,multiply,nu_readback,cpu,cpu,1,76.533981
512,multiply,nu_readback,gpu_copy,d0,1,120.682025
512,multiply,nu_readback,gpu_shared,d0,1,95.95468
512,multiply,nu_readback,gpu_shared,d1,2,87.434739
512,multiply,nu_readback,gpu_copy,i0,2,97.655065
512,multiply,nu_readback,gpu_shared,i0,2,93.662355
512,multiply,nu_readback,cpu,cpu,2,77.113908
512,multiply,nu_readback,gpu_copy,d0,2,117.150882
512,multiply,nu_readback,gpu_shared,d0,2,91.055638
512,multiply,nu_readback,gpu_copy,d1,2,92.004559
512,multiply,nu_readback,gpu_copy,i0,3,96.695444
512,multiply,nu_readback,gpu_shared,i0,3,84.846275
512,multiply,nu_readback,cpu,cpu,3,76.919116
512,multiply,nu_readback,gpu_copy,d0,3,125.000308
512,multiply,nu_readback,gpu_shared,d0,3,95.058316
512,multiply,nu_readback,gpu_copy,d1,3,86.530411
512,multiply,nu_readback,gpu_shared,d1,3,96.479763
512,multiply,nu_readback,gpu_shared,i0,4,97.633664
512,multiply,nu_readback,cpu,cpu,4,72.780245
512,multiply,nu_readback,gpu_copy,d0,4,99.752527
512,multiply,nu_readback,gpu_shared,d0,4,98.754014
512,multiply,nu_readback,gpu_copy,d1,4,89.493449
512,multiply,nu_readback,gpu_shared,d1,4,85.528491
512,multiply,nu_readback,gpu_copy,i0,4,90.15093
512,multiply,nu_readback,cpu,cpu,5,74.671996
512,multiply,nu_readback,gpu_copy,d0,5,88.466433
512,multiply,nu_readback,gpu_shared,d0,5,83.312379
512,multiply,nu_readback,gpu_copy,d1,5,89.119786
512,multiply,nu_readback,gpu_shared,d1,5,85.023926
512,multiply,nu_readback,gpu_copy,i0,5,92.836333
512,multiply,nu_readback,gpu_shared,i0,5,89.330717
512,multiply,nu_readback,gpu_copy,d0,6,97.592619
512,multiply,nu_readback,gpu_shared,d0,6,88.773654
512,multiply,nu_readback,gpu_copy,d1,6,88.907713
512,multiply,nu_readback,gpu_shared,d1,6,88.310905
512,multiply,nu_readback,gpu_copy,i0,6,91.806401
512,multiply,nu_readback,gpu_shared,i0,6,99.382099
512,multiply,nu_readback,cpu,cpu,6,75.083139
512,multiply,nu_readback,gpu_shared,d0,7,90.360428
512,multiply,nu_readback,gpu_copy,d1,7,91.338754
512,multiply,nu_readback,gpu_shared,d1,7,85.119293
512,multiply,nu_readback,gpu_copy,i0,7,91.900106
512,multiply,nu_readback,gpu_shared,i0,7,89.512645
512,multiply,nu_readback,cpu,cpu,7,79.451035
512,multiply,nu_readback,gpu_copy,d0,7,91.971919
512,multiply,nu_readback,gpu_copy,d1,8,87.901526
512,multiply,nu_readback,gpu_shared,d1,8,81.549117
512,multiply,nu_readback,gpu_copy,i0,8,93.688384
512,multiply,nu_readback,gpu_shared,i0,8,93.212852
512,multiply,nu_readback,cpu,cpu,8,73.504109
512,multiply,nu_readback,gpu_copy,d0,8,110.843227
512,multiply,nu_readback,gpu_shared,d0,8,90.192187
512,multiply,nu_readback,gpu_shared,d1,9,83.018193
512,multiply,nu_readback,gpu_copy,i0,9,92.288346
512,multiply,nu_readback,gpu_shared,i0,9,92.311229
512,multiply,nu_readback,cpu,cpu,9,77.647127
512,multiply,nu_readback,gpu_copy,d0,9,121.796223
512,multiply,nu_readback,gpu_shared,d0,9,103.485074
512,multiply,nu_readback,gpu_copy,d1,9,90.596967
1024,scale,computed,gpu_shared,d0,0,9.054451
1024,scale,computed,gpu_copy,d1,0,6.460158
1024,scale,computed,gpu_shared,d1,0,4.817019
1024,scale,computed,gpu_copy,i0,0,5.854584
1024,scale,computed,gpu_shared,i0,0,2.139159
1024,scale,computed,cpu,cpu,0,105.862135
1024,scale,computed,gpu_copy,d0,0,16.162081
1024,scale,computed,gpu_copy,d1,1,5.928791
1024,scale,computed,gpu_shared,d1,1,4.673843
1024,scale,computed,gpu_copy,i0,1,6.15956
1024,scale,computed,gpu_shared,i0,1,2.244205
1024,scale,computed,cpu,cpu,1,104.141392
1024,scale,computed,gpu_copy,d0,1,4.058592
1024,scale,computed,gpu_shared,d0,1,18.300009
1024,scale,computed,gpu_shared,d1,2,6.643999
1024,scale,computed,gpu_copy,i0,2,6.014722
1024,scale,computed,gpu_shared,i0,2,1.995613
1024,scale,computed,cpu,cpu,2,105.35813
1024,scale,computed,gpu_copy,d0,2,21.368062
1024,scale,computed,gpu_shared,d0,2,6.330989
1024,scale,computed,gpu_copy,d1,2,6.912458
1024,scale,computed,gpu_copy,i0,3,5.834577
1024,scale,computed,gpu_shared,i0,3,2.006453
1024,scale,computed,cpu,cpu,3,103.21847
1024,scale,computed,gpu_copy,d0,3,15.012037
1024,scale,computed,gpu_shared,d0,3,11.388343
1024,scale,computed,gpu_copy,d1,3,6.017126
1024,scale,computed,gpu_shared,d1,3,4.986684
1024,scale,computed,gpu_shared,i0,4,5.790556
1024,scale,computed,cpu,cpu,4,120.788735
1024,scale,computed,gpu_copy,d0,4,5.778954
1024,scale,computed,gpu_shared,d0,4,13.042593
1024,scale,computed,gpu_copy,d1,4,7.024966
1024,scale,computed,gpu_shared,d1,4,5.029382
1024,scale,computed,gpu_copy,i0,4,7.460985
1024,scale,computed,cpu,cpu,5,111.078977
1024,scale,computed,gpu_copy,d0,5,3.577539
1024,scale,computed,gpu_shared,d0,5,2.463301
1024,scale,computed,gpu_copy,d1,5,8.078511
1024,scale,computed,gpu_shared,d1,5,4.938003
1024,scale,computed,gpu_copy,i0,5,6.104748
1024,scale,computed,gpu_shared,i0,5,1.866684
1024,scale,computed,gpu_copy,d0,6,12.042166
1024,scale,computed,gpu_shared,d0,6,3.085086
1024,scale,computed,gpu_copy,d1,6,6.685697
1024,scale,computed,gpu_shared,d1,6,4.768719
1024,scale,computed,gpu_copy,i0,6,3.140688
1024,scale,computed,gpu_shared,i0,6,2.254373
1024,scale,computed,cpu,cpu,6,111.750493
1024,scale,computed,gpu_shared,d0,7,12.433924
1024,scale,computed,gpu_copy,d1,7,7.110064
1024,scale,computed,gpu_shared,d1,7,5.165926
1024,scale,computed,gpu_copy,i0,7,5.913614
1024,scale,computed,gpu_shared,i0,7,2.166971
1024,scale,computed,cpu,cpu,7,113.854728
1024,scale,computed,gpu_copy,d0,7,24.6434
1024,scale,computed,gpu_copy,d1,8,10.748856
1024,scale,computed,gpu_shared,d1,8,5.375706
1024,scale,computed,gpu_copy,i0,8,6.43973
1024,scale,computed,gpu_shared,i0,8,2.403279
1024,scale,computed,cpu,cpu,8,108.956508
1024,scale,computed,gpu_copy,d0,8,6.550135
1024,scale,computed,gpu_shared,d0,8,13.33182
1024,scale,computed,gpu_shared,d1,9,6.745938
1024,scale,computed,gpu_copy,i0,9,6.214362
1024,scale,computed,gpu_shared,i0,9,2.357855
1024,scale,computed,cpu,cpu,9,113.729305
1024,scale,computed,gpu_copy,d0,9,3.472054
1024,scale,computed,gpu_shared,d0,9,2.803272
1024,scale,computed,gpu_copy,d1,9,6.915975
1024,scale,nu_readback,gpu_shared,d0,0,301.976712
1024,scale,nu_readback,gpu_copy,d1,0,293.71462
1024,scale,nu_readback,gpu_shared,d1,0,306.417092
1024,scale,nu_readback,gpu_copy,i0,0,313.805493
1024,scale,nu_readback,gpu_shared,i0,0,299.020827
1024,scale,nu_readback,cpu,cpu,0,145.728165
1024,scale,nu_readback,gpu_copy,d0,0,332.354664
1024,scale,nu_readback,gpu_copy,d1,1,295.862025
1024,scale,nu_readback,gpu_shared,d1,1,308.033122
1024,scale,nu_readback,gpu_copy,i0,1,296.871859
1024,scale,nu_readback,gpu_shared,i0,1,302.035572
1024,scale,nu_readback,cpu,cpu,1,153.365497
1024,scale,nu_readback,gpu_copy,d0,1,297.94979
1024,scale,nu_readback,gpu_shared,d0,1,322.143156
1024,scale,nu_readback,gpu_shared,d1,2,292.717952
1024,scale,nu_readback,gpu_copy,i0,2,297.296228
1024,scale,nu_readback,gpu_shared,i0,2,291.483862
1024,scale,nu_readback,cpu,cpu,2,156.624505
1024,scale,nu_readback,gpu_copy,d0,2,296.840081
1024,scale,nu_readback,gpu_shared,d0,2,298.436404
1024,scale,nu_readback,gpu_copy,d1,2,302.482202
1024,scale,nu_readback,gpu_copy,i0,3,304.213284
1024,scale,nu_readback,gpu_shared,i0,3,293.347942
1024,scale,nu_readback,cpu,cpu,3,155.071054
1024,scale,nu_readback,gpu_copy,d0,3,313.788082
1024,scale,nu_readback,gpu_shared,d0,3,300.060618
1024,scale,nu_readback,gpu_copy,d1,3,304.24881
1024,scale,nu_readback,gpu_shared,d1,3,297.416281
1024,scale,nu_readback,gpu_shared,i0,4,304.072303
1024,scale,nu_readback,cpu,cpu,4,160.036528
1024,scale,nu_readback,gpu_copy,d0,4,297.027399
1024,scale,nu_readback,gpu_shared,d0,4,322.090801
1024,scale,nu_readback,gpu_copy,d1,4,295.140659
1024,scale,nu_readback,gpu_shared,d1,4,307.793088
1024,scale,nu_readback,gpu_copy,i0,4,310.803484
1024,scale,nu_readback,cpu,cpu,5,155.88818
1024,scale,nu_readback,gpu_copy,d0,5,317.84909
1024,scale,nu_readback,gpu_shared,d0,5,313.95926
1024,scale,nu_readback,gpu_copy,d1,5,289.721643
1024,scale,nu_readback,gpu_shared,d1,5,305.258646
1024,scale,nu_readback,gpu_copy,i0,5,298.506065
1024,scale,nu_readback,gpu_shared,i0,5,300.424374
1024,scale,nu_readback,gpu_copy,d0,6,307.149575
1024,scale,nu_readback,gpu_shared,d0,6,317.6768
1024,scale,nu_readback,gpu_copy,d1,6,301.685946
1024,scale,nu_readback,gpu_shared,d1,6,296.703681
1024,scale,nu_readback,gpu_copy,i0,6,301.182942
1024,scale,nu_readback,gpu_shared,i0,6,298.660402
1024,scale,nu_readback,cpu,cpu,6,152.495856
1024,scale,nu_readback,gpu_shared,d0,7,311.649556
1024,scale,nu_readback,gpu_copy,d1,7,307.692523
1024,scale,nu_readback,gpu_shared,d1,7,300.855365
1024,scale,nu_readback,gpu_copy,i0,7,294.125137
1024,scale,nu_readback,gpu_shared,i0,7,296.87554
1024,scale,nu_readback,cpu,cpu,7,153.724596
1024,scale,nu_readback,gpu_copy,d0,7,323.397888
1024,scale,nu_readback,gpu_copy,d1,8,301.697389
1024,scale,nu_readback,gpu_shared,d1,8,298.273445
1024,scale,nu_readback,gpu_copy,i0,8,324.180239
1024,scale,nu_readback,gpu_shared,i0,8,302.266805
1024,scale,nu_readback,cpu,cpu,8,152.849952
1024,scale,nu_readback,gpu_copy,d0,8,328.284436
1024,scale,nu_readback,gpu_shared,d0,8,312.147832
1024,scale,nu_readback,gpu_shared,d1,9,317.066169
1024,scale,nu_readback,gpu_copy,i0,9,299.685295
1024,scale,nu_readback,gpu_shared,i0,9,313.79063
1024,scale,nu_readback,cpu,cpu,9,151.719395
1024,scale,nu_readback,gpu_copy,d0,9,315.959375
1024,scale,nu_readback,gpu_shared,d0,9,303.288441
1024,scale,nu_readback,gpu_copy,d1,9,305.325012
1024,multiply,computed,gpu_shared,d0,0,21.44775
1024,multiply,computed,gpu_copy,d1,0,28.856339
1024,multiply,computed,gpu_shared,d1,0,23.702956
1024,multiply,computed,gpu_copy,i0,0,72.95897
1024,multiply,computed,gpu_shared,i0,0,40.738108
1024,multiply,computed,cpu,cpu,0,255.481107
1024,multiply,computed,gpu_copy,d0,0,27.291164
1024,multiply,computed,gpu_copy,d1,1,31.47105
1024,multiply,computed,gpu_shared,d1,1,22.359432
1024,multiply,computed,gpu_copy,i0,1,69.304057
1024,multiply,computed,gpu_shared,i0,1,41.672251
1024,multiply,computed,cpu,cpu,1,252.38959
1024,multiply,computed,gpu_copy,d0,1,38.507408
1024,multiply,computed,gpu_shared,d0,1,22.499332
1024,multiply,computed,gpu_shared,d1,2,30.744592
1024,multiply,computed,gpu_copy,i0,2,69.60685
1024,multiply,computed,gpu_shared,i0,2,40.952375
1024,multiply,computed,cpu,cpu,2,251.188251
1024,multiply,computed,gpu_copy,d0,2,53.554431
1024,multiply,computed,gpu_shared,d0,2,27.462683
1024,multiply,computed,gpu_copy,d1,2,34.878475
1024,multiply,computed,gpu_copy,i0,3,69.761888
1024,multiply,computed,gpu_shared,i0,3,40.518991
1024,multiply,computed,cpu,cpu,3,266.079935
1024,multiply,computed,gpu_copy,d0,3,33.013633
1024,multiply,computed,gpu_shared,d0,3,22.683023
1024,multiply,computed,gpu_copy,d1,3,28.617165
1024,multiply,computed,gpu_shared,d1,3,22.069855
1024,multiply,computed,gpu_shared,i0,4,67.211575
1024,multiply,computed,cpu,cpu,4,258.689912
1024,multiply,computed,gpu_copy,d0,4,40.375675
1024,multiply,computed,gpu_shared,d0,4,23.174916
1024,multiply,computed,gpu_copy,d1,4,30.973969
1024,multiply,computed,gpu_shared,d1,4,22.531502
1024,multiply,computed,gpu_copy,i0,4,69.188193
1024,multiply,computed,cpu,cpu,5,259.021217
1024,multiply,computed,gpu_copy,d0,5,38.245182
1024,multiply,computed,gpu_shared,d0,5,22.44971
1024,multiply,computed,gpu_copy,d1,5,37.013997
1024,multiply,computed,gpu_shared,d1,5,22.97263
1024,multiply,computed,gpu_copy,i0,5,69.945207
1024,multiply,computed,gpu_shared,i0,5,41.268592
1024,multiply,computed,gpu_copy,d0,6,38.654631
1024,multiply,computed,gpu_shared,d0,6,22.631608
1024,multiply,computed,gpu_copy,d1,6,30.420011
1024,multiply,computed,gpu_shared,d1,6,23.913998
1024,multiply,computed,gpu_copy,i0,6,68.408146
1024,multiply,computed,gpu_shared,i0,6,41.273651
1024,multiply,computed,cpu,cpu,6,253.77987
1024,multiply,computed,gpu_shared,d0,7,21.028403
1024,multiply,computed,gpu_copy,d1,7,33.620289
1024,multiply,computed,gpu_shared,d1,7,23.600445
1024,multiply,computed,gpu_copy,i0,7,68.692824
1024,multiply,computed,gpu_shared,i0,7,41.14309
1024,multiply,computed,cpu,cpu,7,246.973259
1024,multiply,computed,gpu_copy,d0,7,39.883722
1024,multiply,computed,gpu_copy,d1,8,37.241889
1024,multiply,computed,gpu_shared,d1,8,23.523223
1024,multiply,computed,gpu_copy,i0,8,68.470672
1024,multiply,computed,gpu_shared,i0,8,41.193212
1024,multiply,computed,cpu,cpu,8,260.335486
1024,multiply,computed,gpu_copy,d0,8,33.421
1024,multiply,computed,gpu_shared,d0,8,22.473684
1024,multiply,computed,gpu_shared,d1,9,25.333622
1024,multiply,computed,gpu_copy,i0,9,68.622523
1024,multiply,computed,gpu_shared,i0,9,42.765369
1024,multiply,computed,cpu,cpu,9,255.319649
1024,multiply,computed,gpu_copy,d0,9,39.843628
1024,multiply,computed,gpu_shared,d0,9,23.067476
1024,multiply,computed,gpu_copy,d1,9,31.121382
1024,multiply,nu_readback,gpu_shared,d0,0,334.408085
1024,multiply,nu_readback,gpu_copy,d1,0,324.419509
1024,multiply,nu_readback,gpu_shared,d1,0,327.471432
1024,multiply,nu_readback,gpu_copy,i0,0,366.715137
1024,multiply,nu_readback,gpu_shared,i0,0,365.111381
1024,multiply,nu_readback,cpu,cpu,0,307.303808
1024,multiply,nu_readback,gpu_copy,d0,0,353.609167
1024,multiply,nu_readback,gpu_copy,d1,1,327.400562
1024,multiply,nu_readback,gpu_shared,d1,1,320.984164
1024,multiply,nu_readback,gpu_copy,i0,1,368.825694
1024,multiply,nu_readback,gpu_shared,i0,1,364.637563
1024,multiply,nu_readback,cpu,cpu,1,309.341779
1024,multiply,nu_readback,gpu_copy,d0,1,345.628057
1024,multiply,nu_readback,gpu_shared,d0,1,352.605425
1024,multiply,nu_readback,gpu_shared,d1,2,330.859722
1024,multiply,nu_readback,gpu_copy,i0,2,353.668407
1024,multiply,nu_readback,gpu_shared,i0,2,360.541332
1024,multiply,nu_readback,cpu,cpu,2,302.4282
1024,multiply,nu_readback,gpu_copy,d0,2,299.982362
1024,multiply,nu_readback,gpu_shared,d0,2,332.620239
1024,multiply,nu_readback,gpu_copy,d1,2,319.685124
1024,multiply,nu_readback,gpu_copy,i0,3,352.686196
1024,multiply,nu_readback,gpu_shared,i0,3,359.06856
1024,multiply,nu_readback,cpu,cpu,3,308.756645
1024,multiply,nu_readback,gpu_copy,d0,3,336.807119
1024,multiply,nu_readback,gpu_shared,d0,3,326.404955
1024,multiply,nu_readback,gpu_copy,d1,3,324.66654
1024,multiply,nu_readback,gpu_shared,d1,3,320.835491
1024,multiply,nu_readback,gpu_shared,i0,4,361.178046
1024,multiply,nu_readback,cpu,cpu,4,311.927299
1024,multiply,nu_readback,gpu_copy,d0,4,359.381621
1024,multiply,nu_readback,gpu_shared,d0,4,328.08272
1024,multiply,nu_readback,gpu_copy,d1,4,328.660442
1024,multiply,nu_readback,gpu_shared,d1,4,317.701124
1024,multiply,nu_readback,gpu_copy,i0,4,361.475567
1024,multiply,nu_readback,cpu,cpu,5,309.917961
1024,multiply,nu_readback,gpu_copy,d0,5,350.910031
1024,multiply,nu_readback,gpu_shared,d0,5,331.113144
1024,multiply,nu_readback,gpu_copy,d1,5,323.074196
1024,multiply,nu_readback,gpu_shared,d1,5,334.201385
1024,multiply,nu_readback,gpu_copy,i0,5,354.510894
1024,multiply,nu_readback,gpu_shared,i0,5,361.646196
1024,multiply,nu_readback,gpu_copy,d0,6,356.258467
1024,multiply,nu_readback,gpu_shared,d0,6,328.131191
1024,multiply,nu_readback,gpu_copy,d1,6,331.768911
1024,multiply,nu_readback,gpu_shared,d1,6,330.18941
1024,multiply,nu_readback,gpu_copy,i0,6,373.136808
1024,multiply,nu_readback,gpu_shared,i0,6,374.540004
1024,multiply,nu_readback,cpu,cpu,6,316.096397
1024,multiply,nu_readback,gpu_shared,d0,7,325.556875
1024,multiply,nu_readback,gpu_copy,d1,7,334.534143
1024,multiply,nu_readback,gpu_shared,d1,7,308.867633
1024,multiply,nu_readback,gpu_copy,i0,7,363.618406
1024,multiply,nu_readback,gpu_shared,i0,7,365.365849
1024,multiply,nu_readback,cpu,cpu,7,324.151536
1024,multiply,nu_readback,gpu_copy,d0,7,363.215629
1024,multiply,nu_readback,gpu_copy,d1,8,351.306418
1024,multiply,nu_readback,gpu_shared,d1,8,347.914605
1024,multiply,nu_readback,gpu_copy,i0,8,405.06464
1024,multiply,nu_readback,gpu_shared,i0,8,376.87124
1024,multiply,nu_readback,cpu,cpu,8,327.131426
1024,multiply,nu_readback,gpu_copy,d0,8,372.651511
1024,multiply,nu_readback,gpu_shared,d0,8,340.602486
1024,multiply,nu_readback,gpu_shared,d1,9,336.474135
1024,multiply,nu_readback,gpu_copy,i0,9,392.818946
1024,multiply,nu_readback,gpu_shared,i0,9,379.593202
1024,multiply,nu_readback,cpu,cpu,9,325.110938
1024,multiply,nu_readback,gpu_copy,d0,9,373.913794
1024,multiply,nu_readback,gpu_shared,d0,9,392.59445
1024,multiply,nu_readback,gpu_copy,d1,9,378.025334