nu_plugin_vulkan_matrix 0.1.1

GPU matrix operations for Nushell using Vulkan
size,operation,boundary,mode,device,samples,mean_ms,min_ms,max_ms,run,phase
256,scale,computed,gpu_shared,d0,10,1.6954542,0.822127,2.697911,1,before
256,scale,computed,gpu_shared,d1,10,1.0494887000000002,0.867652,1.618056,1,before
256,scale,computed,gpu_shared,i0,10,1.0112032,0.704318,1.354856,1,before
256,scale,computed,gpu_copy,d1,10,1.9645233999999998,1.536976,3.285523,1,before
256,scale,computed,gpu_copy,i0,10,1.1289862,0.934495,1.473647,1,before
256,scale,computed,gpu_copy,d0,10,3.4533879,1.630068,9.145749,1,before
256,scale,computed,cpu,cpu,10,8.4338265,7.802383,9.985218,1,before
256,scale,nu_readback,gpu_shared,d0,10,30.584764000000007,24.724227,34.302659,1,before
256,scale,nu_readback,gpu_shared,d1,10,20.9334911,17.805996,27.48776,1,before
256,scale,nu_readback,gpu_shared,i0,10,20.536641,17.632684,24.055705,1,before
256,scale,nu_readback,gpu_copy,d1,10,22.4469866,19.021804,27.763012,1,before
256,scale,nu_readback,gpu_copy,i0,10,24.461695000000002,21.490129,27.070926,1,before
256,scale,nu_readback,gpu_copy,d0,10,27.7906468,19.397662,46.278375,1,before
256,scale,nu_readback,cpu,cpu,10,11.615636599999998,10.526423,12.522371,1,before
256,multiply,computed,gpu_shared,d0,10,9.6980688,3.492037,13.987533,1,before
256,multiply,computed,gpu_shared,d1,10,5.8538987,4.971063,6.377987,1,before
256,multiply,computed,gpu_shared,i0,10,5.204016599999999,4.767536,8.152163,1,before
256,multiply,computed,gpu_copy,d1,10,6.618755,4.946268,8.95258,1,before
256,multiply,computed,gpu_copy,i0,10,7.4884512999999995,5.419036,9.332486,1,before
256,multiply,computed,gpu_copy,d0,10,9.5805333,4.361622,14.466994,1,before
256,multiply,computed,cpu,cpu,10,17.951924599999998,15.991245,20.740496,1,before
256,multiply,nu_readback,gpu_shared,d0,10,29.192730000000005,20.429599,35.248476,1,before
256,multiply,nu_readback,gpu_shared,d1,10,25.5051883,23.156084,29.481834,1,before
256,multiply,nu_readback,gpu_shared,i0,10,24.6680604,22.411621,28.158797,1,before
256,multiply,nu_readback,gpu_copy,d1,10,26.1272545,23.862035,30.230684,1,before
256,multiply,nu_readback,gpu_copy,i0,10,28.156239899999996,27.098998,30.903526,1,before
256,multiply,nu_readback,gpu_copy,d0,10,32.7079368,26.921869,45.004849,1,before
256,multiply,nu_readback,cpu,cpu,10,21.514788,19.887984,23.286085,1,before
512,scale,computed,gpu_shared,d0,10,6.670154200000001,1.163992,13.94827,1,before
512,scale,computed,gpu_shared,d1,10,2.0008871000000004,1.476022,3.813164,1,before
512,scale,computed,gpu_shared,i0,10,1.5281828,0.870648,4.223646,1,before
512,scale,computed,gpu_copy,d1,10,2.9782291,2.673436,3.479143,1,before
512,scale,computed,gpu_copy,i0,10,4.0940669,1.303872,5.807899,1,before
512,scale,computed,gpu_copy,d0,10,12.320498999999998,2.036653,17.034171,1,before
512,scale,computed,cpu,cpu,10,29.915006400000003,28.236831,32.354119,1,before
512,scale,nu_readback,gpu_shared,d0,10,84.7888846,72.881862,92.624184,1,before
512,scale,nu_readback,gpu_shared,d1,10,76.7142617,70.912634,84.483863,1,before
512,scale,nu_readback,gpu_shared,i0,10,79.8486881,75.624747,89.737282,1,before
512,scale,nu_readback,gpu_copy,d1,10,81.6158807,75.248829,90.337867,1,before
512,scale,nu_readback,gpu_copy,i0,10,81.7216081,74.380686,89.766907,1,before
512,scale,nu_readback,gpu_copy,d0,10,91.59489840000002,79.12029,106.33882,1,before
512,scale,nu_readback,cpu,cpu,10,41.3031295,38.110452,44.727623,1,before
512,multiply,computed,gpu_shared,d0,10,14.264077,4.725447,17.940656,1,before
512,multiply,computed,gpu_shared,d1,10,8.004019,6.432419,10.014773,1,before
512,multiply,computed,gpu_shared,i0,10,13.921286499999999,13.301799,16.520628,1,before
512,multiply,computed,gpu_copy,d1,10,9.845584799999997,8.62403,12.063659,1,before
512,multiply,computed,gpu_copy,i0,10,18.3450126,17.459472,20.243914,1,before
512,multiply,computed,gpu_copy,d0,10,23.546480700000004,7.826088,35.647848,1,before
512,multiply,computed,cpu,cpu,10,68.7466295,64.766127,77.250296,1,before
512,multiply,nu_readback,gpu_shared,d0,10,93.93911840000001,82.395343,108.419665,1,before
512,multiply,nu_readback,gpu_shared,d1,10,84.5550376,79.632108,89.459886,1,before
512,multiply,nu_readback,gpu_shared,i0,10,92.1211213,88.301765,100.044006,1,before
512,multiply,nu_readback,gpu_copy,d1,10,87.0239437,79.097707,93.788005,1,before
512,multiply,nu_readback,gpu_copy,i0,10,93.02231300000001,88.27266,98.979228,1,before
512,multiply,nu_readback,gpu_copy,d0,10,101.8118312,84.516583,120.580634,1,before
512,multiply,nu_readback,cpu,cpu,10,80.87019199999999,78.074838,89.009078,1,before
1024,scale,computed,gpu_shared,d0,10,11.9101596,4.771032,17.885774,1,before
1024,scale,computed,gpu_shared,d1,10,5.3717179,4.52234,7.906787,1,before
1024,scale,computed,gpu_shared,i0,10,2.752432,1.60432,6.270538,1,before
1024,scale,computed,gpu_copy,d1,10,7.154594,6.38455,8.456799,1,before
1024,scale,computed,gpu_copy,i0,10,6.5153745,5.647691,7.53168,1,before
1024,scale,computed,gpu_copy,d0,10,19.0489252,3.793657,30.694737,1,before
1024,scale,computed,cpu,cpu,10,109.04247339999999,105.031801,113.803714,1,before
1024,scale,nu_readback,gpu_shared,d0,10,346.1532647,311.791019,390.659762,1,before
1024,scale,nu_readback,gpu_shared,d1,10,323.15594580000004,297.044769,396.092263,1,before
1024,scale,nu_readback,gpu_shared,i0,10,322.82011079999995,300.788693,358.554075,1,before
1024,scale,nu_readback,gpu_copy,d1,10,329.4182081,298.689223,378.852411,1,before
1024,scale,nu_readback,gpu_copy,i0,10,327.23503489999996,303.304709,354.35706,1,before
1024,scale,nu_readback,gpu_copy,d0,10,337.73582550000003,306.915794,372.1769,1,before
1024,scale,nu_readback,cpu,cpu,10,170.2087149,156.130628,197.53157,1,before
1024,multiply,computed,gpu_shared,d0,10,21.799604199999997,14.595792,23.852777,1,before
1024,multiply,computed,gpu_shared,d1,10,23.5560719,21.807328,25.998773,1,before
1024,multiply,computed,gpu_shared,i0,10,44.1563363,40.165518,67.887132,1,before
1024,multiply,computed,gpu_copy,d1,10,30.772648299999997,30.171946,31.877894,1,before
1024,multiply,computed,gpu_copy,i0,10,69.25953510000001,68.522402,70.048788,1,before
1024,multiply,computed,gpu_copy,d0,10,33.652328000000004,26.638462,40.444446,1,before
1024,multiply,computed,cpu,cpu,10,271.5803967,249.370131,283.027159,1,before
1024,multiply,nu_readback,gpu_shared,d0,10,330.26607670000004,314.774458,352.847307,1,before
1024,multiply,nu_readback,gpu_shared,d1,10,333.91529909999997,309.303566,359.556052,1,before
1024,multiply,nu_readback,gpu_shared,i0,10,371.9329112,358.277606,384.296808,1,before
1024,multiply,nu_readback,gpu_copy,d1,10,333.7013917,320.519066,348.39079,1,before
1024,multiply,nu_readback,gpu_copy,i0,10,366.5912984,354.104313,396.5776,1,before
1024,multiply,nu_readback,gpu_copy,d0,10,344.76962620000006,319.903084,362.33498,1,before
1024,multiply,nu_readback,cpu,cpu,10,322.92576799999995,305.293697,333.989118,1,before
256,scale,computed,gpu_shared,d0,10,3.918866,0.76041,15.59264,1,after
256,scale,computed,gpu_shared,d1,10,1.6315433,0.898707,5.789552,1,after
256,scale,computed,gpu_shared,i0,10,0.8383264,0.546364,1.241043,1,after
256,scale,computed,gpu_copy,d1,10,1.9670013000000002,1.48251,2.913435,1,after
256,scale,computed,gpu_copy,i0,10,1.5958147,0.925838,4.837155,1,after
256,scale,computed,gpu_copy,d0,10,8.2852065,1.493161,28.751125,1,after
256,scale,computed,cpu,cpu,10,7.768996400000001,7.245303,8.556045,1,after
256,scale,nu_readback,gpu_shared,d0,10,33.3776778,19.494941,46.165004,1,after
256,scale,nu_readback,gpu_shared,d1,10,20.0084197,18.513069,20.877206,1,after
256,scale,nu_readback,gpu_shared,i0,10,22.1892529,19.468191,26.699518,1,after
256,scale,nu_readback,gpu_copy,d1,10,20.8770753,19.5809,22.606243,1,after
256,scale,nu_readback,gpu_copy,i0,10,24.726352100000003,22.343777,28.733994,1,after
256,scale,nu_readback,gpu_copy,d0,10,36.881407499999995,17.897818,54.978727,1,after
256,scale,nu_readback,cpu,cpu,10,11.066176,9.941335,13.670314,1,after
256,multiply,computed,gpu_shared,d0,10,9.651831,2.51673,14.163539,1,after
256,multiply,computed,gpu_shared,d1,10,6.2562246,5.592887,6.973168,1,after
256,multiply,computed,gpu_shared,i0,10,5.2745405,4.784327,6.626395,1,after
256,multiply,computed,gpu_copy,d1,10,7.316363900000001,6.563017,7.720084,1,after
256,multiply,computed,gpu_copy,i0,10,8.5784054,5.193045,9.73381,1,after
256,multiply,computed,gpu_copy,d0,10,21.7341546,3.44954,32.471759,1,after
256,multiply,computed,cpu,cpu,10,17.6120132,15.313863,20.53486,1,after
256,multiply,nu_readback,gpu_shared,d0,10,35.4608853,20.049089,45.105378,1,after
256,multiply,nu_readback,gpu_shared,d1,10,25.0940347,22.89518,27.198084,1,after
256,multiply,nu_readback,gpu_shared,i0,10,23.9778628,22.792229,26.438855,1,after
256,multiply,nu_readback,gpu_copy,d1,10,26.208436299999995,24.553848,28.012304,1,after
256,multiply,nu_readback,gpu_copy,i0,10,27.5984051,26.082733,30.719738,1,after
256,multiply,nu_readback,gpu_copy,d0,10,46.205668200000005,20.937608,65.627065,1,after
256,multiply,nu_readback,cpu,cpu,10,20.2184652,17.970503,23.219291,1,after
512,scale,computed,gpu_shared,d0,10,7.8246886999999985,1.982438,14.586243,1,after
512,scale,computed,gpu_shared,d1,10,1.8297599999999998,1.505694,2.510448,1,after
512,scale,computed,gpu_shared,i0,10,1.4276706999999997,0.882337,4.182651,1,after
512,scale,computed,gpu_copy,d1,10,3.2557205,2.621524,4.157994,1,after
512,scale,computed,gpu_copy,i0,10,4.119822,1.251993,5.882294,1,after
512,scale,computed,gpu_copy,d0,10,13.243644300000003,2.081512,23.899624,1,after
512,scale,computed,cpu,cpu,10,28.845973800000003,26.471125,30.418168,1,after
512,scale,nu_readback,gpu_shared,d0,10,91.54293890000001,73.561417,109.373092,1,after
512,scale,nu_readback,gpu_shared,d1,10,78.3357961,72.56141,82.751999,1,after
512,scale,nu_readback,gpu_shared,i0,10,78.6289041,73.106002,87.072105,1,after
512,scale,nu_readback,gpu_copy,d1,10,78.94749909999999,73.97824,92.795844,1,after
512,scale,nu_readback,gpu_copy,i0,10,81.0100531,76.790659,86.230723,1,after
512,scale,nu_readback,gpu_copy,d0,10,96.2935963,75.771518,116.313189,1,after
512,scale,nu_readback,cpu,cpu,10,41.6194962,39.336174,45.060376,1,after
512,multiply,computed,gpu_shared,d0,10,14.866214100000002,12.061048,16.376475,1,after
512,multiply,computed,gpu_shared,d1,10,7.7671183,7.236226,8.277398,1,after
512,multiply,computed,gpu_shared,i0,10,14.166650999999998,13.580057,16.986116,1,after
512,multiply,computed,gpu_copy,d1,10,9.5570553,8.647826,10.216165,1,after
512,multiply,computed,gpu_copy,i0,10,17.2243423,14.106954,17.890986,1,after
512,multiply,computed,gpu_copy,d0,10,22.153258399999995,7.201992,37.220029,1,after
512,multiply,computed,cpu,cpu,10,65.35168089999999,63.255005,67.076565,1,after
512,multiply,nu_readback,gpu_shared,d0,10,89.8551085,78.814034,104.507166,1,after
512,multiply,nu_readback,gpu_shared,d1,10,86.4509556,80.66613,95.229131,1,after
512,multiply,nu_readback,gpu_shared,i0,10,91.779844,86.74531,97.27671,1,after
512,multiply,nu_readback,gpu_copy,d1,10,88.4251427,82.2992,97.357931,1,after
512,multiply,nu_readback,gpu_copy,i0,10,94.3051094,90.209869,102.468793,1,after
512,multiply,nu_readback,gpu_copy,d0,10,103.0191415,87.237863,125.702742,1,after
512,multiply,nu_readback,cpu,cpu,10,76.67185020000001,72.916382,83.634477,1,after
1024,scale,computed,gpu_shared,d0,10,11.580245600000001,3.06698,15.587342,1,after
1024,scale,computed,gpu_shared,d1,10,4.961154100000001,4.196706,6.655539,1,after
1024,scale,computed,gpu_shared,i0,10,2.3969805,1.650222,5.307678,1,after
1024,scale,computed,gpu_copy,d1,10,6.830067,5.744529,7.854643,1,after
1024,scale,computed,gpu_copy,i0,10,5.7254592,2.555581,6.866581,1,after
1024,scale,computed,gpu_copy,d0,10,18.275285900000004,3.655182,25.91847,1,after
1024,scale,computed,cpu,cpu,10,107.4719365,102.254808,114.148466,1,after
1024,scale,nu_readback,gpu_shared,d0,10,316.21203270000007,298.12609,341.972797,1,after
1024,scale,nu_readback,gpu_shared,d1,10,307.979943,293.323194,325.225196,1,after
1024,scale,nu_readback,gpu_shared,i0,10,303.148227,292.87137,317.945338,1,after
1024,scale,nu_readback,gpu_copy,d1,10,305.51817850000003,299.271511,310.790829,1,after
1024,scale,nu_readback,gpu_copy,i0,10,302.28535910000005,290.143902,311.427375,1,after
1024,scale,nu_readback,gpu_copy,d0,10,327.0503987,291.139594,355.43158,1,after
1024,scale,nu_readback,cpu,cpu,10,156.46091819999998,150.042851,172.928933,1,after
1024,multiply,computed,gpu_shared,d0,10,22.972762499999998,12.444901,30.223269,1,after
1024,multiply,computed,gpu_shared,d1,10,24.481040300000004,22.017684,30.275095,1,after
1024,multiply,computed,gpu_shared,i0,10,43.8775914,40.726678,67.815621,1,after
1024,multiply,computed,gpu_copy,d1,10,31.5528751,28.141496,37.593495,1,after
1024,multiply,computed,gpu_copy,i0,10,68.8654242,68.212788,69.270331,1,after
1024,multiply,computed,gpu_copy,d0,10,35.7763557,25.682664,41.807694,1,after
1024,multiply,computed,cpu,cpu,10,261.0147842,246.967245,269.308189,1,after
1024,multiply,nu_readback,gpu_shared,d0,10,324.1781665,305.00726,350.059922,1,after
1024,multiply,nu_readback,gpu_shared,d1,10,324.30908659999994,312.558516,354.343761,1,after
1024,multiply,nu_readback,gpu_shared,i0,10,363.1532595,353.831482,369.35971,1,after
1024,multiply,nu_readback,gpu_copy,d1,10,333.2971337,322.190626,346.72426,1,after
1024,multiply,nu_readback,gpu_copy,i0,10,363.3774333,353.231226,369.642501,1,after
1024,multiply,nu_readback,gpu_copy,d0,10,339.696483,322.692832,353.870601,1,after
1024,multiply,nu_readback,cpu,cpu,10,305.94153919999997,297.68949,311.48366,1,after
256,scale,computed,gpu_shared,d0,10,6.3654047,0.759669,15.17037,2,before
256,scale,computed,gpu_shared,d1,10,1.5255971999999998,0.784175,3.898535,2,before
256,scale,computed,gpu_shared,i0,10,1.015355,0.65728,1.612762,2,before
256,scale,computed,gpu_copy,d1,10,2.3528562,1.515192,3.333005,2,before
256,scale,computed,gpu_copy,i0,10,1.7674616999999997,1.001799,4.563358,2,before
256,scale,computed,gpu_copy,d0,10,11.6027567,1.623152,28.355298,2,before
256,scale,computed,cpu,cpu,10,8.1358232,7.112949,9.536476,2,before
256,scale,nu_readback,gpu_shared,d0,10,31.959324899999995,21.750431,43.691235,2,before
256,scale,nu_readback,gpu_shared,d1,10,20.500417499999998,18.467368,23.150018,2,before
256,scale,nu_readback,gpu_shared,i0,10,21.0991654,18.9913,23.954261,2,before
256,scale,nu_readback,gpu_copy,d1,10,21.629398400000003,19.231807,26.547052,2,before
256,scale,nu_readback,gpu_copy,i0,10,24.468886500000004,22.894323,26.840797,2,before
256,scale,nu_readback,gpu_copy,d0,10,42.010682599999996,28.525052,56.139745,2,before
256,scale,nu_readback,cpu,cpu,10,10.897309400000001,9.860868,12.051203,2,before
256,multiply,computed,gpu_shared,d0,10,9.7197734,3.530782,14.815272,2,before
256,multiply,computed,gpu_shared,d1,10,5.1204116,4.47299,5.941826,2,before
256,multiply,computed,gpu_shared,i0,10,5.063365000000001,4.318173,5.613868,2,before
256,multiply,computed,gpu_copy,d1,10,6.192915100000001,5.136642,8.18604,2,before
256,multiply,computed,gpu_copy,i0,10,8.8869328,8.339615,9.548678,2,before
256,multiply,computed,gpu_copy,d0,10,20.118880499999996,3.88533,32.547326,2,before
256,multiply,computed,cpu,cpu,10,17.3270568,15.696778,19.525713,2,before
256,multiply,nu_readback,gpu_shared,d0,10,33.143107900000004,19.599149,49.032677,2,before
256,multiply,nu_readback,gpu_shared,d1,10,24.948650800000003,22.52027,30.225728,2,before
256,multiply,nu_readback,gpu_shared,i0,10,25.603137099999998,22.818853,31.585391,2,before
256,multiply,nu_readback,gpu_copy,d1,10,25.4632707,23.275601,28.385754,2,before
256,multiply,nu_readback,gpu_copy,i0,10,27.7897948,26.289694,30.984826,2,before
256,multiply,nu_readback,gpu_copy,d0,10,45.5106156,24.139955,65.050831,2,before
256,multiply,nu_readback,cpu,cpu,10,20.1877923,18.740666,22.153278,2,before
512,scale,computed,gpu_shared,d0,10,6.6612881,2.418869,13.173997,2,before
512,scale,computed,gpu_shared,d1,10,1.8325929000000003,1.431697,2.325145,2,before
512,scale,computed,gpu_shared,i0,10,1.4963969000000001,0.821354,4.464574,2,before
512,scale,computed,gpu_copy,d1,10,3.5509124,2.808662,6.334715,2,before
512,scale,computed,gpu_copy,i0,10,3.7482614000000005,1.140926,5.529751,2,before
512,scale,computed,gpu_copy,d0,10,14.312471999999996,2.019337,27.884404,2,before
512,scale,computed,cpu,cpu,10,28.794172100000004,27.172513,31.294552,2,before
512,scale,nu_readback,gpu_shared,d0,10,90.70645239999999,76.09174,110.435299,2,before
512,scale,nu_readback,gpu_shared,d1,10,77.80557909999999,71.961626,83.129369,2,before
512,scale,nu_readback,gpu_shared,i0,10,79.0440482,76.00013,84.619645,2,before
512,scale,nu_readback,gpu_copy,d1,10,78.11000600000001,74.926678,84.575722,2,before
512,scale,nu_readback,gpu_copy,i0,10,80.97268590000002,76.649324,90.048348,2,before
512,scale,nu_readback,gpu_copy,d0,10,90.63294290000002,76.07592,110.399833,2,before
512,scale,nu_readback,cpu,cpu,10,40.0668612,37.24864,41.750756,2,before
512,multiply,computed,gpu_shared,d0,10,10.4896393,5.25431,17.641768,2,before
512,multiply,computed,gpu_shared,d1,10,9.7262424,8.960638,11.739354,2,before
512,multiply,computed,gpu_shared,i0,10,13.9974715,13.65537,16.529222,2,before
512,multiply,computed,gpu_copy,d1,10,11.9354399,11.130965,12.599761,2,before
512,multiply,computed,gpu_copy,i0,10,17.8291137,17.244961,18.429419,2,before
512,multiply,computed,gpu_copy,d0,10,27.6702065,5.141741,42.356139,2,before
512,multiply,computed,cpu,cpu,10,64.41742350000001,61.353281,68.739216,2,before
512,multiply,nu_readback,gpu_shared,d0,10,92.9724074,83.312379,103.485074,2,before
512,multiply,nu_readback,gpu_shared,d1,10,85.7721799,80.344362,96.479763,2,before
512,multiply,nu_readback,gpu_shared,i0,10,92.32075270000001,84.846275,99.382099,2,before
512,multiply,nu_readback,gpu_copy,d1,10,89.1281415,86.530411,92.004559,2,before
512,multiply,nu_readback,gpu_copy,i0,10,93.28350670000002,88.603659,97.655065,2,before
512,multiply,nu_readback,gpu_copy,d0,10,109.24895389999999,88.466433,125.000308,2,before
512,multiply,nu_readback,cpu,cpu,10,76.06141939999999,72.780245,79.451035,2,before
1024,scale,computed,gpu_shared,d0,10,9.223378799999999,2.463301,18.300009,2,before
1024,scale,computed,gpu_shared,d1,10,5.314521900000001,4.673843,6.745938,2,before
1024,scale,computed,gpu_shared,i0,10,2.5225148000000006,1.866684,5.790556,2,before
1024,scale,computed,gpu_copy,d1,10,7.1882602,5.928791,10.748856,2,before
1024,scale,computed,gpu_copy,i0,10,5.9137569999999995,3.140688,7.460985,2,before
1024,scale,computed,gpu_copy,d0,10,11.266502,3.472054,24.6434,2,before
1024,scale,computed,cpu,cpu,10,109.8738873,103.21847,120.788735,2,before
1024,scale,nu_readback,gpu_shared,d0,10,310.34295800000007,298.436404,322.143156,2,before
1024,scale,nu_readback,gpu_shared,d1,10,303.0534841,292.717952,317.066169,2,before
1024,scale,nu_readback,gpu_shared,i0,10,300.1978257,291.483862,313.79063,2,before
1024,scale,nu_readback,gpu_copy,d1,10,299.7570829,289.721643,307.692523,2,before
1024,scale,nu_readback,gpu_copy,i0,10,304.06700259999997,294.125137,324.180239,2,before
1024,scale,nu_readback,gpu_copy,d0,10,313.06003799999996,296.840081,332.354664,2,before
1024,scale,nu_readback,cpu,cpu,10,153.7503728,145.728165,160.036528,2,before
1024,multiply,computed,gpu_shared,d0,10,22.891858499999998,21.028403,27.462683,2,before
1024,multiply,computed,gpu_shared,d1,10,24.0752255,22.069855,30.744592,2,before
1024,multiply,computed,gpu_shared,i0,10,43.87372140000001,40.518991,67.211575,2,before
1024,multiply,computed,gpu_copy,d1,10,32.4214566,28.617165,37.241889,2,before
1024,multiply,computed,gpu_copy,i0,10,69.49593300000001,68.408146,72.95897,2,before
1024,multiply,computed,gpu_copy,d0,10,38.2790474,27.291164,53.554431,2,before
1024,multiply,computed,cpu,cpu,10,255.92582760000005,246.973259,266.079935,2,before
1024,multiply,nu_readback,gpu_shared,d0,10,339.2119569999999,325.556875,392.59445,2,before
1024,multiply,nu_readback,gpu_shared,d1,10,327.5499101,308.867633,347.914605,2,before
1024,multiply,nu_readback,gpu_shared,i0,10,366.85533730000003,359.06856,379.593202,2,before
1024,multiply,nu_readback,gpu_copy,d1,10,334.3541179,319.685124,378.025334,2,before
1024,multiply,nu_readback,gpu_copy,i0,10,369.25206949999995,352.686196,405.06464,2,before
1024,multiply,nu_readback,gpu_copy,d0,10,351.2357758,299.982362,373.913794,2,before
1024,multiply,nu_readback,cpu,cpu,10,314.21659889999995,302.4282,327.131426,2,before
256,scale,computed,gpu_shared,d0,10,9.7321894,0.644727,22.43855,2,after
256,scale,computed,gpu_shared,d1,10,1.3174288,0.877649,1.845134,2,after
256,scale,computed,gpu_shared,i0,10,0.8529457,0.584114,1.653578,2,after
256,scale,computed,gpu_copy,d1,10,2.3513794999999997,1.739368,2.984148,2,after
256,scale,computed,gpu_copy,i0,10,1.873644,0.895742,5.334129,2,after
256,scale,computed,gpu_copy,d0,10,17.1498734,1.639993,26.906512,2,after
256,scale,computed,cpu,cpu,10,8.155529699999999,7.365659,8.915165,2,after
256,scale,nu_readback,gpu_shared,d0,10,35.70078600000001,18.281165,45.841529,2,after
256,scale,nu_readback,gpu_shared,d1,10,21.005196899999998,18.155591,24.871726,2,after
256,scale,nu_readback,gpu_shared,i0,10,20.8206416,18.483972,25.527763,2,after
256,scale,nu_readback,gpu_copy,d1,10,21.493713800000002,19.86786,25.635242,2,after
256,scale,nu_readback,gpu_copy,i0,10,24.1233835,22.116282,26.668029,2,after
256,scale,nu_readback,gpu_copy,d0,10,54.6869086,35.540524,63.137066,2,after
256,scale,nu_readback,cpu,cpu,10,10.870427799999998,9.554841,13.121811,2,after
256,multiply,computed,gpu_shared,d0,10,16.4008155,2.873543,23.052619,2,after
256,multiply,computed,gpu_shared,d1,10,6.317186899999999,5.504635,7.519634,2,after
256,multiply,computed,gpu_shared,i0,10,5.3223589,4.646733,7.452169,2,after
256,multiply,computed,gpu_copy,d1,10,7.331525300000001,6.357137,8.122072,2,after
256,multiply,computed,gpu_copy,i0,10,9.230163000000001,5.463529,14.008276,2,after
256,multiply,computed,gpu_copy,d0,10,39.1962159,33.286261,43.265379,2,after
256,multiply,computed,cpu,cpu,10,19.4667891,17.385383,23.0963,2,after
256,multiply,nu_readback,gpu_shared,d0,10,40.9335849,26.010078,46.342799,2,after
256,multiply,nu_readback,gpu_shared,d1,10,25.5846563,23.569769,28.420551,2,after
256,multiply,nu_readback,gpu_shared,i0,10,24.1871169,21.976332,29.768743,2,after
256,multiply,nu_readback,gpu_copy,d1,10,26.455129,24.218103,30.182601,2,after
256,multiply,nu_readback,gpu_copy,i0,10,28.5466463,26.174913,31.460773,2,after
256,multiply,nu_readback,gpu_copy,d0,10,63.97507210000001,33.100536,80.515355,2,after
256,multiply,nu_readback,cpu,cpu,10,20.3150807,18.152246,23.687228,2,after
512,scale,computed,gpu_shared,d0,10,12.2176418,1.995463,15.152479,2,after
512,scale,computed,gpu_shared,d1,10,2.3024197,1.51429,5.295147,2,after
512,scale,computed,gpu_shared,i0,10,1.9177188,1.043446,4.464686,2,after
512,scale,computed,gpu_copy,d1,10,3.0201844000000007,2.60311,3.364855,2,after
512,scale,computed,gpu_copy,i0,10,5.7334279,5.036116,7.30721,2,after
512,scale,computed,gpu_copy,d0,10,25.676130199999996,19.903956,34.716956,2,after
512,scale,computed,cpu,cpu,10,29.975228400000002,28.159107,33.188139,2,after
512,scale,nu_readback,gpu_shared,d0,10,97.2348039,78.305806,109.052864,2,after
512,scale,nu_readback,gpu_shared,d1,10,78.6661842,73.216942,85.466995,2,after
512,scale,nu_readback,gpu_shared,i0,10,79.522574,76.023571,81.796544,2,after
512,scale,nu_readback,gpu_copy,d1,10,78.3079155,76.264918,84.646332,2,after
512,scale,nu_readback,gpu_copy,i0,10,79.3468255,74.438559,83.187665,2,after
512,scale,nu_readback,gpu_copy,d0,10,115.2006247,103.15014,126.025951,2,after
512,scale,nu_readback,cpu,cpu,10,42.482728900000005,40.24827,45.082292,2,after
512,multiply,computed,gpu_shared,d0,10,15.459673199999997,6.279754,24.438492,2,after
512,multiply,computed,gpu_shared,d1,10,10.2681132,8.938007,12.524803,2,after
512,multiply,computed,gpu_shared,i0,10,14.273330900000001,13.56845,17.251144,2,after
512,multiply,computed,gpu_copy,d1,10,12.2025749,11.556787,13.922867,2,after
512,multiply,computed,gpu_copy,i0,10,18.235050599999997,17.341071,19.455144,2,after
512,multiply,computed,gpu_copy,d0,10,37.123953699999994,14.745604,48.7945,2,after
512,multiply,computed,cpu,cpu,10,67.64068329999999,64.689117,71.141822,2,after
512,multiply,nu_readback,gpu_shared,d0,10,98.5612034,72.034428,107.675369,2,after
512,multiply,nu_readback,gpu_shared,d1,10,84.6506026,79.922957,91.196849,2,after
512,multiply,nu_readback,gpu_shared,i0,10,91.06061310000001,87.890243,97.80916,2,after
512,multiply,nu_readback,gpu_copy,d1,10,86.4019912,81.663007,93.669337,2,after
512,multiply,nu_readback,gpu_copy,i0,10,92.00262230000001,87.556053,98.729257,2,after
512,multiply,nu_readback,gpu_copy,d0,10,127.21974949999999,117.151935,138.351887,2,after
512,multiply,nu_readback,cpu,cpu,10,78.7464952,74.199275,81.676091,2,after
1024,scale,computed,gpu_shared,d0,10,11.633139199999999,2.701303,16.161593,2,after
1024,scale,computed,gpu_shared,d1,10,5.3827401,4.8065,6.181662,2,after
1024,scale,computed,gpu_shared,i0,10,2.5048483999999998,1.653058,5.669191,2,after
1024,scale,computed,gpu_copy,d1,10,6.988828600000001,6.31002,9.637294,2,after
1024,scale,computed,gpu_copy,i0,10,6.1731188,5.686433,7.364626,2,after
1024,scale,computed,gpu_copy,d0,10,26.1405257,10.447448,31.857741,2,after
1024,scale,computed,cpu,cpu,10,107.95492299999998,105.158209,111.999005,2,after
1024,scale,nu_readback,gpu_shared,d0,10,318.3919053,308.501098,337.473505,2,after
1024,scale,nu_readback,gpu_shared,d1,10,300.24387149999995,290.047074,319.043345,2,after
1024,scale,nu_readback,gpu_shared,i0,10,297.2971931,292.800954,307.721835,2,after
1024,scale,nu_readback,gpu_copy,d1,10,300.3502752,289.505819,319.960357,2,after
1024,scale,nu_readback,gpu_copy,i0,10,296.7608769,290.03443,303.393721,2,after
1024,scale,nu_readback,gpu_copy,d0,10,328.00945920000004,299.209344,354.848989,2,after
1024,scale,nu_readback,cpu,cpu,10,157.5728119,151.400175,161.180103,2,after
1024,multiply,computed,gpu_shared,d0,10,25.435604100000003,11.519538,32.597013,2,after
1024,multiply,computed,gpu_shared,d1,10,24.674512799999995,22.567,31.575027,2,after
1024,multiply,computed,gpu_shared,i0,10,44.43335780000001,40.58094,67.741033,2,after
1024,multiply,computed,gpu_copy,d1,10,32.3990287,29.538738,36.865705,2,after
1024,multiply,computed,gpu_copy,i0,10,70.0834911,68.798675,74.326354,2,after
1024,multiply,computed,gpu_copy,d0,10,43.5746282,13.405548,60.620779,2,after
1024,multiply,computed,cpu,cpu,10,266.3602505,250.37292,278.897064,2,after
1024,multiply,nu_readback,gpu_shared,d0,10,340.6446625,333.012527,355.909879,2,after
1024,multiply,nu_readback,gpu_shared,d1,10,327.86505109999996,313.928321,343.375044,2,after
1024,multiply,nu_readback,gpu_shared,i0,10,363.5555397,354.156223,378.194263,2,after
1024,multiply,nu_readback,gpu_copy,d1,10,337.7027779,328.062088,345.694708,2,after
1024,multiply,nu_readback,gpu_copy,i0,10,363.95215479999996,352.866202,377.739398,2,after
1024,multiply,nu_readback,gpu_copy,d0,10,374.74579959999994,357.995889,399.359943,2,after
1024,multiply,nu_readback,cpu,cpu,10,306.17744239999996,292.655934,317.547073,2,after