table-a100.md

bert-base-uncased - A100 - half - cuda

batch_size	seq_len	pad_percentage	HF_time	BT_time	Speedup
8	64	0	0.012947250976562501	0.007366779174804688	1.7575185395598296
8	64	0.1	0.012887490234375	0.0072092669677734375	1.7876283805252486
8	64	0.2	0.012887449951171874	0.007392645263671876	1.7432799074645124
8	64	0.5	0.012756295166015626	0.007139061889648438	1.7868307297506574
8	64	0.75	0.0132109521484375	0.007268699951171876	1.8175123800931694
8	128	0	0.012552437744140625	0.0075138049316406256	1.6705833939449668
8	128	0.1	0.0132246533203125	0.007377489624023438	1.7925682033152373
8	128	0.2	0.01270349853515625	0.007361699829101562	1.7256202820085118
8	128	0.5	0.01253486572265625	0.0073076123046875	1.715316193582917
8	128	0.75	0.01280079833984375	0.007162613525390625	1.7871686493298042
8	256	0	0.013096918945312501	0.0073260644531249995	1.7877154956950851
8	256	0.1	0.012815031738281251	0.007538012084960938	1.7000545493749575
8	256	0.2	0.0127824072265625	0.007293112182617187	1.75266839539762
8	256	0.5	0.012925665283203125	0.007354347534179687	1.7575543205064037
8	256	0.75	0.012753940429687501	0.007219097900390626	1.766694482560956

batch_size	seq_len	pad_percentage	HF_time	BT_time	Speedup
16	64	0	0.012791541748046874	0.0075867138671875	1.6860451009455133
16	64	0.1	0.012824945068359375	0.007612374877929687	1.6847495392722085
16	64	0.2	0.01257017333984375	0.007708118896484375	1.6307705561699273
16	64	0.5	0.012674600830078124	0.0073746228027343754	1.7186778455134835
16	64	0.75	0.013131120605468751	0.007327129516601563	1.7921234469401286
16	128	0	0.0125453515625	0.0074241845703125	1.689795215041635
16	128	0.1	0.012719411621093751	0.00749285400390625	1.697538963719664
16	128	0.2	0.01282830322265625	0.007500534057617188	1.7103186418610328
16	128	0.5	0.012582399902343751	0.007418777465820313	1.6960206665199498
16	128	0.75	0.01282303955078125	0.007292477416992188	1.758392767991617
16	256	0	0.013372744140625002	0.00832458740234375	1.6064152485034833
16	256	0.1	0.012801024169921875	0.007841935424804687	1.6323807168101871
16	256	0.2	0.013163704833984375	0.0075897857666015625	1.7343974176333854
16	256	0.5	0.013022576904296874	0.0077078936767578125	1.6895117460642748
16	256	0.75	0.01305870361328125	0.007338618774414063	1.779449786765071

batch_size	seq_len	pad_percentage	HF_time	BT_time	Speedup
64	64	0	0.013192867431640625	0.00828737548828125	1.591923456382057
64	64	0.1	0.01270013916015625	0.008382853393554688	1.5150138698502096
64	64	0.2	0.012997877197265625	0.008232857666015624	1.578780749595551
64	64	0.5	0.012849664306640625	0.008375623779296874	1.5341740084365802
64	64	0.75	0.013100318603515626	0.008229109497070312	1.5919485101248851
64	128	0	0.014951875000000002	0.013786091308593752	1.0845623074235367
64	128	0.1	0.014791700439453126	0.012987801513671874	1.1388917842548134
64	128	0.2	0.014881505126953125	0.012005662841796876	1.2395404837743906
64	128	0.5	0.01511077880859375	0.008753684692382812	1.7262192253443496
64	128	0.75	0.015181844482421875	0.008237485961914063	1.8430191629600325
64	256	0	0.032153271484374996	0.0269648681640625	1.1924134502992807
64	256	0.1	0.03160266845703125	0.0255294677734375	1.2378898274531478
64	256	0.2	0.032148212890625	0.023026831054687502	1.3961197185263878
64	256	0.5	0.0324914794921875	0.01525843994140625	2.1294103209081428
64	256	0.75	0.032503767089843746	0.0089327001953125	3.638739281421348