[Benchmark] Benchmark to(device)

[vmoens]

No description provided.

[github-actions]

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 47. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_common_ops	1.2604ms	1.2182ms	820.9071 Ops/s	813.8796 Ops/s	$\color{#35bf28}+0.86\%$
test_creation	4.3791μs	4.1891μs	238.7167 KOps/s	242.9321 KOps/s	$\color{#d91a1a}-1.74\%$
test_creation_empty	17.0342μs	16.3979μs	60.9834 KOps/s	60.6388 KOps/s	$\color{#35bf28}+0.57\%$
test_creation_nested_1	30.7423μs	28.5510μs	35.0251 KOps/s	34.0413 KOps/s	$\color{#35bf28}+2.89\%$
test_creation_nested_2	29.8333μs	28.8961μs	34.6068 KOps/s	34.0831 KOps/s	$\color{#35bf28}+1.54\%$
test_clone	28.2143μs	26.7031μs	37.4488 KOps/s	38.0033 KOps/s	$\color{#d91a1a}-1.46\%$
test_getitem[int]	38.7461μs	32.3966μs	30.8674 KOps/s	31.0041 KOps/s	$\color{#d91a1a}-0.44\%$
test_getitem[slice_int]	73.9413μs	66.6663μs	15.0001 KOps/s	14.9836 KOps/s	$\color{#35bf28}+0.11\%$
test_getitem[range]	74.2921μs	69.1876μs	14.4535 KOps/s	14.6059 KOps/s	$\color{#d91a1a}-1.04\%$
test_getitem[tuple]	65.0411μs	62.0465μs	16.1169 KOps/s	16.1197 KOps/s	$\color{#d91a1a}-0.02\%$
test_getitem[list]	65.8684μs	60.9788μs	16.3991 KOps/s	16.4881 KOps/s	$\color{#d91a1a}-0.54\%$
test_setitem_dim[int]	71.3000μs	45.6449μs	21.9083 KOps/s	21.9449 KOps/s	$\color{#d91a1a}-0.17\%$
test_setitem_dim[slice_int]	0.1758ms	81.1112μs	12.3287 KOps/s	12.1614 KOps/s	$\color{#35bf28}+1.38\%$
test_setitem_dim[range]	0.1788ms	77.0089μs	12.9855 KOps/s	12.9054 KOps/s	$\color{#35bf28}+0.62\%$
test_setitem_dim[tuple]	0.1193ms	74.4281μs	13.4358 KOps/s	13.4092 KOps/s	$\color{#35bf28}+0.20\%$
test_setitem	40.0194μs	38.8999μs	25.7070 KOps/s	26.4821 KOps/s	$\color{#d91a1a}-2.93\%$
test_set	38.7954μs	37.9036μs	26.3827 KOps/s	26.9395 KOps/s	$\color{#d91a1a}-2.07\%$
test_set_shared	0.1761ms	0.1725ms	5.7976 KOps/s	5.5898 KOps/s	$\color{#35bf28}+3.72\%$
test_update	48.4875μs	47.6425μs	20.9897 KOps/s	20.9379 KOps/s	$\color{#35bf28}+0.25\%$
test_update_nested	68.6918μs	67.8326μs	14.7422 KOps/s	14.6867 KOps/s	$\color{#35bf28}+0.38\%$
test_set_nested	48.4155μs	47.2545μs	21.1620 KOps/s	21.2628 KOps/s	$\color{#d91a1a}-0.47\%$
test_set_nested_new	67.1287μs	65.3483μs	15.3026 KOps/s	15.2878 KOps/s	$\color{#35bf28}+0.10\%$
test_select	0.1048ms	0.1030ms	9.7084 KOps/s	9.7137 KOps/s	$\color{#d91a1a}-0.05\%$
test_creation[device0]	1.3230ms	0.4980ms	2.0082 KOps/s	2.0212 KOps/s	$\color{#d91a1a}-0.64\%$
test_creation_from_tensor	0.5925ms	0.4588ms	2.1796 KOps/s	2.1421 KOps/s	$\color{#35bf28}+1.75\%$
test_add_one[memmap_tensor0]	38.4354μs	31.0937μs	32.1609 KOps/s	32.5054 KOps/s	$\color{#d91a1a}-1.06\%$
test_contiguous[memmap_tensor0]	8.7811μs	8.3946μs	119.1236 KOps/s	125.4655 KOps/s	$\textbf{\color{#d91a1a}-5.05\%}$
test_stack[memmap_tensor0]	0.1725ms	42.4503μs	23.5570 KOps/s	22.6395 KOps/s	$\color{#35bf28}+4.05\%$
test_reshape_pytree	38.4604μs	35.5565μs	28.1242 KOps/s	27.6355 KOps/s	$\color{#35bf28}+1.77\%$
test_reshape_td	51.3526μs	48.5635μs	20.5916 KOps/s	20.2104 KOps/s	$\color{#35bf28}+1.89\%$
test_view_pytree	34.1914μs	32.7556μs	30.5291 KOps/s	30.0088 KOps/s	$\color{#35bf28}+1.73\%$
test_view_td	10.0471μs	9.0904μs	110.0063 KOps/s	113.2958 KOps/s	$\color{#d91a1a}-2.90\%$
test_unbind_pytree	38.0654μs	36.7597μs	27.2037 KOps/s	27.6739 KOps/s	$\color{#d91a1a}-1.70\%$
test_unbind_td	0.1856ms	0.1829ms	5.4665 KOps/s	5.4929 KOps/s	$\color{#d91a1a}-0.48\%$
test_split_pytree	43.0505μs	41.3203μs	24.2012 KOps/s	24.3498 KOps/s	$\color{#d91a1a}-0.61\%$
test_split_td	0.1185ms	0.1151ms	8.6918 KOps/s	8.6866 KOps/s	$\color{#35bf28}+0.06\%$
test_add_pytree	47.7655μs	45.8325μs	21.8186 KOps/s	22.0234 KOps/s	$\color{#d91a1a}-0.93\%$
test_add_td	79.9829μs	77.7171μs	12.8672 KOps/s	13.3213 KOps/s	$\color{#d91a1a}-3.41\%$
test_distributed	77.6010μs	77.6010μs	12.8864 KOps/s	11.6008 KOps/s	$\textbf{\color{#35bf28}+11.08\%}$
test_tdmodule	63.6010μs	27.8449μs	35.9132 KOps/s	34.9557 KOps/s	$\color{#35bf28}+2.74\%$
test_tdmodule_dispatch	63.8316ms	66.5463μs	15.0271 KOps/s	16.0410 KOps/s	$\textbf{\color{#d91a1a}-6.32\%}$
test_tdseq	0.1906ms	37.8101μs	26.4480 KOps/s	25.6436 KOps/s	$\color{#35bf28}+3.14\%$
test_tdseq_dispatch	0.1280ms	69.5180μs	14.3848 KOps/s	14.0158 KOps/s	$\color{#35bf28}+2.63\%$
test_instantiation_functorch	1.7595ms	1.6069ms	622.3001 Ops/s	640.2802 Ops/s	$\color{#d91a1a}-2.81\%$
test_instantiation_td	8.5516ms	1.2837ms	779.0093 Ops/s	836.0473 Ops/s	$\textbf{\color{#d91a1a}-6.82\%}$
test_exec_functorch	0.1877ms	0.1831ms	5.4628 KOps/s	5.6044 KOps/s	$\color{#d91a1a}-2.53\%$
test_exec_td	0.3305ms	0.3253ms	3.0738 KOps/s	3.0600 KOps/s	$\color{#35bf28}+0.45\%$

[tcbegley]

LGTM!

[github-actions]

$\color{#35bf28}\textsf{\Large✔\kern{0.2cm}\normalsize OK}$ Result of GPU Benchmark Tests

Total Benchmarks: 47. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}0$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_common_ops	1.1232ms	1.0766ms	928.8860 Ops/s	921.1330 Ops/s	$\color{#35bf28}+0.84\%$
test_creation	3.8350μs	3.2666μs	306.1258 KOps/s	307.7201 KOps/s	$\color{#d91a1a}-0.52\%$
test_creation_empty	14.4871μs	13.4890μs	74.1343 KOps/s	74.2203 KOps/s	$\color{#d91a1a}-0.12\%$
test_creation_nested_1	24.0982μs	22.1941μs	45.0570 KOps/s	44.3319 KOps/s	$\color{#35bf28}+1.64\%$
test_creation_nested_2	24.5262μs	23.6078μs	42.3589 KOps/s	42.1579 KOps/s	$\color{#35bf28}+0.48\%$
test_clone	23.5502μs	21.8500μs	45.7665 KOps/s	45.7861 KOps/s	$\color{#d91a1a}-0.04\%$
test_getitem[int]	27.8318μs	26.4922μs	37.7470 KOps/s	38.6608 KOps/s	$\color{#d91a1a}-2.36\%$
test_getitem[slice_int]	56.3528μs	53.0438μs	18.8523 KOps/s	18.9903 KOps/s	$\color{#d91a1a}-0.73\%$
test_getitem[range]	64.3704μs	58.8155μs	17.0023 KOps/s	17.0098 KOps/s	$\color{#d91a1a}-0.04\%$
test_getitem[tuple]	54.6059μs	49.9416μs	20.0234 KOps/s	20.6643 KOps/s	$\color{#d91a1a}-3.10\%$
test_getitem[list]	58.7554μs	52.3576μs	19.0994 KOps/s	19.2817 KOps/s	$\color{#d91a1a}-0.95\%$
test_setitem_dim[int]	67.7010μs	37.9697μs	26.3368 KOps/s	26.0684 KOps/s	$\color{#35bf28}+1.03\%$
test_setitem_dim[slice_int]	0.1961ms	67.8758μs	14.7328 KOps/s	14.7313 KOps/s	$\color{#35bf28}+0.01\%$
test_setitem_dim[range]	0.1982ms	67.7301μs	14.7645 KOps/s	14.6643 KOps/s	$\color{#35bf28}+0.68\%$
test_setitem_dim[tuple]	0.1213ms	61.2643μs	16.3227 KOps/s	16.4124 KOps/s	$\color{#d91a1a}-0.55\%$
test_setitem	31.9281μs	30.3152μs	32.9867 KOps/s	32.4005 KOps/s	$\color{#35bf28}+1.81\%$
test_set	31.2731μs	29.5788μs	33.8080 KOps/s	33.4311 KOps/s	$\color{#35bf28}+1.13\%$
test_set_shared	0.1717ms	0.1674ms	5.9726 KOps/s	5.8525 KOps/s	$\color{#35bf28}+2.05\%$
test_update	38.9602μs	37.6532μs	26.5581 KOps/s	26.5426 KOps/s	$\color{#35bf28}+0.06\%$
test_update_nested	57.7193μs	54.4123μs	18.3782 KOps/s	18.5271 KOps/s	$\color{#d91a1a}-0.80\%$
test_set_nested	38.9432μs	37.2366μs	26.8553 KOps/s	26.6323 KOps/s	$\color{#35bf28}+0.84\%$
test_set_nested_new	53.2383μs	51.5554μs	19.3966 KOps/s	19.1714 KOps/s	$\color{#35bf28}+1.17\%$
test_select	86.6335μs	81.5595μs	12.2610 KOps/s	12.0047 KOps/s	$\color{#35bf28}+2.13\%$
test_creation[device0]	1.3380ms	0.5091ms	1.9642 KOps/s	1.7195 KOps/s	$\textbf{\color{#35bf28}+14.23\%}$
test_creation_from_tensor	0.6008ms	0.4716ms	2.1202 KOps/s	2.0980 KOps/s	$\color{#35bf28}+1.06\%$
test_add_one[memmap_tensor0]	52.4973μs	29.3338μs	34.0903 KOps/s	34.0615 KOps/s	$\color{#35bf28}+0.08\%$
test_contiguous[memmap_tensor0]	8.5661μs	8.0354μs	124.4489 KOps/s	125.4883 KOps/s	$\color{#d91a1a}-0.83\%$
test_stack[memmap_tensor0]	0.2116ms	46.1703μs	21.6589 KOps/s	21.5702 KOps/s	$\color{#35bf28}+0.41\%$
test_reshape_pytree	31.7102μs	28.9053μs	34.5957 KOps/s	35.1331 KOps/s	$\color{#d91a1a}-1.53\%$
test_reshape_td	42.5352μs	39.7015μs	25.1880 KOps/s	25.1002 KOps/s	$\color{#35bf28}+0.35\%$
test_view_pytree	27.2591μs	26.1016μs	38.3118 KOps/s	38.7916 KOps/s	$\color{#d91a1a}-1.24\%$
test_view_td	8.2710μs	7.1184μs	140.4804 KOps/s	142.9036 KOps/s	$\color{#d91a1a}-1.70\%$
test_unbind_pytree	32.5042μs	30.4162μs	32.8772 KOps/s	32.7653 KOps/s	$\color{#35bf28}+0.34\%$
test_unbind_td	0.1539ms	0.1509ms	6.6270 KOps/s	6.9651 KOps/s	$\color{#d91a1a}-4.85\%$
test_split_pytree	35.9802μs	33.6553μs	29.7130 KOps/s	29.7239 KOps/s	$\color{#d91a1a}-0.04\%$
test_split_td	98.9505μs	94.6739μs	10.5626 KOps/s	10.8533 KOps/s	$\color{#d91a1a}-2.68\%$
test_add_pytree	40.0102μs	37.6641μs	26.5505 KOps/s	27.0816 KOps/s	$\color{#d91a1a}-1.96\%$
test_add_td	64.7363μs	61.2600μs	16.3239 KOps/s	16.4400 KOps/s	$\color{#d91a1a}-0.71\%$
test_distributed	0.1083ms	0.1083ms	9.2335 KOps/s	9.1323 KOps/s	$\color{#35bf28}+1.11\%$
test_tdmodule	0.1168ms	24.1332μs	41.4366 KOps/s	42.8568 KOps/s	$\color{#d91a1a}-3.31\%$
test_tdmodule_dispatch	0.2237ms	53.0911μs	18.8356 KOps/s	19.3372 KOps/s	$\color{#d91a1a}-2.59\%$
test_tdseq	0.1155ms	32.0818μs	31.1703 KOps/s	31.7417 KOps/s	$\color{#d91a1a}-1.80\%$
test_tdseq_dispatch	0.1507ms	62.7798μs	15.9287 KOps/s	16.1876 KOps/s	$\color{#d91a1a}-1.60\%$
test_instantiation_functorch	1.3400ms	1.2662ms	789.7704 Ops/s	779.4269 Ops/s	$\color{#35bf28}+1.33\%$
test_instantiation_td	1.0497ms	0.9934ms	1.0067 KOps/s	1.0011 KOps/s	$\color{#35bf28}+0.56\%$
test_exec_functorch	0.1937ms	0.1586ms	6.3049 KOps/s	6.4094 KOps/s	$\color{#d91a1a}-1.63\%$
test_exec_td	0.2839ms	0.2761ms	3.6214 KOps/s	3.6649 KOps/s	$\color{#d91a1a}-1.18\%$