[Performance] Faster to

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 105. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.8000μs	20.2308μs	49.4297 KOps/s	50.7316 KOps/s	$\color{#d91a1a}-2.57\%$
test_plain_set_stack_nested	0.2084ms	0.1858ms	5.3811 KOps/s	5.5108 KOps/s	$\color{#d91a1a}-2.35\%$
test_plain_set_nested_inplace	49.5000μs	23.6173μs	42.3418 KOps/s	43.1572 KOps/s	$\color{#d91a1a}-1.89\%$
test_plain_set_stack_nested_inplace	0.3676ms	0.2203ms	4.5384 KOps/s	4.6359 KOps/s	$\color{#d91a1a}-2.10\%$
test_items	0.1385ms	3.1021μs	322.3640 KOps/s	320.9234 KOps/s	$\color{#35bf28}+0.45\%$
test_items_nested	0.4512ms	0.3998ms	2.5015 KOps/s	2.6172 KOps/s	$\color{#d91a1a}-4.42\%$
test_items_nested_locked	0.4854ms	0.3962ms	2.5238 KOps/s	2.7095 KOps/s	$\textbf{\color{#d91a1a}-6.86\%}$
test_items_nested_leaf	0.8595ms	0.2377ms	4.2070 KOps/s	4.4756 KOps/s	$\textbf{\color{#d91a1a}-6.00\%}$
test_items_stack_nested	1.9654ms	1.9045ms	525.0760 Ops/s	534.0572 Ops/s	$\color{#d91a1a}-1.68\%$
test_items_stack_nested_leaf	1.7734ms	1.7255ms	579.5478 Ops/s	592.7155 Ops/s	$\color{#d91a1a}-2.22\%$
test_items_stack_nested_locked	1.0487ms	0.9704ms	1.0305 KOps/s	1.0670 KOps/s	$\color{#d91a1a}-3.42\%$
test_keys	30.6000μs	4.6122μs	216.8161 KOps/s	208.2717 KOps/s	$\color{#35bf28}+4.10\%$
test_keys_nested	0.8103ms	0.1726ms	5.7950 KOps/s	5.4111 KOps/s	$\textbf{\color{#35bf28}+7.10\%}$
test_keys_nested_locked	0.2472ms	0.1714ms	5.8336 KOps/s	5.8324 KOps/s	$\color{#35bf28}+0.02\%$
test_keys_nested_leaf	0.2795ms	0.1696ms	5.8952 KOps/s	5.7950 KOps/s	$\color{#35bf28}+1.73\%$
test_keys_stack_nested	1.8156ms	1.7437ms	573.4861 Ops/s	579.1397 Ops/s	$\color{#d91a1a}-0.98\%$
test_keys_stack_nested_leaf	1.9169ms	1.7795ms	561.9645 Ops/s	576.1767 Ops/s	$\color{#d91a1a}-2.47\%$
test_keys_stack_nested_locked	0.8231ms	0.7776ms	1.2860 KOps/s	1.2800 KOps/s	$\color{#35bf28}+0.47\%$
test_values	32.4000μs	1.3684μs	730.7777 KOps/s	736.8762 KOps/s	$\color{#d91a1a}-0.83\%$
test_values_nested	0.1701ms	64.5790μs	15.4849 KOps/s	15.3700 KOps/s	$\color{#35bf28}+0.75\%$
test_values_nested_locked	0.1348ms	64.7857μs	15.4355 KOps/s	15.3902 KOps/s	$\color{#35bf28}+0.29\%$
test_values_nested_leaf	79.7000μs	56.0727μs	17.8340 KOps/s	17.3484 KOps/s	$\color{#35bf28}+2.80\%$
test_values_stack_nested	1.5765ms	1.5218ms	657.1349 Ops/s	664.5738 Ops/s	$\color{#d91a1a}-1.12\%$
test_values_stack_nested_leaf	1.6144ms	1.5075ms	663.3497 Ops/s	669.5039 Ops/s	$\color{#d91a1a}-0.92\%$
test_values_stack_nested_locked	0.7193ms	0.6333ms	1.5790 KOps/s	1.5821 KOps/s	$\color{#d91a1a}-0.20\%$
test_membership	17.0000μs	1.8511μs	540.2073 KOps/s	547.0552 KOps/s	$\color{#d91a1a}-1.25\%$
test_membership_nested	25.7990μs	3.7146μs	269.2053 KOps/s	267.9222 KOps/s	$\color{#35bf28}+0.48\%$
test_membership_nested_leaf	24.7990μs	3.7509μs	266.6061 KOps/s	267.7303 KOps/s	$\color{#d91a1a}-0.42\%$
test_membership_stacked_nested	42.5000μs	14.6363μs	68.3234 KOps/s	67.9492 KOps/s	$\color{#35bf28}+0.55\%$
test_membership_stacked_nested_leaf	68.6000μs	14.7768μs	67.6739 KOps/s	68.0597 KOps/s	$\color{#d91a1a}-0.57\%$
test_membership_nested_last	29.8000μs	7.5376μs	132.6685 KOps/s	132.0954 KOps/s	$\color{#35bf28}+0.43\%$
test_membership_nested_leaf_last	25.0000μs	7.5858μs	131.8251 KOps/s	132.9267 KOps/s	$\color{#d91a1a}-0.83\%$
test_membership_stacked_nested_last	0.2523ms	0.2239ms	4.4658 KOps/s	4.4826 KOps/s	$\color{#d91a1a}-0.37\%$
test_membership_stacked_nested_leaf_last	43.7000μs	17.0746μs	58.5666 KOps/s	59.0854 KOps/s	$\color{#d91a1a}-0.88\%$
test_nested_getleaf	59.8990μs	15.4726μs	64.6303 KOps/s	64.8957 KOps/s	$\color{#d91a1a}-0.41\%$
test_nested_get	38.5000μs	14.7708μs	67.7011 KOps/s	68.3613 KOps/s	$\color{#d91a1a}-0.97\%$
test_stacked_getleaf	0.9346ms	0.8226ms	1.2156 KOps/s	1.2336 KOps/s	$\color{#d91a1a}-1.46\%$
test_stacked_get	0.8174ms	0.7836ms	1.2762 KOps/s	1.2918 KOps/s	$\color{#d91a1a}-1.21\%$
test_nested_getitemleaf	56.3000μs	15.4703μs	64.6398 KOps/s	64.8968 KOps/s	$\color{#d91a1a}-0.40\%$
test_nested_getitem	36.0000μs	14.7697μs	67.7061 KOps/s	67.9172 KOps/s	$\color{#d91a1a}-0.31\%$
test_stacked_getitemleaf	0.9371ms	0.8252ms	1.2118 KOps/s	1.2323 KOps/s	$\color{#d91a1a}-1.67\%$
test_stacked_getitem	0.8163ms	0.7841ms	1.2753 KOps/s	1.2895 KOps/s	$\color{#d91a1a}-1.10\%$
test_lock_nested	63.6663ms	1.4560ms	686.7906 Ops/s	721.3215 Ops/s	$\color{#d91a1a}-4.79\%$
test_lock_stack_nested	83.1413ms	18.7845ms	53.2355 Ops/s	52.5114 Ops/s	$\color{#35bf28}+1.38\%$
test_unlock_nested	59.8542ms	1.4587ms	685.5324 Ops/s	688.3126 Ops/s	$\color{#d91a1a}-0.40\%$
test_unlock_stack_nested	81.5671ms	19.2343ms	51.9904 Ops/s	51.6508 Ops/s	$\color{#35bf28}+0.66\%$
test_flatten_speed	0.9984ms	0.9692ms	1.0318 KOps/s	1.0244 KOps/s	$\color{#35bf28}+0.72\%$
test_unflatten_speed	1.7978ms	1.6960ms	589.6255 Ops/s	580.5905 Ops/s	$\color{#35bf28}+1.56\%$
test_common_ops	4.6313ms	1.0200ms	980.3550 Ops/s	984.7005 Ops/s	$\color{#d91a1a}-0.44\%$
test_creation	30.1000μs	6.0295μs	165.8515 KOps/s	165.4722 KOps/s	$\color{#35bf28}+0.23\%$
test_creation_empty	28.8000μs	13.3710μs	74.7885 KOps/s	74.1870 KOps/s	$\color{#35bf28}+0.81\%$
test_creation_nested_1	47.3000μs	22.6736μs	44.1042 KOps/s	43.6574 KOps/s	$\color{#35bf28}+1.02\%$
test_creation_nested_2	48.6990μs	25.6770μs	38.9453 KOps/s	38.7466 KOps/s	$\color{#35bf28}+0.51\%$
test_clone	0.1138ms	24.1760μs	41.3634 KOps/s	41.9313 KOps/s	$\color{#d91a1a}-1.35\%$
test_getitem[int]	54.6000μs	26.9507μs	37.1048 KOps/s	37.0899 KOps/s	$\color{#35bf28}+0.04\%$
test_getitem[slice_int]	0.1226ms	50.5109μs	19.7977 KOps/s	20.2308 KOps/s	$\color{#d91a1a}-2.14\%$
test_getitem[range]	0.1267ms	76.5767μs	13.0588 KOps/s	13.1814 KOps/s	$\color{#d91a1a}-0.93\%$
test_getitem[tuple]	89.3000μs	41.3595μs	24.1782 KOps/s	24.2878 KOps/s	$\color{#d91a1a}-0.45\%$
test_getitem[list]	0.2942ms	71.7151μs	13.9441 KOps/s	13.9350 KOps/s	$\color{#35bf28}+0.07\%$
test_setitem_dim[int]	47.6000μs	33.8322μs	29.5576 KOps/s	31.2000 KOps/s	$\textbf{\color{#d91a1a}-5.26\%}$
test_setitem_dim[slice_int]	89.9000μs	59.7446μs	16.7379 KOps/s	17.0793 KOps/s	$\color{#d91a1a}-2.00\%$
test_setitem_dim[range]	0.1172ms	79.1585μs	12.6329 KOps/s	12.8776 KOps/s	$\color{#d91a1a}-1.90\%$
test_setitem_dim[tuple]	70.0000μs	50.1106μs	19.9559 KOps/s	20.4725 KOps/s	$\color{#d91a1a}-2.52\%$
test_setitem	0.1043ms	29.0359μs	34.4401 KOps/s	33.4315 KOps/s	$\color{#35bf28}+3.02\%$
test_set	0.1228ms	28.1365μs	35.5411 KOps/s	33.8765 KOps/s	$\color{#35bf28}+4.91\%$
test_set_shared	0.3935ms	0.1732ms	5.7722 KOps/s	5.6590 KOps/s	$\color{#35bf28}+2.00\%$
test_update	0.1905ms	31.6934μs	31.5523 KOps/s	31.4406 KOps/s	$\color{#35bf28}+0.36\%$
test_update_nested	0.1911ms	48.8582μs	20.4674 KOps/s	20.2422 KOps/s	$\color{#35bf28}+1.11\%$
test_set_nested	0.1243ms	30.5258μs	32.7592 KOps/s	31.9842 KOps/s	$\color{#35bf28}+2.42\%$
test_set_nested_new	0.1914ms	50.3774μs	19.8502 KOps/s	20.2185 KOps/s	$\color{#d91a1a}-1.82\%$
test_select	0.1222ms	94.3464μs	10.5992 KOps/s	10.5109 KOps/s	$\color{#35bf28}+0.84\%$
test_unbind_speed	0.8246ms	0.6283ms	1.5917 KOps/s	1.5542 KOps/s	$\color{#35bf28}+2.41\%$
test_unbind_speed_stack0	72.0030ms	8.0455ms	124.2927 Ops/s	121.6582 Ops/s	$\color{#35bf28}+2.17\%$
test_unbind_speed_stack1	15.3600μs	0.9689μs	1.0321 MOps/s	885.6163 KOps/s	$\textbf{\color{#35bf28}+16.53\%}$
test_creation[device0]	4.9015ms	0.3340ms	2.9944 KOps/s	3.0297 KOps/s	$\color{#d91a1a}-1.17\%$
test_creation_from_tensor	0.5122ms	0.3677ms	2.7193 KOps/s	2.6565 KOps/s	$\color{#35bf28}+2.37\%$
test_add_one[memmap_tensor0]	1.5868ms	30.7769μs	32.4919 KOps/s	31.8792 KOps/s	$\color{#35bf28}+1.92\%$
test_contiguous[memmap_tensor0]	37.7000μs	8.2932μs	120.5807 KOps/s	111.2167 KOps/s	$\textbf{\color{#35bf28}+8.42\%}$
test_stack[memmap_tensor0]	82.4000μs	25.5511μs	39.1373 KOps/s	38.8655 KOps/s	$\color{#35bf28}+0.70\%$
test_memmaptd_index	0.3310ms	0.2936ms	3.4062 KOps/s	3.3205 KOps/s	$\color{#35bf28}+2.58\%$
test_memmaptd_index_astensor	1.2753ms	1.0864ms	920.4370 Ops/s	821.9821 Ops/s	$\textbf{\color{#35bf28}+11.98\%}$
test_memmaptd_index_op	2.4138ms	2.3578ms	424.1268 Ops/s	414.8448 Ops/s	$\color{#35bf28}+2.24\%$
test_reshape_pytree	91.3000μs	31.7804μs	31.4660 KOps/s	31.1976 KOps/s	$\color{#35bf28}+0.86\%$
test_reshape_td	62.1000μs	39.2508μs	25.4772 KOps/s	25.1460 KOps/s	$\color{#35bf28}+1.32\%$
test_view_pytree	0.1121ms	30.9828μs	32.2760 KOps/s	31.4027 KOps/s	$\color{#35bf28}+2.78\%$
test_view_td	32.8000μs	8.8720μs	112.7141 KOps/s	116.3612 KOps/s	$\color{#d91a1a}-3.13\%$
test_unbind_pytree	70.4000μs	37.3618μs	26.7653 KOps/s	26.6408 KOps/s	$\color{#35bf28}+0.47\%$
test_unbind_td	1.0213ms	92.0393μs	10.8649 KOps/s	10.7145 KOps/s	$\color{#35bf28}+1.40\%$
test_split_pytree	0.4485ms	36.4782μs	27.4136 KOps/s	27.0955 KOps/s	$\color{#35bf28}+1.17\%$
test_split_td	0.7934ms	0.1038ms	9.6337 KOps/s	9.5967 KOps/s	$\color{#35bf28}+0.39\%$
test_add_pytree	5.6608ms	46.6852μs	21.4201 KOps/s	19.6244 KOps/s	$\textbf{\color{#35bf28}+9.15\%}$
test_add_td	0.2376ms	72.4988μs	13.7933 KOps/s	13.5387 KOps/s	$\color{#35bf28}+1.88\%$
test_distributed	22.4000μs	8.1261μs	123.0610 KOps/s	120.7648 KOps/s	$\color{#35bf28}+1.90\%$
test_tdmodule	0.2245ms	25.5753μs	39.1002 KOps/s	38.1865 KOps/s	$\color{#35bf28}+2.39\%$
test_tdmodule_dispatch	0.3007ms	48.7413μs	20.5165 KOps/s	19.9570 KOps/s	$\color{#35bf28}+2.80\%$
test_tdseq	0.4393ms	27.5876μs	36.2482 KOps/s	36.3664 KOps/s	$\color{#d91a1a}-0.33\%$
test_tdseq_dispatch	0.4724ms	53.7443μs	18.6066 KOps/s	18.2213 KOps/s	$\color{#35bf28}+2.11\%$
test_instantiation_functorch	1.7259ms	1.5391ms	649.7093 Ops/s	645.7889 Ops/s	$\color{#35bf28}+0.61\%$
test_instantiation_td	1.8468ms	1.2625ms	792.0568 Ops/s	785.8843 Ops/s	$\color{#35bf28}+0.79\%$
test_exec_functorch	0.2279ms	0.1868ms	5.3537 KOps/s	5.4413 KOps/s	$\color{#d91a1a}-1.61\%$
test_exec_td	0.2655ms	0.1781ms	5.6148 KOps/s	5.6898 KOps/s	$\color{#d91a1a}-1.32\%$
test_vmap_mlp_speed[True-True]	47.5839ms	1.2724ms	785.8887 Ops/s	930.8915 Ops/s	$\textbf{\color{#d91a1a}-15.58\%}$
test_vmap_mlp_speed[True-False]	5.9452ms	0.5471ms	1.8278 KOps/s	1.5329 KOps/s	$\textbf{\color{#35bf28}+19.24\%}$
test_vmap_mlp_speed[False-True]	6.0389ms	0.9178ms	1.0895 KOps/s	900.4048 Ops/s	$\textbf{\color{#35bf28}+21.00\%}$
test_vmap_mlp_speed[False-False]	6.1524ms	0.4381ms	2.2827 KOps/s	2.3341 KOps/s	$\color{#d91a1a}-2.20\%$