[Performance] Make copy_ a no-op if tensors are identical

[vmoens]

Updated version of #510

[github-actions]

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

Total Benchmarks: 113. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.3240μs	15.5137μs	64.4592 KOps/s	63.5857 KOps/s	$\color{#35bf28}+1.37\%$
test_plain_set_stack_nested	0.2026ms	0.1433ms	6.9806 KOps/s	7.0415 KOps/s	$\color{#d91a1a}-0.86\%$
test_plain_set_nested_inplace	57.7370μs	18.1546μs	55.0825 KOps/s	52.2228 KOps/s	$\textbf{\color{#35bf28}+5.48\%}$
test_plain_set_stack_nested_inplace	0.2440ms	0.1784ms	5.6064 KOps/s	5.7409 KOps/s	$\color{#d91a1a}-2.34\%$
test_items	19.2260μs	2.5591μs	390.7686 KOps/s	401.0244 KOps/s	$\color{#d91a1a}-2.56\%$
test_items_nested	0.4745ms	0.2686ms	3.7234 KOps/s	3.6970 KOps/s	$\color{#35bf28}+0.71\%$
test_items_nested_locked	1.0656ms	0.2713ms	3.6854 KOps/s	3.6823 KOps/s	$\color{#35bf28}+0.09\%$
test_items_nested_leaf	0.5145ms	0.1667ms	5.9994 KOps/s	6.0642 KOps/s	$\color{#d91a1a}-1.07\%$
test_items_stack_nested	2.5592ms	1.4885ms	671.8376 Ops/s	667.6541 Ops/s	$\color{#35bf28}+0.63\%$
test_items_stack_nested_leaf	1.8129ms	1.3581ms	736.3088 Ops/s	733.9149 Ops/s	$\color{#35bf28}+0.33\%$
test_items_stack_nested_locked	1.9579ms	0.7751ms	1.2901 KOps/s	1.2752 KOps/s	$\color{#35bf28}+1.17\%$
test_keys	18.1040μs	3.8704μs	258.3680 KOps/s	257.4328 KOps/s	$\color{#35bf28}+0.36\%$
test_keys_nested	0.5422ms	0.1425ms	7.0185 KOps/s	6.6830 KOps/s	$\textbf{\color{#35bf28}+5.02\%}$
test_keys_nested_locked	0.2480ms	0.1407ms	7.1094 KOps/s	7.0322 KOps/s	$\color{#35bf28}+1.10\%$
test_keys_nested_leaf	0.3780ms	0.1404ms	7.1223 KOps/s	6.9889 KOps/s	$\color{#35bf28}+1.91\%$
test_keys_stack_nested	2.0937ms	1.4088ms	709.8155 Ops/s	698.5194 Ops/s	$\color{#35bf28}+1.62\%$
test_keys_stack_nested_leaf	1.7722ms	1.4154ms	706.5152 Ops/s	705.2572 Ops/s	$\color{#35bf28}+0.18\%$
test_keys_stack_nested_locked	1.1328ms	0.6918ms	1.4456 KOps/s	1.4269 KOps/s	$\color{#35bf28}+1.31\%$
test_values	6.6272μs	1.1789μs	848.2218 KOps/s	863.7460 KOps/s	$\color{#d91a1a}-1.80\%$
test_values_nested	96.3800μs	49.7084μs	20.1173 KOps/s	20.4129 KOps/s	$\color{#d91a1a}-1.45\%$
test_values_nested_locked	95.1530μs	50.3636μs	19.8556 KOps/s	20.0471 KOps/s	$\color{#d91a1a}-0.96\%$
test_values_nested_leaf	72.8160μs	44.3006μs	22.5730 KOps/s	22.7943 KOps/s	$\color{#d91a1a}-0.97\%$
test_values_stack_nested	1.5174ms	1.2014ms	832.3292 Ops/s	822.6289 Ops/s	$\color{#35bf28}+1.18\%$
test_values_stack_nested_leaf	1.3292ms	1.1976ms	835.0236 Ops/s	826.9352 Ops/s	$\color{#35bf28}+0.98\%$
test_values_stack_nested_locked	0.7989ms	0.5235ms	1.9104 KOps/s	1.8809 KOps/s	$\color{#35bf28}+1.57\%$
test_membership	15.1280μs	1.3785μs	725.4074 KOps/s	749.2656 KOps/s	$\color{#d91a1a}-3.18\%$
test_membership_nested	21.1790μs	2.8088μs	356.0206 KOps/s	359.2406 KOps/s	$\color{#d91a1a}-0.90\%$
test_membership_nested_leaf	26.1180μs	2.8173μs	354.9481 KOps/s	358.1263 KOps/s	$\color{#d91a1a}-0.89\%$
test_membership_stacked_nested	31.6590μs	11.9764μs	83.4975 KOps/s	84.9651 KOps/s	$\color{#d91a1a}-1.73\%$
test_membership_stacked_nested_leaf	30.7970μs	12.0269μs	83.1471 KOps/s	84.0226 KOps/s	$\color{#d91a1a}-1.04\%$
test_membership_nested_last	33.1720μs	5.9636μs	167.6843 KOps/s	168.8428 KOps/s	$\color{#d91a1a}-0.69\%$
test_membership_nested_leaf_last	26.5800μs	5.9849μs	167.0860 KOps/s	161.9192 KOps/s	$\color{#35bf28}+3.19\%$
test_membership_stacked_nested_last	0.2534ms	0.1699ms	5.8848 KOps/s	5.9290 KOps/s	$\color{#d91a1a}-0.74\%$
test_membership_stacked_nested_leaf_last	53.8910μs	13.8193μs	72.3626 KOps/s	72.8154 KOps/s	$\color{#d91a1a}-0.62\%$
test_nested_getleaf	54.1200μs	10.5773μs	94.5418 KOps/s	92.2632 KOps/s	$\color{#35bf28}+2.47\%$
test_nested_get	52.6180μs	10.1162μs	98.8509 KOps/s	98.5666 KOps/s	$\color{#35bf28}+0.29\%$
test_stacked_getleaf	0.7195ms	0.6362ms	1.5719 KOps/s	1.5519 KOps/s	$\color{#35bf28}+1.29\%$
test_stacked_get	0.6781ms	0.6066ms	1.6485 KOps/s	1.6517 KOps/s	$\color{#d91a1a}-0.20\%$
test_nested_getitemleaf	48.1390μs	10.7243μs	93.2466 KOps/s	92.1082 KOps/s	$\color{#35bf28}+1.24\%$
test_nested_getitem	60.2030μs	10.2084μs	97.9585 KOps/s	97.5673 KOps/s	$\color{#35bf28}+0.40\%$
test_stacked_getitemleaf	0.9300ms	0.6353ms	1.5740 KOps/s	1.5514 KOps/s	$\color{#35bf28}+1.46\%$
test_stacked_getitem	0.8889ms	0.6080ms	1.6447 KOps/s	1.6405 KOps/s	$\color{#35bf28}+0.25\%$
test_lock_nested	59.4649ms	0.6113ms	1.6360 KOps/s	1.8052 KOps/s	$\textbf{\color{#d91a1a}-9.37\%}$
test_lock_stack_nested	7.7154ms	5.0260ms	198.9673 Ops/s	199.6216 Ops/s	$\color{#d91a1a}-0.33\%$
test_unlock_nested	0.8615ms	0.4372ms	2.2871 KOps/s	2.2740 KOps/s	$\color{#35bf28}+0.58\%$
test_unlock_stack_nested	72.9064ms	6.9381ms	144.1312 Ops/s	143.8644 Ops/s	$\color{#35bf28}+0.19\%$
test_flatten_speed	0.3284ms	0.2676ms	3.7370 KOps/s	3.7325 KOps/s	$\color{#35bf28}+0.12\%$
test_unflatten_speed	0.5485ms	0.4621ms	2.1641 KOps/s	2.1900 KOps/s	$\color{#d91a1a}-1.18\%$
test_common_ops	5.0402ms	0.6618ms	1.5111 KOps/s	1.4568 KOps/s	$\color{#35bf28}+3.73\%$
test_creation	19.3960μs	2.6128μs	382.7299 KOps/s	409.7604 KOps/s	$\textbf{\color{#d91a1a}-6.60\%}$
test_creation_empty	30.1660μs	7.9780μs	125.3449 KOps/s	119.0596 KOps/s	$\textbf{\color{#35bf28}+5.28\%}$
test_creation_nested_1	88.3640μs	11.5635μs	86.4790 KOps/s	85.7299 KOps/s	$\color{#35bf28}+0.87\%$
test_creation_nested_2	56.8060μs	15.0170μs	66.5911 KOps/s	66.3560 KOps/s	$\color{#35bf28}+0.35\%$
test_clone	79.7080μs	13.6276μs	73.3803 KOps/s	74.7041 KOps/s	$\color{#d91a1a}-1.77\%$
test_getitem[int]	39.9550μs	13.1453μs	76.0730 KOps/s	77.5432 KOps/s	$\color{#d91a1a}-1.90\%$
test_getitem[slice_int]	55.7630μs	24.4740μs	40.8597 KOps/s	40.8222 KOps/s	$\color{#35bf28}+0.09\%$
test_getitem[range]	87.0720μs	43.4578μs	23.0108 KOps/s	22.3807 KOps/s	$\color{#35bf28}+2.82\%$
test_getitem[tuple]	54.7020μs	20.3588μs	49.1188 KOps/s	50.0770 KOps/s	$\color{#d91a1a}-1.91\%$
test_getitem[list]	0.2000ms	38.9722μs	25.6593 KOps/s	25.2817 KOps/s	$\color{#35bf28}+1.49\%$
test_setitem_dim[int]	49.6130μs	27.0287μs	36.9977 KOps/s	35.9833 KOps/s	$\color{#35bf28}+2.82\%$
test_setitem_dim[slice_int]	0.1069ms	51.3309μs	19.4814 KOps/s	19.4232 KOps/s	$\color{#35bf28}+0.30\%$
test_setitem_dim[range]	0.1593ms	69.6675μs	14.3539 KOps/s	13.8871 KOps/s	$\color{#35bf28}+3.36\%$
test_setitem_dim[tuple]	94.9970μs	40.6165μs	24.6206 KOps/s	24.8547 KOps/s	$\color{#d91a1a}-0.94\%$
test_setitem	80.5700μs	18.2625μs	54.7571 KOps/s	52.9372 KOps/s	$\color{#35bf28}+3.44\%$
test_set	81.9930μs	17.7308μs	56.3992 KOps/s	54.3842 KOps/s	$\color{#35bf28}+3.71\%$
test_set_shared	3.0258ms	0.1423ms	7.0287 KOps/s	6.9274 KOps/s	$\color{#35bf28}+1.46\%$
test_update	90.4380μs	18.4985μs	54.0584 KOps/s	49.1942 KOps/s	$\textbf{\color{#35bf28}+9.89\%}$
test_update_nested	0.1086ms	25.5289μs	39.1712 KOps/s	35.8460 KOps/s	$\textbf{\color{#35bf28}+9.28\%}$
test_set_nested	70.6110μs	19.1250μs	52.2875 KOps/s	49.4471 KOps/s	$\textbf{\color{#35bf28}+5.74\%}$
test_set_nested_new	84.7880μs	24.2503μs	41.2367 KOps/s	39.0173 KOps/s	$\textbf{\color{#35bf28}+5.69\%}$
test_select	0.1115ms	49.3472μs	20.2646 KOps/s	19.6802 KOps/s	$\color{#35bf28}+2.97\%$
test_unbind_speed	0.6768ms	0.3736ms	2.6768 KOps/s	2.7039 KOps/s	$\color{#d91a1a}-1.00\%$
test_unbind_speed_stack0	69.5982ms	4.8639ms	205.5959 Ops/s	212.6370 Ops/s	$\color{#d91a1a}-3.31\%$
test_unbind_speed_stack1	2.6489μs	0.6606μs	1.5137 MOps/s	1.5262 MOps/s	$\color{#d91a1a}-0.81\%$
test_split	58.5186ms	1.7578ms	568.8790 Ops/s	559.7347 Ops/s	$\color{#35bf28}+1.63\%$
test_chunk	59.8944ms	1.7252ms	579.6269 Ops/s	571.2625 Ops/s	$\color{#35bf28}+1.46\%$
test_creation[device0]	4.7992ms	0.2946ms	3.3943 KOps/s	3.4630 KOps/s	$\color{#d91a1a}-1.98\%$
test_creation_from_tensor	0.8214ms	0.3235ms	3.0914 KOps/s	3.0566 KOps/s	$\color{#35bf28}+1.14\%$
test_add_one[memmap_tensor0]	82.1630μs	25.2613μs	39.5862 KOps/s	38.4226 KOps/s	$\color{#35bf28}+3.03\%$
test_contiguous[memmap_tensor0]	44.3330μs	5.9114μs	169.1646 KOps/s	172.8253 KOps/s	$\color{#d91a1a}-2.12\%$
test_stack[memmap_tensor0]	77.3540μs	19.4255μs	51.4786 KOps/s	51.1712 KOps/s	$\color{#35bf28}+0.60\%$
test_memmaptd_index	0.3624ms	0.1982ms	5.0445 KOps/s	5.0749 KOps/s	$\color{#d91a1a}-0.60\%$
test_memmaptd_index_astensor	0.3379ms	0.2568ms	3.8946 KOps/s	3.9201 KOps/s	$\color{#d91a1a}-0.65\%$
test_memmaptd_index_op	0.5845ms	0.4893ms	2.0439 KOps/s	1.9961 KOps/s	$\color{#35bf28}+2.39\%$
test_reshape_pytree	55.5940μs	23.1095μs	43.2723 KOps/s	42.8726 KOps/s	$\color{#35bf28}+0.93\%$
test_reshape_td	87.2220μs	32.5483μs	30.7236 KOps/s	31.5252 KOps/s	$\color{#d91a1a}-2.54\%$
test_view_pytree	66.5740μs	23.1569μs	43.1837 KOps/s	42.2972 KOps/s	$\color{#35bf28}+2.10\%$
test_view_td	21.6510μs	4.9570μs	201.7352 KOps/s	210.0338 KOps/s	$\color{#d91a1a}-3.95\%$
test_unbind_pytree	58.8690μs	26.6528μs	37.5195 KOps/s	37.8758 KOps/s	$\color{#d91a1a}-0.94\%$
test_unbind_td	0.1195ms	59.3196μs	16.8578 KOps/s	16.9087 KOps/s	$\color{#d91a1a}-0.30\%$
test_split_pytree	0.5197ms	26.2803μs	38.0513 KOps/s	37.5366 KOps/s	$\color{#35bf28}+1.37\%$
test_split_td	97.8620μs	45.9944μs	21.7418 KOps/s	21.5416 KOps/s	$\color{#35bf28}+0.93\%$
test_add_pytree	64.4600μs	31.9839μs	31.2657 KOps/s	28.9720 KOps/s	$\textbf{\color{#35bf28}+7.92\%}$
test_add_td	0.1014ms	44.2918μs	22.5776 KOps/s	21.3024 KOps/s	$\textbf{\color{#35bf28}+5.99\%}$
test_distributed	19.5360μs	6.0735μs	164.6496 KOps/s	168.9517 KOps/s	$\color{#d91a1a}-2.55\%$
test_tdmodule	0.7940ms	20.8883μs	47.8736 KOps/s	43.9300 KOps/s	$\textbf{\color{#35bf28}+8.98\%}$
test_tdmodule_dispatch	0.2019ms	37.9662μs	26.3392 KOps/s	24.3469 KOps/s	$\textbf{\color{#35bf28}+8.18\%}$
test_tdseq	49.7330μs	22.8677μs	43.7298 KOps/s	40.1651 KOps/s	$\textbf{\color{#35bf28}+8.88\%}$
test_tdseq_dispatch	0.1305ms	41.4886μs	24.1030 KOps/s	22.8316 KOps/s	$\textbf{\color{#35bf28}+5.57\%}$
test_instantiation_functorch	1.6540ms	1.2925ms	773.7077 Ops/s	755.1587 Ops/s	$\color{#35bf28}+2.46\%$
test_instantiation_td	1.5557ms	1.0296ms	971.2156 Ops/s	911.5993 Ops/s	$\textbf{\color{#35bf28}+6.54\%}$
test_exec_functorch	0.2291ms	0.1616ms	6.1878 KOps/s	6.2471 KOps/s	$\color{#d91a1a}-0.95\%$
test_exec_functional_call	0.2486ms	0.1477ms	6.7709 KOps/s	6.5906 KOps/s	$\color{#35bf28}+2.74\%$
test_exec_td	0.2870ms	0.1452ms	6.8876 KOps/s	6.8940 KOps/s	$\color{#d91a1a}-0.09\%$
test_exec_td_decorator	0.8330ms	0.1777ms	5.6270 KOps/s	5.6048 KOps/s	$\color{#35bf28}+0.40\%$
test_vmap_mlp_speed[True-True]	1.2983ms	0.8773ms	1.1399 KOps/s	1.0741 KOps/s	$\textbf{\color{#35bf28}+6.12\%}$
test_vmap_mlp_speed[True-False]	0.7235ms	0.4719ms	2.1193 KOps/s	2.0876 KOps/s	$\color{#35bf28}+1.52\%$
test_vmap_mlp_speed[False-True]	1.2206ms	0.7749ms	1.2904 KOps/s	1.2358 KOps/s	$\color{#35bf28}+4.42\%$
test_vmap_mlp_speed[False-False]	0.5036ms	0.3871ms	2.5835 KOps/s	2.5322 KOps/s	$\color{#35bf28}+2.03\%$
test_vmap_mlp_speed_decorator[True-True]	2.3704ms	1.7310ms	577.6935 Ops/s	552.3910 Ops/s	$\color{#35bf28}+4.58\%$
test_vmap_mlp_speed_decorator[True-False]	0.9645ms	0.5130ms	1.9491 KOps/s	1.8999 KOps/s	$\color{#35bf28}+2.59\%$
test_vmap_mlp_speed_decorator[False-True]	1.9684ms	1.4463ms	691.4158 Ops/s	660.7043 Ops/s	$\color{#35bf28}+4.65\%$
test_vmap_mlp_speed_decorator[False-False]	0.9798ms	0.3976ms	2.5151 KOps/s	2.4738 KOps/s	$\color{#35bf28}+1.67\%$

[github-actions]

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

Total Benchmarks: 127. Improved: $\large\color{#35bf28}29$. Worsened: $\large\color{#d91a1a}1$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.5487ms	12.8039μs	78.1014 KOps/s	78.4907 KOps/s	$\color{#d91a1a}-0.50\%$
test_plain_set_stack_nested	0.1362ms	0.1153ms	8.6736 KOps/s	8.2624 KOps/s	$\color{#35bf28}+4.98\%$
test_plain_set_nested_inplace	38.2610μs	14.1859μs	70.4927 KOps/s	66.2438 KOps/s	$\textbf{\color{#35bf28}+6.41\%}$
test_plain_set_stack_nested_inplace	0.1703ms	0.1433ms	6.9800 KOps/s	7.0190 KOps/s	$\color{#d91a1a}-0.55\%$
test_items	18.8000μs	4.6349μs	215.7559 KOps/s	211.9976 KOps/s	$\color{#35bf28}+1.77\%$
test_items_nested	0.3910ms	0.3361ms	2.9754 KOps/s	2.9626 KOps/s	$\color{#35bf28}+0.43\%$
test_items_nested_locked	0.3932ms	0.3377ms	2.9616 KOps/s	2.9304 KOps/s	$\color{#35bf28}+1.07\%$
test_items_nested_leaf	0.2326ms	0.1975ms	5.0631 KOps/s	5.0263 KOps/s	$\color{#35bf28}+0.73\%$
test_items_stack_nested	1.5613ms	1.4754ms	677.7858 Ops/s	663.8340 Ops/s	$\color{#35bf28}+2.10\%$
test_items_stack_nested_leaf	1.3634ms	1.3023ms	767.8583 Ops/s	750.1647 Ops/s	$\color{#35bf28}+2.36\%$
test_items_stack_nested_locked	0.8778ms	0.8236ms	1.2142 KOps/s	1.1748 KOps/s	$\color{#35bf28}+3.35\%$
test_keys	20.4400μs	4.5679μs	218.9206 KOps/s	218.8186 KOps/s	$\color{#35bf28}+0.05\%$
test_keys_nested	3.4048ms	90.8237μs	11.0103 KOps/s	11.0846 KOps/s	$\color{#d91a1a}-0.67\%$
test_keys_nested_locked	0.1146ms	90.6584μs	11.0304 KOps/s	11.1620 KOps/s	$\color{#d91a1a}-1.18\%$
test_keys_nested_leaf	42.8885ms	86.8877μs	11.5091 KOps/s	12.1897 KOps/s	$\textbf{\color{#d91a1a}-5.58\%}$
test_keys_stack_nested	1.3792ms	1.2853ms	778.0457 Ops/s	757.7148 Ops/s	$\color{#35bf28}+2.68\%$
test_keys_stack_nested_leaf	1.3551ms	1.2823ms	779.8545 Ops/s	761.8074 Ops/s	$\color{#35bf28}+2.37\%$
test_keys_stack_nested_locked	0.6964ms	0.6334ms	1.5789 KOps/s	1.5455 KOps/s	$\color{#35bf28}+2.16\%$
test_values	6.7037μs	1.8960μs	527.4275 KOps/s	521.5566 KOps/s	$\color{#35bf28}+1.13\%$
test_values_nested	69.5010μs	42.7003μs	23.4190 KOps/s	23.1621 KOps/s	$\color{#35bf28}+1.11\%$
test_values_nested_locked	65.0210μs	44.9033μs	22.2701 KOps/s	22.0585 KOps/s	$\color{#35bf28}+0.96\%$
test_values_nested_leaf	57.2110μs	37.1368μs	26.9274 KOps/s	26.6648 KOps/s	$\color{#35bf28}+0.99\%$
test_values_stack_nested	1.2320ms	1.1274ms	887.0293 Ops/s	868.2667 Ops/s	$\color{#35bf28}+2.16\%$
test_values_stack_nested_leaf	1.1763ms	1.1100ms	900.9005 Ops/s	884.4522 Ops/s	$\color{#35bf28}+1.86\%$
test_values_stack_nested_locked	0.5598ms	0.5052ms	1.9796 KOps/s	1.9399 KOps/s	$\color{#35bf28}+2.04\%$
test_membership	4.0062μs	0.9318μs	1.0732 MOps/s	1.0569 MOps/s	$\color{#35bf28}+1.54\%$
test_membership_nested	21.2410μs	2.1860μs	457.4467 KOps/s	447.5371 KOps/s	$\color{#35bf28}+2.21\%$
test_membership_nested_leaf	10.4200μs	2.0835μs	479.9538 KOps/s	470.6439 KOps/s	$\color{#35bf28}+1.98\%$
test_membership_stacked_nested	39.5010μs	10.7390μs	93.1186 KOps/s	90.7875 KOps/s	$\color{#35bf28}+2.57\%$
test_membership_stacked_nested_leaf	34.7820μs	10.7329μs	93.1713 KOps/s	91.5096 KOps/s	$\color{#35bf28}+1.82\%$
test_membership_nested_last	33.1310μs	4.5268μs	220.9073 KOps/s	218.0709 KOps/s	$\color{#35bf28}+1.30\%$
test_membership_nested_leaf_last	22.7900μs	4.5028μs	222.0825 KOps/s	217.5531 KOps/s	$\color{#35bf28}+2.08\%$
test_membership_stacked_nested_last	0.1605ms	0.1330ms	7.5199 KOps/s	7.4277 KOps/s	$\color{#35bf28}+1.24\%$
test_membership_stacked_nested_leaf_last	29.3910μs	12.5498μs	79.6823 KOps/s	79.2798 KOps/s	$\color{#35bf28}+0.51\%$
test_nested_getleaf	31.9610μs	8.3613μs	119.5987 KOps/s	118.5932 KOps/s	$\color{#35bf28}+0.85\%$
test_nested_get	23.0800μs	7.8725μs	127.0241 KOps/s	125.3909 KOps/s	$\color{#35bf28}+1.30\%$
test_stacked_getleaf	0.6136ms	0.5612ms	1.7818 KOps/s	1.7635 KOps/s	$\color{#35bf28}+1.04\%$
test_stacked_get	0.6167ms	0.5342ms	1.8720 KOps/s	1.8727 KOps/s	$\color{#d91a1a}-0.04\%$
test_nested_getitemleaf	23.3700μs	8.4071μs	118.9470 KOps/s	117.6476 KOps/s	$\color{#35bf28}+1.10\%$
test_nested_getitem	29.2500μs	7.9108μs	126.4092 KOps/s	123.6611 KOps/s	$\color{#35bf28}+2.22\%$
test_stacked_getitemleaf	0.8524ms	0.5657ms	1.7678 KOps/s	1.7602 KOps/s	$\color{#35bf28}+0.43\%$
test_stacked_getitem	0.6204ms	0.5301ms	1.8865 KOps/s	1.8821 KOps/s	$\color{#35bf28}+0.23\%$
test_lock_nested	3.2228ms	0.5505ms	1.8165 KOps/s	1.7662 KOps/s	$\color{#35bf28}+2.84\%$
test_lock_stack_nested	82.3490ms	7.2251ms	138.4070 Ops/s	133.6922 Ops/s	$\color{#35bf28}+3.53\%$
test_unlock_nested	2.3443ms	0.4278ms	2.3378 KOps/s	2.2603 KOps/s	$\color{#35bf28}+3.43\%$
test_unlock_stack_nested	69.0773ms	6.2740ms	159.3887 Ops/s	157.8591 Ops/s	$\color{#35bf28}+0.97\%$
test_flatten_speed	0.2246ms	0.1860ms	5.3759 KOps/s	5.3303 KOps/s	$\color{#35bf28}+0.85\%$
test_unflatten_speed	0.3971ms	0.3639ms	2.7480 KOps/s	2.7303 KOps/s	$\color{#35bf28}+0.64\%$
test_common_ops	1.1183ms	0.5919ms	1.6895 KOps/s	1.5927 KOps/s	$\textbf{\color{#35bf28}+6.07\%}$
test_creation	30.9200μs	2.0432μs	489.4399 KOps/s	465.0022 KOps/s	$\textbf{\color{#35bf28}+5.26\%}$
test_creation_empty	18.6600μs	7.0231μs	142.3875 KOps/s	138.2920 KOps/s	$\color{#35bf28}+2.96\%$
test_creation_nested_1	31.5910μs	9.3284μs	107.1998 KOps/s	105.3544 KOps/s	$\color{#35bf28}+1.75\%$
test_creation_nested_2	29.3100μs	11.9502μs	83.6805 KOps/s	81.4590 KOps/s	$\color{#35bf28}+2.73\%$
test_clone	79.2410μs	13.7816μs	72.5604 KOps/s	64.7868 KOps/s	$\textbf{\color{#35bf28}+12.00\%}$
test_getitem[int]	26.6210μs	12.0851μs	82.7466 KOps/s	77.7683 KOps/s	$\textbf{\color{#35bf28}+6.40\%}$
test_getitem[slice_int]	47.0300μs	22.8566μs	43.7511 KOps/s	40.2683 KOps/s	$\textbf{\color{#35bf28}+8.65\%}$
test_getitem[range]	63.2610μs	40.2241μs	24.8607 KOps/s	22.3154 KOps/s	$\textbf{\color{#35bf28}+11.41\%}$
test_getitem[tuple]	41.6120μs	19.4752μs	51.3475 KOps/s	46.2564 KOps/s	$\textbf{\color{#35bf28}+11.01\%}$
test_getitem[list]	0.2767ms	36.6105μs	27.3146 KOps/s	24.6156 KOps/s	$\textbf{\color{#35bf28}+10.96\%}$
test_setitem_dim[int]	44.1410μs	26.5411μs	37.6775 KOps/s	35.5083 KOps/s	$\textbf{\color{#35bf28}+6.11\%}$
test_setitem_dim[slice_int]	64.3410μs	46.7091μs	21.4091 KOps/s	20.3892 KOps/s	$\textbf{\color{#35bf28}+5.00\%}$
test_setitem_dim[range]	83.2220μs	64.5080μs	15.5019 KOps/s	15.0643 KOps/s	$\color{#35bf28}+2.90\%$
test_setitem_dim[tuple]	68.5710μs	39.4679μs	25.3371 KOps/s	24.1922 KOps/s	$\color{#35bf28}+4.73\%$
test_setitem	70.6710μs	17.7113μs	56.4610 KOps/s	51.5546 KOps/s	$\textbf{\color{#35bf28}+9.52\%}$
test_set	70.0310μs	17.2349μs	58.0217 KOps/s	52.5466 KOps/s	$\textbf{\color{#35bf28}+10.42\%}$
test_set_shared	2.7865ms	0.1037ms	9.6386 KOps/s	8.1589 KOps/s	$\textbf{\color{#35bf28}+18.14\%}$
test_update	95.4920μs	18.6072μs	53.7425 KOps/s	48.6966 KOps/s	$\textbf{\color{#35bf28}+10.36\%}$
test_update_nested	89.7120μs	25.2409μs	39.6182 KOps/s	37.1785 KOps/s	$\textbf{\color{#35bf28}+6.56\%}$
test_set_nested	81.5910μs	18.5839μs	53.8101 KOps/s	50.3833 KOps/s	$\textbf{\color{#35bf28}+6.80\%}$
test_set_nested_new	75.2210μs	22.8331μs	43.7960 KOps/s	40.7562 KOps/s	$\textbf{\color{#35bf28}+7.46\%}$
test_select	92.0010μs	44.7440μs	22.3494 KOps/s	20.9956 KOps/s	$\textbf{\color{#35bf28}+6.45\%}$
test_to	74.5520μs	52.3221μs	19.1124 KOps/s	18.6552 KOps/s	$\color{#35bf28}+2.45\%$
test_to_nonblocking	64.5910μs	34.6905μs	28.8264 KOps/s	27.9686 KOps/s	$\color{#35bf28}+3.07\%$
test_unbind_speed	0.4061ms	0.3556ms	2.8124 KOps/s	2.7079 KOps/s	$\color{#35bf28}+3.86\%$
test_unbind_speed_stack0	62.8848ms	4.2907ms	233.0621 Ops/s	239.4317 Ops/s	$\color{#d91a1a}-2.66\%$
test_unbind_speed_stack1	1.3995μs	0.5329μs	1.8766 MOps/s	1.9019 MOps/s	$\color{#d91a1a}-1.33\%$
test_split	56.7696ms	1.7481ms	572.0379 Ops/s	549.6593 Ops/s	$\color{#35bf28}+4.07\%$
test_chunk	53.1605ms	1.7247ms	579.8175 Ops/s	556.3689 Ops/s	$\color{#35bf28}+4.21\%$
test_creation[device0]	0.3802ms	0.3116ms	3.2091 KOps/s	3.2392 KOps/s	$\color{#d91a1a}-0.93\%$
test_creation[device1]	0.6818ms	0.3149ms	3.1756 KOps/s	3.2090 KOps/s	$\color{#d91a1a}-1.04\%$
test_creation_from_tensor	0.6600ms	0.3405ms	2.9372 KOps/s	2.9619 KOps/s	$\color{#d91a1a}-0.83\%$
test_add_one[memmap_tensor0]	71.9610μs	23.4717μs	42.6045 KOps/s	39.7465 KOps/s	$\textbf{\color{#35bf28}+7.19\%}$
test_add_one[memmap_tensor1]	0.2073ms	72.6632μs	13.7621 KOps/s	13.4872 KOps/s	$\color{#35bf28}+2.04\%$
test_contiguous[memmap_tensor0]	36.1710μs	5.8779μs	170.1278 KOps/s	168.4631 KOps/s	$\color{#35bf28}+0.99\%$
test_contiguous[memmap_tensor1]	49.7110μs	21.3424μs	46.8550 KOps/s	45.2468 KOps/s	$\color{#35bf28}+3.55\%$
test_stack[memmap_tensor0]	48.7810μs	19.8176μs	50.4602 KOps/s	48.2755 KOps/s	$\color{#35bf28}+4.53\%$
test_stack[memmap_tensor1]	0.1588ms	75.4282μs	13.2576 KOps/s	13.3119 KOps/s	$\color{#d91a1a}-0.41\%$
test_memmaptd_index	0.2787ms	0.2312ms	4.3253 KOps/s	4.0514 KOps/s	$\textbf{\color{#35bf28}+6.76\%}$
test_memmaptd_index_astensor	0.3179ms	0.2886ms	3.4656 KOps/s	3.2567 KOps/s	$\textbf{\color{#35bf28}+6.41\%}$
test_memmaptd_index_op	0.6270ms	0.5645ms	1.7715 KOps/s	1.6534 KOps/s	$\textbf{\color{#35bf28}+7.14\%}$
test_reshape_pytree	54.2610μs	20.5521μs	48.6569 KOps/s	46.5656 KOps/s	$\color{#35bf28}+4.49\%$
test_reshape_td	50.1910μs	30.1735μs	33.1417 KOps/s	31.6320 KOps/s	$\color{#35bf28}+4.77\%$
test_view_pytree	0.3601ms	20.5351μs	48.6972 KOps/s	46.9877 KOps/s	$\color{#35bf28}+3.64\%$
test_view_td	18.4400μs	4.0356μs	247.7927 KOps/s	248.7242 KOps/s	$\color{#d91a1a}-0.37\%$
test_unbind_pytree	45.0800μs	25.2305μs	39.6346 KOps/s	37.8337 KOps/s	$\color{#35bf28}+4.76\%$
test_unbind_td	84.2410μs	56.3395μs	17.7495 KOps/s	17.0004 KOps/s	$\color{#35bf28}+4.41\%$
test_split_pytree	40.2200μs	23.7962μs	42.0235 KOps/s	40.3359 KOps/s	$\color{#35bf28}+4.18\%$
test_split_td	69.1110μs	42.8427μs	23.3412 KOps/s	21.9260 KOps/s	$\textbf{\color{#35bf28}+6.45\%}$
test_add_pytree	51.6500μs	31.6844μs	31.5613 KOps/s	29.2840 KOps/s	$\textbf{\color{#35bf28}+7.78\%}$
test_add_td	75.5020μs	45.6111μs	21.9245 KOps/s	20.5375 KOps/s	$\textbf{\color{#35bf28}+6.75\%}$
test_distributed	20.4700μs	5.5633μs	179.7489 KOps/s	182.1728 KOps/s	$\color{#d91a1a}-1.33\%$
test_tdmodule	33.0200μs	16.6078μs	60.2126 KOps/s	58.3780 KOps/s	$\color{#35bf28}+3.14\%$
test_tdmodule_dispatch	0.1334ms	32.8319μs	30.4582 KOps/s	29.7790 KOps/s	$\color{#35bf28}+2.28\%$
test_tdseq	35.5600μs	19.8340μs	50.4184 KOps/s	49.7682 KOps/s	$\color{#35bf28}+1.31\%$
test_tdseq_dispatch	56.5610μs	36.2428μs	27.5917 KOps/s	27.1695 KOps/s	$\color{#35bf28}+1.55\%$
test_instantiation_functorch	1.9746ms	1.6563ms	603.7714 Ops/s	582.8394 Ops/s	$\color{#35bf28}+3.59\%$
test_instantiation_td	1.7000ms	1.1544ms	866.2190 Ops/s	844.6354 Ops/s	$\color{#35bf28}+2.56\%$
test_exec_functorch	0.2036ms	0.1551ms	6.4464 KOps/s	6.1126 KOps/s	$\textbf{\color{#35bf28}+5.46\%}$
test_exec_functional_call	0.2129ms	0.1568ms	6.3763 KOps/s	6.1643 KOps/s	$\color{#35bf28}+3.44\%$
test_exec_td	0.1793ms	0.1483ms	6.7432 KOps/s	6.5354 KOps/s	$\color{#35bf28}+3.18\%$
test_exec_td_decorator	0.8534ms	0.1844ms	5.4238 KOps/s	5.1998 KOps/s	$\color{#35bf28}+4.31\%$
test_vmap_mlp_speed[True-True]	1.2860ms	1.0891ms	918.1929 Ops/s	915.4228 Ops/s	$\color{#35bf28}+0.30\%$
test_vmap_mlp_speed[True-False]	0.6753ms	0.6234ms	1.6040 KOps/s	1.5898 KOps/s	$\color{#35bf28}+0.89\%$
test_vmap_mlp_speed[False-True]	1.1643ms	1.0006ms	999.4174 Ops/s	946.7073 Ops/s	$\textbf{\color{#35bf28}+5.57\%}$
test_vmap_mlp_speed[False-False]	0.6119ms	0.5535ms	1.8068 KOps/s	1.7157 KOps/s	$\textbf{\color{#35bf28}+5.31\%}$
test_vmap_mlp_speed_decorator[True-True]	3.0797ms	2.0732ms	482.3367 Ops/s	468.6838 Ops/s	$\color{#35bf28}+2.91\%$
test_vmap_mlp_speed_decorator[True-False]	1.2251ms	0.6684ms	1.4962 KOps/s	1.4974 KOps/s	$\color{#d91a1a}-0.08\%$
test_vmap_mlp_speed_decorator[False-True]	2.2328ms	1.8018ms	555.0051 Ops/s	546.1029 Ops/s	$\color{#35bf28}+1.63\%$
test_vmap_mlp_speed_decorator[False-False]	1.0516ms	0.5678ms	1.7613 KOps/s	1.7433 KOps/s	$\color{#35bf28}+1.03\%$
test_vmap_transformer_speed[True-True]	12.9594ms	12.8713ms	77.6919 Ops/s	77.4304 Ops/s	$\color{#35bf28}+0.34\%$
test_vmap_transformer_speed[True-False]	8.4914ms	8.3931ms	119.1451 Ops/s	119.0909 Ops/s	$\color{#35bf28}+0.05\%$
test_vmap_transformer_speed[False-True]	12.8107ms	12.7070ms	78.6971 Ops/s	78.5455 Ops/s	$\color{#35bf28}+0.19\%$
test_vmap_transformer_speed[False-False]	8.3901ms	8.3066ms	120.3868 Ops/s	118.9734 Ops/s	$\color{#35bf28}+1.19\%$
test_vmap_transformer_speed_decorator[True-True]	0.1441s	70.5959ms	14.1651 Ops/s	14.8834 Ops/s	$\color{#d91a1a}-4.83\%$
test_vmap_transformer_speed_decorator[True-False]	22.5718ms	20.3111ms	49.2342 Ops/s	49.5731 Ops/s	$\color{#d91a1a}-0.68\%$
test_vmap_transformer_speed_decorator[False-True]	60.6943ms	59.5541ms	16.7915 Ops/s	16.5465 Ops/s	$\color{#35bf28}+1.48\%$
test_vmap_transformer_speed_decorator[False-False]	22.2465ms	19.8524ms	50.3718 Ops/s	50.5151 Ops/s	$\color{#d91a1a}-0.28\%$