[Tests] Reorder and regroup tests

[vmoens]

This PR regroups and reorders tests for an easier sync with pytorch/pytorch#112441

[github-actions]

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

Total Benchmarks: 120. Improved: $\large\color{#35bf28}20$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	28.3030μs	16.1052μs	62.0919 KOps/s	57.8712 KOps/s	$\textbf{\color{#35bf28}+7.29\%}$
test_plain_set_stack_nested	0.2707ms	0.1451ms	6.8908 KOps/s	6.8627 KOps/s	$\color{#35bf28}+0.41\%$
test_plain_set_nested_inplace	54.7810μs	18.3790μs	54.4099 KOps/s	51.9690 KOps/s	$\color{#35bf28}+4.70\%$
test_plain_set_stack_nested_inplace	0.3199ms	0.1757ms	5.6901 KOps/s	5.6170 KOps/s	$\color{#35bf28}+1.30\%$
test_items	37.2290μs	2.6243μs	381.0485 KOps/s	416.3175 KOps/s	$\textbf{\color{#d91a1a}-8.47\%}$
test_items_nested	0.4019ms	0.2707ms	3.6940 KOps/s	3.7750 KOps/s	$\color{#d91a1a}-2.15\%$
test_items_nested_locked	0.4289ms	0.2708ms	3.6927 KOps/s	3.7092 KOps/s	$\color{#d91a1a}-0.45\%$
test_items_nested_leaf	0.6523ms	0.1672ms	5.9806 KOps/s	6.0647 KOps/s	$\color{#d91a1a}-1.39\%$
test_items_stack_nested	1.5689ms	1.3251ms	754.6548 Ops/s	755.0180 Ops/s	$\color{#d91a1a}-0.05\%$
test_items_stack_nested_leaf	2.1370ms	1.2093ms	826.9415 Ops/s	838.8365 Ops/s	$\color{#d91a1a}-1.42\%$
test_items_stack_nested_locked	1.1520ms	0.8879ms	1.1262 KOps/s	1.2756 KOps/s	$\textbf{\color{#d91a1a}-11.71\%}$
test_keys	20.5780μs	3.8167μs	262.0034 KOps/s	257.3378 KOps/s	$\color{#35bf28}+1.81\%$
test_keys_nested	58.5043ms	0.1577ms	6.3395 KOps/s	6.6873 KOps/s	$\textbf{\color{#d91a1a}-5.20\%}$
test_keys_nested_locked	0.3129ms	0.1457ms	6.8653 KOps/s	6.7771 KOps/s	$\color{#35bf28}+1.30\%$
test_keys_nested_leaf	0.2451ms	0.1301ms	7.6881 KOps/s	7.7152 KOps/s	$\color{#d91a1a}-0.35\%$
test_keys_stack_nested	1.6384ms	1.2914ms	774.3507 Ops/s	766.3654 Ops/s	$\color{#35bf28}+1.04\%$
test_keys_stack_nested_leaf	1.4532ms	1.2914ms	774.3714 Ops/s	777.6121 Ops/s	$\color{#d91a1a}-0.42\%$
test_keys_stack_nested_locked	1.0619ms	0.8269ms	1.2093 KOps/s	1.3982 KOps/s	$\textbf{\color{#d91a1a}-13.51\%}$
test_values	9.9960μs	1.1768μs	849.7787 KOps/s	852.4700 KOps/s	$\color{#d91a1a}-0.32\%$
test_values_nested	0.2792ms	53.5041μs	18.6901 KOps/s	19.0949 KOps/s	$\color{#d91a1a}-2.12\%$
test_values_nested_locked	95.7680μs	52.0357μs	19.2176 KOps/s	19.1725 KOps/s	$\color{#35bf28}+0.23\%$
test_values_nested_leaf	96.0080μs	46.1691μs	21.6595 KOps/s	21.7844 KOps/s	$\color{#d91a1a}-0.57\%$
test_values_stack_nested	1.2892ms	1.0424ms	959.3246 Ops/s	950.5216 Ops/s	$\color{#35bf28}+0.93\%$
test_values_stack_nested_leaf	1.2758ms	1.0374ms	963.9217 Ops/s	976.8290 Ops/s	$\color{#d91a1a}-1.32\%$
test_values_stack_nested_locked	0.8438ms	0.6129ms	1.6315 KOps/s	1.9218 KOps/s	$\textbf{\color{#d91a1a}-15.11\%}$
test_membership	41.8570μs	1.4492μs	690.0493 KOps/s	750.3323 KOps/s	$\textbf{\color{#d91a1a}-8.03\%}$
test_membership_nested	0.1575ms	2.9105μs	343.5784 KOps/s	348.9233 KOps/s	$\color{#d91a1a}-1.53\%$
test_membership_nested_leaf	38.9110μs	2.8909μs	345.9189 KOps/s	334.4699 KOps/s	$\color{#35bf28}+3.42\%$
test_membership_stacked_nested	37.7800μs	11.8806μs	84.1707 KOps/s	84.4095 KOps/s	$\color{#d91a1a}-0.28\%$
test_membership_stacked_nested_leaf	58.4990μs	11.7236μs	85.2983 KOps/s	83.3608 KOps/s	$\color{#35bf28}+2.32\%$
test_membership_nested_last	31.7090μs	6.0424μs	165.4970 KOps/s	164.0056 KOps/s	$\color{#35bf28}+0.91\%$
test_membership_nested_leaf_last	56.2950μs	5.9261μs	168.7448 KOps/s	163.0772 KOps/s	$\color{#35bf28}+3.48\%$
test_membership_stacked_nested_last	0.3236ms	0.1677ms	5.9638 KOps/s	5.7886 KOps/s	$\color{#35bf28}+3.03\%$
test_membership_stacked_nested_leaf_last	61.5740μs	14.1800μs	70.5219 KOps/s	70.8662 KOps/s	$\color{#d91a1a}-0.49\%$
test_nested_getleaf	71.2540μs	10.5317μs	94.9512 KOps/s	91.7168 KOps/s	$\color{#35bf28}+3.53\%$
test_nested_get	38.4300μs	9.9668μs	100.3330 KOps/s	96.9005 KOps/s	$\color{#35bf28}+3.54\%$
test_stacked_getleaf	0.6246ms	0.4066ms	2.4592 KOps/s	2.1057 KOps/s	$\textbf{\color{#35bf28}+16.79\%}$
test_stacked_get	0.6264ms	0.3731ms	2.6804 KOps/s	2.2794 KOps/s	$\textbf{\color{#35bf28}+17.59\%}$
test_nested_getitemleaf	48.8310μs	10.6788μs	93.6432 KOps/s	91.3170 KOps/s	$\color{#35bf28}+2.55\%$
test_nested_getitem	31.6080μs	10.0761μs	99.2449 KOps/s	96.2262 KOps/s	$\color{#35bf28}+3.14\%$
test_stacked_getitemleaf	0.6457ms	0.4070ms	2.4571 KOps/s	2.1216 KOps/s	$\textbf{\color{#35bf28}+15.82\%}$
test_stacked_getitem	0.5936ms	0.3721ms	2.6875 KOps/s	2.2597 KOps/s	$\textbf{\color{#35bf28}+18.93\%}$
test_lock_nested	1.3653ms	0.4199ms	2.3815 KOps/s	2.3848 KOps/s	$\color{#d91a1a}-0.14\%$
test_lock_stack_nested	81.9629ms	6.8408ms	146.1826 Ops/s	147.4776 Ops/s	$\color{#d91a1a}-0.88\%$
test_unlock_nested	68.2685ms	0.4949ms	2.0205 KOps/s	2.3354 KOps/s	$\textbf{\color{#d91a1a}-13.48\%}$
test_unlock_stack_nested	79.9009ms	6.4022ms	156.1952 Ops/s	155.0993 Ops/s	$\color{#35bf28}+0.71\%$
test_flatten_speed	0.6112ms	0.3665ms	2.7284 KOps/s	2.7012 KOps/s	$\color{#35bf28}+1.01\%$
test_unflatten_speed	0.5443ms	0.4608ms	2.1699 KOps/s	2.1570 KOps/s	$\color{#35bf28}+0.60\%$
test_common_ops	1.2262ms	0.6817ms	1.4669 KOps/s	1.4027 KOps/s	$\color{#35bf28}+4.58\%$
test_creation	22.8630μs	1.9692μs	507.8262 KOps/s	470.3225 KOps/s	$\textbf{\color{#35bf28}+7.97\%}$
test_creation_empty	61.4740μs	8.6843μs	115.1507 KOps/s	94.9602 KOps/s	$\textbf{\color{#35bf28}+21.26\%}$
test_creation_nested_1	40.8760μs	11.4976μs	86.9744 KOps/s	74.6253 KOps/s	$\textbf{\color{#35bf28}+16.55\%}$
test_creation_nested_2	54.7310μs	16.8479μs	59.3545 KOps/s	52.4660 KOps/s	$\textbf{\color{#35bf28}+13.13\%}$
test_clone	0.1673ms	12.6744μs	78.8993 KOps/s	79.8467 KOps/s	$\color{#d91a1a}-1.19\%$
test_getitem[int]	50.9650μs	11.9432μs	83.7300 KOps/s	82.9171 KOps/s	$\color{#35bf28}+0.98\%$
test_getitem[slice_int]	57.6870μs	23.4988μs	42.5554 KOps/s	40.9024 KOps/s	$\color{#35bf28}+4.04\%$
test_getitem[range]	91.5000μs	42.8484μs	23.3381 KOps/s	22.7992 KOps/s	$\color{#35bf28}+2.36\%$
test_getitem[tuple]	78.9170μs	19.3221μs	51.7543 KOps/s	51.2392 KOps/s	$\color{#35bf28}+1.01\%$
test_getitem[list]	0.2605ms	37.1257μs	26.9355 KOps/s	25.8310 KOps/s	$\color{#35bf28}+4.28\%$
test_setitem_dim[int]	61.1240μs	29.4470μs	33.9594 KOps/s	31.1935 KOps/s	$\textbf{\color{#35bf28}+8.87\%}$
test_setitem_dim[slice_int]	0.1030ms	57.6149μs	17.3566 KOps/s	16.8230 KOps/s	$\color{#35bf28}+3.17\%$
test_setitem_dim[range]	0.1313ms	74.9473μs	13.3427 KOps/s	13.1453 KOps/s	$\color{#35bf28}+1.50\%$
test_setitem_dim[tuple]	78.1150μs	44.4075μs	22.5187 KOps/s	21.0910 KOps/s	$\textbf{\color{#35bf28}+6.77\%}$
test_setitem	0.2080ms	17.8236μs	56.1054 KOps/s	53.3919 KOps/s	$\textbf{\color{#35bf28}+5.08\%}$
test_set	0.1234ms	17.3850μs	57.5208 KOps/s	54.9918 KOps/s	$\color{#35bf28}+4.60\%$
test_set_shared	3.2599ms	0.1430ms	6.9914 KOps/s	7.0898 KOps/s	$\color{#d91a1a}-1.39\%$
test_update	0.1090ms	19.5221μs	51.2240 KOps/s	46.5558 KOps/s	$\textbf{\color{#35bf28}+10.03\%}$
test_update_nested	0.2305ms	25.8779μs	38.6430 KOps/s	35.2208 KOps/s	$\textbf{\color{#35bf28}+9.72\%}$
test_set_nested	0.1875ms	19.0727μs	52.4309 KOps/s	50.2251 KOps/s	$\color{#35bf28}+4.39\%$
test_set_nested_new	0.2395ms	24.2250μs	41.2796 KOps/s	40.8504 KOps/s	$\color{#35bf28}+1.05\%$
test_select	0.1117ms	47.9072μs	20.8737 KOps/s	20.3933 KOps/s	$\color{#35bf28}+2.36\%$
test_unbind_speed	0.4095ms	0.3432ms	2.9138 KOps/s	2.8856 KOps/s	$\color{#35bf28}+0.98\%$
test_unbind_speed_stack0	73.0337ms	4.5304ms	220.7314 Ops/s	235.4083 Ops/s	$\textbf{\color{#d91a1a}-6.23\%}$
test_unbind_speed_stack1	3.1067μs	0.6244μs	1.6015 MOps/s	1.5655 MOps/s	$\color{#35bf28}+2.30\%$
test_split	3.1036ms	1.5816ms	632.2879 Ops/s	583.8312 Ops/s	$\textbf{\color{#35bf28}+8.30\%}$
test_chunk	69.2770ms	1.6823ms	594.4212 Ops/s	594.4688 Ops/s	$-0.01\%$
test_creation[device0]	3.4956ms	0.1034ms	9.6755 KOps/s	9.7760 KOps/s	$\color{#d91a1a}-1.03\%$
test_creation_from_tensor	0.1943ms	80.9404μs	12.3548 KOps/s	12.2406 KOps/s	$\color{#35bf28}+0.93\%$
test_add_one[memmap_tensor0]	0.3091ms	5.3936μs	185.4032 KOps/s	192.7443 KOps/s	$\color{#d91a1a}-3.81\%$
test_contiguous[memmap_tensor0]	17.5020μs	0.6466μs	1.5466 MOps/s	1.5474 MOps/s	$\color{#d91a1a}-0.05\%$
test_stack[memmap_tensor0]	61.4340μs	3.7316μs	267.9782 KOps/s	268.7465 KOps/s	$\color{#d91a1a}-0.29\%$
test_memmaptd_index	0.2533ms	0.1996ms	5.0112 KOps/s	4.8321 KOps/s	$\color{#35bf28}+3.71\%$
test_memmaptd_index_astensor	1.0091ms	0.2595ms	3.8539 KOps/s	3.7508 KOps/s	$\color{#35bf28}+2.75\%$
test_memmaptd_index_op	1.1923ms	0.5196ms	1.9245 KOps/s	1.7994 KOps/s	$\textbf{\color{#35bf28}+6.95\%}$
test_serialize_model	0.1033s	0.1008s	9.9163 Ops/s	8.9845 Ops/s	$\textbf{\color{#35bf28}+10.37\%}$
test_serialize_model_pickle	0.4481s	0.3823s	2.6158 Ops/s	2.6300 Ops/s	$\color{#d91a1a}-0.54\%$
test_serialize_weights	0.1726s	0.1093s	9.1509 Ops/s	9.3902 Ops/s	$\color{#d91a1a}-2.55\%$
test_serialize_weights_returnearly	0.3916s	0.1627s	6.1464 Ops/s	7.4606 Ops/s	$\textbf{\color{#d91a1a}-17.62\%}$
test_serialize_weights_pickle	0.8428s	0.4911s	2.0361 Ops/s	1.5441 Ops/s	$\textbf{\color{#35bf28}+31.86\%}$
test_serialize_weights_filesystem	0.1626s	98.2269ms	10.1805 Ops/s	10.8885 Ops/s	$\textbf{\color{#d91a1a}-6.50\%}$
test_serialize_model_filesystem	96.9790ms	91.9220ms	10.8788 Ops/s	11.1281 Ops/s	$\color{#d91a1a}-2.24\%$
test_reshape_pytree	61.8240μs	23.2369μs	43.0351 KOps/s	42.4294 KOps/s	$\color{#35bf28}+1.43\%$
test_reshape_td	78.0540μs	30.4979μs	32.7891 KOps/s	33.1803 KOps/s	$\color{#d91a1a}-1.18\%$
test_view_pytree	59.5910μs	22.9946μs	43.4886 KOps/s	42.3826 KOps/s	$\color{#35bf28}+2.61\%$
test_view_td	44.8550μs	4.7699μs	209.6487 KOps/s	203.5345 KOps/s	$\color{#35bf28}+3.00\%$
test_unbind_pytree	76.3720μs	26.2723μs	38.0630 KOps/s	37.4089 KOps/s	$\color{#35bf28}+1.75\%$
test_unbind_td	0.1075ms	55.5694μs	17.9955 KOps/s	18.0748 KOps/s	$\color{#d91a1a}-0.44\%$
test_split_pytree	70.0600μs	26.3462μs	37.9561 KOps/s	37.2305 KOps/s	$\color{#35bf28}+1.95\%$
test_split_td	0.5855ms	43.7204μs	22.8726 KOps/s	23.0588 KOps/s	$\color{#d91a1a}-0.81\%$
test_add_pytree	71.9530μs	32.2706μs	30.9880 KOps/s	30.5243 KOps/s	$\color{#35bf28}+1.52\%$
test_add_td	0.1152ms	45.9568μs	21.7596 KOps/s	20.6633 KOps/s	$\textbf{\color{#35bf28}+5.31\%}$
test_distributed	0.1801ms	0.1005ms	9.9513 KOps/s	9.8492 KOps/s	$\color{#35bf28}+1.04\%$
test_tdmodule	0.1901ms	22.1699μs	45.1062 KOps/s	43.1686 KOps/s	$\color{#35bf28}+4.49\%$
test_tdmodule_dispatch	0.1930ms	39.7824μs	25.1368 KOps/s	23.6184 KOps/s	$\textbf{\color{#35bf28}+6.43\%}$
test_tdseq	63.0570μs	24.7704μs	40.3707 KOps/s	39.1704 KOps/s	$\color{#35bf28}+3.06\%$
test_tdseq_dispatch	0.1601ms	45.1805μs	22.1335 KOps/s	21.6398 KOps/s	$\color{#35bf28}+2.28\%$
test_instantiation_functorch	1.5771ms	1.3174ms	759.0814 Ops/s	740.3648 Ops/s	$\color{#35bf28}+2.53\%$
test_instantiation_td	1.5210ms	1.0188ms	981.5750 Ops/s	991.4864 Ops/s	$\color{#d91a1a}-1.00\%$
test_exec_functorch	0.2850ms	0.1617ms	6.1860 KOps/s	6.2735 KOps/s	$\color{#d91a1a}-1.40\%$
test_exec_functional_call	0.2231ms	0.1487ms	6.7265 KOps/s	6.7179 KOps/s	$\color{#35bf28}+0.13\%$
test_exec_td	0.2616ms	0.1441ms	6.9388 KOps/s	6.9493 KOps/s	$\color{#d91a1a}-0.15\%$
test_exec_td_decorator	72.7482ms	0.2002ms	4.9951 KOps/s	5.5500 KOps/s	$\textbf{\color{#d91a1a}-10.00\%}$
test_vmap_mlp_speed[True-True]	1.2694ms	0.9028ms	1.1077 KOps/s	1.0927 KOps/s	$\color{#35bf28}+1.37\%$
test_vmap_mlp_speed[True-False]	0.9306ms	0.4828ms	2.0711 KOps/s	2.0754 KOps/s	$\color{#d91a1a}-0.21\%$
test_vmap_mlp_speed[False-True]	1.1588ms	0.7905ms	1.2650 KOps/s	1.2663 KOps/s	$\color{#d91a1a}-0.10\%$
test_vmap_mlp_speed[False-False]	0.5683ms	0.3929ms	2.5455 KOps/s	2.5377 KOps/s	$\color{#35bf28}+0.30\%$
test_vmap_mlp_speed_decorator[True-True]	3.0699ms	2.4336ms	410.9173 Ops/s	537.4567 Ops/s	$\textbf{\color{#d91a1a}-23.54\%}$
test_vmap_mlp_speed_decorator[True-False]	0.9827ms	0.5318ms	1.8802 KOps/s	1.8571 KOps/s	$\color{#35bf28}+1.25\%$
test_vmap_mlp_speed_decorator[False-True]	2.6855ms	1.9759ms	506.1094 Ops/s	653.3487 Ops/s	$\textbf{\color{#d91a1a}-22.54\%}$
test_vmap_mlp_speed_decorator[False-False]	0.7985ms	0.4065ms	2.4603 KOps/s	2.4255 KOps/s	$\color{#35bf28}+1.44\%$

[github-actions]

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

Total Benchmarks: 128. Improved: $\large\color{#35bf28}11$. Worsened: $\large\color{#d91a1a}21$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.2610μs	14.1417μs	70.7129 KOps/s	77.4190 KOps/s	$\textbf{\color{#d91a1a}-8.66\%}$
test_plain_set_stack_nested	0.1508ms	0.1187ms	8.4247 KOps/s	8.5470 KOps/s	$\color{#d91a1a}-1.43\%$
test_plain_set_nested_inplace	41.5200μs	15.4930μs	64.5452 KOps/s	70.7638 KOps/s	$\textbf{\color{#d91a1a}-8.79\%}$
test_plain_set_stack_nested_inplace	0.1688ms	0.1455ms	6.8727 KOps/s	6.9412 KOps/s	$\color{#d91a1a}-0.99\%$
test_items	28.3900μs	4.6982μs	212.8456 KOps/s	209.9882 KOps/s	$\color{#35bf28}+1.36\%$
test_items_nested	0.3973ms	0.3397ms	2.9436 KOps/s	2.9519 KOps/s	$\color{#d91a1a}-0.28\%$
test_items_nested_locked	0.3779ms	0.3421ms	2.9231 KOps/s	2.9251 KOps/s	$\color{#d91a1a}-0.07\%$
test_items_nested_leaf	0.2786ms	0.2006ms	4.9862 KOps/s	5.0012 KOps/s	$\color{#d91a1a}-0.30\%$
test_items_stack_nested	1.3590ms	1.3142ms	760.9273 Ops/s	743.6950 Ops/s	$\color{#35bf28}+2.32\%$
test_items_stack_nested_leaf	1.1938ms	1.1440ms	874.1469 Ops/s	853.7740 Ops/s	$\color{#35bf28}+2.39\%$
test_items_stack_nested_locked	0.9676ms	0.9116ms	1.0970 KOps/s	1.1709 KOps/s	$\textbf{\color{#d91a1a}-6.31\%}$
test_keys	24.1500μs	4.6361μs	215.6969 KOps/s	216.8534 KOps/s	$\color{#d91a1a}-0.53\%$
test_keys_nested	0.8616ms	93.9827μs	10.6403 KOps/s	10.5702 KOps/s	$\color{#35bf28}+0.66\%$
test_keys_nested_locked	0.1178ms	93.7242μs	10.6696 KOps/s	10.7218 KOps/s	$\color{#d91a1a}-0.49\%$
test_keys_nested_leaf	0.1791ms	77.4550μs	12.9107 KOps/s	12.9460 KOps/s	$\color{#d91a1a}-0.27\%$
test_keys_stack_nested	1.2413ms	1.1649ms	858.4462 Ops/s	849.8004 Ops/s	$\color{#35bf28}+1.02\%$
test_keys_stack_nested_leaf	1.2493ms	1.1388ms	878.1039 Ops/s	849.0962 Ops/s	$\color{#35bf28}+3.42\%$
test_keys_stack_nested_locked	0.8011ms	0.7349ms	1.3607 KOps/s	1.4791 KOps/s	$\textbf{\color{#d91a1a}-8.00\%}$
test_values	7.9967μs	1.8945μs	527.8369 KOps/s	528.2845 KOps/s	$\color{#d91a1a}-0.08\%$
test_values_nested	68.7210μs	45.8437μs	21.8133 KOps/s	22.0702 KOps/s	$\color{#d91a1a}-1.16\%$
test_values_nested_locked	73.1710μs	48.1959μs	20.7486 KOps/s	21.0618 KOps/s	$\color{#d91a1a}-1.49\%$
test_values_nested_leaf	58.6810μs	39.9638μs	25.0227 KOps/s	25.4136 KOps/s	$\color{#d91a1a}-1.54\%$
test_values_stack_nested	1.0333ms	0.9655ms	1.0358 KOps/s	996.3630 Ops/s	$\color{#35bf28}+3.95\%$
test_values_stack_nested_leaf	1.0131ms	0.9506ms	1.0520 KOps/s	1.0322 KOps/s	$\color{#35bf28}+1.92\%$
test_values_stack_nested_locked	0.6516ms	0.5899ms	1.6952 KOps/s	1.9183 KOps/s	$\textbf{\color{#d91a1a}-11.63\%}$
test_membership	21.5110μs	1.0595μs	943.8789 KOps/s	1.0613 MOps/s	$\textbf{\color{#d91a1a}-11.06\%}$
test_membership_nested	23.1500μs	2.3356μs	428.1588 KOps/s	429.1382 KOps/s	$\color{#d91a1a}-0.23\%$
test_membership_nested_leaf	14.0655μs	2.2404μs	446.3514 KOps/s	441.3583 KOps/s	$\color{#35bf28}+1.13\%$
test_membership_stacked_nested	28.4510μs	11.1387μs	89.7772 KOps/s	90.1912 KOps/s	$\color{#d91a1a}-0.46\%$
test_membership_stacked_nested_leaf	36.9100μs	11.0859μs	90.2046 KOps/s	89.5549 KOps/s	$\color{#35bf28}+0.73\%$
test_membership_nested_last	32.2300μs	4.7644μs	209.8879 KOps/s	210.0763 KOps/s	$\color{#d91a1a}-0.09\%$
test_membership_nested_leaf_last	21.6500μs	4.7987μs	208.3896 KOps/s	208.6073 KOps/s	$\color{#d91a1a}-0.10\%$
test_membership_stacked_nested_last	0.1729ms	0.1368ms	7.3117 KOps/s	7.3760 KOps/s	$\color{#d91a1a}-0.87\%$
test_membership_stacked_nested_leaf_last	39.8400μs	13.0891μs	76.3997 KOps/s	77.1456 KOps/s	$\color{#d91a1a}-0.97\%$
test_nested_getleaf	32.6900μs	8.4324μs	118.5900 KOps/s	118.6016 KOps/s	$-0.01\%$
test_nested_get	30.1710μs	7.9701μs	125.4697 KOps/s	124.8764 KOps/s	$\color{#35bf28}+0.48\%$
test_stacked_getleaf	0.3901ms	0.3243ms	3.0839 KOps/s	2.5675 KOps/s	$\textbf{\color{#35bf28}+20.11\%}$
test_stacked_get	0.3252ms	0.2888ms	3.4622 KOps/s	2.7995 KOps/s	$\textbf{\color{#35bf28}+23.67\%}$
test_nested_getitemleaf	30.5710μs	8.4739μs	118.0091 KOps/s	117.9308 KOps/s	$\color{#35bf28}+0.07\%$
test_nested_getitem	26.8000μs	8.0259μs	124.5962 KOps/s	124.4663 KOps/s	$\color{#35bf28}+0.10\%$
test_stacked_getitemleaf	0.3603ms	0.3199ms	3.1256 KOps/s	2.5547 KOps/s	$\textbf{\color{#35bf28}+22.35\%}$
test_stacked_getitem	0.3447ms	0.2867ms	3.4881 KOps/s	2.7719 KOps/s	$\textbf{\color{#35bf28}+25.84\%}$
test_lock_nested	7.2899ms	0.4273ms	2.3401 KOps/s	2.3663 KOps/s	$\color{#d91a1a}-1.11\%$
test_lock_stack_nested	83.9311ms	6.5792ms	151.9945 Ops/s	150.9959 Ops/s	$\color{#35bf28}+0.66\%$
test_unlock_nested	0.8153ms	0.4136ms	2.4178 KOps/s	2.3929 KOps/s	$\color{#35bf28}+1.04\%$
test_unlock_stack_nested	84.4430ms	6.8833ms	145.2789 Ops/s	142.4728 Ops/s	$\color{#35bf28}+1.97\%$
test_flatten_speed	79.1060ms	0.2841ms	3.5201 KOps/s	3.7986 KOps/s	$\textbf{\color{#d91a1a}-7.33\%}$
test_unflatten_speed	0.4277ms	0.3539ms	2.8258 KOps/s	2.7778 KOps/s	$\color{#35bf28}+1.73\%$
test_common_ops	1.0753ms	0.6356ms	1.5733 KOps/s	1.6392 KOps/s	$\color{#d91a1a}-4.02\%$
test_creation	19.4700μs	1.5978μs	625.8798 KOps/s	625.3951 KOps/s	$\color{#35bf28}+0.08\%$
test_creation_empty	30.3000μs	9.4056μs	106.3196 KOps/s	145.5207 KOps/s	$\textbf{\color{#d91a1a}-26.94\%}$
test_creation_nested_1	33.5000μs	11.4486μs	87.3472 KOps/s	113.7668 KOps/s	$\textbf{\color{#d91a1a}-23.22\%}$
test_creation_nested_2	34.1210μs	16.0095μs	62.4630 KOps/s	74.3270 KOps/s	$\textbf{\color{#d91a1a}-15.96\%}$
test_clone	29.1400μs	13.1952μs	75.7849 KOps/s	71.6729 KOps/s	$\textbf{\color{#35bf28}+5.74\%}$
test_getitem[int]	55.3410μs	11.4504μs	87.3329 KOps/s	85.9827 KOps/s	$\color{#35bf28}+1.57\%$
test_getitem[slice_int]	42.7910μs	21.8601μs	45.7455 KOps/s	44.4463 KOps/s	$\color{#35bf28}+2.92\%$
test_getitem[range]	62.1310μs	38.0810μs	26.2598 KOps/s	25.2587 KOps/s	$\color{#35bf28}+3.96\%$
test_getitem[tuple]	57.4110μs	19.1708μs	52.1626 KOps/s	50.4330 KOps/s	$\color{#35bf28}+3.43\%$
test_getitem[list]	58.3510μs	34.3018μs	29.1530 KOps/s	27.7059 KOps/s	$\textbf{\color{#35bf28}+5.22\%}$
test_setitem_dim[int]	47.5210μs	28.1761μs	35.4910 KOps/s	37.5469 KOps/s	$\textbf{\color{#d91a1a}-5.48\%}$
test_setitem_dim[slice_int]	70.3310μs	50.3325μs	19.8679 KOps/s	20.4655 KOps/s	$\color{#d91a1a}-2.92\%$
test_setitem_dim[range]	86.5610μs	65.6257μs	15.2379 KOps/s	15.9387 KOps/s	$\color{#d91a1a}-4.40\%$
test_setitem_dim[tuple]	74.5210μs	43.1653μs	23.1668 KOps/s	23.9093 KOps/s	$\color{#d91a1a}-3.11\%$
test_setitem	0.1030ms	18.2416μs	54.8196 KOps/s	55.5459 KOps/s	$\color{#d91a1a}-1.31\%$
test_set	0.1055ms	17.5638μs	56.9353 KOps/s	56.0640 KOps/s	$\color{#35bf28}+1.55\%$
test_set_shared	2.7016ms	0.1020ms	9.8010 KOps/s	9.5446 KOps/s	$\color{#35bf28}+2.69\%$
test_update	0.1299ms	20.8123μs	48.0486 KOps/s	51.0171 KOps/s	$\textbf{\color{#d91a1a}-5.82\%}$
test_update_nested	70.6810μs	27.4286μs	36.4582 KOps/s	39.0796 KOps/s	$\textbf{\color{#d91a1a}-6.71\%}$
test_set_nested	0.1217ms	18.8481μs	53.0556 KOps/s	52.2353 KOps/s	$\color{#35bf28}+1.57\%$
test_set_nested_new	0.1268ms	22.4136μs	44.6158 KOps/s	45.0933 KOps/s	$\color{#d91a1a}-1.06\%$
test_select	66.8010μs	44.4769μs	22.4836 KOps/s	23.2315 KOps/s	$\color{#d91a1a}-3.22\%$
test_to	76.4710μs	55.4728μs	18.0269 KOps/s	18.1810 KOps/s	$\color{#d91a1a}-0.85\%$
test_to_nonblocking	71.7810μs	34.6925μs	28.8247 KOps/s	28.4318 KOps/s	$\color{#35bf28}+1.38\%$
test_unbind_speed	0.4472ms	0.3298ms	3.0321 KOps/s	2.9866 KOps/s	$\color{#35bf28}+1.53\%$
test_unbind_speed_stack0	77.7353ms	4.0722ms	245.5657 Ops/s	234.7257 Ops/s	$\color{#35bf28}+4.62\%$
test_unbind_speed_stack1	4.1491μs	0.5369μs	1.8627 MOps/s	1.8573 MOps/s	$\color{#35bf28}+0.29\%$
test_split	2.0015ms	1.5735ms	635.5216 Ops/s	607.8149 Ops/s	$\color{#35bf28}+4.56\%$
test_chunk	74.2382ms	1.6944ms	590.1921 Ops/s	564.4858 Ops/s	$\color{#35bf28}+4.55\%$
test_creation[device0]	0.1478ms	76.0720μs	13.1454 KOps/s	13.5492 KOps/s	$\color{#d91a1a}-2.98\%$
test_creation_from_tensor	0.1509ms	58.0039μs	17.2402 KOps/s	18.1093 KOps/s	$\color{#d91a1a}-4.80\%$
test_add_one[memmap_tensor0]	86.9310μs	6.9404μs	144.0829 KOps/s	129.0507 KOps/s	$\textbf{\color{#35bf28}+11.65\%}$
test_contiguous[memmap_tensor0]	13.9200μs	0.6621μs	1.5103 MOps/s	1.5650 MOps/s	$\color{#d91a1a}-3.50\%$
test_stack[memmap_tensor0]	32.7900μs	4.6968μs	212.9132 KOps/s	210.0173 KOps/s	$\color{#35bf28}+1.38\%$
test_memmaptd_index	0.3062ms	0.2413ms	4.1448 KOps/s	4.1090 KOps/s	$\color{#35bf28}+0.87\%$
test_memmaptd_index_astensor	0.3629ms	0.3001ms	3.3326 KOps/s	3.3187 KOps/s	$\color{#35bf28}+0.42\%$
test_memmaptd_index_op	0.7351ms	0.5983ms	1.6713 KOps/s	1.6824 KOps/s	$\color{#d91a1a}-0.66\%$
test_serialize_model	0.1673s	98.5848ms	10.1436 Ops/s	9.6808 Ops/s	$\color{#35bf28}+4.78\%$
test_serialize_model_pickle	1.3490s	1.2360s	0.8091 Ops/s	0.8082 Ops/s	$\color{#35bf28}+0.11\%$
test_serialize_weights	0.1651s	95.1322ms	10.5117 Ops/s	9.8519 Ops/s	$\textbf{\color{#35bf28}+6.70\%}$
test_serialize_weights_returnearly	0.2459s	70.0404ms	14.2775 Ops/s	12.9376 Ops/s	$\textbf{\color{#35bf28}+10.36\%}$
test_serialize_weights_pickle	1.4106s	1.2449s	0.8033 Ops/s	0.8032 Ops/s	$+0.00\%$
test_reshape_pytree	42.2210μs	25.4806μs	39.2456 KOps/s	40.7301 KOps/s	$\color{#d91a1a}-3.64\%$
test_reshape_td	49.7910μs	29.2164μs	34.2273 KOps/s	35.3365 KOps/s	$\color{#d91a1a}-3.14\%$
test_view_pytree	51.7010μs	24.5474μs	40.7375 KOps/s	40.7039 KOps/s	$\color{#35bf28}+0.08\%$
test_view_td	51.9710μs	4.0686μs	245.7822 KOps/s	238.9190 KOps/s	$\color{#35bf28}+2.87\%$
test_unbind_pytree	59.4700μs	30.4312μs	32.8610 KOps/s	31.0980 KOps/s	$\textbf{\color{#35bf28}+5.67\%}$
test_unbind_td	0.1015ms	52.9739μs	18.8772 KOps/s	18.9211 KOps/s	$\color{#d91a1a}-0.23\%$
test_split_pytree	46.7200μs	29.2123μs	34.2322 KOps/s	34.5621 KOps/s	$\color{#d91a1a}-0.95\%$
test_split_td	0.6709ms	40.5434μs	24.6649 KOps/s	24.1839 KOps/s	$\color{#35bf28}+1.99\%$
test_add_pytree	0.1851ms	36.3178μs	27.5347 KOps/s	26.2559 KOps/s	$\color{#35bf28}+4.87\%$
test_add_td	0.1959ms	49.9511μs	20.0196 KOps/s	22.0192 KOps/s	$\textbf{\color{#d91a1a}-9.08\%}$
test_distributed	1.6383ms	72.5755μs	13.7788 KOps/s	11.3275 KOps/s	$\textbf{\color{#35bf28}+21.64\%}$
test_tdmodule	33.1100μs	18.3272μs	54.5636 KOps/s	57.3276 KOps/s	$\color{#d91a1a}-4.82\%$
test_tdmodule_dispatch	0.2230ms	36.4164μs	27.4602 KOps/s	29.9538 KOps/s	$\textbf{\color{#d91a1a}-8.33\%}$
test_tdseq	39.6200μs	21.4461μs	46.6284 KOps/s	50.0647 KOps/s	$\textbf{\color{#d91a1a}-6.86\%}$
test_tdseq_dispatch	57.8110μs	38.3449μs	26.0791 KOps/s	27.8861 KOps/s	$\textbf{\color{#d91a1a}-6.48\%}$
test_instantiation_functorch	2.0659ms	1.6799ms	595.2909 Ops/s	591.9169 Ops/s	$\color{#35bf28}+0.57\%$
test_instantiation_td	1.7367ms	1.1707ms	854.1879 Ops/s	846.4974 Ops/s	$\color{#35bf28}+0.91\%$
test_exec_functorch	0.1993ms	0.1619ms	6.1785 KOps/s	6.0348 KOps/s	$\color{#35bf28}+2.38\%$
test_exec_functional_call	0.1974ms	0.1632ms	6.1283 KOps/s	6.0321 KOps/s	$\color{#35bf28}+1.59\%$
test_exec_td	0.2009ms	0.1541ms	6.4900 KOps/s	6.4039 KOps/s	$\color{#35bf28}+1.35\%$
test_exec_td_decorator	0.7850ms	0.1924ms	5.1982 KOps/s	4.9736 KOps/s	$\color{#35bf28}+4.52\%$
test_vmap_mlp_speed[True-True]	1.5224ms	1.1243ms	889.4705 Ops/s	887.1760 Ops/s	$\color{#35bf28}+0.26\%$
test_vmap_mlp_speed[True-False]	0.8900ms	0.6739ms	1.4838 KOps/s	1.5058 KOps/s	$\color{#d91a1a}-1.46\%$
test_vmap_mlp_speed[False-True]	1.0675ms	1.0328ms	968.2858 Ops/s	972.8457 Ops/s	$\color{#d91a1a}-0.47\%$
test_vmap_mlp_speed[False-False]	0.6600ms	0.6011ms	1.6636 KOps/s	1.6784 KOps/s	$\color{#d91a1a}-0.88\%$
test_vmap_mlp_speed_decorator[True-True]	3.1760ms	2.5448ms	392.9614 Ops/s	477.2229 Ops/s	$\textbf{\color{#d91a1a}-17.66\%}$
test_vmap_mlp_speed_decorator[True-False]	1.2097ms	0.7224ms	1.3842 KOps/s	1.4071 KOps/s	$\color{#d91a1a}-1.62\%$
test_vmap_mlp_speed_decorator[False-True]	2.5447ms	2.1309ms	469.2827 Ops/s	549.5264 Ops/s	$\textbf{\color{#d91a1a}-14.60\%}$
test_vmap_mlp_speed_decorator[False-False]	1.0272ms	0.6195ms	1.6142 KOps/s	1.6072 KOps/s	$\color{#35bf28}+0.44\%$
test_vmap_transformer_speed[True-True]	12.7697ms	12.5562ms	79.6419 Ops/s	77.9719 Ops/s	$\color{#35bf28}+2.14\%$
test_vmap_transformer_speed[True-False]	8.4028ms	8.2841ms	120.7125 Ops/s	120.2799 Ops/s	$\color{#35bf28}+0.36\%$
test_vmap_transformer_speed[False-True]	12.6310ms	12.4644ms	80.2285 Ops/s	80.6780 Ops/s	$\color{#d91a1a}-0.56\%$
test_vmap_transformer_speed[False-False]	8.6454ms	8.2510ms	121.1970 Ops/s	121.7466 Ops/s	$\color{#d91a1a}-0.45\%$
test_vmap_transformer_speed_decorator[True-True]	77.9128ms	76.9329ms	12.9983 Ops/s	14.2144 Ops/s	$\textbf{\color{#d91a1a}-8.55\%}$
test_vmap_transformer_speed_decorator[True-False]	21.7294ms	19.9788ms	50.0531 Ops/s	50.1907 Ops/s	$\color{#d91a1a}-0.27\%$
test_vmap_transformer_speed_decorator[False-True]	70.9348ms	69.6344ms	14.3607 Ops/s	17.1990 Ops/s	$\textbf{\color{#d91a1a}-16.50\%}$
test_vmap_transformer_speed_decorator[False-False]	0.1150s	21.3255ms	46.8922 Ops/s	46.7995 Ops/s	$\color{#35bf28}+0.20\%$