Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BugFix] Fix empty tuple index #811

Merged
merged 1 commit into from
Jun 11, 2024
Merged

[BugFix] Fix empty tuple index #811

merged 1 commit into from
Jun 11, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jun 11, 2024

No description provided.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jun 11, 2024
@vmoens vmoens added the bug Something isn't working label Jun 11, 2024
@vmoens vmoens merged commit dcaeeb4 into main Jun 11, 2024
16 of 28 checks passed
@vmoens vmoens deleted the fix-index-tuple branch June 11, 2024 14:08
Copy link

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

Total Benchmarks: 144. Improved: $\large\color{#35bf28}32$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_plain_set_nested 29.9260μs 16.1712μs 61.8382 KOps/s 57.5696 KOps/s $\textbf{\color{#35bf28}+7.41\%}$
test_plain_set_stack_nested 36.6890μs 16.3745μs 61.0706 KOps/s 56.8741 KOps/s $\textbf{\color{#35bf28}+7.38\%}$
test_plain_set_nested_inplace 66.3660μs 18.1058μs 55.2311 KOps/s 50.4521 KOps/s $\textbf{\color{#35bf28}+9.47\%}$
test_plain_set_stack_nested_inplace 40.9680μs 17.9394μs 55.7431 KOps/s 50.3710 KOps/s $\textbf{\color{#35bf28}+10.66\%}$
test_items 22.5620μs 2.5533μs 391.6498 KOps/s 380.2911 KOps/s $\color{#35bf28}+2.99\%$
test_items_nested 0.4360ms 0.2639ms 3.7894 KOps/s 3.7376 KOps/s $\color{#35bf28}+1.39\%$
test_items_nested_locked 0.9887ms 0.2669ms 3.7470 KOps/s 3.7357 KOps/s $\color{#35bf28}+0.30\%$
test_items_nested_leaf 0.1507ms 76.1948μs 13.1243 KOps/s 13.0977 KOps/s $\color{#35bf28}+0.20\%$
test_items_stack_nested 0.9161ms 0.2654ms 3.7685 KOps/s 3.6820 KOps/s $\color{#35bf28}+2.35\%$
test_items_stack_nested_leaf 0.1654ms 76.0038μs 13.1572 KOps/s 12.8378 KOps/s $\color{#35bf28}+2.49\%$
test_items_stack_nested_locked 0.5023ms 0.2651ms 3.7720 KOps/s 3.6579 KOps/s $\color{#35bf28}+3.12\%$
test_keys 24.1460μs 3.8203μs 261.7587 KOps/s 256.6853 KOps/s $\color{#35bf28}+1.98\%$
test_keys_nested 0.2260ms 0.1381ms 7.2424 KOps/s 7.2383 KOps/s $\color{#35bf28}+0.06\%$
test_keys_nested_locked 0.6907ms 0.1422ms 7.0341 KOps/s 7.0548 KOps/s $\color{#d91a1a}-0.29\%$
test_keys_nested_leaf 0.2177ms 0.1169ms 8.5542 KOps/s 8.5815 KOps/s $\color{#d91a1a}-0.32\%$
test_keys_stack_nested 0.2438ms 0.1383ms 7.2295 KOps/s 7.2398 KOps/s $\color{#d91a1a}-0.14\%$
test_keys_stack_nested_leaf 0.2219ms 0.1154ms 8.6643 KOps/s 8.6599 KOps/s $\color{#35bf28}+0.05\%$
test_keys_stack_nested_locked 0.2575ms 0.1430ms 6.9954 KOps/s 7.0458 KOps/s $\color{#d91a1a}-0.72\%$
test_values 5.5453μs 1.2196μs 819.9733 KOps/s 864.7870 KOps/s $\textbf{\color{#d91a1a}-5.18\%}$
test_values_nested 97.6040μs 50.2787μs 19.8891 KOps/s 19.6151 KOps/s $\color{#35bf28}+1.40\%$
test_values_nested_locked 0.1278ms 49.8449μs 20.0622 KOps/s 19.4380 KOps/s $\color{#35bf28}+3.21\%$
test_values_nested_leaf 91.7230μs 45.8461μs 21.8121 KOps/s 21.6911 KOps/s $\color{#35bf28}+0.56\%$
test_values_stack_nested 0.1145ms 50.3475μs 19.8619 KOps/s 19.2711 KOps/s $\color{#35bf28}+3.07\%$
test_values_stack_nested_leaf 92.3530μs 45.8265μs 21.8215 KOps/s 21.8877 KOps/s $\color{#d91a1a}-0.30\%$
test_values_stack_nested_locked 92.6840μs 50.4098μs 19.8374 KOps/s 19.2346 KOps/s $\color{#35bf28}+3.13\%$
test_membership 17.6530μs 1.3471μs 742.3102 KOps/s 734.2222 KOps/s $\color{#35bf28}+1.10\%$
test_membership_nested 24.9370μs 3.4297μs 291.5713 KOps/s 285.5433 KOps/s $\color{#35bf28}+2.11\%$
test_membership_nested_leaf 46.8270μs 3.4689μs 288.2788 KOps/s 289.8022 KOps/s $\color{#d91a1a}-0.53\%$
test_membership_stacked_nested 35.8670μs 3.4078μs 293.4408 KOps/s 256.9655 KOps/s $\textbf{\color{#35bf28}+14.19\%}$
test_membership_stacked_nested_leaf 26.4690μs 3.4439μs 290.3698 KOps/s 287.1487 KOps/s $\color{#35bf28}+1.12\%$
test_membership_nested_last 35.8480μs 4.2833μs 233.4638 KOps/s 238.9870 KOps/s $\color{#d91a1a}-2.31\%$
test_membership_nested_leaf_last 28.0930μs 4.2755μs 233.8889 KOps/s 235.0072 KOps/s $\color{#d91a1a}-0.48\%$
test_membership_stacked_nested_last 26.0390μs 4.1775μs 239.3761 KOps/s 101.7607 KOps/s $\textbf{\color{#35bf28}+135.23\%}$
test_membership_stacked_nested_leaf_last 19.0260μs 4.2476μs 235.4268 KOps/s 100.2227 KOps/s $\textbf{\color{#35bf28}+134.90\%}$
test_nested_getleaf 32.3910μs 10.7011μs 93.4483 KOps/s 90.1388 KOps/s $\color{#35bf28}+3.67\%$
test_nested_get 31.8900μs 10.1526μs 98.4966 KOps/s 97.8670 KOps/s $\color{#35bf28}+0.64\%$
test_stacked_getleaf 27.7330μs 10.7606μs 92.9314 KOps/s 92.6632 KOps/s $\color{#35bf28}+0.29\%$
test_stacked_get 33.4930μs 10.1397μs 98.6218 KOps/s 98.3820 KOps/s $\color{#35bf28}+0.24\%$
test_nested_getitemleaf 37.3610μs 11.2491μs 88.8957 KOps/s 87.7358 KOps/s $\color{#35bf28}+1.32\%$
test_nested_getitem 35.5970μs 10.3714μs 96.4193 KOps/s 95.1860 KOps/s $\color{#35bf28}+1.30\%$
test_stacked_getitemleaf 38.1520μs 11.1786μs 89.4568 KOps/s 89.8062 KOps/s $\color{#d91a1a}-0.39\%$
test_stacked_getitem 38.5930μs 10.4003μs 96.1509 KOps/s 96.6666 KOps/s $\color{#d91a1a}-0.53\%$
test_lock_nested 0.7803ms 0.3381ms 2.9579 KOps/s 2.9250 KOps/s $\color{#35bf28}+1.13\%$
test_lock_stack_nested 0.4515ms 0.3098ms 3.2284 KOps/s 3.2901 KOps/s $\color{#d91a1a}-1.88\%$
test_unlock_nested 0.7278ms 0.3431ms 2.9148 KOps/s 2.8969 KOps/s $\color{#35bf28}+0.62\%$
test_unlock_stack_nested 0.3972ms 0.3177ms 3.1474 KOps/s 3.2338 KOps/s $\color{#d91a1a}-2.67\%$
test_flatten_speed 0.4753ms 96.2309μs 10.3917 KOps/s 10.4135 KOps/s $\color{#d91a1a}-0.21\%$
test_unflatten_speed 0.7727ms 0.4115ms 2.4302 KOps/s 2.4272 KOps/s $\color{#35bf28}+0.12\%$
test_common_ops 4.9346ms 0.7164ms 1.3958 KOps/s 1.4043 KOps/s $\color{#d91a1a}-0.60\%$
test_creation 26.2890μs 1.9485μs 513.2086 KOps/s 508.9303 KOps/s $\color{#35bf28}+0.84\%$
test_creation_empty 90.7510μs 8.3148μs 120.2679 KOps/s 89.1362 KOps/s $\textbf{\color{#35bf28}+34.93\%}$
test_creation_nested_1 35.5770μs 11.1165μs 89.9562 KOps/s 71.0467 KOps/s $\textbf{\color{#35bf28}+26.62\%}$
test_creation_nested_2 41.0870μs 14.3321μs 69.7732 KOps/s 58.1076 KOps/s $\textbf{\color{#35bf28}+20.08\%}$
test_clone 0.1194ms 13.4329μs 74.4439 KOps/s 74.5372 KOps/s $\color{#d91a1a}-0.13\%$
test_getitem[int] 30.0160μs 11.5118μs 86.8674 KOps/s 87.3181 KOps/s $\color{#d91a1a}-0.52\%$
test_getitem[slice_int] 58.0090μs 22.6997μs 44.0535 KOps/s 45.3339 KOps/s $\color{#d91a1a}-2.82\%$
test_getitem[range] 79.7500μs 58.8284μs 16.9986 KOps/s 16.8424 KOps/s $\color{#35bf28}+0.93\%$
test_getitem[tuple] 58.6300μs 18.9982μs 52.6364 KOps/s 52.9516 KOps/s $\color{#d91a1a}-0.60\%$
test_getitem[list] 0.1056ms 41.0161μs 24.3807 KOps/s 24.2313 KOps/s $\color{#35bf28}+0.62\%$
test_setitem_dim[int] 58.3300μs 31.5175μs 31.7284 KOps/s 28.1158 KOps/s $\textbf{\color{#35bf28}+12.85\%}$
test_setitem_dim[slice_int] 85.8210μs 57.4002μs 17.4215 KOps/s 16.2662 KOps/s $\textbf{\color{#35bf28}+7.10\%}$
test_setitem_dim[range] 0.1122ms 80.4093μs 12.4364 KOps/s 11.7718 KOps/s $\textbf{\color{#35bf28}+5.65\%}$
test_setitem_dim[tuple] 73.9490μs 46.6195μs 21.4502 KOps/s 19.9768 KOps/s $\textbf{\color{#35bf28}+7.38\%}$
test_setitem 63.2890μs 18.6075μs 53.7418 KOps/s 48.4406 KOps/s $\textbf{\color{#35bf28}+10.94\%}$
test_set 53.3810μs 18.1329μs 55.1485 KOps/s 49.5278 KOps/s $\textbf{\color{#35bf28}+11.35\%}$
test_set_shared 1.5458ms 0.1424ms 7.0238 KOps/s 7.0893 KOps/s $\color{#d91a1a}-0.92\%$
test_update 0.1059ms 18.9281μs 52.8315 KOps/s 45.3330 KOps/s $\textbf{\color{#35bf28}+16.54\%}$
test_update_nested 85.5810μs 26.6839μs 37.4758 KOps/s 33.1758 KOps/s $\textbf{\color{#35bf28}+12.96\%}$
test_update__nested 74.8410μs 25.8084μs 38.7471 KOps/s 38.9685 KOps/s $\color{#d91a1a}-0.57\%$
test_set_nested 63.8500μs 19.9618μs 50.0956 KOps/s 45.6052 KOps/s $\textbf{\color{#35bf28}+9.85\%}$
test_set_nested_new 86.0520μs 24.6264μs 40.6069 KOps/s 37.9834 KOps/s $\textbf{\color{#35bf28}+6.91\%}$
test_select 0.1540ms 41.5891μs 24.0448 KOps/s 23.9385 KOps/s $\color{#35bf28}+0.44\%$
test_select_nested 0.2067ms 63.5078μs 15.7461 KOps/s 16.0598 KOps/s $\color{#d91a1a}-1.95\%$
test_exclude_nested 0.1884ms 0.1212ms 8.2516 KOps/s 8.1332 KOps/s $\color{#35bf28}+1.46\%$
test_empty[True] 0.7229ms 0.4000ms 2.5002 KOps/s 2.5189 KOps/s $\color{#d91a1a}-0.75\%$
test_empty[False] 5.1376μs 1.1818μs 846.1934 KOps/s 823.7701 KOps/s $\color{#35bf28}+2.72\%$
test_unbind_speed 1.5239ms 0.2590ms 3.8613 KOps/s 3.8493 KOps/s $\color{#35bf28}+0.31\%$
test_unbind_speed_stack0 0.5897ms 0.2588ms 3.8635 KOps/s 3.9855 KOps/s $\color{#d91a1a}-3.06\%$
test_unbind_speed_stack1 62.7343ms 0.7366ms 1.3575 KOps/s 1.3625 KOps/s $\color{#d91a1a}-0.36\%$
test_split 63.2088ms 1.6172ms 618.3484 Ops/s 619.8941 Ops/s $\color{#d91a1a}-0.25\%$
test_chunk 61.7420ms 1.6110ms 620.7230 Ops/s 608.1616 Ops/s $\color{#35bf28}+2.07\%$
test_creation[device0] 0.3543ms 84.6327μs 11.8158 KOps/s 11.7819 KOps/s $\color{#35bf28}+0.29\%$
test_creation_from_tensor 4.9622ms 87.1667μs 11.4723 KOps/s 11.6967 KOps/s $\color{#d91a1a}-1.92\%$
test_add_one[memmap_tensor0] 0.1424ms 5.4894μs 182.1682 KOps/s 185.7517 KOps/s $\color{#d91a1a}-1.93\%$
test_contiguous[memmap_tensor0] 13.9160μs 0.6531μs 1.5310 MOps/s 1.5038 MOps/s $\color{#35bf28}+1.81\%$
test_stack[memmap_tensor0] 29.6660μs 3.5658μs 280.4433 KOps/s 284.7135 KOps/s $\color{#d91a1a}-1.50\%$
test_memmaptd_index 0.9989ms 0.2514ms 3.9784 KOps/s 3.9269 KOps/s $\color{#35bf28}+1.31\%$
test_memmaptd_index_astensor 0.5927ms 0.3261ms 3.0666 KOps/s 3.0637 KOps/s $\color{#35bf28}+0.09\%$
test_memmaptd_index_op 1.1193ms 0.5711ms 1.7512 KOps/s 1.6181 KOps/s $\textbf{\color{#35bf28}+8.22\%}$
test_serialize_model 0.1652s 0.1113s 8.9843 Ops/s 8.7275 Ops/s $\color{#35bf28}+2.94\%$
test_serialize_model_pickle 0.4491s 0.3778s 2.6472 Ops/s 2.5884 Ops/s $\color{#35bf28}+2.27\%$
test_serialize_weights 0.1704s 0.1106s 9.0417 Ops/s 9.1154 Ops/s $\color{#d91a1a}-0.81\%$
test_serialize_weights_returnearly 0.1988s 0.1361s 7.3466 Ops/s 7.4527 Ops/s $\color{#d91a1a}-1.42\%$
test_serialize_weights_pickle 1.1528s 0.6080s 1.6448 Ops/s 2.3621 Ops/s $\textbf{\color{#d91a1a}-30.37\%}$
test_serialize_weights_filesystem 94.6786ms 89.9766ms 11.1140 Ops/s 10.1689 Ops/s $\textbf{\color{#35bf28}+9.29\%}$
test_serialize_model_filesystem 0.1561s 97.4785ms 10.2587 Ops/s 10.7755 Ops/s $\color{#d91a1a}-4.80\%$
test_reshape_pytree 63.5900μs 24.8614μs 40.2229 KOps/s 39.2179 KOps/s $\color{#35bf28}+2.56\%$
test_reshape_td 75.0810μs 34.6967μs 28.8212 KOps/s 28.4503 KOps/s $\color{#35bf28}+1.30\%$
test_view_pytree 57.0270μs 25.1666μs 39.7352 KOps/s 38.1832 KOps/s $\color{#35bf28}+4.06\%$
test_view_td 85.0800μs 39.8606μs 25.0874 KOps/s 24.2189 KOps/s $\color{#35bf28}+3.59\%$
test_unbind_pytree 66.1940μs 28.9961μs 34.4874 KOps/s 33.9885 KOps/s $\color{#35bf28}+1.47\%$
test_unbind_td 0.3909ms 38.3232μs 26.0939 KOps/s 26.3358 KOps/s $\color{#d91a1a}-0.92\%$
test_split_pytree 62.3070μs 29.1638μs 34.2891 KOps/s 33.7435 KOps/s $\color{#35bf28}+1.62\%$
test_split_td 0.1253ms 40.7861μs 24.5182 KOps/s 24.7009 KOps/s $\color{#d91a1a}-0.74\%$
test_add_pytree 81.7240μs 34.4165μs 29.0558 KOps/s 28.9247 KOps/s $\color{#35bf28}+0.45\%$
test_add_td 0.1221ms 51.9266μs 19.2580 KOps/s 17.3777 KOps/s $\textbf{\color{#35bf28}+10.82\%}$
test_distributed 0.2088ms 0.1003ms 9.9740 KOps/s 9.4847 KOps/s $\textbf{\color{#35bf28}+5.16\%}$
test_tdmodule 40.0650μs 16.4500μs 60.7904 KOps/s 55.5389 KOps/s $\textbf{\color{#35bf28}+9.46\%}$
test_tdmodule_dispatch 82.1540μs 33.4732μs 29.8746 KOps/s 27.6706 KOps/s $\textbf{\color{#35bf28}+7.97\%}$
test_tdseq 44.6140μs 18.8044μs 53.1790 KOps/s 47.3123 KOps/s $\textbf{\color{#35bf28}+12.40\%}$
test_tdseq_dispatch 62.4570μs 35.9328μs 27.8297 KOps/s 24.0106 KOps/s $\textbf{\color{#35bf28}+15.91\%}$
test_instantiation_functorch 1.5721ms 1.3398ms 746.3963 Ops/s 747.9261 Ops/s $\color{#d91a1a}-0.20\%$
test_instantiation_td 1.6531ms 1.0240ms 976.5653 Ops/s 969.4070 Ops/s $\color{#35bf28}+0.74\%$
test_exec_functorch 0.3237ms 0.1647ms 6.0722 KOps/s 6.1981 KOps/s $\color{#d91a1a}-2.03\%$
test_exec_functional_call 0.4244ms 0.1516ms 6.5945 KOps/s 6.7326 KOps/s $\color{#d91a1a}-2.05\%$
test_exec_td 0.3605ms 0.1543ms 6.4824 KOps/s 6.7275 KOps/s $\color{#d91a1a}-3.64\%$
test_exec_td_decorator 0.5347ms 0.2229ms 4.4868 KOps/s 4.5314 KOps/s $\color{#d91a1a}-0.98\%$
test_vmap_mlp_speed[True-True] 0.6904ms 0.4868ms 2.0543 KOps/s 2.1097 KOps/s $\color{#d91a1a}-2.63\%$
test_vmap_mlp_speed[True-False] 0.7709ms 0.4838ms 2.0669 KOps/s 2.1219 KOps/s $\color{#d91a1a}-2.59\%$
test_vmap_mlp_speed[False-True] 0.6208ms 0.3974ms 2.5166 KOps/s 2.6137 KOps/s $\color{#d91a1a}-3.71\%$
test_vmap_mlp_speed[False-False] 0.6488ms 0.3998ms 2.5010 KOps/s 2.6210 KOps/s $\color{#d91a1a}-4.58\%$
test_vmap_mlp_speed_decorator[True-True] 1.1447ms 0.5528ms 1.8088 KOps/s 1.8354 KOps/s $\color{#d91a1a}-1.44\%$
test_vmap_mlp_speed_decorator[True-False] 1.0195ms 0.5538ms 1.8058 KOps/s 1.8168 KOps/s $\color{#d91a1a}-0.61\%$
test_vmap_mlp_speed_decorator[False-True] 0.6448ms 0.4585ms 2.1808 KOps/s 2.2479 KOps/s $\color{#d91a1a}-2.98\%$
test_vmap_mlp_speed_decorator[False-False] 0.7273ms 0.4601ms 2.1736 KOps/s 2.2330 KOps/s $\color{#d91a1a}-2.66\%$
test_to_module_speed[True] 2.2863ms 1.6860ms 593.1360 Ops/s 583.8519 Ops/s $\color{#35bf28}+1.59\%$
test_to_module_speed[False] 2.9461ms 1.6608ms 602.1330 Ops/s 595.1902 Ops/s $\color{#35bf28}+1.17\%$
test_tc_init 65.2320μs 23.0644μs 43.3568 KOps/s 33.7848 KOps/s $\textbf{\color{#35bf28}+28.33\%}$
test_tc_init_nested 0.1021ms 44.0119μs 22.7211 KOps/s 16.1617 KOps/s $\textbf{\color{#35bf28}+40.59\%}$
test_tc_first_layer_tensor 5.5090μs 0.6946μs 1.4397 MOps/s 1.3946 MOps/s $\color{#35bf28}+3.23\%$
test_tc_first_layer_nontensor 5.2619μs 0.6703μs 1.4919 MOps/s 1.4243 MOps/s $\color{#35bf28}+4.75\%$
test_tc_second_layer_tensor 35.7670μs 1.8656μs 536.0220 KOps/s 520.5899 KOps/s $\color{#35bf28}+2.96\%$
test_tc_second_layer_nontensor 20.1780μs 1.6463μs 607.4082 KOps/s 582.4900 KOps/s $\color{#35bf28}+4.28\%$
test_unbind 5.7914ms 5.3749ms 186.0487 Ops/s 149.2230 Ops/s $\textbf{\color{#35bf28}+24.68\%}$
test_full_like 15.1266ms 10.6186ms 94.1747 Ops/s 89.0726 Ops/s $\textbf{\color{#35bf28}+5.73\%}$
test_zeros_like 12.9997ms 5.7823ms 172.9424 Ops/s 176.0072 Ops/s $\color{#d91a1a}-1.74\%$
test_ones_like 11.3815ms 6.1187ms 163.4335 Ops/s 158.2290 Ops/s $\color{#35bf28}+3.29\%$
test_clone 14.5606ms 7.7269ms 129.4173 Ops/s 125.8438 Ops/s $\color{#35bf28}+2.84\%$
test_squeeze 63.9000μs 13.4072μs 74.5865 KOps/s 72.7159 KOps/s $\color{#35bf28}+2.57\%$
test_unsqueeze 0.2094ms 59.7825μs 16.7273 KOps/s 16.1688 KOps/s $\color{#35bf28}+3.45\%$
test_split 0.2541ms 0.1102ms 9.0752 KOps/s 8.8758 KOps/s $\color{#35bf28}+2.25\%$
test_permute 0.2299ms 0.1268ms 7.8860 KOps/s 7.8161 KOps/s $\color{#35bf28}+0.89\%$
test_stack 23.8999ms 21.3021ms 46.9436 Ops/s 45.7121 Ops/s $\color{#35bf28}+2.69\%$
test_cat 26.2941ms 21.4078ms 46.7119 Ops/s 45.8069 Ops/s $\color{#35bf28}+1.98\%$

Copy link

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

Total Benchmarks: 152. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}23$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_plain_set_nested 0.1375ms 13.5066μs 74.0380 KOps/s 76.1846 KOps/s $\color{#d91a1a}-2.82\%$
test_plain_set_stack_nested 36.0910μs 13.7578μs 72.6860 KOps/s 74.7993 KOps/s $\color{#d91a1a}-2.83\%$
test_plain_set_nested_inplace 67.2810μs 14.8786μs 67.2107 KOps/s 69.2350 KOps/s $\color{#d91a1a}-2.92\%$
test_plain_set_stack_nested_inplace 50.1310μs 14.9735μs 66.7846 KOps/s 68.6466 KOps/s $\color{#d91a1a}-2.71\%$
test_items 86.9620μs 4.7170μs 212.0005 KOps/s 211.5887 KOps/s $\color{#35bf28}+0.19\%$
test_items_nested 0.5287ms 0.3417ms 2.9264 KOps/s 2.9169 KOps/s $\color{#35bf28}+0.33\%$
test_items_nested_locked 0.5279ms 0.3436ms 2.9105 KOps/s 2.9070 KOps/s $\color{#35bf28}+0.12\%$
test_items_nested_leaf 0.1035ms 82.1261μs 12.1764 KOps/s 12.1342 KOps/s $\color{#35bf28}+0.35\%$
test_items_stack_nested 0.5053ms 0.3387ms 2.9521 KOps/s 2.8953 KOps/s $\color{#35bf28}+1.96\%$
test_items_stack_nested_leaf 0.1070ms 81.2940μs 12.3010 KOps/s 11.8887 KOps/s $\color{#35bf28}+3.47\%$
test_items_stack_nested_locked 0.3870ms 0.3432ms 2.9139 KOps/s 2.8748 KOps/s $\color{#35bf28}+1.36\%$
test_keys 20.8900μs 4.3550μs 229.6232 KOps/s 227.3649 KOps/s $\color{#35bf28}+0.99\%$
test_keys_nested 89.7420μs 67.3809μs 14.8410 KOps/s 14.9228 KOps/s $\color{#d91a1a}-0.55\%$
test_keys_nested_locked 0.8223ms 71.8910μs 13.9099 KOps/s 13.7558 KOps/s $\color{#35bf28}+1.12\%$
test_keys_nested_leaf 85.8020μs 58.0399μs 17.2295 KOps/s 17.2258 KOps/s $\color{#35bf28}+0.02\%$
test_keys_stack_nested 87.9020μs 66.8494μs 14.9590 KOps/s 14.8281 KOps/s $\color{#35bf28}+0.88\%$
test_keys_stack_nested_leaf 0.1456ms 58.0214μs 17.2350 KOps/s 17.2256 KOps/s $\color{#35bf28}+0.05\%$
test_keys_stack_nested_locked 0.1229ms 71.9859μs 13.8916 KOps/s 13.7722 KOps/s $\color{#35bf28}+0.87\%$
test_values 9.0070μs 1.8248μs 548.0192 KOps/s 554.6388 KOps/s $\color{#d91a1a}-1.19\%$
test_values_nested 69.5810μs 35.0694μs 28.5149 KOps/s 28.7403 KOps/s $\color{#d91a1a}-0.78\%$
test_values_nested_locked 57.6820μs 36.9640μs 27.0534 KOps/s 27.0096 KOps/s $\color{#35bf28}+0.16\%$
test_values_nested_leaf 0.1229ms 31.6085μs 31.6371 KOps/s 32.2010 KOps/s $\color{#d91a1a}-1.75\%$
test_values_stack_nested 66.7810μs 36.2681μs 27.5724 KOps/s 28.1116 KOps/s $\color{#d91a1a}-1.92\%$
test_values_stack_nested_leaf 0.1203ms 32.3898μs 30.8739 KOps/s 31.4056 KOps/s $\color{#d91a1a}-1.69\%$
test_values_stack_nested_locked 60.3110μs 37.8129μs 26.4460 KOps/s 26.6414 KOps/s $\color{#d91a1a}-0.73\%$
test_membership 3.2887μs 0.7118μs 1.4049 MOps/s 1.4341 MOps/s $\color{#d91a1a}-2.03\%$
test_membership_nested 20.6200μs 2.5662μs 389.6851 KOps/s 382.8177 KOps/s $\color{#35bf28}+1.79\%$
test_membership_nested_leaf 26.8210μs 2.6259μs 380.8213 KOps/s 384.4307 KOps/s $\color{#d91a1a}-0.94\%$
test_membership_stacked_nested 23.1710μs 2.5791μs 387.7352 KOps/s 380.7163 KOps/s $\color{#35bf28}+1.84\%$
test_membership_stacked_nested_leaf 49.6110μs 2.6308μs 380.1060 KOps/s 383.3831 KOps/s $\color{#d91a1a}-0.85\%$
test_membership_nested_last 34.3710μs 3.1291μs 319.5762 KOps/s 320.9814 KOps/s $\color{#d91a1a}-0.44\%$
test_membership_nested_leaf_last 30.4810μs 3.1349μs 318.9892 KOps/s 319.6908 KOps/s $\color{#d91a1a}-0.22\%$
test_membership_stacked_nested_last 27.9910μs 9.7677μs 102.3786 KOps/s 279.6277 KOps/s $\textbf{\color{#d91a1a}-63.39\%}$
test_membership_stacked_nested_leaf_last 80.0320μs 9.7176μs 102.9061 KOps/s 278.4216 KOps/s $\textbf{\color{#d91a1a}-63.04\%}$
test_nested_getleaf 0.1784ms 8.3971μs 119.0887 KOps/s 119.7562 KOps/s $\color{#d91a1a}-0.56\%$
test_nested_get 28.3010μs 7.9419μs 125.9151 KOps/s 127.7413 KOps/s $\color{#d91a1a}-1.43\%$
test_stacked_getleaf 0.1973ms 8.4516μs 118.3203 KOps/s 119.1728 KOps/s $\color{#d91a1a}-0.72\%$
test_stacked_get 0.1688ms 7.9372μs 125.9891 KOps/s 126.2469 KOps/s $\color{#d91a1a}-0.20\%$
test_nested_getitemleaf 36.2410μs 8.5511μs 116.9442 KOps/s 117.0908 KOps/s $\color{#d91a1a}-0.13\%$
test_nested_getitem 24.0110μs 8.0793μs 123.7725 KOps/s 124.8220 KOps/s $\color{#d91a1a}-0.84\%$
test_stacked_getitemleaf 39.3910μs 8.5943μs 116.3567 KOps/s 116.6963 KOps/s $\color{#d91a1a}-0.29\%$
test_stacked_getitem 86.3720μs 8.0970μs 123.5032 KOps/s 123.8450 KOps/s $\color{#d91a1a}-0.28\%$
test_lock_nested 58.1757ms 0.4079ms 2.4518 KOps/s 2.4650 KOps/s $\color{#d91a1a}-0.54\%$
test_lock_stack_nested 0.3515ms 0.2994ms 3.3402 KOps/s 3.2775 KOps/s $\color{#35bf28}+1.91\%$
test_unlock_nested 61.0034ms 0.4150ms 2.4097 KOps/s 2.4561 KOps/s $\color{#d91a1a}-1.89\%$
test_unlock_stack_nested 0.3519ms 0.3069ms 3.2588 KOps/s 3.2042 KOps/s $\color{#35bf28}+1.70\%$
test_flatten_speed 0.2062ms 0.1007ms 9.9327 KOps/s 9.8716 KOps/s $\color{#35bf28}+0.62\%$
test_unflatten_speed 0.3570ms 0.2928ms 3.4150 KOps/s 3.4220 KOps/s $\color{#d91a1a}-0.20\%$
test_common_ops 1.1617ms 0.6244ms 1.6017 KOps/s 1.6662 KOps/s $\color{#d91a1a}-3.87\%$
test_creation 18.2410μs 1.6716μs 598.2466 KOps/s 603.1947 KOps/s $\color{#d91a1a}-0.82\%$
test_creation_empty 36.3110μs 10.1453μs 98.5680 KOps/s 107.2269 KOps/s $\textbf{\color{#d91a1a}-8.08\%}$
test_creation_nested_1 37.4710μs 11.7618μs 85.0209 KOps/s 88.4186 KOps/s $\color{#d91a1a}-3.84\%$
test_creation_nested_2 36.0610μs 14.1392μs 70.7255 KOps/s 75.4023 KOps/s $\textbf{\color{#d91a1a}-6.20\%}$
test_clone 40.0010μs 11.6028μs 86.1861 KOps/s 86.2320 KOps/s $\color{#d91a1a}-0.05\%$
test_getitem[int] 95.1920μs 11.4575μs 87.2788 KOps/s 91.2097 KOps/s $\color{#d91a1a}-4.31\%$
test_getitem[slice_int] 63.1910μs 21.5199μs 46.4686 KOps/s 48.0351 KOps/s $\color{#d91a1a}-3.26\%$
test_getitem[range] 66.9810μs 49.1290μs 20.3546 KOps/s 21.5290 KOps/s $\textbf{\color{#d91a1a}-5.46\%}$
test_getitem[tuple] 67.8620μs 19.6558μs 50.8757 KOps/s 54.3386 KOps/s $\textbf{\color{#d91a1a}-6.37\%}$
test_getitem[list] 0.1710ms 35.4969μs 28.1715 KOps/s 30.1376 KOps/s $\textbf{\color{#d91a1a}-6.52\%}$
test_setitem_dim[int] 49.1010μs 31.1241μs 32.1294 KOps/s 34.1837 KOps/s $\textbf{\color{#d91a1a}-6.01\%}$
test_setitem_dim[slice_int] 75.3920μs 52.8671μs 18.9154 KOps/s 20.3606 KOps/s $\textbf{\color{#d91a1a}-7.10\%}$
test_setitem_dim[range] 88.3510μs 68.6785μs 14.5606 KOps/s 14.5928 KOps/s $\color{#d91a1a}-0.22\%$
test_setitem_dim[tuple] 63.2710μs 45.9379μs 21.7685 KOps/s 22.7680 KOps/s $\color{#d91a1a}-4.39\%$
test_setitem 50.1610μs 17.0717μs 58.5764 KOps/s 60.0248 KOps/s $\color{#d91a1a}-2.41\%$
test_set 88.1520μs 16.8480μs 59.3542 KOps/s 61.7469 KOps/s $\color{#d91a1a}-3.88\%$
test_set_shared 0.9909ms 97.5805μs 10.2480 KOps/s 10.3833 KOps/s $\color{#d91a1a}-1.30\%$
test_update 0.1625ms 20.0726μs 49.8191 KOps/s 52.6279 KOps/s $\textbf{\color{#d91a1a}-5.34\%}$
test_update_nested 0.1102ms 25.3149μs 39.5024 KOps/s 40.8431 KOps/s $\color{#d91a1a}-3.28\%$
test_update__nested 0.1742ms 22.5981μs 44.2515 KOps/s 45.0141 KOps/s $\color{#d91a1a}-1.69\%$
test_set_nested 98.1120μs 17.9878μs 55.5932 KOps/s 55.3501 KOps/s $\color{#35bf28}+0.44\%$
test_set_nested_new 55.1910μs 20.7162μs 48.2715 KOps/s 49.6348 KOps/s $\color{#d91a1a}-2.75\%$
test_select 0.9764ms 34.9983μs 28.5728 KOps/s 29.7456 KOps/s $\color{#d91a1a}-3.94\%$
test_select_nested 93.1230μs 53.3577μs 18.7414 KOps/s 18.5423 KOps/s $\color{#35bf28}+1.07\%$
test_exclude_nested 0.2835ms 0.1071ms 9.3365 KOps/s 9.0250 KOps/s $\color{#35bf28}+3.45\%$
test_empty[True] 0.4476ms 0.3446ms 2.9016 KOps/s 2.8762 KOps/s $\color{#35bf28}+0.88\%$
test_empty[False] 2.6910μs 0.9068μs 1.1028 MOps/s 1.0787 MOps/s $\color{#35bf28}+2.24\%$
test_to 0.1034ms 77.3180μs 12.9336 KOps/s 13.1304 KOps/s $\color{#d91a1a}-1.50\%$
test_to_nonblocking 0.2619ms 68.5577μs 14.5863 KOps/s 16.1856 KOps/s $\textbf{\color{#d91a1a}-9.88\%}$
test_unbind_speed 1.5143ms 0.2818ms 3.5489 KOps/s 3.8040 KOps/s $\textbf{\color{#d91a1a}-6.71\%}$
test_unbind_speed_stack0 0.3525ms 0.2647ms 3.7777 KOps/s 3.7809 KOps/s $\color{#d91a1a}-0.08\%$
test_unbind_speed_stack1 77.2762ms 0.8000ms 1.2501 KOps/s 1.2394 KOps/s $\color{#35bf28}+0.86\%$
test_split 76.0972ms 1.7360ms 576.0423 Ops/s 593.8823 Ops/s $\color{#d91a1a}-3.00\%$
test_chunk 76.6368ms 1.7368ms 575.7721 Ops/s 594.7506 Ops/s $\color{#d91a1a}-3.19\%$
test_creation[device0] 0.2393ms 63.1082μs 15.8458 KOps/s 17.1616 KOps/s $\textbf{\color{#d91a1a}-7.67\%}$
test_creation_from_tensor 0.2520ms 59.8508μs 16.7082 KOps/s 17.9332 KOps/s $\textbf{\color{#d91a1a}-6.83\%}$
test_add_one[memmap_tensor0] 86.8920μs 7.1869μs 139.1420 KOps/s 148.7567 KOps/s $\textbf{\color{#d91a1a}-6.46\%}$
test_contiguous[memmap_tensor0] 26.6810μs 0.7066μs 1.4153 MOps/s 1.4199 MOps/s $\color{#d91a1a}-0.32\%$
test_stack[memmap_tensor0] 25.8700μs 5.1521μs 194.0947 KOps/s 207.4559 KOps/s $\textbf{\color{#d91a1a}-6.44\%}$
test_memmaptd_index 1.1156ms 0.3123ms 3.2025 KOps/s 3.3539 KOps/s $\color{#d91a1a}-4.51\%$
test_memmaptd_index_astensor 0.6548ms 0.3827ms 2.6129 KOps/s 2.6992 KOps/s $\color{#d91a1a}-3.20\%$
test_memmaptd_index_op 1.2465ms 0.7115ms 1.4056 KOps/s 1.4975 KOps/s $\textbf{\color{#d91a1a}-6.14\%}$
test_serialize_model 0.1838s 0.1112s 8.9924 Ops/s 8.5882 Ops/s $\color{#35bf28}+4.71\%$
test_serialize_model_pickle 1.3482s 1.2360s 0.8090 Ops/s 0.8082 Ops/s $\color{#35bf28}+0.11\%$
test_serialize_weights 0.1784s 0.1090s 9.1765 Ops/s 8.6571 Ops/s $\textbf{\color{#35bf28}+6.00\%}$
test_serialize_weights_returnearly 0.2505s 98.7404ms 10.1276 Ops/s 9.9087 Ops/s $\color{#35bf28}+2.21\%$
test_serialize_weights_pickle 1.3571s 1.2485s 0.8010 Ops/s 0.8008 Ops/s $\color{#35bf28}+0.01\%$
test_reshape_pytree 0.2065ms 27.7799μs 35.9972 KOps/s 36.9224 KOps/s $\color{#d91a1a}-2.51\%$
test_reshape_td 0.1838ms 36.9152μs 27.0891 KOps/s 30.1177 KOps/s $\textbf{\color{#d91a1a}-10.06\%}$
test_view_pytree 0.2638ms 26.7077μs 37.4424 KOps/s 37.9096 KOps/s $\color{#d91a1a}-1.23\%$
test_view_td 85.0510μs 36.2879μs 27.5574 KOps/s 28.3060 KOps/s $\color{#d91a1a}-2.64\%$
test_unbind_pytree 0.1788ms 32.3603μs 30.9020 KOps/s 30.6224 KOps/s $\color{#35bf28}+0.91\%$
test_unbind_td 0.4821ms 41.6533μs 24.0077 KOps/s 23.3100 KOps/s $\color{#35bf28}+2.99\%$
test_split_pytree 0.1465ms 35.8977μs 27.8569 KOps/s 27.2232 KOps/s $\color{#35bf28}+2.33\%$
test_split_td 0.4101ms 43.4889μs 22.9944 KOps/s 25.5946 KOps/s $\textbf{\color{#d91a1a}-10.16\%}$
test_add_pytree 0.1566ms 38.4111μs 26.0341 KOps/s 26.2129 KOps/s $\color{#d91a1a}-0.68\%$
test_add_td 0.1847ms 51.1918μs 19.5344 KOps/s 18.7857 KOps/s $\color{#35bf28}+3.99\%$
test_distributed 0.2269ms 66.5414μs 15.0282 KOps/s 14.1912 KOps/s $\textbf{\color{#35bf28}+5.90\%}$
test_tdmodule 89.0020μs 15.5947μs 64.1243 KOps/s 62.5668 KOps/s $\color{#35bf28}+2.49\%$
test_tdmodule_dispatch 51.7610μs 30.7593μs 32.5105 KOps/s 32.0462 KOps/s $\color{#35bf28}+1.45\%$
test_tdseq 42.5610μs 17.5437μs 57.0007 KOps/s 55.6565 KOps/s $\color{#35bf28}+2.42\%$
test_tdseq_dispatch 0.1273ms 34.3752μs 29.0907 KOps/s 28.9227 KOps/s $\color{#35bf28}+0.58\%$
test_instantiation_functorch 1.6500ms 1.5439ms 647.7237 Ops/s 653.7862 Ops/s $\color{#d91a1a}-0.93\%$
test_instantiation_td 80.4943ms 1.1281ms 886.4604 Ops/s 960.4457 Ops/s $\textbf{\color{#d91a1a}-7.70\%}$
test_exec_functorch 0.2469ms 0.1484ms 6.7373 KOps/s 6.7981 KOps/s $\color{#d91a1a}-0.89\%$
test_exec_functional_call 0.3117ms 0.1342ms 7.4542 KOps/s 7.4456 KOps/s $\color{#35bf28}+0.12\%$
test_exec_td 0.3035ms 0.1333ms 7.5009 KOps/s 7.1129 KOps/s $\textbf{\color{#35bf28}+5.45\%}$
test_exec_td_decorator 0.7061ms 0.2059ms 4.8563 KOps/s 4.8835 KOps/s $\color{#d91a1a}-0.56\%$
test_vmap_mlp_speed[True-True] 0.7343ms 0.5732ms 1.7446 KOps/s 1.7116 KOps/s $\color{#35bf28}+1.93\%$
test_vmap_mlp_speed[True-False] 0.7680ms 0.5877ms 1.7015 KOps/s 1.7511 KOps/s $\color{#d91a1a}-2.83\%$
test_vmap_mlp_speed[False-True] 0.6560ms 0.5013ms 1.9948 KOps/s 1.9018 KOps/s $\color{#35bf28}+4.89\%$
test_vmap_mlp_speed[False-False] 0.6766ms 0.5156ms 1.9395 KOps/s 1.8944 KOps/s $\color{#35bf28}+2.38\%$
test_vmap_mlp_speed_decorator[True-True] 0.7974ms 0.6337ms 1.5780 KOps/s 1.5763 KOps/s $\color{#35bf28}+0.11\%$
test_vmap_mlp_speed_decorator[True-False] 0.9853ms 0.6409ms 1.5604 KOps/s 1.5774 KOps/s $\color{#d91a1a}-1.08\%$
test_vmap_mlp_speed_decorator[False-True] 0.7734ms 0.5676ms 1.7619 KOps/s 1.7972 KOps/s $\color{#d91a1a}-1.96\%$
test_vmap_mlp_speed_decorator[False-False] 0.7085ms 0.5568ms 1.7960 KOps/s 1.7922 KOps/s $\color{#35bf28}+0.21\%$
test_vmap_transformer_speed[True-True] 7.8264ms 7.4338ms 134.5210 Ops/s 134.2660 Ops/s $\color{#35bf28}+0.19\%$
test_vmap_transformer_speed[True-False] 7.7015ms 7.4246ms 134.6868 Ops/s 134.0029 Ops/s $\color{#35bf28}+0.51\%$
test_vmap_transformer_speed[False-True] 7.6549ms 7.3858ms 135.3948 Ops/s 135.5157 Ops/s $\color{#d91a1a}-0.09\%$
test_vmap_transformer_speed[False-False] 7.6343ms 7.3506ms 136.0429 Ops/s 135.4128 Ops/s $\color{#35bf28}+0.47\%$
test_vmap_transformer_speed_decorator[True-True] 18.7094ms 18.0621ms 55.3647 Ops/s 55.0832 Ops/s $\color{#35bf28}+0.51\%$
test_vmap_transformer_speed_decorator[True-False] 18.9947ms 18.0127ms 55.5164 Ops/s 55.2445 Ops/s $\color{#35bf28}+0.49\%$
test_vmap_transformer_speed_decorator[False-True] 18.5812ms 17.9399ms 55.7415 Ops/s 55.5202 Ops/s $\color{#35bf28}+0.40\%$
test_vmap_transformer_speed_decorator[False-False] 18.6116ms 17.9713ms 55.6442 Ops/s 55.5646 Ops/s $\color{#35bf28}+0.14\%$
test_to_module_speed[True] 2.0421ms 1.5260ms 655.3003 Ops/s 649.0567 Ops/s $\color{#35bf28}+0.96\%$
test_to_module_speed[False] 1.6361ms 1.5199ms 657.9528 Ops/s 656.8561 Ops/s $\color{#35bf28}+0.17\%$
test_tc_init 0.1525ms 27.5495μs 36.2983 KOps/s 37.8331 KOps/s $\color{#d91a1a}-4.06\%$
test_tc_init_nested 0.2460ms 60.7498μs 16.4609 KOps/s 17.0533 KOps/s $\color{#d91a1a}-3.47\%$
test_tc_first_layer_tensor 4.7851μs 0.3606μs 2.7731 MOps/s 2.7901 MOps/s $\color{#d91a1a}-0.61\%$
test_tc_first_layer_nontensor 19.2012μs 0.3935μs 2.5411 MOps/s 2.5447 MOps/s $\color{#d91a1a}-0.14\%$
test_tc_second_layer_tensor 38.7988μs 0.9679μs 1.0332 MOps/s 955.2992 KOps/s $\textbf{\color{#35bf28}+8.15\%}$
test_tc_second_layer_nontensor 32.8390μs 0.8292μs 1.2060 MOps/s 1.2313 MOps/s $\color{#d91a1a}-2.06\%$
test_unbind 98.3945ms 6.8812ms 145.3233 Ops/s 130.0184 Ops/s $\textbf{\color{#35bf28}+11.77\%}$
test_full_like 14.6262ms 13.6215ms 73.4135 Ops/s 86.5132 Ops/s $\textbf{\color{#d91a1a}-15.14\%}$
test_zeros_like 8.5366ms 7.9341ms 126.0375 Ops/s 127.1017 Ops/s $\color{#d91a1a}-0.84\%$
test_ones_like 8.3863ms 7.9263ms 126.1616 Ops/s 126.2756 Ops/s $\color{#d91a1a}-0.09\%$
test_clone 10.1899ms 9.6039ms 104.1248 Ops/s 103.7391 Ops/s $\color{#35bf28}+0.37\%$
test_squeeze 0.1764ms 11.8435μs 84.4345 KOps/s 92.6865 KOps/s $\textbf{\color{#d91a1a}-8.90\%}$
test_unsqueeze 0.1604ms 55.0490μs 18.1656 KOps/s 19.5989 KOps/s $\textbf{\color{#d91a1a}-7.31\%}$
test_split 0.2379ms 0.1024ms 9.7636 KOps/s 10.0064 KOps/s $\color{#d91a1a}-2.43\%$
test_permute 0.2899ms 0.1156ms 8.6521 KOps/s 9.0854 KOps/s $\color{#d91a1a}-4.77\%$
test_stack 28.6865ms 27.8822ms 35.8651 Ops/s 36.0053 Ops/s $\color{#d91a1a}-0.39\%$
test_cat 28.4044ms 27.7436ms 36.0443 Ops/s 36.1842 Ops/s $\color{#d91a1a}-0.39\%$

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants