[BugFix] Fix map test with fork on cuda

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 127. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	39.8750μs	16.8405μs	59.3805 KOps/s	58.1149 KOps/s	$\color{#35bf28}+2.18\%$
test_plain_set_stack_nested	39.3740μs	16.2793μs	61.4275 KOps/s	57.8638 KOps/s	$\textbf{\color{#35bf28}+6.16\%}$
test_plain_set_nested_inplace	55.5640μs	18.8537μs	53.0399 KOps/s	51.7607 KOps/s	$\color{#35bf28}+2.47\%$
test_plain_set_stack_nested_inplace	61.3040μs	18.8106μs	53.1615 KOps/s	52.1840 KOps/s	$\color{#35bf28}+1.87\%$
test_items	20.0980μs	2.6534μs	376.8736 KOps/s	390.6741 KOps/s	$\color{#d91a1a}-3.53\%$
test_items_nested	1.1588ms	0.2649ms	3.7748 KOps/s	3.7637 KOps/s	$\color{#35bf28}+0.29\%$
test_items_nested_locked	0.4898ms	0.2679ms	3.7328 KOps/s	3.6629 KOps/s	$\color{#35bf28}+1.91\%$
test_items_nested_leaf	0.1649ms	77.0393μs	12.9804 KOps/s	13.0034 KOps/s	$\color{#d91a1a}-0.18\%$
test_items_stack_nested	0.4956ms	0.2632ms	3.7990 KOps/s	3.7277 KOps/s	$\color{#35bf28}+1.92\%$
test_items_stack_nested_leaf	0.4491ms	79.9859μs	12.5022 KOps/s	12.4837 KOps/s	$\color{#35bf28}+0.15\%$
test_items_stack_nested_locked	0.4760ms	0.2666ms	3.7511 KOps/s	3.6774 KOps/s	$\color{#35bf28}+2.00\%$
test_keys	30.4370μs	3.9911μs	250.5546 KOps/s	257.5265 KOps/s	$\color{#d91a1a}-2.71\%$
test_keys_nested	0.2314ms	0.1400ms	7.1452 KOps/s	7.2510 KOps/s	$\color{#d91a1a}-1.46\%$
test_keys_nested_locked	1.8833ms	0.1453ms	6.8817 KOps/s	6.9425 KOps/s	$\color{#d91a1a}-0.88\%$
test_keys_nested_leaf	0.5844ms	0.1229ms	8.1348 KOps/s	8.5165 KOps/s	$\color{#d91a1a}-4.48\%$
test_keys_stack_nested	0.2344ms	0.1410ms	7.0917 KOps/s	7.2481 KOps/s	$\color{#d91a1a}-2.16\%$
test_keys_stack_nested_leaf	0.2188ms	0.1192ms	8.3866 KOps/s	8.5421 KOps/s	$\color{#d91a1a}-1.82\%$
test_keys_stack_nested_locked	0.2845ms	0.1452ms	6.8848 KOps/s	6.8069 KOps/s	$\color{#35bf28}+1.14\%$
test_values	4.3622μs	1.1373μs	879.2463 KOps/s	860.6742 KOps/s	$\color{#35bf28}+2.16\%$
test_values_nested	0.1014ms	51.2823μs	19.4999 KOps/s	19.6212 KOps/s	$\color{#d91a1a}-0.62\%$
test_values_nested_locked	94.8070μs	51.2432μs	19.5148 KOps/s	19.4623 KOps/s	$\color{#35bf28}+0.27\%$
test_values_nested_leaf	0.2919ms	46.6346μs	21.4433 KOps/s	21.5943 KOps/s	$\color{#d91a1a}-0.70\%$
test_values_stack_nested	0.1075ms	51.2852μs	19.4988 KOps/s	19.4778 KOps/s	$\color{#35bf28}+0.11\%$
test_values_stack_nested_leaf	87.7040μs	46.4972μs	21.5067 KOps/s	21.7387 KOps/s	$\color{#d91a1a}-1.07\%$
test_values_stack_nested_locked	0.1014ms	51.5733μs	19.3899 KOps/s	19.2191 KOps/s	$\color{#35bf28}+0.89\%$
test_membership	30.8880μs	1.3795μs	724.9075 KOps/s	754.1845 KOps/s	$\color{#d91a1a}-3.88\%$
test_membership_nested	47.0170μs	3.5180μs	284.2543 KOps/s	289.7407 KOps/s	$\color{#d91a1a}-1.89\%$
test_membership_nested_leaf	28.9040μs	3.5315μs	283.1619 KOps/s	286.8534 KOps/s	$\color{#d91a1a}-1.29\%$
test_membership_stacked_nested	29.1250μs	3.4793μs	287.4131 KOps/s	275.8226 KOps/s	$\color{#35bf28}+4.20\%$
test_membership_stacked_nested_leaf	21.9510μs	3.5125μs	284.6965 KOps/s	288.6067 KOps/s	$\color{#d91a1a}-1.35\%$
test_membership_nested_last	19.7270μs	4.2895μs	233.1289 KOps/s	235.8267 KOps/s	$\color{#d91a1a}-1.14\%$
test_membership_nested_leaf_last	23.4630μs	4.3008μs	232.5160 KOps/s	234.5349 KOps/s	$\color{#d91a1a}-0.86\%$
test_membership_stacked_nested_last	29.5960μs	4.2455μs	235.5444 KOps/s	236.8386 KOps/s	$\color{#d91a1a}-0.55\%$
test_membership_stacked_nested_leaf_last	28.3030μs	4.2780μs	233.7546 KOps/s	235.5729 KOps/s	$\color{#d91a1a}-0.77\%$
test_nested_getleaf	44.6830μs	10.6585μs	93.8218 KOps/s	92.1189 KOps/s	$\color{#35bf28}+1.85\%$
test_nested_get	60.0720μs	10.1566μs	98.4577 KOps/s	99.2430 KOps/s	$\color{#d91a1a}-0.79\%$
test_stacked_getleaf	34.8150μs	10.4778μs	95.4399 KOps/s	94.1488 KOps/s	$\color{#35bf28}+1.37\%$
test_stacked_get	34.5730μs	10.0841μs	99.1656 KOps/s	97.6568 KOps/s	$\color{#35bf28}+1.55\%$
test_nested_getitemleaf	39.3530μs	11.2074μs	89.2264 KOps/s	87.1033 KOps/s	$\color{#35bf28}+2.44\%$
test_nested_getitem	34.7040μs	10.4056μs	96.1018 KOps/s	96.1418 KOps/s	$\color{#d91a1a}-0.04\%$
test_stacked_getitemleaf	35.0060μs	11.2062μs	89.2360 KOps/s	89.0138 KOps/s	$\color{#35bf28}+0.25\%$
test_stacked_getitem	32.8610μs	10.3735μs	96.3997 KOps/s	97.2771 KOps/s	$\color{#d91a1a}-0.90\%$
test_lock_nested	48.7816ms	0.4068ms	2.4581 KOps/s	2.8128 KOps/s	$\textbf{\color{#d91a1a}-12.61\%}$
test_lock_stack_nested	0.5219ms	0.3194ms	3.1312 KOps/s	3.1525 KOps/s	$\color{#d91a1a}-0.68\%$
test_unlock_nested	0.7474ms	0.3605ms	2.7738 KOps/s	2.4615 KOps/s	$\textbf{\color{#35bf28}+12.69\%}$
test_unlock_stack_nested	0.5642ms	0.3249ms	3.0781 KOps/s	3.0911 KOps/s	$\color{#d91a1a}-0.42\%$
test_flatten_speed	0.1860ms	97.1267μs	10.2958 KOps/s	10.2418 KOps/s	$\color{#35bf28}+0.53\%$
test_unflatten_speed	0.7274ms	0.4118ms	2.4284 KOps/s	2.3994 KOps/s	$\color{#35bf28}+1.21\%$
test_common_ops	4.1796ms	0.6959ms	1.4370 KOps/s	1.4074 KOps/s	$\color{#35bf28}+2.10\%$
test_creation	26.0890μs	2.0019μs	499.5252 KOps/s	527.2850 KOps/s	$\textbf{\color{#d91a1a}-5.26\%}$
test_creation_empty	37.1090μs	9.0775μs	110.1621 KOps/s	95.0774 KOps/s	$\textbf{\color{#35bf28}+15.87\%}$
test_creation_nested_1	35.5760μs	11.8635μs	84.2918 KOps/s	75.1711 KOps/s	$\textbf{\color{#35bf28}+12.13\%}$
test_creation_nested_2	40.3550μs	15.2727μs	65.4764 KOps/s	59.8508 KOps/s	$\textbf{\color{#35bf28}+9.40\%}$
test_clone	71.8740μs	13.8808μs	72.0422 KOps/s	71.8087 KOps/s	$\color{#35bf28}+0.33\%$
test_getitem[int]	33.3120μs	11.7725μs	84.9439 KOps/s	86.7141 KOps/s	$\color{#d91a1a}-2.04\%$
test_getitem[slice_int]	61.6750μs	23.5285μs	42.5016 KOps/s	44.7651 KOps/s	$\textbf{\color{#d91a1a}-5.06\%}$
test_getitem[range]	96.5500μs	65.2938μs	15.3154 KOps/s	16.5468 KOps/s	$\textbf{\color{#d91a1a}-7.44\%}$
test_getitem[tuple]	57.3770μs	19.5594μs	51.1262 KOps/s	52.7220 KOps/s	$\color{#d91a1a}-3.03\%$
test_getitem[list]	0.1089ms	41.5384μs	24.0741 KOps/s	24.1885 KOps/s	$\color{#d91a1a}-0.47\%$
test_setitem_dim[int]	63.2980μs	34.5216μs	28.9674 KOps/s	28.6481 KOps/s	$\color{#35bf28}+1.11\%$
test_setitem_dim[slice_int]	98.6040μs	61.6244μs	16.2273 KOps/s	16.2200 KOps/s	$\color{#35bf28}+0.04\%$
test_setitem_dim[range]	0.1433ms	87.5073μs	11.4276 KOps/s	11.7116 KOps/s	$\color{#d91a1a}-2.42\%$
test_setitem_dim[tuple]	0.1040ms	49.9223μs	20.0311 KOps/s	19.6242 KOps/s	$\color{#35bf28}+2.07\%$
test_setitem	53.9600μs	19.7135μs	50.7267 KOps/s	48.4367 KOps/s	$\color{#35bf28}+4.73\%$
test_set	54.1910μs	19.5018μs	51.2772 KOps/s	50.5136 KOps/s	$\color{#35bf28}+1.51\%$
test_set_shared	3.9034ms	0.1435ms	6.9682 KOps/s	6.9793 KOps/s	$\color{#d91a1a}-0.16\%$
test_update	80.9210μs	20.2073μs	49.4870 KOps/s	45.5238 KOps/s	$\textbf{\color{#35bf28}+8.71\%}$
test_update_nested	72.0680μs	28.9866μs	34.4986 KOps/s	33.9837 KOps/s	$\color{#35bf28}+1.52\%$
test_update__nested	93.0830μs	25.5350μs	39.1619 KOps/s	37.7156 KOps/s	$\color{#35bf28}+3.83\%$
test_set_nested	66.0230μs	21.2288μs	47.1058 KOps/s	46.0145 KOps/s	$\color{#35bf28}+2.37\%$
test_set_nested_new	63.1680μs	25.5845μs	39.0861 KOps/s	38.1522 KOps/s	$\color{#35bf28}+2.45\%$
test_select	0.1084ms	41.6086μs	24.0335 KOps/s	24.4280 KOps/s	$\color{#d91a1a}-1.61\%$
test_select_nested	0.1401ms	61.1798μs	16.3453 KOps/s	16.1845 KOps/s	$\color{#35bf28}+0.99\%$
test_exclude_nested	0.2360ms	0.1224ms	8.1710 KOps/s	8.3580 KOps/s	$\color{#d91a1a}-2.24\%$
test_empty[True]	0.4854ms	0.4021ms	2.4872 KOps/s	2.4964 KOps/s	$\color{#d91a1a}-0.37\%$
test_empty[False]	6.0434μs	1.1494μs	870.0008 KOps/s	867.7324 KOps/s	$\color{#35bf28}+0.26\%$
test_unbind_speed	0.3589ms	0.2610ms	3.8314 KOps/s	3.6860 KOps/s	$\color{#35bf28}+3.94\%$
test_unbind_speed_stack0	4.5916ms	0.2721ms	3.6758 KOps/s	3.8284 KOps/s	$\color{#d91a1a}-3.99\%$
test_unbind_speed_stack1	65.2879ms	0.7410ms	1.3496 KOps/s	1.2525 KOps/s	$\textbf{\color{#35bf28}+7.75\%}$
test_split	68.6510ms	1.6292ms	613.7831 Ops/s	616.5034 Ops/s	$\color{#d91a1a}-0.44\%$
test_chunk	67.7464ms	1.6340ms	611.9977 Ops/s	615.1264 Ops/s	$\color{#d91a1a}-0.51\%$
test_creation[device0]	0.1890ms	0.1043ms	9.5861 KOps/s	9.5522 KOps/s	$\color{#35bf28}+0.35\%$
test_creation_from_tensor	3.7267ms	85.2445μs	11.7310 KOps/s	11.9841 KOps/s	$\color{#d91a1a}-2.11\%$
test_add_one[memmap_tensor0]	68.4070μs	5.5893μs	178.9130 KOps/s	175.3892 KOps/s	$\color{#35bf28}+2.01\%$
test_contiguous[memmap_tensor0]	10.7300μs	0.6327μs	1.5805 MOps/s	1.5861 MOps/s	$\color{#d91a1a}-0.35\%$
test_stack[memmap_tensor0]	28.2530μs	3.5887μs	278.6524 KOps/s	275.6703 KOps/s	$\color{#35bf28}+1.08\%$
test_memmaptd_index	1.0091ms	0.2466ms	4.0558 KOps/s	3.9624 KOps/s	$\color{#35bf28}+2.36\%$
test_memmaptd_index_astensor	0.6565ms	0.3216ms	3.1095 KOps/s	3.0927 KOps/s	$\color{#35bf28}+0.54\%$
test_memmaptd_index_op	1.1904ms	0.5880ms	1.7006 KOps/s	1.6196 KOps/s	$\textbf{\color{#35bf28}+5.00\%}$
test_serialize_model	0.1705s	0.1092s	9.1546 Ops/s	8.8828 Ops/s	$\color{#35bf28}+3.06\%$
test_serialize_model_pickle	0.4641s	0.3795s	2.6348 Ops/s	2.6127 Ops/s	$\color{#35bf28}+0.84\%$
test_serialize_weights	0.1053s	99.4160ms	10.0587 Ops/s	9.0459 Ops/s	$\textbf{\color{#35bf28}+11.20\%}$
test_serialize_weights_returnearly	0.1889s	0.1367s	7.3149 Ops/s	8.0903 Ops/s	$\textbf{\color{#d91a1a}-9.58\%}$
test_serialize_weights_pickle	1.0859s	0.6212s	1.6098 Ops/s	1.5546 Ops/s	$\color{#35bf28}+3.55\%$
test_serialize_weights_filesystem	0.1562s	97.7867ms	10.2263 Ops/s	10.9581 Ops/s	$\textbf{\color{#d91a1a}-6.68\%}$
test_serialize_model_filesystem	0.1006s	92.3799ms	10.8249 Ops/s	9.8307 Ops/s	$\textbf{\color{#35bf28}+10.11\%}$
test_reshape_pytree	67.8570μs	25.7005μs	38.9097 KOps/s	39.8228 KOps/s	$\color{#d91a1a}-2.29\%$
test_reshape_td	78.8370μs	33.6383μs	29.7281 KOps/s	30.1104 KOps/s	$\color{#d91a1a}-1.27\%$
test_view_pytree	55.3530μs	25.2757μs	39.5637 KOps/s	39.5767 KOps/s	$\color{#d91a1a}-0.03\%$
test_view_td	0.1360ms	37.3261μs	26.7909 KOps/s	26.3191 KOps/s	$\color{#35bf28}+1.79\%$
test_unbind_pytree	63.8900μs	29.3536μs	34.0674 KOps/s	33.6351 KOps/s	$\color{#35bf28}+1.29\%$
test_unbind_td	0.3689ms	38.9699μs	25.6609 KOps/s	25.8813 KOps/s	$\color{#d91a1a}-0.85\%$
test_split_pytree	77.4150μs	30.4977μs	32.7894 KOps/s	34.3517 KOps/s	$\color{#d91a1a}-4.55\%$
test_split_td	0.4540ms	45.8036μs	21.8323 KOps/s	23.7529 KOps/s	$\textbf{\color{#d91a1a}-8.09\%}$
test_add_pytree	0.2394ms	36.7156μs	27.2364 KOps/s	28.4809 KOps/s	$\color{#d91a1a}-4.37\%$
test_add_td	0.1320ms	56.3951μs	17.7320 KOps/s	18.4410 KOps/s	$\color{#d91a1a}-3.84\%$
test_distributed	0.2144ms	0.1002ms	9.9803 KOps/s	9.7952 KOps/s	$\color{#35bf28}+1.89\%$
test_tdmodule	28.7240μs	17.0914μs	58.5089 KOps/s	57.0842 KOps/s	$\color{#35bf28}+2.50\%$
test_tdmodule_dispatch	76.4630μs	33.9664μs	29.4409 KOps/s	28.0972 KOps/s	$\color{#35bf28}+4.78\%$
test_tdseq	32.4610μs	19.2606μs	51.9193 KOps/s	47.7509 KOps/s	$\textbf{\color{#35bf28}+8.73\%}$
test_tdseq_dispatch	66.5240μs	38.1280μs	26.2274 KOps/s	24.6302 KOps/s	$\textbf{\color{#35bf28}+6.49\%}$
test_instantiation_functorch	1.9055ms	1.3549ms	738.0774 Ops/s	748.4108 Ops/s	$\color{#d91a1a}-1.38\%$
test_instantiation_td	64.8389ms	1.1092ms	901.5708 Ops/s	965.5844 Ops/s	$\textbf{\color{#d91a1a}-6.63\%}$
test_exec_functorch	0.2995ms	0.1643ms	6.0864 KOps/s	6.0754 KOps/s	$\color{#35bf28}+0.18\%$
test_exec_functional_call	0.2623ms	0.1531ms	6.5299 KOps/s	6.6104 KOps/s	$\color{#d91a1a}-1.22\%$
test_exec_td	0.3592ms	0.1478ms	6.7670 KOps/s	6.8019 KOps/s	$\color{#d91a1a}-0.51\%$
test_exec_td_decorator	0.5715ms	0.2244ms	4.4571 KOps/s	4.5392 KOps/s	$\color{#d91a1a}-1.81\%$
test_vmap_mlp_speed[True-True]	0.7639ms	0.4928ms	2.0291 KOps/s	2.0330 KOps/s	$\color{#d91a1a}-0.19\%$
test_vmap_mlp_speed[True-False]	1.0606ms	0.4895ms	2.0429 KOps/s	2.0399 KOps/s	$\color{#35bf28}+0.15\%$
test_vmap_mlp_speed[False-True]	0.7894ms	0.4020ms	2.4875 KOps/s	2.4852 KOps/s	$\color{#35bf28}+0.09\%$
test_vmap_mlp_speed[False-False]	0.9310ms	0.4008ms	2.4952 KOps/s	2.4930 KOps/s	$\color{#35bf28}+0.09\%$
test_vmap_mlp_speed_decorator[True-True]	1.5633ms	0.5750ms	1.7392 KOps/s	1.7846 KOps/s	$\color{#d91a1a}-2.55\%$
test_vmap_mlp_speed_decorator[True-False]	0.8374ms	0.5576ms	1.7934 KOps/s	1.7929 KOps/s	$\color{#35bf28}+0.03\%$
test_vmap_mlp_speed_decorator[False-True]	0.7235ms	0.4644ms	2.1531 KOps/s	2.1750 KOps/s	$\color{#d91a1a}-1.01\%$
test_vmap_mlp_speed_decorator[False-False]	1.0150ms	0.4655ms	2.1482 KOps/s	2.1681 KOps/s	$\color{#d91a1a}-0.92\%$
test_to_module_speed[True]	2.0757ms	1.7075ms	585.6447 Ops/s	592.3807 Ops/s	$\color{#d91a1a}-1.14\%$
test_to_module_speed[False]	2.5936ms	1.6831ms	594.1538 Ops/s	601.4312 Ops/s	$\color{#d91a1a}-1.21\%$