[BugFix] consistent use of non_blocking in tensordict and torch.Tensor

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 127. Improved: $\large\color{#35bf28}18$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	46.0660μs	16.0714μs	62.2224 KOps/s	60.1791 KOps/s	$\color{#35bf28}+3.40\%$
test_plain_set_stack_nested	38.6630μs	15.9613μs	62.6517 KOps/s	58.9656 KOps/s	$\textbf{\color{#35bf28}+6.25\%}$
test_plain_set_nested_inplace	51.2960μs	18.7123μs	53.4408 KOps/s	52.3316 KOps/s	$\color{#35bf28}+2.12\%$
test_plain_set_stack_nested_inplace	40.0650μs	19.0158μs	52.5877 KOps/s	51.9327 KOps/s	$\color{#35bf28}+1.26\%$
test_items	28.6340μs	2.4990μs	400.1585 KOps/s	392.8515 KOps/s	$\color{#35bf28}+1.86\%$
test_items_nested	0.4895ms	0.2690ms	3.7170 KOps/s	3.7101 KOps/s	$\color{#35bf28}+0.19\%$
test_items_nested_locked	6.6776ms	0.2693ms	3.7130 KOps/s	3.6773 KOps/s	$\color{#35bf28}+0.97\%$
test_items_nested_leaf	0.1488ms	76.7337μs	13.0321 KOps/s	12.7672 KOps/s	$\color{#35bf28}+2.07\%$
test_items_stack_nested	1.3256ms	0.2715ms	3.6830 KOps/s	3.6542 KOps/s	$\color{#35bf28}+0.79\%$
test_items_stack_nested_leaf	0.1525ms	78.5861μs	12.7249 KOps/s	13.1298 KOps/s	$\color{#d91a1a}-3.08\%$
test_items_stack_nested_locked	0.3991ms	0.2722ms	3.6743 KOps/s	3.6420 KOps/s	$\color{#35bf28}+0.89\%$
test_keys	32.2300μs	3.9301μs	254.4457 KOps/s	253.7211 KOps/s	$\color{#35bf28}+0.29\%$
test_keys_nested	0.2377ms	0.1358ms	7.3632 KOps/s	7.3512 KOps/s	$\color{#35bf28}+0.16\%$
test_keys_nested_locked	0.8783ms	0.1408ms	7.1007 KOps/s	7.1427 KOps/s	$\color{#d91a1a}-0.59\%$
test_keys_nested_leaf	0.1984ms	0.1152ms	8.6780 KOps/s	8.7017 KOps/s	$\color{#d91a1a}-0.27\%$
test_keys_stack_nested	0.2581ms	0.1370ms	7.3008 KOps/s	7.4877 KOps/s	$\color{#d91a1a}-2.50\%$
test_keys_stack_nested_leaf	0.1944ms	0.1149ms	8.7055 KOps/s	8.8714 KOps/s	$\color{#d91a1a}-1.87\%$
test_keys_stack_nested_locked	0.2690ms	0.1410ms	7.0911 KOps/s	7.2576 KOps/s	$\color{#d91a1a}-2.29\%$
test_values	7.7620μs	1.1585μs	863.1550 KOps/s	862.4270 KOps/s	$\color{#35bf28}+0.08\%$
test_values_nested	0.1050ms	50.6321μs	19.7503 KOps/s	19.5438 KOps/s	$\color{#35bf28}+1.06\%$
test_values_nested_locked	91.2610μs	50.5478μs	19.7832 KOps/s	19.6746 KOps/s	$\color{#35bf28}+0.55\%$
test_values_nested_leaf	93.5150μs	45.7974μs	21.8353 KOps/s	21.8742 KOps/s	$\color{#d91a1a}-0.18\%$
test_values_stack_nested	0.1432ms	51.7879μs	19.3095 KOps/s	19.2234 KOps/s	$\color{#35bf28}+0.45\%$
test_values_stack_nested_leaf	0.1004ms	45.7943μs	21.8368 KOps/s	22.2885 KOps/s	$\color{#d91a1a}-2.03\%$
test_values_stack_nested_locked	83.7670μs	51.3221μs	19.4848 KOps/s	19.4272 KOps/s	$\color{#35bf28}+0.30\%$
test_membership	17.1720μs	1.3590μs	735.8101 KOps/s	762.7415 KOps/s	$\color{#d91a1a}-3.53\%$
test_membership_nested	28.9140μs	3.4539μs	289.5249 KOps/s	288.9927 KOps/s	$\color{#35bf28}+0.18\%$
test_membership_nested_leaf	43.7820μs	3.4698μs	288.1975 KOps/s	282.4631 KOps/s	$\color{#35bf28}+2.03\%$
test_membership_stacked_nested	29.4950μs	3.4930μs	286.2843 KOps/s	281.2370 KOps/s	$\color{#35bf28}+1.79\%$
test_membership_stacked_nested_leaf	32.0000μs	3.4276μs	291.7473 KOps/s	289.8649 KOps/s	$\color{#35bf28}+0.65\%$
test_membership_nested_last	29.2550μs	4.2474μs	235.4355 KOps/s	234.3747 KOps/s	$\color{#35bf28}+0.45\%$
test_membership_nested_leaf_last	56.4390μs	4.2939μs	232.8889 KOps/s	231.6506 KOps/s	$\color{#35bf28}+0.53\%$
test_membership_stacked_nested_last	28.3530μs	7.2851μs	137.2668 KOps/s	73.9942 KOps/s	$\textbf{\color{#35bf28}+85.51\%}$
test_membership_stacked_nested_leaf_last	43.5820μs	7.3169μs	136.6702 KOps/s	74.1721 KOps/s	$\textbf{\color{#35bf28}+84.26\%}$
test_nested_getleaf	40.3460μs	10.7366μs	93.1393 KOps/s	92.5121 KOps/s	$\color{#35bf28}+0.68\%$
test_nested_get	32.0700μs	10.0224μs	99.7768 KOps/s	96.6559 KOps/s	$\color{#35bf28}+3.23\%$
test_stacked_getleaf	44.4640μs	10.6192μs	94.1689 KOps/s	94.4023 KOps/s	$\color{#d91a1a}-0.25\%$
test_stacked_get	95.0380μs	10.1014μs	98.9959 KOps/s	98.3904 KOps/s	$\color{#35bf28}+0.62\%$
test_nested_getitemleaf	48.2500μs	11.2256μs	89.0819 KOps/s	87.9032 KOps/s	$\color{#35bf28}+1.34\%$
test_nested_getitem	37.2190μs	10.3996μs	96.1577 KOps/s	96.2683 KOps/s	$\color{#d91a1a}-0.11\%$
test_stacked_getitemleaf	29.5860μs	11.1651μs	89.5651 KOps/s	88.5772 KOps/s	$\color{#35bf28}+1.12\%$
test_stacked_getitem	94.5070μs	10.4661μs	95.5462 KOps/s	92.4303 KOps/s	$\color{#35bf28}+3.37\%$
test_lock_nested	50.7443ms	0.3951ms	2.5308 KOps/s	2.9129 KOps/s	$\textbf{\color{#d91a1a}-13.12\%}$
test_lock_stack_nested	0.4254ms	0.3025ms	3.3053 KOps/s	3.4111 KOps/s	$\color{#d91a1a}-3.10\%$
test_unlock_nested	99.8771ms	0.4499ms	2.2227 KOps/s	2.2003 KOps/s	$\color{#35bf28}+1.02\%$
test_unlock_stack_nested	0.4525ms	0.3123ms	3.2016 KOps/s	3.2945 KOps/s	$\color{#d91a1a}-2.82\%$
test_flatten_speed	0.5859ms	92.5311μs	10.8072 KOps/s	10.8323 KOps/s	$\color{#d91a1a}-0.23\%$
test_unflatten_speed	0.6103ms	0.4097ms	2.4409 KOps/s	2.4842 KOps/s	$\color{#d91a1a}-1.74\%$
test_common_ops	4.8074ms	0.6764ms	1.4785 KOps/s	1.4060 KOps/s	$\textbf{\color{#35bf28}+5.15\%}$
test_creation	14.6780μs	1.9086μs	523.9375 KOps/s	537.1130 KOps/s	$\color{#d91a1a}-2.45\%$
test_creation_empty	33.4820μs	8.7742μs	113.9710 KOps/s	99.6015 KOps/s	$\textbf{\color{#35bf28}+14.43\%}$
test_creation_nested_1	40.3060μs	11.6237μs	86.0311 KOps/s	79.3169 KOps/s	$\textbf{\color{#35bf28}+8.47\%}$
test_creation_nested_2	41.2570μs	14.8691μs	67.2534 KOps/s	61.4990 KOps/s	$\textbf{\color{#35bf28}+9.36\%}$
test_clone	0.1097ms	13.6995μs	72.9953 KOps/s	73.7388 KOps/s	$\color{#d91a1a}-1.01\%$
test_getitem[int]	29.6250μs	11.4072μs	87.6642 KOps/s	86.9499 KOps/s	$\color{#35bf28}+0.82\%$
test_getitem[slice_int]	93.9290μs	22.7518μs	43.9525 KOps/s	42.7840 KOps/s	$\color{#35bf28}+2.73\%$
test_getitem[range]	82.2040μs	42.5656μs	23.4932 KOps/s	23.6840 KOps/s	$\color{#d91a1a}-0.81\%$
test_getitem[tuple]	63.1480μs	18.8821μs	52.9602 KOps/s	53.6705 KOps/s	$\color{#d91a1a}-1.32\%$
test_getitem[list]	0.4537ms	38.3524μs	26.0740 KOps/s	26.0151 KOps/s	$\color{#35bf28}+0.23\%$
test_setitem_dim[int]	67.1860μs	32.3917μs	30.8721 KOps/s	28.8167 KOps/s	$\textbf{\color{#35bf28}+7.13\%}$
test_setitem_dim[slice_int]	0.1050ms	57.0606μs	17.5252 KOps/s	16.2082 KOps/s	$\textbf{\color{#35bf28}+8.13\%}$
test_setitem_dim[range]	0.1391ms	75.3641μs	13.2689 KOps/s	12.7165 KOps/s	$\color{#35bf28}+4.34\%$
test_setitem_dim[tuple]	91.6820μs	48.2449μs	20.7276 KOps/s	20.2070 KOps/s	$\color{#35bf28}+2.58\%$
test_setitem	0.1495ms	19.3586μs	51.6565 KOps/s	48.5863 KOps/s	$\textbf{\color{#35bf28}+6.32\%}$
test_set	0.1772ms	19.1330μs	52.2658 KOps/s	49.2695 KOps/s	$\textbf{\color{#35bf28}+6.08\%}$
test_set_shared	1.6746ms	0.1416ms	7.0620 KOps/s	6.9757 KOps/s	$\color{#35bf28}+1.24\%$
test_update	0.1423ms	19.7734μs	50.5729 KOps/s	44.9133 KOps/s	$\textbf{\color{#35bf28}+12.60\%}$
test_update_nested	0.1542ms	27.6864μs	36.1188 KOps/s	32.5868 KOps/s	$\textbf{\color{#35bf28}+10.84\%}$
test_update__nested	0.1385ms	26.0721μs	38.3551 KOps/s	40.3502 KOps/s	$\color{#d91a1a}-4.94\%$
test_set_nested	0.1208ms	20.1564μs	49.6121 KOps/s	45.1859 KOps/s	$\textbf{\color{#35bf28}+9.80\%}$
test_set_nested_new	0.1459ms	24.5539μs	40.7267 KOps/s	38.5447 KOps/s	$\textbf{\color{#35bf28}+5.66\%}$
test_select	1.1191ms	39.3876μs	25.3887 KOps/s	24.8411 KOps/s	$\color{#35bf28}+2.20\%$
test_select_nested	0.1194ms	59.3850μs	16.8393 KOps/s	16.6388 KOps/s	$\color{#35bf28}+1.20\%$
test_exclude_nested	0.2700ms	0.1199ms	8.3425 KOps/s	8.4730 KOps/s	$\color{#d91a1a}-1.54\%$
test_empty[True]	0.5607ms	0.3903ms	2.5620 KOps/s	2.5637 KOps/s	$\color{#d91a1a}-0.07\%$
test_empty[False]	9.6030μs	1.0612μs	942.2968 KOps/s	959.8328 KOps/s	$\color{#d91a1a}-1.83\%$
test_unbind_speed	1.8589ms	0.2507ms	3.9890 KOps/s	4.0156 KOps/s	$\color{#d91a1a}-0.66\%$
test_unbind_speed_stack0	0.4808ms	0.2440ms	4.0985 KOps/s	4.1840 KOps/s	$\color{#d91a1a}-2.04\%$
test_unbind_speed_stack1	0.1297s	0.6927ms	1.4436 KOps/s	1.4856 KOps/s	$\color{#d91a1a}-2.83\%$
test_split	1.7122ms	1.4950ms	668.9110 Ops/s	576.0954 Ops/s	$\textbf{\color{#35bf28}+16.11\%}$
test_chunk	0.1318s	1.6966ms	589.4188 Ops/s	663.9852 Ops/s	$\textbf{\color{#d91a1a}-11.23\%}$
test_creation[device0]	0.2467ms	0.1020ms	9.8000 KOps/s	9.3962 KOps/s	$\color{#35bf28}+4.30\%$
test_creation_from_tensor	5.7008ms	83.0387μs	12.0426 KOps/s	11.8533 KOps/s	$\color{#35bf28}+1.60\%$
test_add_one[memmap_tensor0]	0.1032ms	5.5758μs	179.3458 KOps/s	171.6828 KOps/s	$\color{#35bf28}+4.46\%$
test_contiguous[memmap_tensor0]	7.8950μs	0.6455μs	1.5493 MOps/s	1.5418 MOps/s	$\color{#35bf28}+0.48\%$
test_stack[memmap_tensor0]	39.7040μs	3.5487μs	281.7901 KOps/s	271.3755 KOps/s	$\color{#35bf28}+3.84\%$
test_memmaptd_index	0.9921ms	0.2443ms	4.0939 KOps/s	4.1867 KOps/s	$\color{#d91a1a}-2.22\%$
test_memmaptd_index_astensor	0.7291ms	0.3080ms	3.2464 KOps/s	3.3141 KOps/s	$\color{#d91a1a}-2.04\%$
test_memmaptd_index_op	1.1796ms	0.5805ms	1.7226 KOps/s	1.6667 KOps/s	$\color{#35bf28}+3.35\%$
test_serialize_model	0.1147s	0.1037s	9.6418 Ops/s	8.2787 Ops/s	$\textbf{\color{#35bf28}+16.47\%}$
test_serialize_model_pickle	0.4480s	0.3778s	2.6467 Ops/s	2.6246 Ops/s	$\color{#35bf28}+0.84\%$
test_serialize_weights	0.1102s	0.1019s	9.8149 Ops/s	9.6875 Ops/s	$\color{#35bf28}+1.31\%$
test_serialize_weights_returnearly	0.1355s	0.1237s	8.0819 Ops/s	6.9568 Ops/s	$\textbf{\color{#35bf28}+16.17\%}$
test_serialize_weights_pickle	0.5801s	0.4506s	2.2194 Ops/s	2.3231 Ops/s	$\color{#d91a1a}-4.46\%$
test_serialize_weights_filesystem	0.2307s	0.1127s	8.8702 Ops/s	10.9648 Ops/s	$\textbf{\color{#d91a1a}-19.10\%}$
test_serialize_model_filesystem	0.1006s	93.4403ms	10.7020 Ops/s	10.3244 Ops/s	$\color{#35bf28}+3.66\%$
test_reshape_pytree	66.5250μs	21.1236μs	47.3404 KOps/s	47.0566 KOps/s	$\color{#35bf28}+0.60\%$
test_reshape_td	74.2600μs	33.5718μs	29.7869 KOps/s	30.0081 KOps/s	$\color{#d91a1a}-0.74\%$
test_view_pytree	54.7720μs	21.0341μs	47.5418 KOps/s	46.5941 KOps/s	$\color{#35bf28}+2.03\%$
test_view_td	0.1375s	68.4285μs	14.6138 KOps/s	15.8680 KOps/s	$\textbf{\color{#d91a1a}-7.90\%}$
test_unbind_pytree	69.4900μs	24.5754μs	40.6911 KOps/s	41.1327 KOps/s	$\color{#d91a1a}-1.07\%$
test_unbind_td	0.1706s	51.6720μs	19.3529 KOps/s	27.6053 KOps/s	$\textbf{\color{#d91a1a}-29.89\%}$
test_split_pytree	56.9470μs	23.9957μs	41.6742 KOps/s	42.1310 KOps/s	$\color{#d91a1a}-1.08\%$
test_split_td	0.1274ms	41.4795μs	24.1083 KOps/s	24.3467 KOps/s	$\color{#d91a1a}-0.98\%$
test_add_pytree	0.1071ms	30.0780μs	33.2469 KOps/s	32.0342 KOps/s	$\color{#35bf28}+3.79\%$
test_add_td	0.1173ms	51.3217μs	19.4849 KOps/s	18.6348 KOps/s	$\color{#35bf28}+4.56\%$
test_distributed	0.2440ms	0.1007ms	9.9274 KOps/s	9.7970 KOps/s	$\color{#35bf28}+1.33\%$
test_tdmodule	81.9540μs	16.7677μs	59.6385 KOps/s	57.5032 KOps/s	$\color{#35bf28}+3.71\%$
test_tdmodule_dispatch	57.3970μs	33.0593μs	30.2486 KOps/s	29.4662 KOps/s	$\color{#35bf28}+2.66\%$
test_tdseq	46.5670μs	19.4814μs	51.3310 KOps/s	49.7710 KOps/s	$\color{#35bf28}+3.13\%$
test_tdseq_dispatch	74.1290μs	37.7541μs	26.4872 KOps/s	25.7731 KOps/s	$\color{#35bf28}+2.77\%$
test_instantiation_functorch	1.5830ms	1.3047ms	766.4729 Ops/s	763.5343 Ops/s	$\color{#35bf28}+0.38\%$
test_instantiation_td	1.6662ms	1.0233ms	977.2028 Ops/s	994.6530 Ops/s	$\color{#d91a1a}-1.75\%$
test_exec_functorch	0.4182ms	0.1646ms	6.0738 KOps/s	6.2512 KOps/s	$\color{#d91a1a}-2.84\%$
test_exec_functional_call	0.3173ms	0.1479ms	6.7591 KOps/s	6.8374 KOps/s	$\color{#d91a1a}-1.14\%$
test_exec_td	0.2577ms	0.1451ms	6.8904 KOps/s	7.0272 KOps/s	$\color{#d91a1a}-1.95\%$
test_exec_td_decorator	0.8829ms	0.2010ms	4.9750 KOps/s	5.0514 KOps/s	$\color{#d91a1a}-1.51\%$
test_vmap_mlp_speed[True-True]	0.7057ms	0.4720ms	2.1188 KOps/s	2.0863 KOps/s	$\color{#35bf28}+1.56\%$
test_vmap_mlp_speed[True-False]	0.7506ms	0.4685ms	2.1343 KOps/s	2.0826 KOps/s	$\color{#35bf28}+2.48\%$
test_vmap_mlp_speed[False-True]	0.6248ms	0.3842ms	2.6029 KOps/s	2.5656 KOps/s	$\color{#35bf28}+1.46\%$
test_vmap_mlp_speed[False-False]	0.6194ms	0.3859ms	2.5912 KOps/s	2.5525 KOps/s	$\color{#35bf28}+1.52\%$
test_vmap_mlp_speed_decorator[True-True]	0.8924ms	0.4911ms	2.0364 KOps/s	1.9885 KOps/s	$\color{#35bf28}+2.41\%$
test_vmap_mlp_speed_decorator[True-False]	0.7966ms	0.4940ms	2.0243 KOps/s	1.9802 KOps/s	$\color{#35bf28}+2.23\%$
test_vmap_mlp_speed_decorator[False-True]	0.6869ms	0.4211ms	2.3749 KOps/s	2.4422 KOps/s	$\color{#d91a1a}-2.75\%$
test_vmap_mlp_speed_decorator[False-False]	0.6685ms	0.4034ms	2.4789 KOps/s	2.4403 KOps/s	$\color{#35bf28}+1.58\%$
test_to_module_speed[True]	2.5723ms	1.5608ms	640.6998 Ops/s	714.8989 Ops/s	$\textbf{\color{#d91a1a}-10.38\%}$
test_to_module_speed[False]	2.8347ms	1.4103ms	709.0915 Ops/s	724.3699 Ops/s	$\color{#d91a1a}-2.11\%$