[Feature] TensorStack (2)

[vmoens]

Description

[github-actions]

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

Total Benchmarks: 109. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	47.0010μs	20.1499μs	49.6279 KOps/s	49.2698 KOps/s	$\color{#35bf28}+0.73\%$
test_plain_set_stack_nested	0.2260ms	0.1862ms	5.3710 KOps/s	5.2885 KOps/s	$\color{#35bf28}+1.56\%$
test_plain_set_nested_inplace	47.9000μs	23.7944μs	42.0267 KOps/s	41.8756 KOps/s	$\color{#35bf28}+0.36\%$
test_plain_set_stack_nested_inplace	0.3222ms	0.2221ms	4.5031 KOps/s	4.4930 KOps/s	$\color{#35bf28}+0.23\%$
test_items	70.8000μs	3.3839μs	295.5206 KOps/s	272.6459 KOps/s	$\textbf{\color{#35bf28}+8.39\%}$
test_items_nested	2.7128ms	0.3915ms	2.5542 KOps/s	2.7356 KOps/s	$\textbf{\color{#d91a1a}-6.63\%}$
test_items_nested_locked	0.4459ms	0.3686ms	2.7129 KOps/s	2.7541 KOps/s	$\color{#d91a1a}-1.49\%$
test_items_nested_leaf	0.9316ms	0.2273ms	4.4001 KOps/s	4.5189 KOps/s	$\color{#d91a1a}-2.63\%$
test_items_stack_nested	2.1763ms	2.0213ms	494.7428 Ops/s	501.2848 Ops/s	$\color{#d91a1a}-1.31\%$
test_items_stack_nested_leaf	1.9422ms	1.8370ms	544.3582 Ops/s	547.4333 Ops/s	$\color{#d91a1a}-0.56\%$
test_items_stack_nested_locked	6.0711ms	1.0334ms	967.6805 Ops/s	1.0122 KOps/s	$\color{#d91a1a}-4.40\%$
test_keys	29.1000μs	5.1275μs	195.0276 KOps/s	197.0544 KOps/s	$\color{#d91a1a}-1.03\%$
test_keys_nested	2.4120ms	0.1848ms	5.4104 KOps/s	5.4576 KOps/s	$\color{#d91a1a}-0.86\%$
test_keys_nested_locked	0.2670ms	0.1816ms	5.5069 KOps/s	5.5044 KOps/s	$\color{#35bf28}+0.05\%$
test_keys_nested_leaf	0.3484ms	0.1754ms	5.7010 KOps/s	5.2578 KOps/s	$\textbf{\color{#35bf28}+8.43\%}$
test_keys_stack_nested	1.9296ms	1.7778ms	562.4817 Ops/s	553.3976 Ops/s	$\color{#35bf28}+1.64\%$
test_keys_stack_nested_leaf	3.4001ms	1.7857ms	560.0195 Ops/s	554.9385 Ops/s	$\color{#35bf28}+0.92\%$
test_keys_stack_nested_locked	3.6881ms	0.7736ms	1.2926 KOps/s	1.3297 KOps/s	$\color{#d91a1a}-2.79\%$
test_values	78.8010μs	1.5106μs	661.9741 KOps/s	639.0567 KOps/s	$\color{#35bf28}+3.59\%$
test_values_nested	94.1010μs	66.4592μs	15.0468 KOps/s	14.9219 KOps/s	$\color{#35bf28}+0.84\%$
test_values_nested_locked	0.1445ms	66.2500μs	15.0943 KOps/s	14.8134 KOps/s	$\color{#35bf28}+1.90\%$
test_values_nested_leaf	0.1285ms	58.3131μs	17.1488 KOps/s	16.7929 KOps/s	$\color{#35bf28}+2.12\%$
test_values_stack_nested	1.7348ms	1.6116ms	620.4991 Ops/s	620.7697 Ops/s	$\color{#d91a1a}-0.04\%$
test_values_stack_nested_leaf	1.7421ms	1.6107ms	620.8547 Ops/s	624.2363 Ops/s	$\color{#d91a1a}-0.54\%$
test_values_stack_nested_locked	0.8085ms	0.6562ms	1.5240 KOps/s	1.5455 KOps/s	$\color{#d91a1a}-1.40\%$
test_membership	20.9000μs	1.8068μs	553.4715 KOps/s	537.0488 KOps/s	$\color{#35bf28}+3.06\%$
test_membership_nested	72.9010μs	3.5793μs	279.3868 KOps/s	277.7211 KOps/s	$\color{#35bf28}+0.60\%$
test_membership_nested_leaf	33.1000μs	3.5518μs	281.5439 KOps/s	278.7462 KOps/s	$\color{#35bf28}+1.00\%$
test_membership_stacked_nested	83.8010μs	14.4579μs	69.1664 KOps/s	69.1699 KOps/s	$-0.01\%$
test_membership_stacked_nested_leaf	40.5000μs	14.1983μs	70.4310 KOps/s	69.2323 KOps/s	$\color{#35bf28}+1.73\%$
test_membership_nested_last	24.4000μs	7.5054μs	133.2371 KOps/s	132.8851 KOps/s	$\color{#35bf28}+0.26\%$
test_membership_nested_leaf_last	89.8010μs	7.6331μs	131.0085 KOps/s	132.6013 KOps/s	$\color{#d91a1a}-1.20\%$
test_membership_stacked_nested_last	0.3393ms	0.2281ms	4.3844 KOps/s	4.3391 KOps/s	$\color{#35bf28}+1.05\%$
test_membership_stacked_nested_leaf_last	47.5000μs	16.8307μs	59.4152 KOps/s	58.4912 KOps/s	$\color{#35bf28}+1.58\%$
test_nested_getleaf	86.5010μs	15.9019μs	62.8855 KOps/s	62.2017 KOps/s	$\color{#35bf28}+1.10\%$
test_nested_get	98.4010μs	15.0458μs	66.4638 KOps/s	65.7156 KOps/s	$\color{#35bf28}+1.14\%$
test_stacked_getleaf	1.0312ms	0.8897ms	1.1240 KOps/s	1.1262 KOps/s	$\color{#d91a1a}-0.19\%$
test_stacked_get	0.9900ms	0.8482ms	1.1790 KOps/s	1.1846 KOps/s	$\color{#d91a1a}-0.47\%$
test_nested_getitemleaf	74.5010μs	15.9200μs	62.8141 KOps/s	62.8558 KOps/s	$\color{#d91a1a}-0.07\%$
test_nested_getitem	85.5010μs	15.0824μs	66.3023 KOps/s	65.7780 KOps/s	$\color{#35bf28}+0.80\%$
test_stacked_getitemleaf	1.0197ms	0.8868ms	1.1276 KOps/s	1.1258 KOps/s	$\color{#35bf28}+0.16\%$
test_stacked_getitem	0.9921ms	0.8484ms	1.1787 KOps/s	1.1811 KOps/s	$\color{#d91a1a}-0.20\%$
test_lock_nested	88.7786ms	1.5340ms	651.8705 Ops/s	699.5552 Ops/s	$\textbf{\color{#d91a1a}-6.82\%}$
test_lock_stack_nested	0.1125s	21.2738ms	47.0062 Ops/s	51.4122 Ops/s	$\textbf{\color{#d91a1a}-8.57\%}$
test_unlock_nested	87.7361ms	1.5401ms	649.3264 Ops/s	652.6771 Ops/s	$\color{#d91a1a}-0.51\%$
test_unlock_stack_nested	0.1148s	21.5142ms	46.4810 Ops/s	50.4989 Ops/s	$\textbf{\color{#d91a1a}-7.96\%}$
test_flatten_speed	1.1016ms	1.0105ms	989.5929 Ops/s	988.8134 Ops/s	$\color{#35bf28}+0.08\%$
test_unflatten_speed	2.1890ms	1.8398ms	543.5456 Ops/s	543.3914 Ops/s	$\color{#35bf28}+0.03\%$
test_common_ops	4.4474ms	1.1169ms	895.3239 Ops/s	908.5515 Ops/s	$\color{#d91a1a}-1.46\%$
test_creation	39.0000μs	6.3003μs	158.7215 KOps/s	160.6572 KOps/s	$\color{#d91a1a}-1.20\%$
test_creation_empty	30.4000μs	13.6338μs	73.3473 KOps/s	73.9411 KOps/s	$\color{#d91a1a}-0.80\%$
test_creation_nested_1	0.1055ms	25.0740μs	39.8819 KOps/s	40.0982 KOps/s	$\color{#d91a1a}-0.54\%$
test_creation_nested_2	78.9010μs	27.9101μs	35.8293 KOps/s	37.0691 KOps/s	$\color{#d91a1a}-3.34\%$
test_clone	0.1757ms	25.2121μs	39.6636 KOps/s	40.7457 KOps/s	$\color{#d91a1a}-2.66\%$
test_getitem[int]	0.1088ms	27.8847μs	35.8619 KOps/s	36.4643 KOps/s	$\color{#d91a1a}-1.65\%$
test_getitem[slice_int]	88.8010μs	54.7542μs	18.2634 KOps/s	18.5799 KOps/s	$\color{#d91a1a}-1.70\%$
test_getitem[range]	0.1625ms	82.2345μs	12.1603 KOps/s	12.3329 KOps/s	$\color{#d91a1a}-1.40\%$
test_getitem[tuple]	0.1603ms	45.3085μs	22.0709 KOps/s	22.2390 KOps/s	$\color{#d91a1a}-0.76\%$
test_getitem[list]	0.3230ms	77.8568μs	12.8441 KOps/s	13.1102 KOps/s	$\color{#d91a1a}-2.03\%$
test_setitem_dim[int]	57.4010μs	33.2274μs	30.0957 KOps/s	30.7041 KOps/s	$\color{#d91a1a}-1.98\%$
test_setitem_dim[slice_int]	79.8010μs	58.9551μs	16.9621 KOps/s	17.1940 KOps/s	$\color{#d91a1a}-1.35\%$
test_setitem_dim[range]	0.1060ms	80.2272μs	12.4646 KOps/s	12.6353 KOps/s	$\color{#d91a1a}-1.35\%$
test_setitem_dim[tuple]	70.5010μs	49.0442μs	20.3898 KOps/s	20.8206 KOps/s	$\color{#d91a1a}-2.07\%$
test_setitem	0.2230ms	33.2175μs	30.1046 KOps/s	31.0265 KOps/s	$\color{#d91a1a}-2.97\%$
test_set	2.1052ms	32.1825μs	31.0728 KOps/s	32.2712 KOps/s	$\color{#d91a1a}-3.71\%$
test_set_shared	3.8627ms	0.1797ms	5.5646 KOps/s	5.5394 KOps/s	$\color{#35bf28}+0.45\%$
test_update	0.2208ms	35.9863μs	27.7884 KOps/s	28.0488 KOps/s	$\color{#d91a1a}-0.93\%$
test_update_nested	0.2586ms	53.2287μs	18.7869 KOps/s	19.0306 KOps/s	$\color{#d91a1a}-1.28\%$
test_set_nested	0.2262ms	35.3385μs	28.2978 KOps/s	29.3735 KOps/s	$\color{#d91a1a}-3.66\%$
test_set_nested_new	0.2629ms	53.6117μs	18.6527 KOps/s	18.9710 KOps/s	$\color{#d91a1a}-1.68\%$
test_select	0.2983ms	97.8248μs	10.2224 KOps/s	10.2923 KOps/s	$\color{#d91a1a}-0.68\%$
test_unbind_speed	0.7005ms	0.6584ms	1.5189 KOps/s	1.5221 KOps/s	$\color{#d91a1a}-0.22\%$
test_unbind_speed_stack0	97.4733ms	9.1368ms	109.4477 Ops/s	107.9531 Ops/s	$\color{#35bf28}+1.38\%$
test_unbind_speed_stack1	77.4010μs	1.1514μs	868.5078 KOps/s	864.9958 KOps/s	$\color{#35bf28}+0.41\%$
test_creation[device0]	4.0811ms	0.4600ms	2.1738 KOps/s	2.2005 KOps/s	$\color{#d91a1a}-1.21\%$
test_creation_from_tensor	3.6747ms	0.5065ms	1.9745 KOps/s	1.9377 KOps/s	$\color{#35bf28}+1.90\%$
test_add_one[memmap_tensor0]	2.5653ms	33.6430μs	29.7238 KOps/s	30.7856 KOps/s	$\color{#d91a1a}-3.45\%$
test_contiguous[memmap_tensor0]	45.3000μs	8.6699μs	115.3422 KOps/s	113.6177 KOps/s	$\color{#35bf28}+1.52\%$
test_stack[memmap_tensor0]	81.3010μs	27.1546μs	36.8262 KOps/s	37.5415 KOps/s	$\color{#d91a1a}-1.91\%$
test_memmaptd_index	0.4378ms	0.3181ms	3.1437 KOps/s	3.0939 KOps/s	$\color{#35bf28}+1.61\%$
test_memmaptd_index_astensor	1.4929ms	1.3727ms	728.5009 Ops/s	731.5983 Ops/s	$\color{#d91a1a}-0.42\%$
test_memmaptd_index_op	2.8805ms	2.6322ms	379.9095 Ops/s	380.9467 Ops/s	$\color{#d91a1a}-0.27\%$
test_reshape_pytree	0.1119ms	37.9807μs	26.3292 KOps/s	26.3145 KOps/s	$\color{#35bf28}+0.06\%$
test_reshape_td	77.9010μs	46.5345μs	21.4894 KOps/s	22.2109 KOps/s	$\color{#d91a1a}-3.25\%$
test_view_pytree	0.1622ms	35.5732μs	28.1111 KOps/s	28.7159 KOps/s	$\color{#d91a1a}-2.11\%$
test_view_td	40.2010μs	8.7574μs	114.1897 KOps/s	113.3673 KOps/s	$\color{#35bf28}+0.73\%$
test_unbind_pytree	81.6010μs	38.7667μs	25.7953 KOps/s	25.9015 KOps/s	$\color{#d91a1a}-0.41\%$
test_unbind_td	0.2777ms	96.7721μs	10.3336 KOps/s	10.0404 KOps/s	$\color{#35bf28}+2.92\%$
test_split_pytree	94.1010μs	45.1784μs	22.1345 KOps/s	22.0312 KOps/s	$\color{#35bf28}+0.47\%$
test_split_td	1.0535ms	0.1165ms	8.5830 KOps/s	8.6373 KOps/s	$\color{#d91a1a}-0.63\%$
test_add_pytree	91.2010μs	47.7415μs	20.9461 KOps/s	21.3212 KOps/s	$\color{#d91a1a}-1.76\%$
test_add_td	0.1391ms	76.5055μs	13.0710 KOps/s	13.4475 KOps/s	$\color{#d91a1a}-2.80\%$
test_distributed	24.8000μs	8.8987μs	112.3757 KOps/s	113.7444 KOps/s	$\color{#d91a1a}-1.20\%$
test_tdmodule	0.1935ms	28.7011μs	34.8418 KOps/s	33.7680 KOps/s	$\color{#35bf28}+3.18\%$
test_tdmodule_dispatch	0.2951ms	55.5519μs	18.0012 KOps/s	17.7050 KOps/s	$\color{#35bf28}+1.67\%$
test_tdseq	0.5754ms	33.2287μs	30.0945 KOps/s	30.7940 KOps/s	$\color{#d91a1a}-2.27\%$
test_tdseq_dispatch	0.5423ms	67.3866μs	14.8397 KOps/s	14.8234 KOps/s	$\color{#35bf28}+0.11\%$
test_instantiation_functorch	1.8086ms	1.6440ms	608.2630 Ops/s	610.6758 Ops/s	$\color{#d91a1a}-0.40\%$
test_instantiation_td	2.0577ms	1.3657ms	732.2513 Ops/s	728.1060 Ops/s	$\color{#35bf28}+0.57\%$
test_exec_functorch	0.2481ms	0.1878ms	5.3246 KOps/s	5.3302 KOps/s	$\color{#d91a1a}-0.10\%$
test_exec_td	0.2611ms	0.1783ms	5.6074 KOps/s	5.5642 KOps/s	$\color{#35bf28}+0.78\%$
test_vmap_mlp_speed[True-True]	7.5885ms	1.2071ms	828.4323 Ops/s	834.7225 Ops/s	$\color{#d91a1a}-0.75\%$
test_vmap_mlp_speed[True-False]	1.0031ms	0.5947ms	1.6814 KOps/s	1.6406 KOps/s	$\color{#35bf28}+2.49\%$
test_vmap_mlp_speed[False-True]	14.5648ms	1.0449ms	957.0605 Ops/s	991.8399 Ops/s	$\color{#d91a1a}-3.51\%$
test_vmap_mlp_speed[False-False]	3.2552ms	0.4534ms	2.2055 KOps/s	2.1998 KOps/s	$\color{#35bf28}+0.26\%$
test_vmap_transformer_speed[True-True]	26.6194ms	14.3297ms	69.7852 Ops/s	66.0110 Ops/s	$\textbf{\color{#35bf28}+5.72\%}$
test_vmap_transformer_speed[True-False]	17.7368ms	9.2223ms	108.4331 Ops/s	107.3142 Ops/s	$\color{#35bf28}+1.04\%$
test_vmap_transformer_speed[False-True]	17.4460ms	13.7574ms	72.6880 Ops/s	73.1794 Ops/s	$\color{#d91a1a}-0.67\%$
test_vmap_transformer_speed[False-False]	21.6909ms	9.0531ms	110.4589 Ops/s	115.5304 Ops/s	$\color{#d91a1a}-4.39\%$