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 collector timeouts #2774

Merged
merged 3 commits into from
Feb 10, 2025
Merged

[BugFix] Fix collector timeouts #2774

merged 3 commits into from
Feb 10, 2025

Conversation

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Feb 10, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2774

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: c322ceb93e92a4fb42534e4bd8e94686889baddc
Pull Request resolved: #2774
@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 Feb 10, 2025
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: b7384dce4528a0bb8a8baa8b148dce481eb6d763
Pull Request resolved: #2774
@vmoens vmoens added bug Something isn't working quality code quality BE Better errors, logs, docs or test utils Suitable for minor Suitable to be integrated in minor release (no new feature) labels Feb 10, 2025
Copy link

github-actions bot commented Feb 10, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.6152s 0.5128s 1.9501 Ops/s 2.0617 Ops/s $\textbf{\color{#d91a1a}-5.41\%}$
test_transformed 1.1002s 1.0059s 0.9941 Ops/s 1.0145 Ops/s $\color{#d91a1a}-2.01\%$
test_serial 1.5997s 1.5178s 0.6588 Ops/s 0.6649 Ops/s $\color{#d91a1a}-0.91\%$
test_parallel 1.3634s 1.2740s 0.7849 Ops/s 0.7710 Ops/s $\color{#35bf28}+1.81\%$
test_step_mdp_speed[True-True-True-True-True] 0.1880ms 29.8834μs 33.4634 KOps/s 33.5115 KOps/s $\color{#d91a1a}-0.14\%$
test_step_mdp_speed[True-True-True-True-False] 58.8800μs 17.7628μs 56.2975 KOps/s 55.9483 KOps/s $\color{#35bf28}+0.62\%$
test_step_mdp_speed[True-True-True-False-True] 50.8450μs 17.1883μs 58.1792 KOps/s 58.5413 KOps/s $\color{#d91a1a}-0.62\%$
test_step_mdp_speed[True-True-True-False-False] 35.7970μs 10.0985μs 99.0248 KOps/s 99.3953 KOps/s $\color{#d91a1a}-0.37\%$
test_step_mdp_speed[True-True-False-True-True] 74.1890μs 32.7831μs 30.5035 KOps/s 31.3319 KOps/s $\color{#d91a1a}-2.64\%$
test_step_mdp_speed[True-True-False-True-False] 0.5907ms 19.5813μs 51.0693 KOps/s 50.7436 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[True-True-False-False-True] 47.5390μs 18.9161μs 52.8650 KOps/s 53.3781 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[True-True-False-False-False] 44.3330μs 11.9316μs 83.8107 KOps/s 83.7699 KOps/s $\color{#35bf28}+0.05\%$
test_step_mdp_speed[True-False-True-True-True] 73.4380μs 34.0861μs 29.3375 KOps/s 29.7769 KOps/s $\color{#d91a1a}-1.48\%$
test_step_mdp_speed[True-False-True-True-False] 74.8600μs 21.3374μs 46.8661 KOps/s 46.5142 KOps/s $\color{#35bf28}+0.76\%$
test_step_mdp_speed[True-False-True-False-True] 72.5360μs 18.7496μs 53.3343 KOps/s 53.1250 KOps/s $\color{#35bf28}+0.39\%$
test_step_mdp_speed[True-False-True-False-False] 45.6350μs 11.8101μs 84.6735 KOps/s 84.2926 KOps/s $\color{#35bf28}+0.45\%$
test_step_mdp_speed[True-False-False-True-True] 79.8500μs 35.5868μs 28.1003 KOps/s 28.0526 KOps/s $\color{#35bf28}+0.17\%$
test_step_mdp_speed[True-False-False-True-False] 58.8900μs 23.0248μs 43.4314 KOps/s 43.0831 KOps/s $\color{#35bf28}+0.81\%$
test_step_mdp_speed[True-False-False-False-True] 89.3470μs 20.6102μs 48.5196 KOps/s 48.7479 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[True-False-False-False-False] 42.4390μs 13.6509μs 73.2553 KOps/s 73.5340 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[False-True-True-True-True] 89.7680μs 34.2778μs 29.1734 KOps/s 30.1620 KOps/s $\color{#d91a1a}-3.28\%$
test_step_mdp_speed[False-True-True-True-False] 57.4570μs 21.4049μs 46.7183 KOps/s 46.2181 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[False-True-True-False-True] 62.9080μs 21.9188μs 45.6229 KOps/s 45.9580 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[False-True-True-False-False] 62.3570μs 13.3616μs 74.8414 KOps/s 75.9600 KOps/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[False-True-False-True-True] 0.1035ms 35.7972μs 27.9351 KOps/s 28.3458 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[False-True-False-True-False] 56.1750μs 23.2123μs 43.0806 KOps/s 42.6609 KOps/s $\color{#35bf28}+0.98\%$
test_step_mdp_speed[False-True-False-False-True] 2.7640ms 23.4865μs 42.5776 KOps/s 43.0233 KOps/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[False-True-False-False-False] 58.8690μs 14.8186μs 67.4828 KOps/s 66.4530 KOps/s $\color{#35bf28}+1.55\%$
test_step_mdp_speed[False-False-True-True-True] 82.4940μs 37.4731μs 26.6858 KOps/s 26.8556 KOps/s $\color{#d91a1a}-0.63\%$
test_step_mdp_speed[False-False-True-True-False] 63.6890μs 25.0664μs 39.8940 KOps/s 39.5652 KOps/s $\color{#35bf28}+0.83\%$
test_step_mdp_speed[False-False-True-False-True] 60.2330μs 23.0203μs 43.4398 KOps/s 42.7775 KOps/s $\color{#35bf28}+1.55\%$
test_step_mdp_speed[False-False-True-False-False] 47.8300μs 14.9261μs 66.9967 KOps/s 65.7141 KOps/s $\color{#35bf28}+1.95\%$
test_step_mdp_speed[False-False-False-True-True] 76.8440μs 38.8500μs 25.7401 KOps/s 25.6169 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[False-False-False-True-False] 70.4810μs 26.3388μs 37.9668 KOps/s 37.2533 KOps/s $\color{#35bf28}+1.92\%$
test_step_mdp_speed[False-False-False-False-True] 53.9920μs 24.5582μs 40.7195 KOps/s 40.5629 KOps/s $\color{#35bf28}+0.39\%$
test_step_mdp_speed[False-False-False-False-False] 44.8640μs 16.4628μs 60.7430 KOps/s 60.1298 KOps/s $\color{#35bf28}+1.02\%$
test_values[generalized_advantage_estimate-True-True] 12.7235ms 9.7395ms 102.6751 Ops/s 98.7398 Ops/s $\color{#35bf28}+3.99\%$
test_values[vec_generalized_advantage_estimate-True-True] 26.1408ms 24.2264ms 41.2773 Ops/s 41.0418 Ops/s $\color{#35bf28}+0.57\%$
test_values[td0_return_estimate-False-False] 0.2593ms 0.2034ms 4.9160 KOps/s 5.4914 KOps/s $\textbf{\color{#d91a1a}-10.48\%}$
test_values[td1_return_estimate-False-False] 27.5092ms 24.5551ms 40.7247 Ops/s 41.1300 Ops/s $\color{#d91a1a}-0.99\%$
test_values[vec_td1_return_estimate-False-False] 27.8506ms 24.4815ms 40.8471 Ops/s 40.9995 Ops/s $\color{#d91a1a}-0.37\%$
test_values[td_lambda_return_estimate-True-False] 40.4555ms 34.9379ms 28.6222 Ops/s 28.6952 Ops/s $\color{#d91a1a}-0.25\%$
test_values[vec_td_lambda_return_estimate-True-False] 26.4130ms 24.2561ms 41.2267 Ops/s 41.0989 Ops/s $\color{#35bf28}+0.31\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 11.9129ms 8.5816ms 116.5290 Ops/s 116.6119 Ops/s $\color{#d91a1a}-0.07\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2333ms 1.9779ms 505.5829 Ops/s 506.0133 Ops/s $\color{#d91a1a}-0.09\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4878ms 0.3662ms 2.7309 KOps/s 2.6038 KOps/s $\color{#35bf28}+4.88\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 46.8788ms 43.4942ms 22.9916 Ops/s 23.6371 Ops/s $\color{#d91a1a}-2.73\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.3615ms 3.5291ms 283.3554 Ops/s 287.1381 Ops/s $\color{#d91a1a}-1.32\%$
test_dqn_speed[False-None] 5.8512ms 1.4017ms 713.4427 Ops/s 711.2593 Ops/s $\color{#35bf28}+0.31\%$
test_dqn_speed[False-backward] 1.9392ms 1.8830ms 531.0710 Ops/s 528.7165 Ops/s $\color{#35bf28}+0.45\%$
test_dqn_speed[True-None] 0.6012ms 0.4762ms 2.0999 KOps/s 2.0540 KOps/s $\color{#35bf28}+2.23\%$
test_dqn_speed[True-backward] 0.9504ms 0.8946ms 1.1178 KOps/s 1.0997 KOps/s $\color{#35bf28}+1.65\%$
test_dqn_speed[reduce-overhead-None] 0.6939ms 0.4793ms 2.0862 KOps/s 2.0686 KOps/s $\color{#35bf28}+0.85\%$
test_dqn_speed[reduce-overhead-backward] 0.9656ms 0.8976ms 1.1140 KOps/s 1.0883 KOps/s $\color{#35bf28}+2.36\%$
test_ddpg_speed[False-None] 3.4130ms 2.9342ms 340.8071 Ops/s 341.4329 Ops/s $\color{#d91a1a}-0.18\%$
test_ddpg_speed[False-backward] 4.6071ms 4.1611ms 240.3236 Ops/s 239.1183 Ops/s $\color{#35bf28}+0.50\%$
test_ddpg_speed[True-None] 1.6557ms 1.2235ms 817.3378 Ops/s 812.9099 Ops/s $\color{#35bf28}+0.54\%$
test_ddpg_speed[True-backward] 2.1557ms 2.1184ms 472.0649 Ops/s 378.3140 Ops/s $\textbf{\color{#35bf28}+24.78\%}$
test_ddpg_speed[reduce-overhead-None] 1.3857ms 1.2260ms 815.6617 Ops/s 803.2294 Ops/s $\color{#35bf28}+1.55\%$
test_ddpg_speed[reduce-overhead-backward] 2.2707ms 2.1801ms 458.7027 Ops/s 468.1575 Ops/s $\color{#d91a1a}-2.02\%$
test_sac_speed[False-None] 10.3686ms 8.2408ms 121.3476 Ops/s 122.0017 Ops/s $\color{#d91a1a}-0.54\%$
test_sac_speed[False-backward] 11.4885ms 10.9848ms 91.0345 Ops/s 91.6978 Ops/s $\color{#d91a1a}-0.72\%$
test_sac_speed[True-None] 2.3397ms 2.0966ms 476.9613 Ops/s 463.9925 Ops/s $\color{#35bf28}+2.80\%$
test_sac_speed[True-backward] 4.5739ms 3.9126ms 255.5821 Ops/s 262.6206 Ops/s $\color{#d91a1a}-2.68\%$
test_sac_speed[reduce-overhead-None] 2.2733ms 2.1085ms 474.2672 Ops/s 463.4419 Ops/s $\color{#35bf28}+2.34\%$
test_sac_speed[reduce-overhead-backward] 4.1302ms 3.7915ms 263.7492 Ops/s 263.4545 Ops/s $\color{#35bf28}+0.11\%$
test_redq_speed[False-None] 15.3972ms 12.9903ms 76.9808 Ops/s 74.7888 Ops/s $\color{#35bf28}+2.93\%$
test_redq_speed[False-backward] 24.9616ms 22.3429ms 44.7569 Ops/s 43.7714 Ops/s $\color{#35bf28}+2.25\%$
test_redq_speed[True-None] 5.7635ms 5.0267ms 198.9371 Ops/s 199.1295 Ops/s $\color{#d91a1a}-0.10\%$
test_redq_speed[True-backward] 13.5676ms 12.5574ms 79.6344 Ops/s 78.2511 Ops/s $\color{#35bf28}+1.77\%$
test_redq_speed[reduce-overhead-None] 6.0503ms 4.9283ms 202.9078 Ops/s 191.6406 Ops/s $\textbf{\color{#35bf28}+5.88\%}$
test_redq_speed[reduce-overhead-backward] 13.9513ms 12.4836ms 80.1053 Ops/s 77.7935 Ops/s $\color{#35bf28}+2.97\%$
test_redq_deprec_speed[False-None] 14.3222ms 12.9384ms 77.2890 Ops/s 75.9839 Ops/s $\color{#35bf28}+1.72\%$
test_redq_deprec_speed[False-backward] 20.6073ms 18.6410ms 53.6452 Ops/s 52.9356 Ops/s $\color{#35bf28}+1.34\%$
test_redq_deprec_speed[True-None] 4.7707ms 3.8711ms 258.3253 Ops/s 257.6845 Ops/s $\color{#35bf28}+0.25\%$
test_redq_deprec_speed[True-backward] 9.3444ms 8.5178ms 117.4007 Ops/s 115.8565 Ops/s $\color{#35bf28}+1.33\%$
test_redq_deprec_speed[reduce-overhead-None] 4.3652ms 3.8493ms 259.7853 Ops/s 256.0880 Ops/s $\color{#35bf28}+1.44\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.2291ms 8.4755ms 117.9874 Ops/s 117.9342 Ops/s $\color{#35bf28}+0.05\%$
test_td3_speed[False-None] 8.2112ms 7.9775ms 125.3521 Ops/s 121.1910 Ops/s $\color{#35bf28}+3.43\%$
test_td3_speed[False-backward] 11.8432ms 10.3962ms 96.1891 Ops/s 93.8913 Ops/s $\color{#35bf28}+2.45\%$
test_td3_speed[True-None] 1.9825ms 1.7704ms 564.8572 Ops/s 545.6040 Ops/s $\color{#35bf28}+3.53\%$
test_td3_speed[True-backward] 3.4212ms 3.3471ms 298.7622 Ops/s 289.1614 Ops/s $\color{#35bf28}+3.32\%$
test_td3_speed[reduce-overhead-None] 1.9349ms 1.7833ms 560.7549 Ops/s 544.9232 Ops/s $\color{#35bf28}+2.91\%$
test_td3_speed[reduce-overhead-backward] 3.7922ms 3.4302ms 291.5288 Ops/s 278.4836 Ops/s $\color{#35bf28}+4.68\%$
test_cql_speed[False-None] 38.7766ms 36.1941ms 27.6288 Ops/s 26.9938 Ops/s $\color{#35bf28}+2.35\%$
test_cql_speed[False-backward] 53.5455ms 47.9641ms 20.8489 Ops/s 20.6901 Ops/s $\color{#35bf28}+0.77\%$
test_cql_speed[True-None] 18.1759ms 16.0847ms 62.1708 Ops/s 60.4704 Ops/s $\color{#35bf28}+2.81\%$
test_cql_speed[True-backward] 25.2593ms 22.9396ms 43.5927 Ops/s 41.7130 Ops/s $\color{#35bf28}+4.51\%$
test_cql_speed[reduce-overhead-None] 18.0870ms 16.3383ms 61.2059 Ops/s 60.6239 Ops/s $\color{#35bf28}+0.96\%$
test_cql_speed[reduce-overhead-backward] 23.8065ms 22.9502ms 43.5726 Ops/s 43.3866 Ops/s $\color{#35bf28}+0.43\%$
test_a2c_speed[False-None] 8.2672ms 7.2322ms 138.2698 Ops/s 136.9349 Ops/s $\color{#35bf28}+0.97\%$
test_a2c_speed[False-backward] 15.2996ms 14.5431ms 68.7610 Ops/s 69.6195 Ops/s $\color{#d91a1a}-1.23\%$
test_a2c_speed[True-None] 4.5849ms 3.7091ms 269.6103 Ops/s 265.2239 Ops/s $\color{#35bf28}+1.65\%$
test_a2c_speed[True-backward] 10.7390ms 10.3705ms 96.4271 Ops/s 94.4525 Ops/s $\color{#35bf28}+2.09\%$
test_a2c_speed[reduce-overhead-None] 4.5268ms 3.7428ms 267.1799 Ops/s 250.5921 Ops/s $\textbf{\color{#35bf28}+6.62\%}$
test_a2c_speed[reduce-overhead-backward] 10.8662ms 10.2647ms 97.4217 Ops/s 96.7325 Ops/s $\color{#35bf28}+0.71\%$
test_ppo_speed[False-None] 8.2141ms 7.4663ms 133.9344 Ops/s 130.4294 Ops/s $\color{#35bf28}+2.69\%$
test_ppo_speed[False-backward] 16.0848ms 14.9563ms 66.8616 Ops/s 66.3149 Ops/s $\color{#35bf28}+0.82\%$
test_ppo_speed[True-None] 4.7531ms 4.0973ms 244.0626 Ops/s 237.6175 Ops/s $\color{#35bf28}+2.71\%$
test_ppo_speed[True-backward] 11.7309ms 10.0395ms 99.6062 Ops/s 98.4207 Ops/s $\color{#35bf28}+1.20\%$
test_ppo_speed[reduce-overhead-None] 4.8691ms 4.0865ms 244.7084 Ops/s 239.1887 Ops/s $\color{#35bf28}+2.31\%$
test_ppo_speed[reduce-overhead-backward] 10.6591ms 10.0498ms 99.5042 Ops/s 99.5452 Ops/s $\color{#d91a1a}-0.04\%$
test_reinforce_speed[False-None] 7.5282ms 6.5685ms 152.2429 Ops/s 150.8059 Ops/s $\color{#35bf28}+0.95\%$
test_reinforce_speed[False-backward] 10.8991ms 9.8621ms 101.3984 Ops/s 100.1032 Ops/s $\color{#35bf28}+1.29\%$
test_reinforce_speed[True-None] 4.0528ms 3.0853ms 324.1174 Ops/s 317.6143 Ops/s $\color{#35bf28}+2.05\%$
test_reinforce_speed[True-backward] 9.5757ms 9.2687ms 107.8901 Ops/s 111.4689 Ops/s $\color{#d91a1a}-3.21\%$
test_reinforce_speed[reduce-overhead-None] 3.4488ms 3.1266ms 319.8326 Ops/s 319.4780 Ops/s $\color{#35bf28}+0.11\%$
test_reinforce_speed[reduce-overhead-backward] 10.0440ms 9.0739ms 110.2057 Ops/s 110.3160 Ops/s $\color{#d91a1a}-0.10\%$
test_iql_speed[False-None] 33.7864ms 32.4968ms 30.7723 Ops/s 29.6531 Ops/s $\color{#35bf28}+3.77\%$
test_iql_speed[False-backward] 47.1456ms 45.7782ms 21.8445 Ops/s 21.7447 Ops/s $\color{#35bf28}+0.46\%$
test_iql_speed[True-None] 12.0197ms 11.4206ms 87.5609 Ops/s 85.4630 Ops/s $\color{#35bf28}+2.45\%$
test_iql_speed[True-backward] 23.5053ms 22.4594ms 44.5247 Ops/s 42.3434 Ops/s $\textbf{\color{#35bf28}+5.15\%}$
test_iql_speed[reduce-overhead-None] 12.3407ms 11.4994ms 86.9614 Ops/s 83.9658 Ops/s $\color{#35bf28}+3.57\%$
test_iql_speed[reduce-overhead-backward] 24.3354ms 23.3634ms 42.8020 Ops/s 42.7906 Ops/s $\color{#35bf28}+0.03\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3605ms 5.0578ms 197.7146 Ops/s 188.8865 Ops/s $\color{#35bf28}+4.67\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9445ms 0.5280ms 1.8940 KOps/s 1.8071 KOps/s $\color{#35bf28}+4.81\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8708ms 0.5014ms 1.9946 KOps/s 1.9419 KOps/s $\color{#35bf28}+2.71\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.4960ms 4.8741ms 205.1646 Ops/s 200.1964 Ops/s $\color{#35bf28}+2.48\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1521ms 0.5178ms 1.9313 KOps/s 1.9357 KOps/s $\color{#d91a1a}-0.23\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8279ms 0.4942ms 2.0234 KOps/s 1.9742 KOps/s $\color{#35bf28}+2.49\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.3986ms 1.6658ms 600.3059 Ops/s 588.1990 Ops/s $\color{#35bf28}+2.06\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.3422ms 1.5928ms 627.8160 Ops/s 625.4823 Ops/s $\color{#35bf28}+0.37\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.5098ms 4.9344ms 202.6587 Ops/s 197.5116 Ops/s $\color{#35bf28}+2.61\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4218ms 0.6630ms 1.5083 KOps/s 1.4861 KOps/s $\color{#35bf28}+1.50\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9054ms 0.6417ms 1.5585 KOps/s 1.5549 KOps/s $\color{#35bf28}+0.23\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.2201ms 4.8928ms 204.3831 Ops/s 204.0370 Ops/s $\color{#35bf28}+0.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.7391ms 0.5422ms 1.8444 KOps/s 1.8960 KOps/s $\color{#d91a1a}-2.72\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9438ms 0.5177ms 1.9315 KOps/s 1.9814 KOps/s $\color{#d91a1a}-2.52\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.3102ms 4.8793ms 204.9478 Ops/s 201.6371 Ops/s $\color{#35bf28}+1.64\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 3.7530ms 0.5226ms 1.9134 KOps/s 1.9450 KOps/s $\color{#d91a1a}-1.63\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7457ms 0.4990ms 2.0041 KOps/s 1.9748 KOps/s $\color{#35bf28}+1.48\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.1062ms 4.8736ms 205.1884 Ops/s 192.3396 Ops/s $\textbf{\color{#35bf28}+6.68\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.3612ms 0.6682ms 1.4966 KOps/s 1.4677 KOps/s $\color{#35bf28}+1.97\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8797ms 0.6350ms 1.5748 KOps/s 1.5174 KOps/s $\color{#35bf28}+3.78\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.6498ms 4.2260ms 236.6310 Ops/s 224.5034 Ops/s $\textbf{\color{#35bf28}+5.40\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.4315ms 2.1859ms 457.4855 Ops/s 424.4147 Ops/s $\textbf{\color{#35bf28}+7.79\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.5492ms 1.4081ms 710.2003 Ops/s 689.0511 Ops/s $\color{#35bf28}+3.07\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4925s 14.1012ms 70.9159 Ops/s 222.9505 Ops/s $\textbf{\color{#d91a1a}-68.19\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.5049ms 2.2989ms 434.9868 Ops/s 402.2612 Ops/s $\textbf{\color{#35bf28}+8.14\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.8368ms 1.3159ms 759.9273 Ops/s 734.3843 Ops/s $\color{#35bf28}+3.48\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.7265ms 4.6969ms 212.9084 Ops/s 213.9674 Ops/s $\color{#d91a1a}-0.49\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.6288ms 2.5192ms 396.9562 Ops/s 400.3470 Ops/s $\color{#d91a1a}-0.85\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.3758ms 1.4502ms 689.5484 Ops/s 670.9729 Ops/s $\color{#35bf28}+2.77\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.8336ms 12.1604ms 82.2344 Ops/s 77.3235 Ops/s $\textbf{\color{#35bf28}+6.35\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 16.0194ms 14.3786ms 69.5478 Ops/s 68.1422 Ops/s $\color{#35bf28}+2.06\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 22.0938ms 20.7976ms 48.0825 Ops/s 45.7388 Ops/s $\textbf{\color{#35bf28}+5.12\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.3139ms 14.4250ms 69.3240 Ops/s 68.3363 Ops/s $\color{#35bf28}+1.45\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.7771ms 20.9047ms 47.8360 Ops/s 47.3468 Ops/s $\color{#35bf28}+1.03\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 17.3906ms 15.8411ms 63.1270 Ops/s 63.3327 Ops/s $\color{#d91a1a}-0.32\%$

Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.8758s 0.7911s 1.2640 Ops/s 1.2873 Ops/s $\color{#d91a1a}-1.81\%$
test_transformed 1.4575s 1.3696s 0.7302 Ops/s 0.7462 Ops/s $\color{#d91a1a}-2.15\%$
test_serial 2.3560s 2.2702s 0.4405 Ops/s 0.4474 Ops/s $\color{#d91a1a}-1.54\%$
test_parallel 1.8680s 1.7933s 0.5576 Ops/s 0.5565 Ops/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[True-True-True-True-True] 0.1748ms 37.8657μs 26.4091 KOps/s 25.9438 KOps/s $\color{#35bf28}+1.79\%$
test_step_mdp_speed[True-True-True-True-False] 0.4169ms 22.4385μs 44.5662 KOps/s 44.6007 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[True-True-True-False-True] 0.4172ms 21.1198μs 47.3489 KOps/s 46.7607 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[True-True-True-False-False] 35.5810μs 12.3760μs 80.8014 KOps/s 80.8175 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[True-True-False-True-True] 0.4449ms 40.5476μs 24.6624 KOps/s 24.6864 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[True-True-False-True-False] 0.4152ms 24.6171μs 40.6221 KOps/s 40.6922 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[True-True-False-False-True] 0.4096ms 23.4246μs 42.6902 KOps/s 42.7415 KOps/s $\color{#d91a1a}-0.12\%$
test_step_mdp_speed[True-True-False-False-False] 36.3800μs 14.6939μs 68.0555 KOps/s 68.3775 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[True-False-True-True-True] 0.4322ms 43.1672μs 23.1657 KOps/s 23.3165 KOps/s $\color{#d91a1a}-0.65\%$
test_step_mdp_speed[True-False-True-True-False] 0.4328ms 26.9202μs 37.1469 KOps/s 37.3874 KOps/s $\color{#d91a1a}-0.64\%$
test_step_mdp_speed[True-False-True-False-True] 0.4178ms 23.6433μs 42.2952 KOps/s 42.4679 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[True-False-True-False-False] 39.4110μs 14.7467μs 67.8117 KOps/s 69.1249 KOps/s $\color{#d91a1a}-1.90\%$
test_step_mdp_speed[True-False-False-True-True] 0.4345ms 45.1988μs 22.1245 KOps/s 21.9801 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[True-False-False-True-False] 0.4162ms 29.2021μs 34.2442 KOps/s 34.2793 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[True-False-False-False-True] 61.2210μs 25.7792μs 38.7909 KOps/s 39.8209 KOps/s $\color{#d91a1a}-2.59\%$
test_step_mdp_speed[True-False-False-False-False] 41.9600μs 16.8577μs 59.3202 KOps/s 60.4981 KOps/s $\color{#d91a1a}-1.95\%$
test_step_mdp_speed[False-True-True-True-True] 0.4399ms 42.9567μs 23.2793 KOps/s 23.0720 KOps/s $\color{#35bf28}+0.90\%$
test_step_mdp_speed[False-True-True-True-False] 0.4188ms 26.6412μs 37.5359 KOps/s 37.2869 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[False-True-True-False-True] 52.3010μs 27.2829μs 36.6531 KOps/s 37.0439 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-True-True-False-False] 0.4164ms 16.2243μs 61.6360 KOps/s 60.9639 KOps/s $\color{#35bf28}+1.10\%$
test_step_mdp_speed[False-True-False-True-True] 0.4362ms 44.8347μs 22.3041 KOps/s 21.9356 KOps/s $\color{#35bf28}+1.68\%$
test_step_mdp_speed[False-True-False-True-False] 0.4232ms 29.2107μs 34.2340 KOps/s 34.5421 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-True-False-False-True] 3.2680ms 30.0385μs 33.2906 KOps/s 33.3271 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[False-True-False-False-False] 51.9300μs 18.3591μs 54.4690 KOps/s 54.5141 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-False-True-True-True] 0.4497ms 47.7406μs 20.9466 KOps/s 21.0013 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[False-False-True-True-False] 0.4169ms 31.2829μs 31.9663 KOps/s 31.8687 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[False-False-True-False-True] 68.0910μs 29.5534μs 33.8371 KOps/s 34.3474 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[False-False-True-False-False] 0.4086ms 18.5354μs 53.9508 KOps/s 54.4181 KOps/s $\color{#d91a1a}-0.86\%$
test_step_mdp_speed[False-False-False-True-True] 0.4456ms 49.2973μs 20.2851 KOps/s 20.6493 KOps/s $\color{#d91a1a}-1.76\%$
test_step_mdp_speed[False-False-False-True-False] 0.4194ms 33.4257μs 29.9171 KOps/s 30.0124 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[False-False-False-False-True] 0.4315ms 31.7677μs 31.4785 KOps/s 32.7237 KOps/s $\color{#d91a1a}-3.81\%$
test_step_mdp_speed[False-False-False-False-False] 44.8610μs 20.8766μs 47.9005 KOps/s 49.5277 KOps/s $\color{#d91a1a}-3.29\%$
test_values[generalized_advantage_estimate-True-True] 25.3401ms 24.8269ms 40.2789 Ops/s 37.3733 Ops/s $\textbf{\color{#35bf28}+7.77\%}$
test_values[vec_generalized_advantage_estimate-True-True] 0.1116s 3.1289ms 319.6041 Ops/s 315.7159 Ops/s $\color{#35bf28}+1.23\%$
test_values[td0_return_estimate-False-False] 0.1102ms 79.8596μs 12.5220 KOps/s 11.7241 KOps/s $\textbf{\color{#35bf28}+6.81\%}$
test_values[td1_return_estimate-False-False] 55.3638ms 54.8666ms 18.2260 Ops/s 17.0201 Ops/s $\textbf{\color{#35bf28}+7.09\%}$
test_values[vec_td1_return_estimate-False-False] 1.2414ms 1.0781ms 927.5505 Ops/s 898.8565 Ops/s $\color{#35bf28}+3.19\%$
test_values[td_lambda_return_estimate-True-False] 87.9362ms 87.3042ms 11.4542 Ops/s 10.8453 Ops/s $\textbf{\color{#35bf28}+5.61\%}$
test_values[vec_td_lambda_return_estimate-True-False] 1.1870ms 1.0736ms 931.4205 Ops/s 920.3801 Ops/s $\color{#35bf28}+1.20\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.7089ms 24.7126ms 40.4652 Ops/s 39.1552 Ops/s $\color{#35bf28}+3.35\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0264ms 0.7515ms 1.3307 KOps/s 1.3282 KOps/s $\color{#35bf28}+0.18\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7582ms 0.6677ms 1.4977 KOps/s 1.4814 KOps/s $\color{#35bf28}+1.10\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5155ms 1.4781ms 676.5279 Ops/s 673.0864 Ops/s $\color{#35bf28}+0.51\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 1.0862ms 0.6846ms 1.4606 KOps/s 1.4436 KOps/s $\color{#35bf28}+1.18\%$
test_dqn_speed[False-None] 7.0912ms 1.4927ms 669.9312 Ops/s 652.1122 Ops/s $\color{#35bf28}+2.73\%$
test_dqn_speed[False-backward] 2.5067ms 2.1074ms 474.5116 Ops/s 469.4494 Ops/s $\color{#35bf28}+1.08\%$
test_dqn_speed[True-None] 0.9560ms 0.5335ms 1.8745 KOps/s 1.8237 KOps/s $\color{#35bf28}+2.78\%$
test_dqn_speed[True-backward] 1.2795ms 1.1989ms 834.1274 Ops/s 813.2552 Ops/s $\color{#35bf28}+2.57\%$
test_dqn_speed[reduce-overhead-None] 0.9810ms 0.5519ms 1.8120 KOps/s 1.7769 KOps/s $\color{#35bf28}+1.98\%$
test_dqn_speed[reduce-overhead-backward] 1.0769ms 1.0409ms 960.7006 Ops/s 941.1090 Ops/s $\color{#35bf28}+2.08\%$
test_ddpg_speed[False-None] 3.2254ms 2.8255ms 353.9142 Ops/s 350.7557 Ops/s $\color{#35bf28}+0.90\%$
test_ddpg_speed[False-backward] 4.6781ms 4.2224ms 236.8343 Ops/s 234.2055 Ops/s $\color{#35bf28}+1.12\%$
test_ddpg_speed[True-None] 1.3859ms 1.2923ms 773.8046 Ops/s 755.9220 Ops/s $\color{#35bf28}+2.37\%$
test_ddpg_speed[True-backward] 2.5910ms 2.5114ms 398.1797 Ops/s 393.2519 Ops/s $\color{#35bf28}+1.25\%$
test_ddpg_speed[reduce-overhead-None] 1.3961ms 1.3016ms 768.3052 Ops/s 754.0806 Ops/s $\color{#35bf28}+1.89\%$
test_ddpg_speed[reduce-overhead-backward] 2.0360ms 1.9773ms 505.7489 Ops/s 496.6806 Ops/s $\color{#35bf28}+1.83\%$
test_sac_speed[False-None] 8.3567ms 7.9059ms 126.4872 Ops/s 124.5076 Ops/s $\color{#35bf28}+1.59\%$
test_sac_speed[False-backward] 11.6621ms 11.1401ms 89.7661 Ops/s 88.4636 Ops/s $\color{#35bf28}+1.47\%$
test_sac_speed[True-None] 1.8714ms 1.7680ms 565.6223 Ops/s 539.6461 Ops/s $\color{#35bf28}+4.81\%$
test_sac_speed[True-backward] 3.7927ms 3.6463ms 274.2522 Ops/s 279.1782 Ops/s $\color{#d91a1a}-1.76\%$
test_sac_speed[reduce-overhead-None] 20.3048ms 11.6388ms 85.9193 Ops/s 84.8874 Ops/s $\color{#35bf28}+1.22\%$
test_sac_speed[reduce-overhead-backward] 1.8389ms 1.7711ms 564.6338 Ops/s 606.9064 Ops/s $\textbf{\color{#d91a1a}-6.97\%}$
test_redq_speed[False-None] 7.8285ms 7.3243ms 136.5326 Ops/s 132.8782 Ops/s $\color{#35bf28}+2.75\%$
test_redq_speed[False-backward] 11.9843ms 11.4628ms 87.2387 Ops/s 87.3231 Ops/s $\color{#d91a1a}-0.10\%$
test_redq_speed[True-None] 2.3277ms 2.2322ms 447.9951 Ops/s 439.1598 Ops/s $\color{#35bf28}+2.01\%$
test_redq_speed[True-backward] 4.2497ms 4.1153ms 242.9975 Ops/s 237.2391 Ops/s $\color{#35bf28}+2.43\%$
test_redq_speed[reduce-overhead-None] 2.5001ms 2.3026ms 434.2852 Ops/s 429.6934 Ops/s $\color{#35bf28}+1.07\%$
test_redq_speed[reduce-overhead-backward] 4.8500ms 4.0724ms 245.5537 Ops/s 240.4644 Ops/s $\color{#35bf28}+2.12\%$
test_redq_deprec_speed[False-None] 9.6025ms 9.0731ms 110.2156 Ops/s 111.3913 Ops/s $\color{#d91a1a}-1.06\%$
test_redq_deprec_speed[False-backward] 12.6034ms 12.0861ms 82.7394 Ops/s 81.6694 Ops/s $\color{#35bf28}+1.31\%$
test_redq_deprec_speed[True-None] 2.7280ms 2.6094ms 383.2352 Ops/s 381.3180 Ops/s $\color{#35bf28}+0.50\%$
test_redq_deprec_speed[True-backward] 4.7468ms 4.3769ms 228.4704 Ops/s 219.1278 Ops/s $\color{#35bf28}+4.26\%$
test_redq_deprec_speed[reduce-overhead-None] 2.7013ms 2.5528ms 391.7245 Ops/s 382.3231 Ops/s $\color{#35bf28}+2.46\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.8388ms 4.3514ms 229.8086 Ops/s 223.1525 Ops/s $\color{#35bf28}+2.98\%$
test_td3_speed[False-None] 8.0204ms 7.9045ms 126.5104 Ops/s 126.3080 Ops/s $\color{#35bf28}+0.16\%$
test_td3_speed[False-backward] 10.9445ms 10.3947ms 96.2032 Ops/s 95.2750 Ops/s $\color{#35bf28}+0.97\%$
test_td3_speed[True-None] 1.6197ms 1.5842ms 631.2234 Ops/s 604.2279 Ops/s $\color{#35bf28}+4.47\%$
test_td3_speed[True-backward] 3.3264ms 3.2520ms 307.5021 Ops/s 301.2746 Ops/s $\color{#35bf28}+2.07\%$
test_td3_speed[reduce-overhead-None] 49.0435ms 25.2999ms 39.5259 Ops/s 39.9970 Ops/s $\color{#d91a1a}-1.18\%$
test_td3_speed[reduce-overhead-backward] 1.5211ms 1.4762ms 677.4100 Ops/s 669.3526 Ops/s $\color{#35bf28}+1.20\%$
test_cql_speed[False-None] 18.4627ms 16.5643ms 60.3710 Ops/s 59.8579 Ops/s $\color{#35bf28}+0.86\%$
test_cql_speed[False-backward] 22.4649ms 22.0219ms 45.4094 Ops/s 45.1993 Ops/s $\color{#35bf28}+0.46\%$
test_cql_speed[True-None] 3.2734ms 3.1426ms 318.2110 Ops/s 314.7765 Ops/s $\color{#35bf28}+1.09\%$
test_cql_speed[True-backward] 5.4450ms 5.3392ms 187.2925 Ops/s 188.0318 Ops/s $\color{#d91a1a}-0.39\%$
test_cql_speed[reduce-overhead-None] 20.4869ms 12.5814ms 79.4824 Ops/s 83.0478 Ops/s $\color{#d91a1a}-4.29\%$
test_cql_speed[reduce-overhead-backward] 1.9826ms 1.7731ms 563.9748 Ops/s 551.0071 Ops/s $\color{#35bf28}+2.35\%$
test_a2c_speed[False-None] 3.6433ms 3.1907ms 313.4103 Ops/s 318.6327 Ops/s $\color{#d91a1a}-1.64\%$
test_a2c_speed[False-backward] 6.6538ms 5.9809ms 167.1988 Ops/s 164.4488 Ops/s $\color{#35bf28}+1.67\%$
test_a2c_speed[True-None] 1.4211ms 1.2995ms 769.5129 Ops/s 759.6018 Ops/s $\color{#35bf28}+1.30\%$
test_a2c_speed[True-backward] 2.8456ms 2.7711ms 360.8711 Ops/s 348.5901 Ops/s $\color{#35bf28}+3.52\%$
test_a2c_speed[reduce-overhead-None] 15.4656ms 8.7831ms 113.8554 Ops/s 114.0776 Ops/s $\color{#d91a1a}-0.19\%$
test_a2c_speed[reduce-overhead-backward] 1.5170ms 1.4172ms 705.6282 Ops/s 696.0024 Ops/s $\color{#35bf28}+1.38\%$
test_ppo_speed[False-None] 3.7859ms 3.6695ms 272.5166 Ops/s 275.1553 Ops/s $\color{#d91a1a}-0.96\%$
test_ppo_speed[False-backward] 7.1463ms 6.7628ms 147.8669 Ops/s 147.3991 Ops/s $\color{#35bf28}+0.32\%$
test_ppo_speed[True-None] 1.4839ms 1.3658ms 732.1947 Ops/s 715.1170 Ops/s $\color{#35bf28}+2.39\%$
test_ppo_speed[True-backward] 3.0162ms 2.9144ms 343.1211 Ops/s 328.5109 Ops/s $\color{#35bf28}+4.45\%$
test_ppo_speed[reduce-overhead-None] 1.0662ms 0.9352ms 1.0692 KOps/s 1.0424 KOps/s $\color{#35bf28}+2.57\%$
test_ppo_speed[reduce-overhead-backward] 1.5596ms 1.3863ms 721.3423 Ops/s 698.3584 Ops/s $\color{#35bf28}+3.29\%$
test_reinforce_speed[False-None] 2.4395ms 2.2851ms 437.6201 Ops/s 444.2100 Ops/s $\color{#d91a1a}-1.48\%$
test_reinforce_speed[False-backward] 3.8142ms 3.2819ms 304.7033 Ops/s 307.9520 Ops/s $\color{#d91a1a}-1.05\%$
test_reinforce_speed[True-None] 1.6440ms 1.2626ms 791.9863 Ops/s 767.9022 Ops/s $\color{#35bf28}+3.14\%$
test_reinforce_speed[True-backward] 3.0355ms 2.8920ms 345.7762 Ops/s 349.4962 Ops/s $\color{#d91a1a}-1.06\%$
test_reinforce_speed[reduce-overhead-None] 18.9760ms 10.0750ms 99.2552 Ops/s 102.3199 Ops/s $\color{#d91a1a}-3.00\%$
test_reinforce_speed[reduce-overhead-backward] 1.6174ms 1.4954ms 668.7294 Ops/s 665.5399 Ops/s $\color{#35bf28}+0.48\%$
test_iql_speed[False-None] 9.6573ms 9.1706ms 109.0443 Ops/s 107.5789 Ops/s $\color{#35bf28}+1.36\%$
test_iql_speed[False-backward] 13.1034ms 12.5596ms 79.6206 Ops/s 77.8260 Ops/s $\color{#35bf28}+2.31\%$
test_iql_speed[True-None] 2.2693ms 2.1102ms 473.8887 Ops/s 456.6904 Ops/s $\color{#35bf28}+3.77\%$
test_iql_speed[True-backward] 4.8949ms 4.5428ms 220.1268 Ops/s 214.5462 Ops/s $\color{#35bf28}+2.60\%$
test_iql_speed[reduce-overhead-None] 18.6188ms 10.7405ms 93.1057 Ops/s 94.2721 Ops/s $\color{#d91a1a}-1.24\%$
test_iql_speed[reduce-overhead-backward] 1.9402ms 1.8552ms 539.0269 Ops/s 524.0670 Ops/s $\color{#35bf28}+2.85\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.5111ms 6.1340ms 163.0270 Ops/s 161.0396 Ops/s $\color{#35bf28}+1.23\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.4864ms 0.2783ms 3.5927 KOps/s 2.9685 KOps/s $\textbf{\color{#35bf28}+21.03\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5208ms 0.2728ms 3.6659 KOps/s 3.5439 KOps/s $\color{#35bf28}+3.45\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1091ms 5.7828ms 172.9269 Ops/s 169.0203 Ops/s $\color{#35bf28}+2.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7290ms 0.3421ms 2.9233 KOps/s 3.0352 KOps/s $\color{#d91a1a}-3.69\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5203ms 0.2409ms 4.1519 KOps/s 3.9449 KOps/s $\textbf{\color{#35bf28}+5.25\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7778ms 1.4629ms 683.5618 Ops/s 786.3322 Ops/s $\textbf{\color{#d91a1a}-13.07\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5738ms 1.3278ms 753.1446 Ops/s 859.9921 Ops/s $\textbf{\color{#d91a1a}-12.42\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2750ms 6.1095ms 163.6789 Ops/s 164.3223 Ops/s $\color{#d91a1a}-0.39\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9388ms 0.4602ms 2.1728 KOps/s 2.2405 KOps/s $\color{#d91a1a}-3.03\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7600ms 0.3976ms 2.5152 KOps/s 2.3959 KOps/s $\color{#35bf28}+4.98\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.9679ms 5.8507ms 170.9190 Ops/s 167.1337 Ops/s $\color{#35bf28}+2.26\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.8228ms 0.3116ms 3.2096 KOps/s 3.4165 KOps/s $\textbf{\color{#d91a1a}-6.06\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7076ms 0.2851ms 3.5076 KOps/s 3.4605 KOps/s $\color{#35bf28}+1.36\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1405ms 5.8137ms 172.0062 Ops/s 167.6658 Ops/s $\color{#35bf28}+2.59\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.9958ms 0.2770ms 3.6099 KOps/s 3.4134 KOps/s $\textbf{\color{#35bf28}+5.76\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5194ms 0.2661ms 3.7574 KOps/s 3.6199 KOps/s $\color{#35bf28}+3.80\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2902ms 6.0132ms 166.3008 Ops/s 163.0377 Ops/s $\color{#35bf28}+2.00\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0677ms 0.4001ms 2.4993 KOps/s 2.3835 KOps/s $\color{#35bf28}+4.86\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5929ms 0.3830ms 2.6110 KOps/s 2.3823 KOps/s $\textbf{\color{#35bf28}+9.60\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.8896ms 5.3727ms 186.1247 Ops/s 180.9404 Ops/s $\color{#35bf28}+2.87\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 10.5071ms 2.0584ms 485.8119 Ops/s 424.2060 Ops/s $\textbf{\color{#35bf28}+14.52\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.9939ms 1.1709ms 854.0626 Ops/s 873.6442 Ops/s $\color{#d91a1a}-2.24\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 7.1926ms 5.5342ms 180.6943 Ops/s 184.0544 Ops/s $\color{#d91a1a}-1.83\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.0085ms 1.9990ms 500.2603 Ops/s 454.9299 Ops/s $\textbf{\color{#35bf28}+9.96\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 9.9994ms 1.2581ms 794.8501 Ops/s 789.8810 Ops/s $\color{#35bf28}+0.63\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.5200s 16.0620ms 62.2589 Ops/s 30.2904 Ops/s $\textbf{\color{#35bf28}+105.54\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.5120ms 2.1378ms 467.7687 Ops/s 464.6329 Ops/s $\color{#35bf28}+0.67\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.3293ms 1.1674ms 856.5681 Ops/s 895.2156 Ops/s $\color{#d91a1a}-4.32\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.7425ms 12.4560ms 80.2824 Ops/s 74.4058 Ops/s $\textbf{\color{#35bf28}+7.90\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 17.8998ms 16.4068ms 60.9504 Ops/s 59.4006 Ops/s $\color{#35bf28}+2.61\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 17.4613ms 17.1643ms 58.2606 Ops/s 55.6155 Ops/s $\color{#35bf28}+4.76\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.3746ms 16.8492ms 59.3500 Ops/s 58.9934 Ops/s $\color{#35bf28}+0.60\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.9859ms 17.5660ms 56.9281 Ops/s 55.3142 Ops/s $\color{#35bf28}+2.92\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.3165ms 18.1374ms 55.1348 Ops/s 54.8207 Ops/s $\color{#35bf28}+0.57\%$

[ghstack-poisoned]
@vmoens vmoens merged commit d3ba700 into gh/vmoens/89/base Feb 10, 2025
1 check passed
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: cb71d95143beb22db1fe1752e72f70c19f43be79
Pull Request resolved: #2774
@vmoens vmoens deleted the gh/vmoens/89/head branch February 10, 2025 12:27
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: cb71d95143beb22db1fe1752e72f70c19f43be79
Pull Request resolved: #2774

(cherry picked from commit f6084b6)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
BE Better errors, logs, docs or test utils 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. quality code quality Suitable for minor Suitable to be integrated in minor release (no new feature)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants