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 done check in maybe_reset #2637

Closed
wants to merge 2 commits into from

Conversation

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Dec 6, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2637

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

❌ 10 New Failures, 1 Cancelled Job, 12 Unrelated Failures

As of commit 25376ea with merge base 19dfefc (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOB - The following job was cancelled. Please retry:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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

Copy link

github-actions bot commented Dec 6, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}16$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4351s 0.4341s 2.3036 Ops/s 2.1940 Ops/s $\color{#35bf28}+5.00\%$
test_transformed 0.6139s 0.6114s 1.6356 Ops/s 1.5849 Ops/s $\color{#35bf28}+3.20\%$
test_serial 1.3698s 1.3682s 0.7309 Ops/s 0.7218 Ops/s $\color{#35bf28}+1.26\%$
test_parallel 1.3952s 1.3071s 0.7650 Ops/s 0.7526 Ops/s $\color{#35bf28}+1.65\%$
test_step_mdp_speed[True-True-True-True-True] 0.2098ms 29.7997μs 33.5574 KOps/s 33.5563 KOps/s $+0.00\%$
test_step_mdp_speed[True-True-True-True-False] 44.4940μs 17.5536μs 56.9685 KOps/s 56.6470 KOps/s $\color{#35bf28}+0.57\%$
test_step_mdp_speed[True-True-True-False-True] 40.8960μs 16.8885μs 59.2117 KOps/s 59.4589 KOps/s $\color{#d91a1a}-0.42\%$
test_step_mdp_speed[True-True-True-False-False] 46.6870μs 10.3474μs 96.6430 KOps/s 100.5706 KOps/s $\color{#d91a1a}-3.91\%$
test_step_mdp_speed[True-True-False-True-True] 71.8040μs 31.9618μs 31.2873 KOps/s 31.3591 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[True-True-False-True-False] 52.1070μs 19.5581μs 51.1297 KOps/s 50.9911 KOps/s $\color{#35bf28}+0.27\%$
test_step_mdp_speed[True-True-False-False-True] 45.8150μs 18.9767μs 52.6962 KOps/s 53.0009 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[True-True-False-False-False] 59.1910μs 11.9199μs 83.8933 KOps/s 83.9873 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-False-True-True-True] 74.4090μs 33.9541μs 29.4515 KOps/s 29.9559 KOps/s $\color{#d91a1a}-1.68\%$
test_step_mdp_speed[True-False-True-True-False] 50.4840μs 21.3813μs 46.7698 KOps/s 46.6315 KOps/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[True-False-True-False-True] 47.8590μs 18.8761μs 52.9770 KOps/s 53.4094 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-False-True-False-False] 51.5560μs 11.7122μs 85.3810 KOps/s 84.6625 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-False-False-True-True] 83.9970μs 36.0225μs 27.7604 KOps/s 28.7219 KOps/s $\color{#d91a1a}-3.35\%$
test_step_mdp_speed[True-False-False-True-False] 70.5330μs 23.3899μs 42.7535 KOps/s 43.2805 KOps/s $\color{#d91a1a}-1.22\%$
test_step_mdp_speed[True-False-False-False-True] 47.5490μs 20.6923μs 48.3271 KOps/s 48.6995 KOps/s $\color{#d91a1a}-0.76\%$
test_step_mdp_speed[True-False-False-False-False] 38.5420μs 13.3759μs 74.7613 KOps/s 74.7781 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[False-True-True-True-True] 71.7540μs 34.1051μs 29.3211 KOps/s 29.5854 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-True-True-True-False] 62.2260μs 21.6955μs 46.0926 KOps/s 46.6007 KOps/s $\color{#d91a1a}-1.09\%$
test_step_mdp_speed[False-True-True-False-True] 57.2870μs 21.4490μs 46.6222 KOps/s 47.1458 KOps/s $\color{#d91a1a}-1.11\%$
test_step_mdp_speed[False-True-True-False-False] 40.0250μs 13.1038μs 76.3135 KOps/s 76.3889 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[False-True-False-True-True] 70.0620μs 35.5382μs 28.1388 KOps/s 28.1757 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[False-True-False-True-False] 54.3320μs 23.2389μs 43.0312 KOps/s 42.9284 KOps/s $\color{#35bf28}+0.24\%$
test_step_mdp_speed[False-True-False-False-True] 2.9015ms 23.1807μs 43.1394 KOps/s 43.3751 KOps/s $\color{#d91a1a}-0.54\%$
test_step_mdp_speed[False-True-False-False-False] 49.0920μs 14.7836μs 67.6425 KOps/s 66.9788 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[False-False-True-True-True] 71.5940μs 37.6973μs 26.5271 KOps/s 26.8248 KOps/s $\color{#d91a1a}-1.11\%$
test_step_mdp_speed[False-False-True-True-False] 62.4570μs 25.0481μs 39.9231 KOps/s 39.8856 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-False-True-False-True] 54.5620μs 23.1630μs 43.1723 KOps/s 43.2988 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[False-False-True-False-False] 70.2820μs 14.8647μs 67.2736 KOps/s 66.9553 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[False-False-False-True-True] 83.8770μs 39.2650μs 25.4680 KOps/s 25.7660 KOps/s $\color{#d91a1a}-1.16\%$
test_step_mdp_speed[False-False-False-True-False] 64.5310μs 26.8746μs 37.2098 KOps/s 37.5578 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[False-False-False-False-True] 60.7140μs 24.5119μs 40.7966 KOps/s 41.1438 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[False-False-False-False-False] 66.3040μs 16.4782μs 60.6861 KOps/s 60.8415 KOps/s $\color{#d91a1a}-0.26\%$
test_values[generalized_advantage_estimate-True-True] 10.8816ms 9.7232ms 102.8470 Ops/s 105.2743 Ops/s $\color{#d91a1a}-2.31\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.0106ms 35.8401ms 27.9017 Ops/s 27.9377 Ops/s $\color{#d91a1a}-0.13\%$
test_values[td0_return_estimate-False-False] 0.2393ms 0.1773ms 5.6401 KOps/s 5.5986 KOps/s $\color{#35bf28}+0.74\%$
test_values[td1_return_estimate-False-False] 26.3979ms 24.2078ms 41.3090 Ops/s 42.8668 Ops/s $\color{#d91a1a}-3.63\%$
test_values[vec_td1_return_estimate-False-False] 37.7950ms 35.9881ms 27.7870 Ops/s 27.8035 Ops/s $\color{#d91a1a}-0.06\%$
test_values[td_lambda_return_estimate-True-False] 36.9541ms 34.5943ms 28.9065 Ops/s 29.1111 Ops/s $\color{#d91a1a}-0.70\%$
test_values[vec_td_lambda_return_estimate-True-False] 38.6001ms 35.9774ms 27.7952 Ops/s 27.8793 Ops/s $\color{#d91a1a}-0.30\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.4665ms 8.3489ms 119.7767 Ops/s 120.9932 Ops/s $\color{#d91a1a}-1.01\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.1528ms 1.8627ms 536.8648 Ops/s 480.6097 Ops/s $\textbf{\color{#35bf28}+11.70\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5755ms 0.3613ms 2.7675 KOps/s 2.8083 KOps/s $\color{#d91a1a}-1.45\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.8632ms 45.7201ms 21.8722 Ops/s 20.3633 Ops/s $\textbf{\color{#35bf28}+7.41\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.2838ms 3.0338ms 329.6180 Ops/s 328.3586 Ops/s $\color{#35bf28}+0.38\%$
test_dqn_speed[False-None] 6.2031ms 1.3937ms 717.5270 Ops/s 714.8127 Ops/s $\color{#35bf28}+0.38\%$
test_dqn_speed[False-backward] 2.3229ms 1.8875ms 529.7910 Ops/s 527.5756 Ops/s $\color{#35bf28}+0.42\%$
test_dqn_speed[True-None] 0.7334ms 0.4623ms 2.1631 KOps/s 2.1570 KOps/s $\color{#35bf28}+0.28\%$
test_dqn_speed[True-backward] 0.9569ms 0.9007ms 1.1102 KOps/s 770.9710 Ops/s $\textbf{\color{#35bf28}+44.01\%}$
test_dqn_speed[reduce-overhead-None] 0.5685ms 0.4620ms 2.1647 KOps/s 2.1357 KOps/s $\color{#35bf28}+1.36\%$
test_dqn_speed[reduce-overhead-backward] 0.9458ms 0.8892ms 1.1247 KOps/s 1.0896 KOps/s $\color{#35bf28}+3.22\%$
test_ddpg_speed[False-None] 3.6479ms 2.8772ms 347.5578 Ops/s 344.6145 Ops/s $\color{#35bf28}+0.85\%$
test_ddpg_speed[False-backward] 4.0835ms 3.9774ms 251.4235 Ops/s 250.6003 Ops/s $\color{#35bf28}+0.33\%$
test_ddpg_speed[True-None] 1.4395ms 1.0012ms 998.8114 Ops/s 998.4639 Ops/s $\color{#35bf28}+0.03\%$
test_ddpg_speed[True-backward] 2.0036ms 1.9029ms 525.5179 Ops/s 440.2358 Ops/s $\textbf{\color{#35bf28}+19.37\%}$
test_ddpg_speed[reduce-overhead-None] 1.3095ms 0.9990ms 1.0010 KOps/s 1.0035 KOps/s $\color{#d91a1a}-0.25\%$
test_ddpg_speed[reduce-overhead-backward] 1.9715ms 1.8983ms 526.7820 Ops/s 516.9930 Ops/s $\color{#35bf28}+1.89\%$
test_sac_speed[False-None] 9.5487ms 8.0196ms 124.6942 Ops/s 122.7742 Ops/s $\color{#35bf28}+1.56\%$
test_sac_speed[False-backward] 12.9201ms 10.7809ms 92.7563 Ops/s 92.7481 Ops/s $+0.01\%$
test_sac_speed[True-None] 2.0484ms 1.8259ms 547.6740 Ops/s 536.2309 Ops/s $\color{#35bf28}+2.13\%$
test_sac_speed[True-backward] 3.6454ms 3.5145ms 284.5375 Ops/s 269.2152 Ops/s $\textbf{\color{#35bf28}+5.69\%}$
test_sac_speed[reduce-overhead-None] 2.3318ms 1.8243ms 548.1648 Ops/s 540.8658 Ops/s $\color{#35bf28}+1.35\%$
test_sac_speed[reduce-overhead-backward] 3.5558ms 3.4996ms 285.7464 Ops/s 281.8097 Ops/s $\color{#35bf28}+1.40\%$
test_redq_speed[False-None] 13.7742ms 12.5852ms 79.4586 Ops/s 64.6857 Ops/s $\textbf{\color{#35bf28}+22.84\%}$
test_redq_speed[False-backward] 23.8952ms 21.9232ms 45.6138 Ops/s 43.3870 Ops/s $\textbf{\color{#35bf28}+5.13\%}$
test_redq_speed[True-None] 5.8186ms 4.7716ms 209.5740 Ops/s 193.9444 Ops/s $\textbf{\color{#35bf28}+8.06\%}$
test_redq_speed[True-backward] 13.8739ms 12.1618ms 82.2250 Ops/s 79.6692 Ops/s $\color{#35bf28}+3.21\%$
test_redq_speed[reduce-overhead-None] 5.2324ms 4.7574ms 210.2006 Ops/s 207.0792 Ops/s $\color{#35bf28}+1.51\%$
test_redq_speed[reduce-overhead-backward] 12.6989ms 12.1408ms 82.3666 Ops/s 78.4052 Ops/s $\textbf{\color{#35bf28}+5.05\%}$
test_redq_deprec_speed[False-None] 15.1570ms 12.7142ms 78.6522 Ops/s 73.4485 Ops/s $\textbf{\color{#35bf28}+7.08\%}$
test_redq_deprec_speed[False-backward] 18.8821ms 18.2027ms 54.9370 Ops/s 51.9615 Ops/s $\textbf{\color{#35bf28}+5.73\%}$
test_redq_deprec_speed[True-None] 4.3851ms 3.6108ms 276.9505 Ops/s 273.2120 Ops/s $\color{#35bf28}+1.37\%$
test_redq_deprec_speed[True-backward] 8.4860ms 7.9955ms 125.0711 Ops/s 114.8546 Ops/s $\textbf{\color{#35bf28}+8.90\%}$
test_redq_deprec_speed[reduce-overhead-None] 4.4178ms 3.5805ms 279.2888 Ops/s 272.5090 Ops/s $\color{#35bf28}+2.49\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.9301ms 8.1806ms 122.2403 Ops/s 119.8425 Ops/s $\color{#35bf28}+2.00\%$
test_td3_speed[False-None] 8.1391ms 7.8988ms 126.6023 Ops/s 121.4651 Ops/s $\color{#35bf28}+4.23\%$
test_td3_speed[False-backward] 10.8933ms 10.2564ms 97.5001 Ops/s 93.1233 Ops/s $\color{#35bf28}+4.70\%$
test_td3_speed[True-None] 2.0377ms 1.7137ms 583.5277 Ops/s 565.3535 Ops/s $\color{#35bf28}+3.21\%$
test_td3_speed[True-backward] 3.6235ms 3.3149ms 301.6637 Ops/s 296.5331 Ops/s $\color{#35bf28}+1.73\%$
test_td3_speed[reduce-overhead-None] 1.8817ms 1.7066ms 585.9460 Ops/s 570.5533 Ops/s $\color{#35bf28}+2.70\%$
test_td3_speed[reduce-overhead-backward] 3.3515ms 3.2966ms 303.3424 Ops/s 297.0528 Ops/s $\color{#35bf28}+2.12\%$
test_cql_speed[False-None] 38.6540ms 36.0268ms 27.7571 Ops/s 27.1417 Ops/s $\color{#35bf28}+2.27\%$
test_cql_speed[False-backward] 51.9895ms 47.2403ms 21.1684 Ops/s 21.3775 Ops/s $\color{#d91a1a}-0.98\%$
test_cql_speed[True-None] 16.4966ms 15.5861ms 64.1599 Ops/s 63.3073 Ops/s $\color{#35bf28}+1.35\%$
test_cql_speed[True-backward] 23.2266ms 22.2685ms 44.9066 Ops/s 44.2539 Ops/s $\color{#35bf28}+1.47\%$
test_cql_speed[reduce-overhead-None] 16.8260ms 15.6184ms 64.0272 Ops/s 62.4956 Ops/s $\color{#35bf28}+2.45\%$
test_cql_speed[reduce-overhead-backward] 24.6891ms 22.4996ms 44.4453 Ops/s 43.8772 Ops/s $\color{#35bf28}+1.29\%$
test_a2c_speed[False-None] 8.0866ms 7.1560ms 139.7433 Ops/s 138.0608 Ops/s $\color{#35bf28}+1.22\%$
test_a2c_speed[False-backward] 15.2669ms 14.3124ms 69.8695 Ops/s 68.8759 Ops/s $\color{#35bf28}+1.44\%$
test_a2c_speed[True-None] 4.8929ms 4.1944ms 238.4137 Ops/s 236.4939 Ops/s $\color{#35bf28}+0.81\%$
test_a2c_speed[True-backward] 11.6996ms 10.7207ms 93.2773 Ops/s 90.0557 Ops/s $\color{#35bf28}+3.58\%$
test_a2c_speed[reduce-overhead-None] 4.8912ms 4.2043ms 237.8490 Ops/s 233.5905 Ops/s $\color{#35bf28}+1.82\%$
test_a2c_speed[reduce-overhead-backward] 11.8047ms 10.7231ms 93.2565 Ops/s 91.9334 Ops/s $\color{#35bf28}+1.44\%$
test_ppo_speed[False-None] 8.9149ms 7.4074ms 134.9995 Ops/s 132.3844 Ops/s $\color{#35bf28}+1.98\%$
test_ppo_speed[False-backward] 16.0764ms 14.7646ms 67.7297 Ops/s 66.9592 Ops/s $\color{#35bf28}+1.15\%$
test_ppo_speed[True-None] 5.6394ms 3.7046ms 269.9352 Ops/s 267.3470 Ops/s $\color{#35bf28}+0.97\%$
test_ppo_speed[True-backward] 10.4999ms 9.6915ms 103.1836 Ops/s 102.6375 Ops/s $\color{#35bf28}+0.53\%$
test_ppo_speed[reduce-overhead-None] 3.7940ms 3.6767ms 271.9856 Ops/s 268.1096 Ops/s $\color{#35bf28}+1.45\%$
test_ppo_speed[reduce-overhead-backward] 18.5024ms 10.1869ms 98.1652 Ops/s 100.5024 Ops/s $\color{#d91a1a}-2.33\%$
test_reinforce_speed[False-None] 7.9996ms 6.4922ms 154.0307 Ops/s 149.8760 Ops/s $\color{#35bf28}+2.77\%$
test_reinforce_speed[False-backward] 11.8428ms 9.8621ms 101.3986 Ops/s 101.6479 Ops/s $\color{#d91a1a}-0.25\%$
test_reinforce_speed[True-None] 3.5055ms 2.6595ms 376.0051 Ops/s 370.4738 Ops/s $\color{#35bf28}+1.49\%$
test_reinforce_speed[True-backward] 9.7064ms 8.7932ms 113.7246 Ops/s 115.7871 Ops/s $\color{#d91a1a}-1.78\%$
test_reinforce_speed[reduce-overhead-None] 3.2138ms 2.6506ms 377.2776 Ops/s 368.0861 Ops/s $\color{#35bf28}+2.50\%$
test_reinforce_speed[reduce-overhead-backward] 9.1695ms 8.6653ms 115.4033 Ops/s 113.9744 Ops/s $\color{#35bf28}+1.25\%$
test_iql_speed[False-None] 34.0862ms 32.2780ms 30.9809 Ops/s 30.8231 Ops/s $\color{#35bf28}+0.51\%$
test_iql_speed[False-backward] 64.8390ms 45.7838ms 21.8418 Ops/s 22.1092 Ops/s $\color{#d91a1a}-1.21\%$
test_iql_speed[True-None] 11.4665ms 10.7252ms 93.2387 Ops/s 91.9555 Ops/s $\color{#35bf28}+1.40\%$
test_iql_speed[True-backward] 23.3034ms 21.8575ms 45.7509 Ops/s 44.8553 Ops/s $\color{#35bf28}+2.00\%$
test_iql_speed[reduce-overhead-None] 11.5332ms 10.7150ms 93.3271 Ops/s 92.6579 Ops/s $\color{#35bf28}+0.72\%$
test_iql_speed[reduce-overhead-backward] 23.9182ms 21.8905ms 45.6820 Ops/s 45.3178 Ops/s $\color{#35bf28}+0.80\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.6432ms 5.0416ms 198.3514 Ops/s 193.5535 Ops/s $\color{#35bf28}+2.48\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.2426ms 0.5136ms 1.9472 KOps/s 1.9372 KOps/s $\color{#35bf28}+0.52\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7147ms 0.4879ms 2.0496 KOps/s 2.0570 KOps/s $\color{#d91a1a}-0.36\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.5726ms 4.8813ms 204.8651 Ops/s 207.4419 Ops/s $\color{#d91a1a}-1.24\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.3653s 0.7864ms 1.2717 KOps/s 1.9591 KOps/s $\textbf{\color{#d91a1a}-35.09\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6574ms 0.4739ms 2.1100 KOps/s 2.0802 KOps/s $\color{#35bf28}+1.43\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7687ms 1.6259ms 615.0314 Ops/s 614.3353 Ops/s $\color{#35bf28}+0.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 8.6844ms 1.6030ms 623.8295 Ops/s 631.8966 Ops/s $\color{#d91a1a}-1.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2079ms 4.9354ms 202.6185 Ops/s 204.3014 Ops/s $\color{#d91a1a}-0.82\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.5481ms 0.6450ms 1.5505 KOps/s 1.5384 KOps/s $\color{#35bf28}+0.78\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8393ms 0.6186ms 1.6165 KOps/s 1.5937 KOps/s $\color{#35bf28}+1.43\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.1352ms 4.8215ms 207.4030 Ops/s 206.7175 Ops/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.5952ms 0.5178ms 1.9313 KOps/s 1.9273 KOps/s $\color{#35bf28}+0.21\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7461ms 0.4946ms 2.0220 KOps/s 2.0194 KOps/s $\color{#35bf28}+0.13\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.5077ms 4.8675ms 205.4462 Ops/s 202.1661 Ops/s $\color{#35bf28}+1.62\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0899ms 0.5006ms 1.9977 KOps/s 1.9662 KOps/s $\color{#35bf28}+1.60\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7144ms 0.4756ms 2.1028 KOps/s 2.0808 KOps/s $\color{#35bf28}+1.05\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2346ms 5.0220ms 199.1219 Ops/s 202.5821 Ops/s $\color{#d91a1a}-1.71\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.1824ms 0.6488ms 1.5414 KOps/s 1.5434 KOps/s $\color{#d91a1a}-0.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7599ms 0.6232ms 1.6047 KOps/s 1.5896 KOps/s $\color{#35bf28}+0.95\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4246s 12.7010ms 78.7340 Ops/s 38.1521 Ops/s $\textbf{\color{#35bf28}+106.37\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.3784ms 2.3392ms 427.4914 Ops/s 400.0356 Ops/s $\textbf{\color{#35bf28}+6.86\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.9202ms 1.2466ms 802.1727 Ops/s 754.9833 Ops/s $\textbf{\color{#35bf28}+6.25\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.7293ms 4.1989ms 238.1596 Ops/s 227.8459 Ops/s $\color{#35bf28}+4.53\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.9300ms 2.3333ms 428.5746 Ops/s 420.5460 Ops/s $\color{#35bf28}+1.91\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.9443ms 1.4583ms 685.7267 Ops/s 720.1031 Ops/s $\color{#d91a1a}-4.77\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4384s 13.1291ms 76.1669 Ops/s 237.4360 Ops/s $\textbf{\color{#d91a1a}-67.92\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 10.0641ms 2.4677ms 405.2335 Ops/s 402.1912 Ops/s $\color{#35bf28}+0.76\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.3816ms 1.4208ms 703.8344 Ops/s 676.9696 Ops/s $\color{#35bf28}+3.97\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.5434ms 11.2197ms 89.1286 Ops/s 82.5768 Ops/s $\textbf{\color{#35bf28}+7.93\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 17.0109ms 14.6718ms 68.1580 Ops/s 68.9481 Ops/s $\color{#d91a1a}-1.15\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 20.9728ms 20.0273ms 49.9317 Ops/s 48.8103 Ops/s $\color{#35bf28}+2.30\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.3161ms 14.8017ms 67.5596 Ops/s 67.9532 Ops/s $\color{#d91a1a}-0.58\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.1187ms 19.9297ms 50.1763 Ops/s 49.9496 Ops/s $\color{#35bf28}+0.45\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.6376ms 15.8857ms 62.9498 Ops/s 63.9498 Ops/s $\color{#d91a1a}-1.56\%$

Copy link

github-actions bot commented Dec 6, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}11$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7453s 0.7444s 1.3434 Ops/s 1.3083 Ops/s $\color{#35bf28}+2.68\%$
test_transformed 1.0960s 1.0169s 0.9834 Ops/s 1.0092 Ops/s $\color{#d91a1a}-2.56\%$
test_serial 2.2387s 2.1576s 0.4635 Ops/s 0.4711 Ops/s $\color{#d91a1a}-1.63\%$
test_parallel 2.0264s 1.9871s 0.5032 Ops/s 0.5152 Ops/s $\color{#d91a1a}-2.31\%$
test_step_mdp_speed[True-True-True-True-True] 0.2338ms 39.9954μs 25.0029 KOps/s 25.4255 KOps/s $\color{#d91a1a}-1.66\%$
test_step_mdp_speed[True-True-True-True-False] 54.8110μs 22.7139μs 44.0259 KOps/s 44.1110 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[True-True-True-False-True] 88.3420μs 21.8570μs 45.7519 KOps/s 45.6983 KOps/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[True-True-True-False-False] 66.0210μs 12.6346μs 79.1474 KOps/s 78.9479 KOps/s $\color{#35bf28}+0.25\%$
test_step_mdp_speed[True-True-False-True-True] 72.5910μs 42.6282μs 23.4587 KOps/s 23.7413 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[True-True-False-True-False] 55.4610μs 24.8119μs 40.3032 KOps/s 40.7815 KOps/s $\color{#d91a1a}-1.17\%$
test_step_mdp_speed[True-True-False-False-True] 55.5000μs 24.5822μs 40.6798 KOps/s 41.6139 KOps/s $\color{#d91a1a}-2.24\%$
test_step_mdp_speed[True-True-False-False-False] 49.4510μs 15.0981μs 66.2335 KOps/s 67.7850 KOps/s $\color{#d91a1a}-2.29\%$
test_step_mdp_speed[True-False-True-True-True] 0.1008ms 45.0434μs 22.2008 KOps/s 23.0467 KOps/s $\color{#d91a1a}-3.67\%$
test_step_mdp_speed[True-False-True-True-False] 58.2910μs 27.2218μs 36.7353 KOps/s 37.0516 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[True-False-True-False-True] 53.3510μs 24.6807μs 40.5175 KOps/s 42.2123 KOps/s $\color{#d91a1a}-4.01\%$
test_step_mdp_speed[True-False-True-False-False] 49.0310μs 15.0208μs 66.5745 KOps/s 68.3176 KOps/s $\color{#d91a1a}-2.55\%$
test_step_mdp_speed[True-False-False-True-True] 91.1710μs 47.4576μs 21.0714 KOps/s 22.2804 KOps/s $\textbf{\color{#d91a1a}-5.43\%}$
test_step_mdp_speed[True-False-False-True-False] 57.3710μs 29.1731μs 34.2782 KOps/s 34.8875 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-False-False-False-True] 59.9810μs 25.9953μs 38.4685 KOps/s 39.3324 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[True-False-False-False-False] 52.5410μs 16.9477μs 59.0051 KOps/s 59.3780 KOps/s $\color{#d91a1a}-0.63\%$
test_step_mdp_speed[False-True-True-True-True] 76.4910μs 45.0371μs 22.2039 KOps/s 22.9608 KOps/s $\color{#d91a1a}-3.30\%$
test_step_mdp_speed[False-True-True-True-False] 58.0400μs 26.9630μs 37.0879 KOps/s 37.1588 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[False-True-True-False-True] 59.9310μs 28.2072μs 35.4519 KOps/s 35.9142 KOps/s $\color{#d91a1a}-1.29\%$
test_step_mdp_speed[False-True-True-False-False] 47.0910μs 17.0481μs 58.6576 KOps/s 61.0371 KOps/s $\color{#d91a1a}-3.90\%$
test_step_mdp_speed[False-True-False-True-True] 78.2910μs 47.4286μs 21.0843 KOps/s 21.8676 KOps/s $\color{#d91a1a}-3.58\%$
test_step_mdp_speed[False-True-False-True-False] 54.1910μs 29.2556μs 34.1815 KOps/s 35.3495 KOps/s $\color{#d91a1a}-3.30\%$
test_step_mdp_speed[False-True-False-False-True] 3.1407ms 30.6045μs 32.6749 KOps/s 34.1596 KOps/s $\color{#d91a1a}-4.35\%$
test_step_mdp_speed[False-True-False-False-False] 48.6710μs 19.0155μs 52.5886 KOps/s 53.5098 KOps/s $\color{#d91a1a}-1.72\%$
test_step_mdp_speed[False-False-True-True-True] 83.7610μs 49.8539μs 20.0586 KOps/s 20.9741 KOps/s $\color{#d91a1a}-4.36\%$
test_step_mdp_speed[False-False-True-True-False] 66.8110μs 32.0873μs 31.1650 KOps/s 31.7150 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[False-False-True-False-True] 64.4910μs 30.2263μs 33.0838 KOps/s 33.8479 KOps/s $\color{#d91a1a}-2.26\%$
test_step_mdp_speed[False-False-True-False-False] 84.8410μs 18.8498μs 53.0509 KOps/s 54.2162 KOps/s $\color{#d91a1a}-2.15\%$
test_step_mdp_speed[False-False-False-True-True] 81.1820μs 50.5323μs 19.7893 KOps/s 20.1515 KOps/s $\color{#d91a1a}-1.80\%$
test_step_mdp_speed[False-False-False-True-False] 0.1081ms 34.3341μs 29.1256 KOps/s 29.8522 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[False-False-False-False-True] 60.4310μs 32.2448μs 31.0128 KOps/s 32.7979 KOps/s $\textbf{\color{#d91a1a}-5.44\%}$
test_step_mdp_speed[False-False-False-False-False] 49.0110μs 20.9101μs 47.8238 KOps/s 47.8301 KOps/s $\color{#d91a1a}-0.01\%$
test_values[generalized_advantage_estimate-True-True] 24.5924ms 24.1327ms 41.4375 Ops/s 41.9225 Ops/s $\color{#d91a1a}-1.16\%$
test_values[vec_generalized_advantage_estimate-True-True] 93.3860ms 2.7585ms 362.5141 Ops/s 352.4001 Ops/s $\color{#35bf28}+2.87\%$
test_values[td0_return_estimate-False-False] 0.1026ms 78.6557μs 12.7136 KOps/s 12.7381 KOps/s $\color{#d91a1a}-0.19\%$
test_values[td1_return_estimate-False-False] 54.0504ms 53.7484ms 18.6052 Ops/s 18.8439 Ops/s $\color{#d91a1a}-1.27\%$
test_values[vec_td1_return_estimate-False-False] 1.3543ms 1.0728ms 932.1404 Ops/s 938.7721 Ops/s $\color{#d91a1a}-0.71\%$
test_values[td_lambda_return_estimate-True-False] 85.5765ms 85.2561ms 11.7294 Ops/s 11.8428 Ops/s $\color{#d91a1a}-0.96\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3656ms 1.0709ms 933.7517 Ops/s 932.7080 Ops/s $\color{#35bf28}+0.11\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.2807ms 24.0314ms 41.6123 Ops/s 42.0456 Ops/s $\color{#d91a1a}-1.03\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0258ms 0.7400ms 1.3514 KOps/s 1.3583 KOps/s $\color{#d91a1a}-0.51\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7479ms 0.6565ms 1.5233 KOps/s 1.5284 KOps/s $\color{#d91a1a}-0.33\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5130ms 1.4674ms 681.4613 Ops/s 682.3994 Ops/s $\color{#d91a1a}-0.14\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7540ms 0.6922ms 1.4447 KOps/s 1.4579 KOps/s $\color{#d91a1a}-0.90\%$
test_dqn_speed[False-None] 6.9034ms 1.5005ms 666.4477 Ops/s 673.0365 Ops/s $\color{#d91a1a}-0.98\%$
test_dqn_speed[False-backward] 2.3822ms 2.0873ms 479.0888 Ops/s 484.0813 Ops/s $\color{#d91a1a}-1.03\%$
test_dqn_speed[True-None] 0.6556ms 0.5357ms 1.8667 KOps/s 1.8689 KOps/s $\color{#d91a1a}-0.12\%$
test_dqn_speed[True-backward] 1.2131ms 1.1013ms 908.0037 Ops/s 908.7716 Ops/s $\color{#d91a1a}-0.08\%$
test_dqn_speed[reduce-overhead-None] 0.6915ms 0.5471ms 1.8278 KOps/s 1.8241 KOps/s $\color{#35bf28}+0.20\%$
test_dqn_speed[reduce-overhead-backward] 1.0252ms 0.9670ms 1.0341 KOps/s 1.0062 KOps/s $\color{#35bf28}+2.78\%$
test_ddpg_speed[False-None] 3.1289ms 2.8158ms 355.1358 Ops/s 354.6442 Ops/s $\color{#35bf28}+0.14\%$
test_ddpg_speed[False-backward] 4.1577ms 3.9987ms 250.0807 Ops/s 245.3650 Ops/s $\color{#35bf28}+1.92\%$
test_ddpg_speed[True-None] 1.2137ms 1.0783ms 927.3862 Ops/s 925.9054 Ops/s $\color{#35bf28}+0.16\%$
test_ddpg_speed[True-backward] 2.2317ms 2.1573ms 463.5505 Ops/s 465.9700 Ops/s $\color{#d91a1a}-0.52\%$
test_ddpg_speed[reduce-overhead-None] 1.2419ms 1.0904ms 917.0795 Ops/s 919.1106 Ops/s $\color{#d91a1a}-0.22\%$
test_ddpg_speed[reduce-overhead-backward] 1.6912ms 1.6320ms 612.7469 Ops/s 566.7491 Ops/s $\textbf{\color{#35bf28}+8.12\%}$
test_sac_speed[False-None] 8.7184ms 7.9754ms 125.3861 Ops/s 127.1983 Ops/s $\color{#d91a1a}-1.42\%$
test_sac_speed[False-backward] 11.2452ms 10.7272ms 93.2213 Ops/s 91.6823 Ops/s $\color{#35bf28}+1.68\%$
test_sac_speed[True-None] 1.6413ms 1.5487ms 645.6851 Ops/s 648.1141 Ops/s $\color{#d91a1a}-0.37\%$
test_sac_speed[True-backward] 3.4689ms 3.4104ms 293.2182 Ops/s 301.2458 Ops/s $\color{#d91a1a}-2.66\%$
test_sac_speed[reduce-overhead-None] 23.1656ms 12.6016ms 79.3550 Ops/s 78.8474 Ops/s $\color{#35bf28}+0.64\%$
test_sac_speed[reduce-overhead-backward] 1.5165ms 1.4760ms 677.4853 Ops/s 756.9279 Ops/s $\textbf{\color{#d91a1a}-10.50\%}$
test_redq_speed[False-None] 8.2606ms 7.3891ms 135.3349 Ops/s 134.8508 Ops/s $\color{#35bf28}+0.36\%$
test_redq_speed[False-backward] 12.5431ms 11.3962ms 87.7484 Ops/s 90.7050 Ops/s $\color{#d91a1a}-3.26\%$
test_redq_speed[True-None] 2.1268ms 2.0204ms 494.9427 Ops/s 500.1870 Ops/s $\color{#d91a1a}-1.05\%$
test_redq_speed[True-backward] 3.6884ms 3.6265ms 275.7499 Ops/s 261.1778 Ops/s $\textbf{\color{#35bf28}+5.58\%}$
test_redq_speed[reduce-overhead-None] 2.1680ms 1.9950ms 501.2629 Ops/s 500.6943 Ops/s $\color{#35bf28}+0.11\%$
test_redq_speed[reduce-overhead-backward] 4.0820ms 3.6397ms 274.7443 Ops/s 272.3482 Ops/s $\color{#35bf28}+0.88\%$
test_redq_deprec_speed[False-None] 9.4124ms 8.8908ms 112.4764 Ops/s 112.4760 Ops/s $+0.00\%$
test_redq_deprec_speed[False-backward] 12.1995ms 11.8006ms 84.7414 Ops/s 84.4906 Ops/s $\color{#35bf28}+0.30\%$
test_redq_deprec_speed[True-None] 2.4019ms 2.3171ms 431.5761 Ops/s 431.5386 Ops/s $+0.01\%$
test_redq_deprec_speed[True-backward] 4.5205ms 3.9771ms 251.4385 Ops/s 252.2430 Ops/s $\color{#d91a1a}-0.32\%$
test_redq_deprec_speed[reduce-overhead-None] 2.5027ms 2.3315ms 428.9056 Ops/s 433.8763 Ops/s $\color{#d91a1a}-1.15\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.4301ms 3.9780ms 251.3851 Ops/s 252.7714 Ops/s $\color{#d91a1a}-0.55\%$
test_td3_speed[False-None] 7.7942ms 7.7685ms 128.7246 Ops/s 128.1094 Ops/s $\color{#35bf28}+0.48\%$
test_td3_speed[False-backward] 10.5864ms 9.9779ms 100.2218 Ops/s 100.4702 Ops/s $\color{#d91a1a}-0.25\%$
test_td3_speed[True-None] 1.6135ms 1.5840ms 631.3052 Ops/s 621.3925 Ops/s $\color{#35bf28}+1.60\%$
test_td3_speed[True-backward] 3.1514ms 3.0963ms 322.9639 Ops/s 322.9284 Ops/s $\color{#35bf28}+0.01\%$
test_td3_speed[reduce-overhead-None] 50.0595ms 25.6409ms 39.0003 Ops/s 37.4732 Ops/s $\color{#35bf28}+4.08\%$
test_td3_speed[reduce-overhead-backward] 1.3064ms 1.2594ms 794.0476 Ops/s 789.7547 Ops/s $\color{#35bf28}+0.54\%$
test_cql_speed[False-None] 16.4516ms 15.9719ms 62.6098 Ops/s 63.0179 Ops/s $\color{#d91a1a}-0.65\%$
test_cql_speed[False-backward] 21.3089ms 20.8501ms 47.9614 Ops/s 47.9913 Ops/s $\color{#d91a1a}-0.06\%$
test_cql_speed[True-None] 3.0896ms 2.9300ms 341.3024 Ops/s 331.8427 Ops/s $\color{#35bf28}+2.85\%$
test_cql_speed[True-backward] 5.5129ms 5.1065ms 195.8283 Ops/s 197.1162 Ops/s $\color{#d91a1a}-0.65\%$
test_cql_speed[reduce-overhead-None] 21.6699ms 13.1156ms 76.2454 Ops/s 76.0390 Ops/s $\color{#35bf28}+0.27\%$
test_cql_speed[reduce-overhead-backward] 1.5260ms 1.4796ms 675.8713 Ops/s 674.4078 Ops/s $\color{#35bf28}+0.22\%$
test_a2c_speed[False-None] 3.3122ms 3.1595ms 316.5072 Ops/s 316.7502 Ops/s $\color{#d91a1a}-0.08\%$
test_a2c_speed[False-backward] 6.5220ms 5.9336ms 168.5331 Ops/s 166.7053 Ops/s $\color{#35bf28}+1.10\%$
test_a2c_speed[True-None] 1.2026ms 1.0012ms 998.7570 Ops/s 997.6392 Ops/s $\color{#35bf28}+0.11\%$
test_a2c_speed[True-backward] 2.6962ms 2.6492ms 377.4658 Ops/s 364.8169 Ops/s $\color{#35bf28}+3.47\%$
test_a2c_speed[reduce-overhead-None] 0.3975s 12.2195ms 81.8363 Ops/s 86.8511 Ops/s $\textbf{\color{#d91a1a}-5.77\%}$
test_a2c_speed[reduce-overhead-backward] 1.0485ms 0.9805ms 1.0199 KOps/s 1.0278 KOps/s $\color{#d91a1a}-0.78\%$
test_ppo_speed[False-None] 4.0192ms 3.6443ms 274.3993 Ops/s 274.8294 Ops/s $\color{#d91a1a}-0.16\%$
test_ppo_speed[False-backward] 7.1950ms 6.6609ms 150.1289 Ops/s 151.3388 Ops/s $\color{#d91a1a}-0.80\%$
test_ppo_speed[True-None] 1.3432ms 0.9413ms 1.0624 KOps/s 1.0463 KOps/s $\color{#35bf28}+1.54\%$
test_ppo_speed[True-backward] 2.6925ms 2.5740ms 388.5001 Ops/s 368.0209 Ops/s $\textbf{\color{#35bf28}+5.56\%}$
test_ppo_speed[reduce-overhead-None] 0.8999ms 0.4874ms 2.0516 KOps/s 1.9065 KOps/s $\textbf{\color{#35bf28}+7.62\%}$
test_ppo_speed[reduce-overhead-backward] 1.1751ms 1.1099ms 900.9479 Ops/s 892.6412 Ops/s $\color{#35bf28}+0.93\%$
test_reinforce_speed[False-None] 2.6360ms 2.2330ms 447.8266 Ops/s 448.2889 Ops/s $\color{#d91a1a}-0.10\%$
test_reinforce_speed[False-backward] 3.7097ms 3.2909ms 303.8644 Ops/s 296.4704 Ops/s $\color{#35bf28}+2.49\%$
test_reinforce_speed[True-None] 1.2443ms 0.8336ms 1.1995 KOps/s 1.1909 KOps/s $\color{#35bf28}+0.72\%$
test_reinforce_speed[True-backward] 2.6381ms 2.5718ms 388.8276 Ops/s 389.2284 Ops/s $\color{#d91a1a}-0.10\%$
test_reinforce_speed[reduce-overhead-None] 22.6905ms 11.6938ms 85.5152 Ops/s 87.9579 Ops/s $\color{#d91a1a}-2.78\%$
test_reinforce_speed[reduce-overhead-backward] 1.2193ms 1.1793ms 847.9435 Ops/s 843.2397 Ops/s $\color{#35bf28}+0.56\%$
test_iql_speed[False-None] 9.6559ms 9.0979ms 109.9155 Ops/s 111.4557 Ops/s $\color{#d91a1a}-1.38\%$
test_iql_speed[False-backward] 13.2760ms 12.8456ms 77.8479 Ops/s 78.2570 Ops/s $\color{#d91a1a}-0.52\%$
test_iql_speed[True-None] 1.9208ms 1.7679ms 565.6488 Ops/s 563.0694 Ops/s $\color{#35bf28}+0.46\%$
test_iql_speed[True-backward] 4.5552ms 4.2768ms 233.8214 Ops/s 235.5986 Ops/s $\color{#d91a1a}-0.75\%$
test_iql_speed[reduce-overhead-None] 19.9646ms 11.3758ms 87.9056 Ops/s 87.9024 Ops/s $+0.00\%$
test_iql_speed[reduce-overhead-backward] 1.4994ms 1.4153ms 706.5603 Ops/s 719.8527 Ops/s $\color{#d91a1a}-1.85\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9259ms 6.4473ms 155.1037 Ops/s 154.6844 Ops/s $\color{#35bf28}+0.27\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6833ms 0.3638ms 2.7491 KOps/s 3.7080 KOps/s $\textbf{\color{#d91a1a}-25.86\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5158ms 0.2992ms 3.3427 KOps/s 2.8387 KOps/s $\textbf{\color{#35bf28}+17.75\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4762ms 6.1855ms 161.6681 Ops/s 160.9100 Ops/s $\color{#35bf28}+0.47\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8501ms 0.3152ms 3.1727 KOps/s 3.0701 KOps/s $\color{#35bf28}+3.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6630ms 0.2773ms 3.6068 KOps/s 3.3502 KOps/s $\textbf{\color{#35bf28}+7.66\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.4014ms 1.2165ms 822.0580 Ops/s 696.1269 Ops/s $\textbf{\color{#35bf28}+18.09\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5742ms 1.1890ms 841.0780 Ops/s 712.1112 Ops/s $\textbf{\color{#35bf28}+18.11\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5126ms 6.4201ms 155.7617 Ops/s 156.2513 Ops/s $\color{#d91a1a}-0.31\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.1856ms 0.4394ms 2.2756 KOps/s 2.3716 KOps/s $\color{#d91a1a}-4.05\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7955ms 0.4712ms 2.1222 KOps/s 2.1770 KOps/s $\color{#d91a1a}-2.51\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.5218ms 6.2788ms 159.2668 Ops/s 159.4513 Ops/s $\color{#d91a1a}-0.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.1233ms 0.3680ms 2.7174 KOps/s 3.3349 KOps/s $\textbf{\color{#d91a1a}-18.52\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5316ms 0.3421ms 2.9229 KOps/s 3.4484 KOps/s $\textbf{\color{#d91a1a}-15.24\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.5682ms 6.2188ms 160.8028 Ops/s 161.2026 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.5037ms 0.2628ms 3.8047 KOps/s 3.9033 KOps/s $\color{#d91a1a}-2.53\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5375ms 0.2664ms 3.7538 KOps/s 3.1753 KOps/s $\textbf{\color{#35bf28}+18.22\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.7659ms 6.4527ms 154.9744 Ops/s 156.8349 Ops/s $\color{#d91a1a}-1.19\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0863ms 0.4126ms 2.4234 KOps/s 2.4408 KOps/s $\color{#d91a1a}-0.71\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6411ms 0.4552ms 2.1970 KOps/s 2.1953 KOps/s $\color{#35bf28}+0.08\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.8691ms 5.2920ms 188.9657 Ops/s 191.2935 Ops/s $\color{#d91a1a}-1.22\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 10.0907ms 2.0723ms 482.5626 Ops/s 447.1980 Ops/s $\textbf{\color{#35bf28}+7.91\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.5968ms 1.2030ms 831.2833 Ops/s 826.5529 Ops/s $\color{#35bf28}+0.57\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4921s 15.0152ms 66.5990 Ops/s 191.5921 Ops/s $\textbf{\color{#d91a1a}-65.24\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.3698ms 2.0187ms 495.3634 Ops/s 446.4351 Ops/s $\textbf{\color{#35bf28}+10.96\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 10.0368ms 1.3349ms 749.1475 Ops/s 852.0625 Ops/s $\textbf{\color{#d91a1a}-12.08\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 9.8807ms 5.6016ms 178.5193 Ops/s 33.4766 Ops/s $\textbf{\color{#35bf28}+433.27\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.7567ms 2.2661ms 441.2962 Ops/s 471.6886 Ops/s $\textbf{\color{#d91a1a}-6.44\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 9.3040ms 1.4413ms 693.8366 Ops/s 731.8678 Ops/s $\textbf{\color{#d91a1a}-5.20\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.5920ms 13.1782ms 75.8832 Ops/s 74.4908 Ops/s $\color{#35bf28}+1.87\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 17.3164ms 16.6561ms 60.0380 Ops/s 58.8739 Ops/s $\color{#35bf28}+1.98\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.2847ms 17.8795ms 55.9299 Ops/s 54.1355 Ops/s $\color{#35bf28}+3.31\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.0950ms 16.6731ms 59.9769 Ops/s 57.9383 Ops/s $\color{#35bf28}+3.52\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.6925ms 17.7296ms 56.4027 Ops/s 55.1139 Ops/s $\color{#35bf28}+2.34\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.6618ms 18.1018ms 55.2431 Ops/s 54.0064 Ops/s $\color{#35bf28}+2.29\%$

[ghstack-poisoned]
@vmoens vmoens closed this Dec 13, 2024
tianyu1997 pushed a commit to tianyu1997/RL that referenced this pull request Mar 18, 2025
ghstack-source-id: 2261561d65663beede765c90d1d7faa2598151a1
Pull Request resolved: pytorch/rl#2637
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
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