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] thread setting bug #1852

Merged
merged 2 commits into from
Jan 31, 2024
Merged

[BugFix] thread setting bug #1852

merged 2 commits into from
Jan 31, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jan 31, 2024

No description provided.

Copy link

pytorch-bot bot commented Jan 31, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1852

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

❌ 2 New Failures, 1 Pending, 3 Unrelated Failures

As of commit 49800e8 with merge base 017bcd0 (image):

NEW FAILURES - The following jobs have failed:

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

BROKEN TRUNK - The following job 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.

@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 Jan 31, 2024
Copy link

github-actions bot commented Jan 31, 2024

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}7$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 63.3458ms 62.2435ms 16.0659 Ops/s 15.6500 Ops/s $\color{#35bf28}+2.66\%$
test_sync 46.6348ms 35.4686ms 28.1939 Ops/s 28.4954 Ops/s $\color{#d91a1a}-1.06\%$
test_async 0.1214s 33.5435ms 29.8120 Ops/s 28.4377 Ops/s $\color{#35bf28}+4.83\%$
test_simple 0.4230s 0.4203s 2.3794 Ops/s 2.2028 Ops/s $\textbf{\color{#35bf28}+8.02\%}$
test_transformed 0.6726s 0.6000s 1.6666 Ops/s 1.6045 Ops/s $\color{#35bf28}+3.87\%$
test_serial 1.4299s 1.3487s 0.7414 Ops/s 0.7242 Ops/s $\color{#35bf28}+2.38\%$
test_parallel 1.2918s 1.2280s 0.8144 Ops/s 0.8149 Ops/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[True-True-True-True-True] 0.2219ms 21.4240μs 46.6766 KOps/s 46.5486 KOps/s $\color{#35bf28}+0.28\%$
test_step_mdp_speed[True-True-True-True-False] 40.7260μs 13.3175μs 75.0893 KOps/s 77.5355 KOps/s $\color{#d91a1a}-3.15\%$
test_step_mdp_speed[True-True-True-False-True] 60.9700μs 12.5783μs 79.5021 KOps/s 80.7961 KOps/s $\color{#d91a1a}-1.60\%$
test_step_mdp_speed[True-True-True-False-False] 26.2290μs 7.7438μs 129.1360 KOps/s 133.8857 KOps/s $\color{#d91a1a}-3.55\%$
test_step_mdp_speed[True-True-False-True-True] 81.8920μs 22.9284μs 43.6140 KOps/s 44.0782 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[True-True-False-True-False] 41.1170μs 14.5980μs 68.5024 KOps/s 70.8372 KOps/s $\color{#d91a1a}-3.30\%$
test_step_mdp_speed[True-True-False-False-True] 74.3390μs 13.8669μs 72.1141 KOps/s 73.4564 KOps/s $\color{#d91a1a}-1.83\%$
test_step_mdp_speed[True-True-False-False-False] 40.5460μs 8.9351μs 111.9184 KOps/s 115.1556 KOps/s $\color{#d91a1a}-2.81\%$
test_step_mdp_speed[True-False-True-True-True] 80.6900μs 24.2337μs 41.2649 KOps/s 41.9184 KOps/s $\color{#d91a1a}-1.56\%$
test_step_mdp_speed[True-False-True-True-False] 46.2270μs 15.8999μs 62.8933 KOps/s 64.7892 KOps/s $\color{#d91a1a}-2.93\%$
test_step_mdp_speed[True-False-True-False-True] 66.3540μs 13.9033μs 71.9256 KOps/s 73.7810 KOps/s $\color{#d91a1a}-2.51\%$
test_step_mdp_speed[True-False-True-False-False] 51.9260μs 8.9412μs 111.8415 KOps/s 114.2423 KOps/s $\color{#d91a1a}-2.10\%$
test_step_mdp_speed[True-False-False-True-True] 88.1550μs 25.7118μs 38.8926 KOps/s 39.7975 KOps/s $\color{#d91a1a}-2.27\%$
test_step_mdp_speed[True-False-False-True-False] 76.6430μs 18.2891μs 54.6774 KOps/s 59.8660 KOps/s $\textbf{\color{#d91a1a}-8.67\%}$
test_step_mdp_speed[True-False-False-False-True] 71.6130μs 15.1654μs 65.9396 KOps/s 67.8870 KOps/s $\color{#d91a1a}-2.87\%$
test_step_mdp_speed[True-False-False-False-False] 66.0330μs 10.2094μs 97.9486 KOps/s 101.9758 KOps/s $\color{#d91a1a}-3.95\%$
test_step_mdp_speed[False-True-True-True-True] 52.0470μs 24.4220μs 40.9466 KOps/s 41.8908 KOps/s $\color{#d91a1a}-2.25\%$
test_step_mdp_speed[False-True-True-True-False] 64.7910μs 15.8901μs 62.9321 KOps/s 63.4624 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[False-True-True-False-True] 44.7940μs 16.1179μs 62.0428 KOps/s 62.9372 KOps/s $\color{#d91a1a}-1.42\%$
test_step_mdp_speed[False-True-True-False-False] 61.1440μs 10.2003μs 98.0365 KOps/s 100.0481 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[False-True-False-True-True] 55.8840μs 25.4437μs 39.3024 KOps/s 39.9294 KOps/s $\color{#d91a1a}-1.57\%$
test_step_mdp_speed[False-True-False-True-False] 62.2260μs 17.1241μs 58.3972 KOps/s 59.9013 KOps/s $\color{#d91a1a}-2.51\%$
test_step_mdp_speed[False-True-False-False-True] 77.7550μs 17.4086μs 57.4430 KOps/s 58.4535 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[False-True-False-False-False] 40.1050μs 11.5670μs 86.4528 KOps/s 89.1925 KOps/s $\color{#d91a1a}-3.07\%$
test_step_mdp_speed[False-False-True-True-True] 83.8460μs 27.3717μs 36.5341 KOps/s 37.9390 KOps/s $\color{#d91a1a}-3.70\%$
test_step_mdp_speed[False-False-True-True-False] 46.6470μs 18.6094μs 53.7364 KOps/s 55.5421 KOps/s $\color{#d91a1a}-3.25\%$
test_step_mdp_speed[False-False-True-False-True] 73.9080μs 17.4168μs 57.4158 KOps/s 58.3815 KOps/s $\color{#d91a1a}-1.65\%$
test_step_mdp_speed[False-False-True-False-False] 32.0390μs 11.7113μs 85.3873 KOps/s 89.3816 KOps/s $\color{#d91a1a}-4.47\%$
test_step_mdp_speed[False-False-False-True-True] 86.4220μs 28.3815μs 35.2343 KOps/s 36.1527 KOps/s $\color{#d91a1a}-2.54\%$
test_step_mdp_speed[False-False-False-True-False] 77.6150μs 19.7918μs 50.5259 KOps/s 52.1235 KOps/s $\color{#d91a1a}-3.07\%$
test_step_mdp_speed[False-False-False-False-True] 42.7390μs 18.5125μs 54.0177 KOps/s 54.7784 KOps/s $\color{#d91a1a}-1.39\%$
test_step_mdp_speed[False-False-False-False-False] 65.6830μs 12.4877μs 80.0788 KOps/s 81.0660 KOps/s $\color{#d91a1a}-1.22\%$
test_values[generalized_advantage_estimate-True-True] 12.7102ms 9.7652ms 102.4048 Ops/s 105.3603 Ops/s $\color{#d91a1a}-2.81\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.6894ms 36.2584ms 27.5798 Ops/s 27.5217 Ops/s $\color{#35bf28}+0.21\%$
test_values[td0_return_estimate-False-False] 0.2699ms 0.1710ms 5.8474 KOps/s 5.6748 KOps/s $\color{#35bf28}+3.04\%$
test_values[td1_return_estimate-False-False] 24.7720ms 24.1847ms 41.3485 Ops/s 42.3587 Ops/s $\color{#d91a1a}-2.38\%$
test_values[vec_td1_return_estimate-False-False] 37.7040ms 36.2290ms 27.6022 Ops/s 27.7111 Ops/s $\color{#d91a1a}-0.39\%$
test_values[td_lambda_return_estimate-True-False] 38.3240ms 35.1680ms 28.4349 Ops/s 29.4584 Ops/s $\color{#d91a1a}-3.47\%$
test_values[vec_td_lambda_return_estimate-True-False] 40.9553ms 36.5979ms 27.3240 Ops/s 27.7263 Ops/s $\color{#d91a1a}-1.45\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.5389ms 8.4038ms 118.9941 Ops/s 122.4249 Ops/s $\color{#d91a1a}-2.80\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.0942ms 1.7827ms 560.9395 Ops/s 561.5133 Ops/s $\color{#d91a1a}-0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4907ms 0.3489ms 2.8662 KOps/s 2.8699 KOps/s $\color{#d91a1a}-0.13\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 49.5025ms 47.6660ms 20.9793 Ops/s 23.1322 Ops/s $\textbf{\color{#d91a1a}-9.31\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6650ms 3.0558ms 327.2483 Ops/s 325.1624 Ops/s $\color{#35bf28}+0.64\%$
test_dqn_speed 12.5760ms 5.8698ms 170.3627 Ops/s 171.8175 Ops/s $\color{#d91a1a}-0.85\%$
test_ddpg_speed 13.6538ms 11.4661ms 87.2133 Ops/s 86.6341 Ops/s $\color{#35bf28}+0.67\%$
test_sac_speed 25.4836ms 23.6182ms 42.3402 Ops/s 42.6058 Ops/s $\color{#d91a1a}-0.62\%$
test_redq_speed 15.4566ms 14.5211ms 68.8652 Ops/s 68.6422 Ops/s $\color{#35bf28}+0.32\%$
test_redq_deprec_speed 23.5804ms 22.2569ms 44.9299 Ops/s 43.4577 Ops/s $\color{#35bf28}+3.39\%$
test_td3_speed 25.9435ms 16.5934ms 60.2648 Ops/s 59.6836 Ops/s $\color{#35bf28}+0.97\%$
test_cql_speed 74.0613ms 73.3450ms 13.6342 Ops/s 13.4191 Ops/s $\color{#35bf28}+1.60\%$
test_a2c_speed 25.0314ms 22.1885ms 45.0684 Ops/s 44.9618 Ops/s $\color{#35bf28}+0.24\%$
test_ppo_speed 23.2244ms 22.3148ms 44.8133 Ops/s 44.8933 Ops/s $\color{#d91a1a}-0.18\%$
test_reinforce_speed 23.6888ms 21.4229ms 46.6789 Ops/s 46.2520 Ops/s $\color{#35bf28}+0.92\%$
test_iql_speed 0.1649s 62.7467ms 15.9371 Ops/s 17.6772 Ops/s $\textbf{\color{#d91a1a}-9.84\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3312ms 3.0447ms 328.4368 Ops/s 342.1744 Ops/s $\color{#d91a1a}-4.01\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6242ms 0.5118ms 1.9538 KOps/s 1.9158 KOps/s $\color{#35bf28}+1.98\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 98.8589ms 0.5566ms 1.7965 KOps/s 2.0124 KOps/s $\textbf{\color{#d91a1a}-10.72\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.4257ms 3.0025ms 333.0592 Ops/s 329.9454 Ops/s $\color{#35bf28}+0.94\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7662ms 0.5229ms 1.9124 KOps/s 1.9730 KOps/s $\color{#d91a1a}-3.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.1077s 0.5826ms 1.7165 KOps/s 2.0587 KOps/s $\textbf{\color{#d91a1a}-16.62\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9275ms 2.6703ms 374.4875 Ops/s 375.8092 Ops/s $\color{#d91a1a}-0.35\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8449ms 0.6373ms 1.5691 KOps/s 1.5836 KOps/s $\color{#d91a1a}-0.91\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9826ms 0.6265ms 1.5961 KOps/s 1.6450 KOps/s $\color{#d91a1a}-2.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3042ms 2.8876ms 346.3098 Ops/s 348.1762 Ops/s $\color{#d91a1a}-0.54\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7642ms 0.5237ms 1.9094 KOps/s 1.9374 KOps/s $\color{#d91a1a}-1.44\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6947ms 0.4921ms 2.0322 KOps/s 2.0505 KOps/s $\color{#d91a1a}-0.89\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.3763ms 2.9966ms 333.7107 Ops/s 316.9389 Ops/s $\textbf{\color{#35bf28}+5.29\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7592ms 0.5222ms 1.9150 KOps/s 1.9085 KOps/s $\color{#35bf28}+0.34\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8113ms 0.4915ms 2.0344 KOps/s 2.0197 KOps/s $\color{#35bf28}+0.73\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.0211ms 2.7301ms 366.2905 Ops/s 365.1603 Ops/s $\color{#35bf28}+0.31\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7952ms 0.6407ms 1.5608 KOps/s 1.5714 KOps/s $\color{#d91a1a}-0.67\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8520ms 0.6037ms 1.6564 KOps/s 1.6460 KOps/s $\color{#35bf28}+0.63\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1138s 8.5145ms 117.4471 Ops/s 106.6283 Ops/s $\textbf{\color{#35bf28}+10.15\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.1229s 13.6454ms 73.2848 Ops/s 87.2410 Ops/s $\textbf{\color{#d91a1a}-16.00\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 3.8154ms 2.4895ms 401.6893 Ops/s 382.3234 Ops/s $\textbf{\color{#35bf28}+5.07\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1145s 8.4478ms 118.3743 Ops/s 114.1812 Ops/s $\color{#35bf28}+3.67\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 13.8920ms 11.2304ms 89.0438 Ops/s 73.3396 Ops/s $\textbf{\color{#35bf28}+21.41\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.6617ms 2.5275ms 395.6416 Ops/s 391.2025 Ops/s $\color{#35bf28}+1.13\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1139s 10.8949ms 91.7863 Ops/s 111.3333 Ops/s $\textbf{\color{#d91a1a}-17.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 13.8421ms 11.4227ms 87.5449 Ops/s 86.8850 Ops/s $\color{#35bf28}+0.76\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.5400ms 2.7240ms 367.1024 Ops/s 366.3075 Ops/s $\color{#35bf28}+0.22\%$

Copy link

github-actions bot commented Jan 31, 2024

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1190s 0.1187s 8.4270 Ops/s 8.6088 Ops/s $\color{#d91a1a}-2.11\%$
test_sync 96.4267ms 96.2358ms 10.3911 Ops/s 10.3958 Ops/s $\color{#d91a1a}-0.05\%$
test_async 0.1820s 91.9493ms 10.8756 Ops/s 10.8541 Ops/s $\color{#35bf28}+0.20\%$
test_single_pixels 0.1294s 0.1291s 7.7443 Ops/s 7.2731 Ops/s $\textbf{\color{#35bf28}+6.48\%}$
test_sync_pixels 81.7592ms 78.7543ms 12.6977 Ops/s 12.0467 Ops/s $\textbf{\color{#35bf28}+5.40\%}$
test_async_pixels 0.2233s 78.1015ms 12.8038 Ops/s 13.2303 Ops/s $\color{#d91a1a}-3.22\%$
test_simple 0.9375s 0.8586s 1.1646 Ops/s 1.2064 Ops/s $\color{#d91a1a}-3.46\%$
test_transformed 1.1650s 1.1060s 0.9042 Ops/s 0.9269 Ops/s $\color{#d91a1a}-2.45\%$
test_serial 2.4221s 2.3557s 0.4245 Ops/s 0.4383 Ops/s $\color{#d91a1a}-3.16\%$
test_parallel 2.0566s 1.8715s 0.5343 Ops/s 0.5413 Ops/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[True-True-True-True-True] 74.4240μs 32.1902μs 31.0654 KOps/s 31.0541 KOps/s $\color{#35bf28}+0.04\%$
test_step_mdp_speed[True-True-True-True-False] 44.4030μs 19.7223μs 50.7041 KOps/s 52.4940 KOps/s $\color{#d91a1a}-3.41\%$
test_step_mdp_speed[True-True-True-False-True] 53.4520μs 18.6390μs 53.6510 KOps/s 54.0651 KOps/s $\color{#d91a1a}-0.77\%$
test_step_mdp_speed[True-True-True-False-False] 37.4020μs 11.4506μs 87.3315 KOps/s 91.0395 KOps/s $\color{#d91a1a}-4.07\%$
test_step_mdp_speed[True-True-False-True-True] 61.8930μs 34.8061μs 28.7306 KOps/s 29.1896 KOps/s $\color{#d91a1a}-1.57\%$
test_step_mdp_speed[True-True-False-True-False] 47.7720μs 21.8391μs 45.7894 KOps/s 47.2307 KOps/s $\color{#d91a1a}-3.05\%$
test_step_mdp_speed[True-True-False-False-True] 68.7730μs 20.5385μs 48.6891 KOps/s 48.6485 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[True-True-False-False-False] 31.9320μs 13.1917μs 75.8053 KOps/s 77.9494 KOps/s $\color{#d91a1a}-2.75\%$
test_step_mdp_speed[True-False-True-True-True] 58.6130μs 37.0430μs 26.9957 KOps/s 27.6048 KOps/s $\color{#d91a1a}-2.21\%$
test_step_mdp_speed[True-False-True-True-False] 42.0920μs 23.4582μs 42.6290 KOps/s 42.7211 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-False-True-False-True] 47.3220μs 20.8666μs 47.9236 KOps/s 49.0789 KOps/s $\color{#d91a1a}-2.35\%$
test_step_mdp_speed[True-False-True-False-False] 30.2310μs 13.1272μs 76.1779 KOps/s 77.8037 KOps/s $\color{#d91a1a}-2.09\%$
test_step_mdp_speed[True-False-False-True-True] 58.6530μs 37.9787μs 26.3305 KOps/s 26.2221 KOps/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[True-False-False-True-False] 44.7220μs 25.3554μs 39.4393 KOps/s 39.3840 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[True-False-False-False-True] 40.1120μs 22.2976μs 44.8478 KOps/s 45.0950 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[True-False-False-False-False] 31.1520μs 14.8896μs 67.1611 KOps/s 68.2661 KOps/s $\color{#d91a1a}-1.62\%$
test_step_mdp_speed[False-True-True-True-True] 64.2030μs 36.3401μs 27.5178 KOps/s 27.5596 KOps/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[False-True-True-True-False] 43.9920μs 23.6187μs 42.3393 KOps/s 43.6038 KOps/s $\color{#d91a1a}-2.90\%$
test_step_mdp_speed[False-True-True-False-True] 47.7720μs 24.5620μs 40.7132 KOps/s 41.4763 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[False-True-True-False-False] 34.6820μs 15.0573μs 66.4128 KOps/s 66.6360 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[False-True-False-True-True] 65.3030μs 38.2458μs 26.1466 KOps/s 26.1180 KOps/s $\color{#35bf28}+0.11\%$
test_step_mdp_speed[False-True-False-True-False] 49.9930μs 25.9276μs 38.5690 KOps/s 39.2401 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[False-True-False-False-True] 53.5030μs 26.6227μs 37.5619 KOps/s 38.0642 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[False-True-False-False-False] 31.5110μs 17.1499μs 58.3093 KOps/s 59.7224 KOps/s $\color{#d91a1a}-2.37\%$
test_step_mdp_speed[False-False-True-True-True] 63.3830μs 40.8167μs 24.4998 KOps/s 25.0644 KOps/s $\color{#d91a1a}-2.25\%$
test_step_mdp_speed[False-False-True-True-False] 43.1120μs 27.4400μs 36.4431 KOps/s 36.5288 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[False-False-True-False-True] 45.1430μs 26.5128μs 37.7176 KOps/s 38.2007 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[False-False-True-False-False] 43.3920μs 16.9231μs 59.0907 KOps/s 59.9663 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[False-False-False-True-True] 63.0230μs 41.8055μs 23.9203 KOps/s 24.0602 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[False-False-False-True-False] 51.8330μs 29.2980μs 34.1320 KOps/s 34.8931 KOps/s $\color{#d91a1a}-2.18\%$
test_step_mdp_speed[False-False-False-False-True] 48.8330μs 27.9372μs 35.7946 KOps/s 36.4089 KOps/s $\color{#d91a1a}-1.69\%$
test_step_mdp_speed[False-False-False-False-False] 44.9320μs 18.8858μs 52.9497 KOps/s 54.2329 KOps/s $\color{#d91a1a}-2.37\%$
test_values[generalized_advantage_estimate-True-True] 26.9679ms 26.2422ms 38.1065 Ops/s 40.4167 Ops/s $\textbf{\color{#d91a1a}-5.72\%}$
test_values[vec_generalized_advantage_estimate-True-True] 96.6235ms 3.5061ms 285.2153 Ops/s 309.5773 Ops/s $\textbf{\color{#d91a1a}-7.87\%}$
test_values[td0_return_estimate-False-False] 97.7250μs 62.4867μs 16.0034 KOps/s 15.5900 KOps/s $\color{#35bf28}+2.65\%$
test_values[td1_return_estimate-False-False] 56.6739ms 54.7786ms 18.2553 Ops/s 18.8972 Ops/s $\color{#d91a1a}-3.40\%$
test_values[vec_td1_return_estimate-False-False] 2.1550ms 1.7793ms 562.0191 Ops/s 565.4655 Ops/s $\color{#d91a1a}-0.61\%$
test_values[td_lambda_return_estimate-True-False] 88.7385ms 87.4546ms 11.4345 Ops/s 11.8889 Ops/s $\color{#d91a1a}-3.82\%$
test_values[vec_td_lambda_return_estimate-True-False] 3.9857ms 1.8112ms 552.1287 Ops/s 555.5966 Ops/s $\color{#d91a1a}-0.62\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.8991ms 23.9752ms 41.7097 Ops/s 41.7990 Ops/s $\color{#d91a1a}-0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8847ms 0.7117ms 1.4051 KOps/s 1.4235 KOps/s $\color{#d91a1a}-1.29\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7351ms 0.6791ms 1.4726 KOps/s 1.5205 KOps/s $\color{#d91a1a}-3.15\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5297ms 1.4672ms 681.5812 Ops/s 687.7735 Ops/s $\color{#d91a1a}-0.90\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9554ms 0.6801ms 1.4704 KOps/s 1.4839 KOps/s $\color{#d91a1a}-0.91\%$
test_dqn_speed 7.6598ms 7.2288ms 138.3361 Ops/s 142.4017 Ops/s $\color{#d91a1a}-2.86\%$
test_ddpg_speed 14.9072ms 14.0906ms 70.9694 Ops/s 73.3486 Ops/s $\color{#d91a1a}-3.24\%$
test_sac_speed 29.4814ms 28.4287ms 35.1757 Ops/s 36.8987 Ops/s $\color{#d91a1a}-4.67\%$
test_redq_speed 12.6989ms 11.5118ms 86.8673 Ops/s 87.4769 Ops/s $\color{#d91a1a}-0.70\%$
test_redq_deprec_speed 23.6534ms 22.6707ms 44.1097 Ops/s 46.0982 Ops/s $\color{#d91a1a}-4.31\%$
test_td3_speed 28.3484ms 18.9595ms 52.7440 Ops/s 55.2973 Ops/s $\color{#d91a1a}-4.62\%$
test_cql_speed 76.1697ms 75.4533ms 13.2532 Ops/s 13.8875 Ops/s $\color{#d91a1a}-4.57\%$
test_a2c_speed 26.9996ms 25.4400ms 39.3081 Ops/s 38.0319 Ops/s $\color{#35bf28}+3.36\%$
test_ppo_speed 26.3240ms 25.3275ms 39.4828 Ops/s 41.4362 Ops/s $\color{#d91a1a}-4.71\%$
test_reinforce_speed 25.1422ms 24.3075ms 41.1396 Ops/s 43.1457 Ops/s $\color{#d91a1a}-4.65\%$
test_iql_speed 52.2764ms 50.2282ms 19.9091 Ops/s 20.7576 Ops/s $\color{#d91a1a}-4.09\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7272ms 3.6028ms 277.5655 Ops/s 280.7323 Ops/s $\color{#d91a1a}-1.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6857ms 0.5521ms 1.8112 KOps/s 1.7536 KOps/s $\color{#35bf28}+3.29\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6702ms 0.5265ms 1.8992 KOps/s 1.8767 KOps/s $\color{#35bf28}+1.20\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8431ms 3.6162ms 276.5361 Ops/s 280.4181 Ops/s $\color{#d91a1a}-1.38\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6903ms 0.5520ms 1.8116 KOps/s 1.8271 KOps/s $\color{#d91a1a}-0.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6616ms 0.5287ms 1.8914 KOps/s 1.9150 KOps/s $\color{#d91a1a}-1.24\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4025ms 3.2652ms 306.2619 Ops/s 305.8300 Ops/s $\color{#35bf28}+0.14\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8388ms 0.6816ms 1.4671 KOps/s 1.5005 KOps/s $\color{#d91a1a}-2.23\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8227ms 0.6586ms 1.5184 KOps/s 1.5426 KOps/s $\color{#d91a1a}-1.57\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7826ms 3.6020ms 277.6270 Ops/s 280.5335 Ops/s $\color{#d91a1a}-1.04\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7202ms 0.5544ms 1.8038 KOps/s 1.7552 KOps/s $\color{#35bf28}+2.77\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7086ms 0.5323ms 1.8785 KOps/s 1.8968 KOps/s $\color{#d91a1a}-0.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8292ms 3.6423ms 274.5493 Ops/s 280.5370 Ops/s $\color{#d91a1a}-2.13\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6972ms 0.5575ms 1.7938 KOps/s 1.8262 KOps/s $\color{#d91a1a}-1.78\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6558ms 0.5291ms 1.8901 KOps/s 1.9084 KOps/s $\color{#d91a1a}-0.96\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4151ms 3.2876ms 304.1751 Ops/s 307.2364 Ops/s $\color{#d91a1a}-1.00\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8367ms 0.6836ms 1.4628 KOps/s 1.4858 KOps/s $\color{#d91a1a}-1.55\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7829ms 0.6613ms 1.5122 KOps/s 1.5404 KOps/s $\color{#d91a1a}-1.84\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1218s 10.0280ms 99.7207 Ops/s 98.9484 Ops/s $\color{#35bf28}+0.78\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.1240s 15.8980ms 62.9011 Ops/s 74.3683 Ops/s $\textbf{\color{#d91a1a}-15.42\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.1497ms 3.1705ms 315.4045 Ops/s 320.0572 Ops/s $\color{#d91a1a}-1.45\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1144s 9.9027ms 100.9830 Ops/s 100.7344 Ops/s $\color{#35bf28}+0.25\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.1714ms 13.6882ms 73.0555 Ops/s 63.5991 Ops/s $\textbf{\color{#35bf28}+14.87\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.8708ms 3.0842ms 324.2355 Ops/s 320.6975 Ops/s $\color{#35bf28}+1.10\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1175s 10.1376ms 98.6423 Ops/s 99.1889 Ops/s $\color{#d91a1a}-0.55\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 16.3952ms 13.9073ms 71.9045 Ops/s 73.3869 Ops/s $\color{#d91a1a}-2.02\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.7868ms 3.3028ms 302.7737 Ops/s 308.7692 Ops/s $\color{#d91a1a}-1.94\%$

@vmoens vmoens added the bug Something isn't working label Jan 31, 2024
@vmoens vmoens merged commit 86b8918 into main Jan 31, 2024
53 of 58 checks passed
@vmoens vmoens deleted the fix-threads branch January 31, 2024 09:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
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.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants