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.

Sign up for GitHub

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

Jump to bottom

[Feature] env.step_mdp #2636

Merged
merged 3 commits into from
Dec 12, 2024
Merged

[Feature] env.step_mdp #2636

merged 3 commits into from
Dec 12, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 6, 2024 •
edited
Loading

@vmoens
Update
bfbfaa7 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Dec 6, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2636

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

❌ 8 New Failures, 18 Unrelated Failures

As of commit cfa6261 with merge base 57dc25a (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 Dec 6, 2024
This was referenced Dec 6, 2024
Merged
Merged
Closed
Merged
Merged
Merged
Merged
@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 6, 2024 •
edited
Loading

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4371s 0.4336s 2.3060 Ops/s 2.2323 Ops/s $\color{#35bf28}+3.30\%$
test_transformed 0.6185s 0.6160s 1.6233 Ops/s 1.5918 Ops/s $\color{#35bf28}+1.98\%$
test_serial 1.3923s 1.3810s 0.7241 Ops/s 0.7310 Ops/s $\color{#d91a1a}-0.94\%$
test_parallel 1.3984s 1.3143s 0.7608 Ops/s 0.7569 Ops/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-True-True-True-True] 0.3468ms 29.6972μs 33.6733 KOps/s 33.6475 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[True-True-True-True-False] 45.7960μs 17.5465μs 56.9915 KOps/s 56.8646 KOps/s $\color{#35bf28}+0.22\%$
test_step_mdp_speed[True-True-True-False-True] 59.1510μs 16.8870μs 59.2172 KOps/s 59.3858 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[True-True-True-False-False] 56.6060μs 9.9655μs 100.3461 KOps/s 101.5573 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[True-True-False-True-True] 0.1097ms 32.4208μs 30.8444 KOps/s 30.7552 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[True-True-False-True-False] 56.4160μs 19.4144μs 51.5082 KOps/s 51.5834 KOps/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[True-True-False-False-True] 59.5720μs 18.8268μs 53.1158 KOps/s 53.2276 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[True-True-False-False-False] 38.0520μs 11.7338μs 85.2235 KOps/s 85.4158 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[True-False-True-True-True] 74.8010μs 34.2296μs 29.2145 KOps/s 29.4396 KOps/s $\color{#d91a1a}-0.76\%$
test_step_mdp_speed[True-False-True-True-False] 66.4950μs 21.3103μs 46.9256 KOps/s 47.0674 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[True-False-True-False-True] 46.3680μs 18.6588μs 53.5940 KOps/s 53.9173 KOps/s $\color{#d91a1a}-0.60\%$
test_step_mdp_speed[True-False-True-False-False] 59.2610μs 11.7129μs 85.3760 KOps/s 85.5980 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[True-False-False-True-True] 79.2400μs 35.8308μs 27.9090 KOps/s 27.9376 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[True-False-False-True-False] 61.8260μs 23.0570μs 43.3708 KOps/s 43.6932 KOps/s $\color{#d91a1a}-0.74\%$
test_step_mdp_speed[True-False-False-False-True] 48.9120μs 20.3651μs 49.1036 KOps/s 49.0996 KOps/s $+0.01\%$
test_step_mdp_speed[True-False-False-False-False] 47.9100μs 13.4448μs 74.3782 KOps/s 74.5902 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[False-True-True-True-True] 0.7125ms 34.0012μs 29.4107 KOps/s 29.4918 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-True-True-True-False] 60.3840μs 21.1275μs 47.3317 KOps/s 47.1553 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[False-True-True-False-True] 46.9290μs 21.4911μs 46.5308 KOps/s 47.2642 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[False-True-True-False-False] 48.1800μs 12.9677μs 77.1144 KOps/s 76.2619 KOps/s $\color{#35bf28}+1.12\%$
test_step_mdp_speed[False-True-False-True-True] 73.8290μs 35.3755μs 28.2682 KOps/s 28.2319 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-True-False-True-False] 46.8180μs 23.1489μs 43.1986 KOps/s 43.7954 KOps/s $\color{#d91a1a}-1.36\%$
test_step_mdp_speed[False-True-False-False-True] 2.7701ms 22.9228μs 43.6248 KOps/s 43.4589 KOps/s $\color{#35bf28}+0.38\%$
test_step_mdp_speed[False-True-False-False-False] 63.4790μs 14.6938μs 68.0559 KOps/s 68.0703 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[False-False-True-True-True] 85.0110μs 37.0931μs 26.9592 KOps/s 26.6788 KOps/s $\color{#35bf28}+1.05\%$
test_step_mdp_speed[False-False-True-True-False] 73.9190μs 24.6493μs 40.5692 KOps/s 40.7049 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[False-False-True-False-True] 0.1203ms 23.4003μs 42.7344 KOps/s 41.9047 KOps/s $\color{#35bf28}+1.98\%$
test_step_mdp_speed[False-False-True-False-False] 0.1438ms 15.0853μs 66.2897 KOps/s 68.0547 KOps/s $\color{#d91a1a}-2.59\%$
test_step_mdp_speed[False-False-False-True-True] 0.1010ms 39.1916μs 25.5157 KOps/s 25.4135 KOps/s $\color{#35bf28}+0.40\%$
test_step_mdp_speed[False-False-False-True-False] 0.1088ms 26.4559μs 37.7988 KOps/s 38.0990 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[False-False-False-False-True] 65.4130μs 24.8116μs 40.3038 KOps/s 40.9118 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[False-False-False-False-False] 40.4060μs 16.3547μs 61.1445 KOps/s 61.4684 KOps/s $\color{#d91a1a}-0.53\%$
test_values[generalized_advantage_estimate-True-True] 9.7826ms 9.5650ms 104.5477 Ops/s 105.8686 Ops/s $\color{#d91a1a}-1.25\%$
test_values[vec_generalized_advantage_estimate-True-True] 35.6808ms 33.7717ms 29.6106 Ops/s 29.7040 Ops/s $\color{#d91a1a}-0.31\%$
test_values[td0_return_estimate-False-False] 0.2394ms 0.1798ms 5.5609 KOps/s 5.4437 KOps/s $\color{#35bf28}+2.15\%$
test_values[td1_return_estimate-False-False] 28.0440ms 24.7044ms 40.4786 Ops/s 42.6092 Ops/s $\textbf{\color{#d91a1a}-5.00\%}$
test_values[vec_td1_return_estimate-False-False] 38.4562ms 34.1468ms 29.2853 Ops/s 29.6102 Ops/s $\color{#d91a1a}-1.10\%$
test_values[td_lambda_return_estimate-True-False] 38.5522ms 35.3831ms 28.2621 Ops/s 29.6722 Ops/s $\color{#d91a1a}-4.75\%$
test_values[vec_td_lambda_return_estimate-True-False] 36.4438ms 33.7761ms 29.6067 Ops/s 29.6354 Ops/s $\color{#d91a1a}-0.10\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.8502ms 8.3401ms 119.9030 Ops/s 122.5114 Ops/s $\color{#d91a1a}-2.13\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3276ms 2.0001ms 499.9769 Ops/s 503.0134 Ops/s $\color{#d91a1a}-0.60\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 1.7313ms 0.3693ms 2.7080 KOps/s 2.8217 KOps/s $\color{#d91a1a}-4.03\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 45.4473ms 43.3496ms 23.0683 Ops/s 24.0376 Ops/s $\color{#d91a1a}-4.03\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.9916ms 3.0585ms 326.9537 Ops/s 327.2909 Ops/s $\color{#d91a1a}-0.10\%$
test_dqn_speed[False-None] 6.4379ms 1.4100ms 709.2417 Ops/s 695.0021 Ops/s $\color{#35bf28}+2.05\%$
test_dqn_speed[False-backward] 2.0345ms 1.9068ms 524.4282 Ops/s 536.5909 Ops/s $\color{#d91a1a}-2.27\%$
test_dqn_speed[True-None] 0.7677ms 0.4726ms 2.1159 KOps/s 2.1526 KOps/s $\color{#d91a1a}-1.71\%$
test_dqn_speed[True-backward] 0.9643ms 0.9073ms 1.1022 KOps/s 823.4079 Ops/s $\textbf{\color{#35bf28}+33.86\%}$
test_dqn_speed[reduce-overhead-None] 1.5240ms 0.4710ms 2.1233 KOps/s 2.1210 KOps/s $\color{#35bf28}+0.11\%$
test_dqn_speed[reduce-overhead-backward] 0.9341ms 0.8919ms 1.1212 KOps/s 1.1130 KOps/s $\color{#35bf28}+0.74\%$
test_ddpg_speed[False-None] 3.3409ms 2.8839ms 346.7581 Ops/s 346.0314 Ops/s $\color{#35bf28}+0.21\%$
test_ddpg_speed[False-backward] 4.1996ms 4.0393ms 247.5679 Ops/s 243.4252 Ops/s $\color{#35bf28}+1.70\%$
test_ddpg_speed[True-None] 1.2050ms 1.0097ms 990.3815 Ops/s 993.7086 Ops/s $\color{#d91a1a}-0.33\%$
test_ddpg_speed[True-backward] 2.0395ms 1.9145ms 522.3431 Ops/s 418.7672 Ops/s $\textbf{\color{#35bf28}+24.73\%}$
test_ddpg_speed[reduce-overhead-None] 1.2372ms 1.0133ms 986.8986 Ops/s 995.6486 Ops/s $\color{#d91a1a}-0.88\%$
test_ddpg_speed[reduce-overhead-backward] 2.0887ms 1.9335ms 517.1947 Ops/s 527.0944 Ops/s $\color{#d91a1a}-1.88\%$
test_sac_speed[False-None] 9.9692ms 8.0941ms 123.5468 Ops/s 124.3181 Ops/s $\color{#d91a1a}-0.62\%$
test_sac_speed[False-backward] 11.3379ms 10.8785ms 91.9247 Ops/s 91.2344 Ops/s $\color{#35bf28}+0.76\%$
test_sac_speed[True-None] 2.2825ms 1.8348ms 545.0163 Ops/s 546.0939 Ops/s $\color{#d91a1a}-0.20\%$
test_sac_speed[True-backward] 3.6493ms 3.5254ms 283.6589 Ops/s 276.0698 Ops/s $\color{#35bf28}+2.75\%$
test_sac_speed[reduce-overhead-None] 2.4195ms 1.8338ms 545.3075 Ops/s 541.9956 Ops/s $\color{#35bf28}+0.61\%$
test_sac_speed[reduce-overhead-backward] 3.5577ms 3.5071ms 285.1363 Ops/s 278.6372 Ops/s $\color{#35bf28}+2.33\%$
test_redq_speed[False-None] 15.0241ms 12.9822ms 77.0283 Ops/s 76.5099 Ops/s $\color{#35bf28}+0.68\%$
test_redq_speed[False-backward] 23.6298ms 22.0278ms 45.3972 Ops/s 44.2926 Ops/s $\color{#35bf28}+2.49\%$
test_redq_speed[True-None] 5.2388ms 4.5296ms 220.7702 Ops/s 206.6682 Ops/s $\textbf{\color{#35bf28}+6.82\%}$
test_redq_speed[True-backward] 12.2256ms 11.8302ms 84.5294 Ops/s 78.7466 Ops/s $\textbf{\color{#35bf28}+7.34\%}$
test_redq_speed[reduce-overhead-None] 5.4468ms 4.7481ms 210.6092 Ops/s 208.5592 Ops/s $\color{#35bf28}+0.98\%$
test_redq_speed[reduce-overhead-backward] 13.7834ms 12.4293ms 80.4552 Ops/s 80.9765 Ops/s $\color{#d91a1a}-0.64\%$
test_redq_deprec_speed[False-None] 15.1226ms 13.2484ms 75.4809 Ops/s 74.0080 Ops/s $\color{#35bf28}+1.99\%$
test_redq_deprec_speed[False-backward] 21.0154ms 19.1272ms 52.2814 Ops/s 53.1361 Ops/s $\color{#d91a1a}-1.61\%$
test_redq_deprec_speed[True-None] 4.2146ms 3.5532ms 281.4332 Ops/s 271.2725 Ops/s $\color{#35bf28}+3.75\%$
test_redq_deprec_speed[True-backward] 8.1088ms 7.9104ms 126.4153 Ops/s 120.8406 Ops/s $\color{#35bf28}+4.61\%$
test_redq_deprec_speed[reduce-overhead-None] 3.7213ms 3.5385ms 282.6078 Ops/s 274.9661 Ops/s $\color{#35bf28}+2.78\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.2996ms 7.9610ms 125.6121 Ops/s 119.7440 Ops/s $\color{#35bf28}+4.90\%$
test_td3_speed[False-None] 8.7474ms 8.0369ms 124.4260 Ops/s 124.4686 Ops/s $\color{#d91a1a}-0.03\%$
test_td3_speed[False-backward] 10.8119ms 10.4036ms 96.1208 Ops/s 96.9560 Ops/s $\color{#d91a1a}-0.86\%$
test_td3_speed[True-None] 1.8994ms 1.7219ms 580.7471 Ops/s 578.5619 Ops/s $\color{#35bf28}+0.38\%$
test_td3_speed[True-backward] 3.3792ms 3.3031ms 302.7461 Ops/s 289.4748 Ops/s $\color{#35bf28}+4.58\%$
test_td3_speed[reduce-overhead-None] 1.9916ms 1.7137ms 583.5241 Ops/s 574.5062 Ops/s $\color{#35bf28}+1.57\%$
test_td3_speed[reduce-overhead-backward] 4.3672ms 3.5397ms 282.5079 Ops/s 297.3473 Ops/s $\color{#d91a1a}-4.99\%$
test_cql_speed[False-None] 37.9618ms 36.4785ms 27.4134 Ops/s 27.7700 Ops/s $\color{#d91a1a}-1.28\%$
test_cql_speed[False-backward] 47.9450ms 46.5957ms 21.4612 Ops/s 21.3819 Ops/s $\color{#35bf28}+0.37\%$
test_cql_speed[True-None] 16.8029ms 15.4667ms 64.6552 Ops/s 63.5588 Ops/s $\color{#35bf28}+1.72\%$
test_cql_speed[True-backward] 22.9719ms 21.8010ms 45.8695 Ops/s 43.6317 Ops/s $\textbf{\color{#35bf28}+5.13\%}$
test_cql_speed[reduce-overhead-None] 16.4588ms 15.4932ms 64.5445 Ops/s 63.6820 Ops/s $\color{#35bf28}+1.35\%$
test_cql_speed[reduce-overhead-backward] 24.3535ms 22.2868ms 44.8696 Ops/s 43.9095 Ops/s $\color{#35bf28}+2.19\%$
test_a2c_speed[False-None] 7.6933ms 7.1347ms 140.1610 Ops/s 135.7704 Ops/s $\color{#35bf28}+3.23\%$
test_a2c_speed[False-backward] 15.1611ms 14.1727ms 70.5581 Ops/s 67.5507 Ops/s $\color{#35bf28}+4.45\%$
test_a2c_speed[True-None] 4.6961ms 4.1757ms 239.4785 Ops/s 234.0867 Ops/s $\color{#35bf28}+2.30\%$
test_a2c_speed[True-backward] 11.5167ms 10.8420ms 92.2336 Ops/s 90.8684 Ops/s $\color{#35bf28}+1.50\%$
test_a2c_speed[reduce-overhead-None] 4.5579ms 4.2072ms 237.6867 Ops/s 235.0337 Ops/s $\color{#35bf28}+1.13\%$
test_a2c_speed[reduce-overhead-backward] 15.9634ms 11.2878ms 88.5910 Ops/s 90.8538 Ops/s $\color{#d91a1a}-2.49\%$
test_ppo_speed[False-None] 8.1268ms 7.4909ms 133.4956 Ops/s 131.3991 Ops/s $\color{#35bf28}+1.60\%$
test_ppo_speed[False-backward] 16.2026ms 15.2063ms 65.7622 Ops/s 66.5395 Ops/s $\color{#d91a1a}-1.17\%$
test_ppo_speed[True-None] 4.3919ms 3.6852ms 271.3563 Ops/s 263.6479 Ops/s $\color{#35bf28}+2.92\%$
test_ppo_speed[True-backward] 10.8609ms 10.1309ms 98.7076 Ops/s 99.7742 Ops/s $\color{#d91a1a}-1.07\%$
test_ppo_speed[reduce-overhead-None] 4.1490ms 3.7142ms 269.2349 Ops/s 268.3038 Ops/s $\color{#35bf28}+0.35\%$
test_ppo_speed[reduce-overhead-backward] 10.1942ms 9.7549ms 102.5124 Ops/s 101.2782 Ops/s $\color{#35bf28}+1.22\%$
test_reinforce_speed[False-None] 7.9866ms 6.5741ms 152.1126 Ops/s 151.7638 Ops/s $\color{#35bf28}+0.23\%$
test_reinforce_speed[False-backward] 10.3967ms 9.8482ms 101.5409 Ops/s 97.2713 Ops/s $\color{#35bf28}+4.39\%$
test_reinforce_speed[True-None] 3.3208ms 2.6677ms 374.8581 Ops/s 361.1717 Ops/s $\color{#35bf28}+3.79\%$
test_reinforce_speed[True-backward] 9.7670ms 8.6700ms 115.3403 Ops/s 109.3107 Ops/s $\textbf{\color{#35bf28}+5.52\%}$
test_reinforce_speed[reduce-overhead-None] 3.0654ms 2.6750ms 373.8311 Ops/s 369.6436 Ops/s $\color{#35bf28}+1.13\%$
test_reinforce_speed[reduce-overhead-backward] 9.3303ms 8.7000ms 114.9427 Ops/s 108.8294 Ops/s $\textbf{\color{#35bf28}+5.62\%}$
test_iql_speed[False-None] 34.3174ms 32.6689ms 30.6102 Ops/s 30.2117 Ops/s $\color{#35bf28}+1.32\%$
test_iql_speed[False-backward] 46.7273ms 45.3339ms 22.0586 Ops/s 21.5612 Ops/s $\color{#35bf28}+2.31\%$
test_iql_speed[True-None] 11.9137ms 10.8561ms 92.1138 Ops/s 89.8505 Ops/s $\color{#35bf28}+2.52\%$
test_iql_speed[True-backward] 22.7319ms 21.8110ms 45.8485 Ops/s 45.3604 Ops/s $\color{#35bf28}+1.08\%$
test_iql_speed[reduce-overhead-None] 11.7513ms 10.6782ms 93.6487 Ops/s 92.2818 Ops/s $\color{#35bf28}+1.48\%$
test_iql_speed[reduce-overhead-backward] 23.0965ms 21.9225ms 45.6153 Ops/s 44.6894 Ops/s $\color{#35bf28}+2.07\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.7215ms 5.1771ms 193.1578 Ops/s 194.9831 Ops/s $\color{#d91a1a}-0.94\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.3266ms 0.5195ms 1.9250 KOps/s 1.8983 KOps/s $\color{#35bf28}+1.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7362ms 0.5023ms 1.9910 KOps/s 2.0342 KOps/s $\color{#d91a1a}-2.12\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.4185ms 4.9311ms 202.7955 Ops/s 206.7973 Ops/s $\color{#d91a1a}-1.94\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.6902ms 0.4973ms 2.0110 KOps/s 1.9870 KOps/s $\color{#35bf28}+1.20\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8569ms 0.4768ms 2.0973 KOps/s 2.0948 KOps/s $\color{#35bf28}+0.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.0268ms 1.6495ms 606.2327 Ops/s 603.1616 Ops/s $\color{#35bf28}+0.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2720ms 1.5972ms 626.0797 Ops/s 627.4328 Ops/s $\color{#d91a1a}-0.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.3906ms 5.0813ms 196.7983 Ops/s 202.1361 Ops/s $\color{#d91a1a}-2.64\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4599ms 0.6486ms 1.5418 KOps/s 1.5444 KOps/s $\color{#d91a1a}-0.17\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8581ms 0.6248ms 1.6005 KOps/s 1.5978 KOps/s $\color{#35bf28}+0.17\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.5020ms 4.9137ms 203.5123 Ops/s 204.3147 Ops/s $\color{#d91a1a}-0.39\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.5295ms 0.5251ms 1.9045 KOps/s 1.9357 KOps/s $\color{#d91a1a}-1.61\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7004ms 0.4953ms 2.0192 KOps/s 2.0071 KOps/s $\color{#35bf28}+0.60\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.2133ms 4.8062ms 208.0657 Ops/s 207.4447 Ops/s $\color{#35bf28}+0.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7922ms 0.5019ms 1.9924 KOps/s 1.9884 KOps/s $\color{#35bf28}+0.20\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7192ms 0.4842ms 2.0652 KOps/s 2.0645 KOps/s $\color{#35bf28}+0.03\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.4747ms 5.0365ms 198.5513 Ops/s 197.3062 Ops/s $\color{#35bf28}+0.63\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.8784ms 0.6607ms 1.5135 KOps/s 1.5115 KOps/s $\color{#35bf28}+0.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8713ms 0.6317ms 1.5830 KOps/s 1.5810 KOps/s $\color{#35bf28}+0.13\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.8123ms 4.2909ms 233.0514 Ops/s 247.6518 Ops/s $\textbf{\color{#d91a1a}-5.90\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.6762ms 2.3843ms 419.4117 Ops/s 421.8035 Ops/s $\color{#d91a1a}-0.57\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.2613ms 1.3231ms 755.8000 Ops/s 755.5437 Ops/s $\color{#35bf28}+0.03\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4375s 12.9801ms 77.0410 Ops/s 34.7614 Ops/s $\textbf{\color{#35bf28}+121.63\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 8.7731ms 2.3418ms 427.0178 Ops/s 477.9369 Ops/s $\textbf{\color{#d91a1a}-10.65\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.6621ms 1.2327ms 811.2117 Ops/s 803.5525 Ops/s $\color{#35bf28}+0.95\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.5215ms 4.6074ms 217.0414 Ops/s 218.5113 Ops/s $\color{#d91a1a}-0.67\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 7.5238ms 2.5156ms 397.5177 Ops/s 376.7762 Ops/s $\textbf{\color{#35bf28}+5.50\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.9318ms 1.4749ms 678.0110 Ops/s 670.1577 Ops/s $\color{#35bf28}+1.17\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 11.9880ms 11.2879ms 88.5901 Ops/s 85.4482 Ops/s $\color{#35bf28}+3.68\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.1247ms 14.5978ms 68.5033 Ops/s 68.4621 Ops/s $\color{#35bf28}+0.06\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 20.3158ms 19.7891ms 50.5328 Ops/s 49.4550 Ops/s $\color{#35bf28}+2.18\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 14.9913ms 14.6672ms 68.1793 Ops/s 68.3571 Ops/s $\color{#d91a1a}-0.26\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.3684ms 20.1393ms 49.6541 Ops/s 49.8629 Ops/s $\color{#d91a1a}-0.42\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 17.8234ms 15.8502ms 63.0907 Ops/s 62.4096 Ops/s $\color{#35bf28}+1.09\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 6, 2024 •
edited
Loading

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}17$. Worsened: $\large\color{#d91a1a}18$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7402s 0.7388s 1.3536 Ops/s 1.3177 Ops/s $\color{#35bf28}+2.73\%$
test_transformed 1.0872s 1.0083s 0.9918 Ops/s 1.0107 Ops/s $\color{#d91a1a}-1.87\%$
test_serial 2.2281s 2.1473s 0.4657 Ops/s 0.4735 Ops/s $\color{#d91a1a}-1.65\%$
test_parallel 2.0266s 1.9741s 0.5066 Ops/s 0.5071 Ops/s $\color{#d91a1a}-0.12\%$
test_step_mdp_speed[True-True-True-True-True] 0.1853ms 38.5271μs 25.9557 KOps/s 26.1133 KOps/s $\color{#d91a1a}-0.60\%$
test_step_mdp_speed[True-True-True-True-False] 0.1371ms 21.9432μs 45.5722 KOps/s 45.0245 KOps/s $\color{#35bf28}+1.22\%$
test_step_mdp_speed[True-True-True-False-True] 60.8610μs 21.4651μs 46.5873 KOps/s 46.1957 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-True-True-False-False] 38.6310μs 12.4068μs 80.6012 KOps/s 80.2611 KOps/s $\color{#35bf28}+0.42\%$
test_step_mdp_speed[True-True-False-True-True] 69.2810μs 41.3934μs 24.1584 KOps/s 24.2017 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-True-False-True-False] 0.1538ms 24.1871μs 41.3444 KOps/s 41.0490 KOps/s $\color{#35bf28}+0.72\%$
test_step_mdp_speed[True-True-False-False-True] 0.2080ms 23.4937μs 42.5646 KOps/s 41.9165 KOps/s $\color{#35bf28}+1.55\%$
test_step_mdp_speed[True-True-False-False-False] 0.1819ms 14.3507μs 69.6829 KOps/s 68.5660 KOps/s $\color{#35bf28}+1.63\%$
test_step_mdp_speed[True-False-True-True-True] 0.2062ms 43.2601μs 23.1160 KOps/s 23.3048 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-False-True-True-False] 0.1582ms 26.4530μs 37.8029 KOps/s 37.7610 KOps/s $\color{#35bf28}+0.11\%$
test_step_mdp_speed[True-False-True-False-True] 65.4320μs 23.6963μs 42.2007 KOps/s 43.3701 KOps/s $\color{#d91a1a}-2.70\%$
test_step_mdp_speed[True-False-True-False-False] 46.2910μs 14.4466μs 69.2207 KOps/s 69.2856 KOps/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[True-False-False-True-True] 87.7120μs 45.8091μs 21.8297 KOps/s 21.9780 KOps/s $\color{#d91a1a}-0.67\%$
test_step_mdp_speed[True-False-False-True-False] 64.4520μs 28.0087μs 35.7032 KOps/s 34.6523 KOps/s $\color{#35bf28}+3.03\%$
test_step_mdp_speed[True-False-False-False-True] 59.4810μs 25.7561μs 38.8258 KOps/s 39.0508 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[True-False-False-False-False] 59.5110μs 16.4727μs 60.7066 KOps/s 59.9150 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[False-True-True-True-True] 77.2210μs 43.5904μs 22.9408 KOps/s 22.8093 KOps/s $\color{#35bf28}+0.58\%$
test_step_mdp_speed[False-True-True-True-False] 0.1065ms 26.2021μs 38.1649 KOps/s 37.7555 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[False-True-True-False-True] 0.1722ms 27.1159μs 36.8787 KOps/s 36.7099 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-True-True-False-False] 47.7910μs 15.8842μs 62.9558 KOps/s 61.1150 KOps/s $\color{#35bf28}+3.01\%$
test_step_mdp_speed[False-True-False-True-True] 80.2420μs 45.8283μs 21.8206 KOps/s 21.9865 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[False-True-False-True-False] 0.1306ms 27.9996μs 35.7147 KOps/s 35.2712 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[False-True-False-False-True] 3.4867ms 29.2074μs 34.2379 KOps/s 33.5031 KOps/s $\color{#35bf28}+2.19\%$
test_step_mdp_speed[False-True-False-False-False] 48.4410μs 17.8654μs 55.9740 KOps/s 53.9738 KOps/s $\color{#35bf28}+3.71\%$
test_step_mdp_speed[False-False-True-True-True] 0.1828ms 47.8409μs 20.9026 KOps/s 20.9152 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[False-False-True-True-False] 77.9310μs 30.5519μs 32.7312 KOps/s 32.4100 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[False-False-True-False-True] 97.9020μs 29.4151μs 33.9961 KOps/s 33.9719 KOps/s $\color{#35bf28}+0.07\%$
test_step_mdp_speed[False-False-True-False-False] 0.1532ms 18.0569μs 55.3806 KOps/s 53.6431 KOps/s $\color{#35bf28}+3.24\%$
test_step_mdp_speed[False-False-False-True-True] 99.1020μs 49.6979μs 20.1216 KOps/s 20.0672 KOps/s $\color{#35bf28}+0.27\%$
test_step_mdp_speed[False-False-False-True-False] 66.0410μs 32.2631μs 30.9951 KOps/s 30.4859 KOps/s $\color{#35bf28}+1.67\%$
test_step_mdp_speed[False-False-False-False-True] 0.2163ms 30.7306μs 32.5409 KOps/s 32.2583 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[False-False-False-False-False] 0.1129ms 19.8110μs 50.4771 KOps/s 48.8116 KOps/s $\color{#35bf28}+3.41\%$
test_values[generalized_advantage_estimate-True-True] 24.9120ms 24.4081ms 40.9700 Ops/s 40.6438 Ops/s $\color{#35bf28}+0.80\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1023s 2.9463ms 339.4142 Ops/s 339.2401 Ops/s $\color{#35bf28}+0.05\%$
test_values[td0_return_estimate-False-False] 0.1027ms 80.4151μs 12.4355 KOps/s 12.4325 KOps/s $\color{#35bf28}+0.02\%$
test_values[td1_return_estimate-False-False] 54.9886ms 54.6516ms 18.2977 Ops/s 18.2537 Ops/s $\color{#35bf28}+0.24\%$
test_values[vec_td1_return_estimate-False-False] 1.3091ms 1.0785ms 927.2056 Ops/s 919.5733 Ops/s $\color{#35bf28}+0.83\%$
test_values[td_lambda_return_estimate-True-False] 87.4667ms 86.7959ms 11.5213 Ops/s 11.4697 Ops/s $\color{#35bf28}+0.45\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3639ms 1.0788ms 926.9517 Ops/s 923.7686 Ops/s $\color{#35bf28}+0.34\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.3695ms 24.1567ms 41.3963 Ops/s 41.0486 Ops/s $\color{#35bf28}+0.85\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0386ms 0.7435ms 1.3451 KOps/s 1.3285 KOps/s $\color{#35bf28}+1.25\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8201ms 0.6678ms 1.4975 KOps/s 1.4945 KOps/s $\color{#35bf28}+0.20\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6252ms 1.4725ms 679.1047 Ops/s 675.9957 Ops/s $\color{#35bf28}+0.46\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.8430ms 0.6796ms 1.4714 KOps/s 1.4639 KOps/s $\color{#35bf28}+0.51\%$
test_dqn_speed[False-None] 7.0168ms 1.5020ms 665.7573 Ops/s 670.3986 Ops/s $\color{#d91a1a}-0.69\%$
test_dqn_speed[False-backward] 2.2880ms 2.1138ms 473.0800 Ops/s 470.2708 Ops/s $\color{#35bf28}+0.60\%$
test_dqn_speed[True-None] 0.7360ms 0.5480ms 1.8249 KOps/s 1.8775 KOps/s $\color{#d91a1a}-2.80\%$
test_dqn_speed[True-backward] 1.3453ms 1.1866ms 842.7665 Ops/s 903.8639 Ops/s $\textbf{\color{#d91a1a}-6.76\%}$
test_dqn_speed[reduce-overhead-None] 0.7402ms 0.5628ms 1.7770 KOps/s 1.8350 KOps/s $\color{#d91a1a}-3.16\%$
test_dqn_speed[reduce-overhead-backward] 1.2084ms 1.0615ms 942.0855 Ops/s 1.0331 KOps/s $\textbf{\color{#d91a1a}-8.81\%}$
test_ddpg_speed[False-None] 3.1432ms 2.8274ms 353.6872 Ops/s 349.8346 Ops/s $\color{#35bf28}+1.10\%$
test_ddpg_speed[False-backward] 4.6490ms 4.1954ms 238.3557 Ops/s 242.5407 Ops/s $\color{#d91a1a}-1.73\%$
test_ddpg_speed[True-None] 1.2143ms 1.0600ms 943.3944 Ops/s 934.7853 Ops/s $\color{#35bf28}+0.92\%$
test_ddpg_speed[True-backward] 2.4635ms 2.3039ms 434.0469 Ops/s 460.4261 Ops/s $\textbf{\color{#d91a1a}-5.73\%}$
test_ddpg_speed[reduce-overhead-None] 1.2282ms 1.0681ms 936.2533 Ops/s 925.9917 Ops/s $\color{#35bf28}+1.11\%$
test_ddpg_speed[reduce-overhead-backward] 1.9062ms 1.7657ms 566.3562 Ops/s 610.9347 Ops/s $\textbf{\color{#d91a1a}-7.30\%}$
test_sac_speed[False-None] 8.5513ms 8.0073ms 124.8857 Ops/s 124.6167 Ops/s $\color{#35bf28}+0.22\%$
test_sac_speed[False-backward] 11.7056ms 11.2788ms 88.6617 Ops/s 89.7945 Ops/s $\color{#d91a1a}-1.26\%$
test_sac_speed[True-None] 1.6550ms 1.5124ms 661.2135 Ops/s 647.5230 Ops/s $\color{#35bf28}+2.11\%$
test_sac_speed[True-backward] 3.3235ms 3.1860ms 313.8739 Ops/s 305.9649 Ops/s $\color{#35bf28}+2.58\%$
test_sac_speed[reduce-overhead-None] 22.0461ms 12.2636ms 81.5421 Ops/s 83.1655 Ops/s $\color{#d91a1a}-1.95\%$
test_sac_speed[reduce-overhead-backward] 1.3642ms 1.3113ms 762.6018 Ops/s 669.8002 Ops/s $\textbf{\color{#35bf28}+13.86\%}$
test_redq_speed[False-None] 8.1843ms 7.4004ms 135.1281 Ops/s 132.9628 Ops/s $\color{#35bf28}+1.63\%$
test_redq_speed[False-backward] 12.1897ms 11.2997ms 88.4977 Ops/s 84.7964 Ops/s $\color{#35bf28}+4.36\%$
test_redq_speed[True-None] 2.2171ms 1.9621ms 509.6482 Ops/s 483.2835 Ops/s $\textbf{\color{#35bf28}+5.46\%}$
test_redq_speed[True-backward] 3.7145ms 3.5808ms 279.2669 Ops/s 273.7747 Ops/s $\color{#35bf28}+2.01\%$
test_redq_speed[reduce-overhead-None] 2.1282ms 1.9580ms 510.7304 Ops/s 503.9221 Ops/s $\color{#35bf28}+1.35\%$
test_redq_speed[reduce-overhead-backward] 4.0087ms 3.6033ms 277.5237 Ops/s 260.3504 Ops/s $\textbf{\color{#35bf28}+6.60\%}$
test_redq_deprec_speed[False-None] 9.5491ms 8.9744ms 111.4283 Ops/s 110.5307 Ops/s $\color{#35bf28}+0.81\%$
test_redq_deprec_speed[False-backward] 12.4401ms 11.9977ms 83.3494 Ops/s 80.7594 Ops/s $\color{#35bf28}+3.21\%$
test_redq_deprec_speed[True-None] 2.5402ms 2.3048ms 433.8711 Ops/s 432.1353 Ops/s $\color{#35bf28}+0.40\%$
test_redq_deprec_speed[True-backward] 4.0856ms 3.9156ms 255.3892 Ops/s 249.6523 Ops/s $\color{#35bf28}+2.30\%$
test_redq_deprec_speed[reduce-overhead-None] 2.5296ms 2.2907ms 436.5514 Ops/s 420.8305 Ops/s $\color{#35bf28}+3.74\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.3796ms 3.9460ms 253.4181 Ops/s 251.7610 Ops/s $\color{#35bf28}+0.66\%$
test_td3_speed[False-None] 7.9022ms 7.8504ms 127.3821 Ops/s 126.7236 Ops/s $\color{#35bf28}+0.52\%$
test_td3_speed[False-backward] 10.7994ms 10.2385ms 97.6703 Ops/s 97.2961 Ops/s $\color{#35bf28}+0.38\%$
test_td3_speed[True-None] 1.5713ms 1.5452ms 647.1655 Ops/s 640.8902 Ops/s $\color{#35bf28}+0.98\%$
test_td3_speed[True-backward] 3.2112ms 3.0524ms 327.6129 Ops/s 323.5268 Ops/s $\color{#35bf28}+1.26\%$
test_td3_speed[reduce-overhead-None] 47.6874ms 24.5784ms 40.6862 Ops/s 38.6172 Ops/s $\textbf{\color{#35bf28}+5.36\%}$
test_td3_speed[reduce-overhead-backward] 1.4300ms 1.2653ms 790.3228 Ops/s 702.0906 Ops/s $\textbf{\color{#35bf28}+12.57\%}$
test_cql_speed[False-None] 16.4325ms 16.1027ms 62.1014 Ops/s 61.8571 Ops/s $\color{#35bf28}+0.40\%$
test_cql_speed[False-backward] 21.8660ms 21.3217ms 46.9005 Ops/s 45.5506 Ops/s $\color{#35bf28}+2.96\%$
test_cql_speed[True-None] 3.0609ms 2.8963ms 345.2698 Ops/s 342.1847 Ops/s $\color{#35bf28}+0.90\%$
test_cql_speed[True-backward] 5.6044ms 5.1816ms 192.9894 Ops/s 189.8854 Ops/s $\color{#35bf28}+1.63\%$
test_cql_speed[reduce-overhead-None] 21.4381ms 13.0386ms 76.6951 Ops/s 76.5757 Ops/s $\color{#35bf28}+0.16\%$
test_cql_speed[reduce-overhead-backward] 1.7377ms 1.5699ms 636.9820 Ops/s 599.9916 Ops/s $\textbf{\color{#35bf28}+6.17\%}$
test_a2c_speed[False-None] 3.3875ms 3.1884ms 313.6365 Ops/s 308.9843 Ops/s $\color{#35bf28}+1.51\%$
test_a2c_speed[False-backward] 6.9764ms 6.3809ms 156.7169 Ops/s 153.0357 Ops/s $\color{#35bf28}+2.41\%$
test_a2c_speed[True-None] 1.1439ms 0.9823ms 1.0180 KOps/s 967.5897 Ops/s $\textbf{\color{#35bf28}+5.21\%}$
test_a2c_speed[True-backward] 2.9499ms 2.7607ms 362.2255 Ops/s 383.3043 Ops/s $\textbf{\color{#d91a1a}-5.50\%}$
test_a2c_speed[reduce-overhead-None] 0.3958s 12.1226ms 82.4903 Ops/s 87.4744 Ops/s $\textbf{\color{#d91a1a}-5.70\%}$
test_a2c_speed[reduce-overhead-backward] 1.1987ms 1.0799ms 926.0383 Ops/s 1.0252 KOps/s $\textbf{\color{#d91a1a}-9.67\%}$
test_ppo_speed[False-None] 4.0375ms 3.7031ms 270.0421 Ops/s 267.7088 Ops/s $\color{#35bf28}+0.87\%$
test_ppo_speed[False-backward] 7.2812ms 7.0583ms 141.6781 Ops/s 142.1164 Ops/s $\color{#d91a1a}-0.31\%$
test_ppo_speed[True-None] 1.1636ms 0.9631ms 1.0383 KOps/s 1.0618 KOps/s $\color{#d91a1a}-2.22\%$
test_ppo_speed[True-backward] 2.8732ms 2.7166ms 368.1107 Ops/s 368.5934 Ops/s $\color{#d91a1a}-0.13\%$
test_ppo_speed[reduce-overhead-None] 0.6697ms 0.4973ms 2.0109 KOps/s 1.9429 KOps/s $\color{#35bf28}+3.50\%$
test_ppo_speed[reduce-overhead-backward] 1.1727ms 1.1096ms 901.2425 Ops/s 935.1211 Ops/s $\color{#d91a1a}-3.62\%$
test_reinforce_speed[False-None] 2.5076ms 2.2607ms 442.3452 Ops/s 440.3205 Ops/s $\color{#35bf28}+0.46\%$
test_reinforce_speed[False-backward] 3.7640ms 3.3567ms 297.9124 Ops/s 289.5804 Ops/s $\color{#35bf28}+2.88\%$
test_reinforce_speed[True-None] 1.0428ms 0.8435ms 1.1856 KOps/s 1.2075 KOps/s $\color{#d91a1a}-1.81\%$
test_reinforce_speed[True-backward] 2.6811ms 2.5446ms 392.9890 Ops/s 413.9466 Ops/s $\textbf{\color{#d91a1a}-5.06\%}$
test_reinforce_speed[reduce-overhead-None] 22.3548ms 11.7009ms 85.4635 Ops/s 89.9148 Ops/s $\color{#d91a1a}-4.95\%$
test_reinforce_speed[reduce-overhead-backward] 1.3336ms 1.1788ms 848.3469 Ops/s 950.7220 Ops/s $\textbf{\color{#d91a1a}-10.77\%}$
test_iql_speed[False-None] 9.7268ms 9.2181ms 108.4818 Ops/s 108.8940 Ops/s $\color{#d91a1a}-0.38\%$
test_iql_speed[False-backward] 13.8790ms 13.2976ms 75.2013 Ops/s 77.1131 Ops/s $\color{#d91a1a}-2.48\%$
test_iql_speed[True-None] 1.9498ms 1.7297ms 578.1371 Ops/s 579.9296 Ops/s $\color{#d91a1a}-0.31\%$
test_iql_speed[True-backward] 4.7691ms 4.3639ms 229.1525 Ops/s 226.5601 Ops/s $\color{#35bf28}+1.14\%$
test_iql_speed[reduce-overhead-None] 20.0815ms 11.3553ms 88.0643 Ops/s 113.1771 Ops/s $\textbf{\color{#d91a1a}-22.19\%}$
test_iql_speed[reduce-overhead-backward] 1.5636ms 1.4110ms 708.7000 Ops/s 638.5764 Ops/s $\textbf{\color{#35bf28}+10.98\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.8127ms 6.2090ms 161.0566 Ops/s 158.6790 Ops/s $\color{#35bf28}+1.50\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5078ms 0.2702ms 3.7007 KOps/s 3.6966 KOps/s $\color{#35bf28}+0.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5365ms 0.3160ms 3.1648 KOps/s 3.6034 KOps/s $\textbf{\color{#d91a1a}-12.17\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3204ms 6.0041ms 166.5535 Ops/s 164.8777 Ops/s $\color{#35bf28}+1.02\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7466ms 0.2561ms 3.9048 KOps/s 3.1119 KOps/s $\textbf{\color{#35bf28}+25.48\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8355ms 0.3361ms 2.9756 KOps/s 3.3600 KOps/s $\textbf{\color{#d91a1a}-11.44\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7971ms 1.3981ms 715.2489 Ops/s 742.0886 Ops/s $\color{#d91a1a}-3.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.3818ms 1.1952ms 836.6620 Ops/s 777.5405 Ops/s $\textbf{\color{#35bf28}+7.60\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5430ms 6.2151ms 160.8979 Ops/s 162.0508 Ops/s $\color{#d91a1a}-0.71\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9958ms 0.4722ms 2.1177 KOps/s 2.2157 KOps/s $\color{#d91a1a}-4.42\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8289ms 0.4502ms 2.2211 KOps/s 2.2619 KOps/s $\color{#d91a1a}-1.80\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4416ms 6.0570ms 165.0993 Ops/s 165.1285 Ops/s $\color{#d91a1a}-0.02\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9380ms 0.3300ms 3.0305 KOps/s 3.1136 KOps/s $\color{#d91a1a}-2.67\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4349ms 0.2521ms 3.9662 KOps/s 3.4200 KOps/s $\textbf{\color{#35bf28}+15.97\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4507ms 5.9725ms 167.4348 Ops/s 167.3542 Ops/s $\color{#35bf28}+0.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.6250ms 0.2594ms 3.8548 KOps/s 2.8439 KOps/s $\textbf{\color{#35bf28}+35.55\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4096ms 0.2378ms 4.2060 KOps/s 2.6874 KOps/s $\textbf{\color{#35bf28}+56.51\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5901ms 6.2101ms 161.0285 Ops/s 161.6511 Ops/s $\color{#d91a1a}-0.39\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.2190ms 0.5080ms 1.9684 KOps/s 2.3845 KOps/s $\textbf{\color{#d91a1a}-17.45\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7130ms 0.4889ms 2.0456 KOps/s 2.2066 KOps/s $\textbf{\color{#d91a1a}-7.30\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.8573ms 5.2523ms 190.3939 Ops/s 190.8805 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.2693ms 2.0300ms 492.6209 Ops/s 443.0491 Ops/s $\textbf{\color{#35bf28}+11.19\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.1964ms 1.2448ms 803.3435 Ops/s 879.6931 Ops/s $\textbf{\color{#d91a1a}-8.68\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4873s 14.9277ms 66.9896 Ops/s 183.6728 Ops/s $\textbf{\color{#d91a1a}-63.53\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 11.2026ms 2.0330ms 491.8799 Ops/s 430.9937 Ops/s $\textbf{\color{#35bf28}+14.13\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.8772ms 1.1703ms 854.4730 Ops/s 866.6412 Ops/s $\color{#d91a1a}-1.40\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.4674ms 5.4975ms 181.9022 Ops/s 33.1849 Ops/s $\textbf{\color{#35bf28}+448.15\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 6.0019ms 2.1486ms 465.4240 Ops/s 521.4142 Ops/s $\textbf{\color{#d91a1a}-10.74\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 10.5264ms 1.4404ms 694.2367 Ops/s 836.6639 Ops/s $\textbf{\color{#d91a1a}-17.02\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.0954ms 12.9168ms 77.4183 Ops/s 77.5192 Ops/s $\color{#d91a1a}-0.13\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 17.4494ms 16.3626ms 61.1151 Ops/s 56.8892 Ops/s $\textbf{\color{#35bf28}+7.43\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.5309ms 17.6543ms 56.6436 Ops/s 55.6157 Ops/s $\color{#35bf28}+1.85\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.8110ms 16.5171ms 60.5435 Ops/s 59.0542 Ops/s $\color{#35bf28}+2.52\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.0637ms 17.4888ms 57.1795 Ops/s 56.3413 Ops/s $\color{#35bf28}+1.49\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.6555ms 18.0435ms 55.4217 Ops/s 54.9043 Ops/s $\color{#35bf28}+0.94\%$

@vmoens
Update
2c63ef9 
[ghstack-poisoned]
@vmoens
Update
cfa6261 
[ghstack-poisoned]
@vmoens vmoens merged commit cfa6261 into gh/vmoens/50/base Dec 12, 2024
14 of 19 checks passed
vmoens added a commit that referenced this pull request Dec 12, 2024
@vmoens
[Feature] env.step_mdp
4bc40a8 
ghstack-source-id: 145e37cd772fdd74e35e5ffe6accc5c81ad689f3
Pull Request resolved: #2636
@vmoens vmoens deleted the gh/vmoens/50/head branch December 12, 2024 21:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
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
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@vmoens @facebook-github-bot