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

[Refactor] Refactor trees #2634

Merged
merged 2 commits into from
Dec 12, 2024
Merged

[Refactor] Refactor trees #2634

merged 2 commits into from
Dec 12, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 6, 2024 •
edited
Loading

@vmoens
Update
afc0f24 
[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/2634

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

❌ 4 New Failures, 12 Unrelated Failures

As of commit e994649 with merge base 19dfefc (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

BROKEN TRUNK - The following jobs failed but was 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: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4332s 0.4288s 2.3322 Ops/s 2.2152 Ops/s $\textbf{\color{#35bf28}+5.28\%}$
test_transformed 0.6994s 0.6201s 1.6127 Ops/s 1.5908 Ops/s $\color{#35bf28}+1.38\%$
test_serial 1.3571s 1.3519s 0.7397 Ops/s 0.7334 Ops/s $\color{#35bf28}+0.86\%$
test_parallel 1.3299s 1.3065s 0.7654 Ops/s 0.7521 Ops/s $\color{#35bf28}+1.77\%$
test_step_mdp_speed[True-True-True-True-True] 0.2532ms 29.6913μs 33.6799 KOps/s 33.8481 KOps/s $\color{#d91a1a}-0.50\%$
test_step_mdp_speed[True-True-True-True-False] 47.2680μs 17.4725μs 57.2326 KOps/s 56.8826 KOps/s $\color{#35bf28}+0.62\%$
test_step_mdp_speed[True-True-True-False-True] 53.2300μs 16.9783μs 58.8986 KOps/s 60.1387 KOps/s $\color{#d91a1a}-2.06\%$
test_step_mdp_speed[True-True-True-False-False] 46.8880μs 9.9045μs 100.9641 KOps/s 100.1104 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-True-False-True-True] 71.0630μs 32.1099μs 31.1431 KOps/s 31.1645 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[True-True-False-True-False] 45.6450μs 19.5605μs 51.1234 KOps/s 50.4571 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[True-True-False-False-True] 57.3770μs 18.7820μs 53.2425 KOps/s 54.1669 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[True-True-False-False-False] 48.7510μs 11.8170μs 84.6242 KOps/s 85.0586 KOps/s $\color{#d91a1a}-0.51\%$
test_step_mdp_speed[True-False-True-True-True] 92.5020μs 33.9969μs 29.4144 KOps/s 29.8433 KOps/s $\color{#d91a1a}-1.44\%$
test_step_mdp_speed[True-False-True-True-False] 53.7910μs 21.3564μs 46.8244 KOps/s 46.4093 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[True-False-True-False-True] 80.3500μs 18.5867μs 53.8019 KOps/s 53.9017 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[True-False-True-False-False] 47.4290μs 11.8572μs 84.3367 KOps/s 84.7743 KOps/s $\color{#d91a1a}-0.52\%$
test_step_mdp_speed[True-False-False-True-True] 86.1310μs 35.1633μs 28.4388 KOps/s 27.8891 KOps/s $\color{#35bf28}+1.97\%$
test_step_mdp_speed[True-False-False-True-False] 57.1270μs 23.1025μs 43.2853 KOps/s 42.8111 KOps/s $\color{#35bf28}+1.11\%$
test_step_mdp_speed[True-False-False-False-True] 56.4650μs 20.5268μs 48.7168 KOps/s 48.7470 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[True-False-False-False-False] 57.8980μs 13.6277μs 73.3800 KOps/s 73.5873 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[False-True-True-True-True] 70.6220μs 34.0319μs 29.3842 KOps/s 29.2934 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[False-True-True-True-False] 76.6030μs 21.3770μs 46.7792 KOps/s 45.9796 KOps/s $\color{#35bf28}+1.74\%$
test_step_mdp_speed[False-True-True-False-True] 57.3970μs 21.4815μs 46.5517 KOps/s 46.8905 KOps/s $\color{#d91a1a}-0.72\%$
test_step_mdp_speed[False-True-True-False-False] 51.2650μs 12.8718μs 77.6890 KOps/s 75.5683 KOps/s $\color{#35bf28}+2.81\%$
test_step_mdp_speed[False-True-False-True-True] 72.3660μs 35.3340μs 28.3014 KOps/s 28.4348 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[False-True-False-True-False] 69.4300μs 22.9492μs 43.5744 KOps/s 43.2902 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-True-False-False-True] 0.1092s 27.1418μs 36.8436 KOps/s 43.5954 KOps/s $\textbf{\color{#d91a1a}-15.49\%}$
test_step_mdp_speed[False-True-False-False-False] 43.7210μs 14.8960μs 67.1321 KOps/s 68.3404 KOps/s $\color{#d91a1a}-1.77\%$
test_step_mdp_speed[False-False-True-True-True] 95.0280μs 37.1695μs 26.9037 KOps/s 26.6723 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[False-False-True-True-False] 58.1090μs 24.9010μs 40.1590 KOps/s 40.4215 KOps/s $\color{#d91a1a}-0.65\%$
test_step_mdp_speed[False-False-True-False-True] 59.0300μs 22.6956μs 44.0614 KOps/s 43.8209 KOps/s $\color{#35bf28}+0.55\%$
test_step_mdp_speed[False-False-True-False-False] 66.7350μs 14.9151μs 67.0463 KOps/s 67.4599 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[False-False-False-True-True] 78.7570μs 39.1444μs 25.5465 KOps/s 25.7618 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[False-False-False-True-False] 61.9660μs 26.8319μs 37.2690 KOps/s 37.2888 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[False-False-False-False-True] 52.8590μs 24.5439μs 40.7433 KOps/s 41.7633 KOps/s $\color{#d91a1a}-2.44\%$
test_step_mdp_speed[False-False-False-False-False] 57.0870μs 16.3843μs 61.0342 KOps/s 60.3054 KOps/s $\color{#35bf28}+1.21\%$
test_values[generalized_advantage_estimate-True-True] 13.4825ms 10.0313ms 99.6876 Ops/s 101.7260 Ops/s $\color{#d91a1a}-2.00\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.0648ms 33.9019ms 29.4969 Ops/s 29.1483 Ops/s $\color{#35bf28}+1.20\%$
test_values[td0_return_estimate-False-False] 0.2601ms 0.2016ms 4.9615 KOps/s 5.5455 KOps/s $\textbf{\color{#d91a1a}-10.53\%}$
test_values[td1_return_estimate-False-False] 26.2327ms 24.8891ms 40.1782 Ops/s 40.5763 Ops/s $\color{#d91a1a}-0.98\%$
test_values[vec_td1_return_estimate-False-False] 39.7126ms 34.0013ms 29.4106 Ops/s 29.0093 Ops/s $\color{#35bf28}+1.38\%$
test_values[td_lambda_return_estimate-True-False] 37.9307ms 35.0717ms 28.5130 Ops/s 28.1464 Ops/s $\color{#35bf28}+1.30\%$
test_values[vec_td_lambda_return_estimate-True-False] 49.9742ms 34.2916ms 29.1617 Ops/s 29.5796 Ops/s $\color{#d91a1a}-1.41\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.1919ms 8.4848ms 117.8576 Ops/s 115.8021 Ops/s $\color{#35bf28}+1.78\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4230ms 2.0006ms 499.8607 Ops/s 492.4516 Ops/s $\color{#35bf28}+1.50\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4840ms 0.3694ms 2.7073 KOps/s 2.7867 KOps/s $\color{#d91a1a}-2.85\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.0609ms 43.3069ms 23.0910 Ops/s 24.2621 Ops/s $\color{#d91a1a}-4.83\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.0785ms 3.0746ms 325.2474 Ops/s 327.0829 Ops/s $\color{#d91a1a}-0.56\%$
test_dqn_speed[False-None] 2.6324ms 1.4303ms 699.1358 Ops/s 707.7422 Ops/s $\color{#d91a1a}-1.22\%$
test_dqn_speed[False-backward] 2.0178ms 1.9322ms 517.5353 Ops/s 522.7280 Ops/s $\color{#d91a1a}-0.99\%$
test_dqn_speed[True-None] 0.6589ms 0.4704ms 2.1258 KOps/s 2.1462 KOps/s $\color{#d91a1a}-0.95\%$
test_dqn_speed[True-backward] 0.9533ms 0.9051ms 1.1049 KOps/s 1.0954 KOps/s $\color{#35bf28}+0.86\%$
test_dqn_speed[reduce-overhead-None] 0.7205ms 0.4729ms 2.1146 KOps/s 2.0923 KOps/s $\color{#35bf28}+1.06\%$
test_dqn_speed[reduce-overhead-backward] 0.9736ms 0.9147ms 1.0933 KOps/s 1.0921 KOps/s $\color{#35bf28}+0.10\%$
test_ddpg_speed[False-None] 3.4742ms 2.9398ms 340.1568 Ops/s 340.9211 Ops/s $\color{#d91a1a}-0.22\%$
test_ddpg_speed[False-backward] 4.2120ms 4.0971ms 244.0763 Ops/s 243.4097 Ops/s $\color{#35bf28}+0.27\%$
test_ddpg_speed[True-None] 1.2574ms 1.0233ms 977.2201 Ops/s 970.6203 Ops/s $\color{#35bf28}+0.68\%$
test_ddpg_speed[True-backward] 2.0054ms 1.9385ms 515.8760 Ops/s 475.2335 Ops/s $\textbf{\color{#35bf28}+8.55\%}$
test_ddpg_speed[reduce-overhead-None] 1.2755ms 1.0238ms 976.7873 Ops/s 991.1169 Ops/s $\color{#d91a1a}-1.45\%$
test_ddpg_speed[reduce-overhead-backward] 2.0991ms 2.0184ms 495.4465 Ops/s 523.5797 Ops/s $\textbf{\color{#d91a1a}-5.37\%}$
test_sac_speed[False-None] 10.1112ms 8.3925ms 119.1535 Ops/s 122.3855 Ops/s $\color{#d91a1a}-2.64\%$
test_sac_speed[False-backward] 12.1946ms 11.4582ms 87.2735 Ops/s 91.0198 Ops/s $\color{#d91a1a}-4.12\%$
test_sac_speed[True-None] 2.4946ms 1.8590ms 537.9250 Ops/s 539.3905 Ops/s $\color{#d91a1a}-0.27\%$
test_sac_speed[True-backward] 3.6159ms 3.5439ms 282.1744 Ops/s 266.1101 Ops/s $\textbf{\color{#35bf28}+6.04\%}$
test_sac_speed[reduce-overhead-None] 2.4473ms 1.8695ms 534.9115 Ops/s 528.9781 Ops/s $\color{#35bf28}+1.12\%$
test_sac_speed[reduce-overhead-backward] 6.2064ms 5.7348ms 174.3725 Ops/s 270.5515 Ops/s $\textbf{\color{#d91a1a}-35.55\%}$
test_redq_speed[False-None] 19.4248ms 14.0533ms 71.1577 Ops/s 74.9521 Ops/s $\textbf{\color{#d91a1a}-5.06\%}$
test_redq_speed[False-backward] 25.3410ms 22.7340ms 43.9870 Ops/s 43.5549 Ops/s $\color{#35bf28}+0.99\%$
test_redq_speed[True-None] 7.3492ms 4.8351ms 206.8207 Ops/s 213.0015 Ops/s $\color{#d91a1a}-2.90\%$
test_redq_speed[True-backward] 16.2981ms 12.5427ms 79.7277 Ops/s 81.2749 Ops/s $\color{#d91a1a}-1.90\%$
test_redq_speed[reduce-overhead-None] 6.7818ms 4.8144ms 207.7123 Ops/s 195.4903 Ops/s $\textbf{\color{#35bf28}+6.25\%}$
test_redq_speed[reduce-overhead-backward] 13.6474ms 12.5118ms 79.9245 Ops/s 71.5696 Ops/s $\textbf{\color{#35bf28}+11.67\%}$
test_redq_deprec_speed[False-None] 15.3597ms 13.1917ms 75.8054 Ops/s 72.3761 Ops/s $\color{#35bf28}+4.74\%$
test_redq_deprec_speed[False-backward] 20.4582ms 19.0183ms 52.5808 Ops/s 51.2821 Ops/s $\color{#35bf28}+2.53\%$
test_redq_deprec_speed[True-None] 4.0523ms 3.5950ms 278.1657 Ops/s 279.8363 Ops/s $\color{#d91a1a}-0.60\%$
test_redq_deprec_speed[True-backward] 9.3402ms 8.5128ms 117.4704 Ops/s 121.1798 Ops/s $\color{#d91a1a}-3.06\%$
test_redq_deprec_speed[reduce-overhead-None] 4.3295ms 3.7306ms 268.0523 Ops/s 278.6413 Ops/s $\color{#d91a1a}-3.80\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.2922ms 8.7642ms 114.1008 Ops/s 119.2369 Ops/s $\color{#d91a1a}-4.31\%$
test_td3_speed[False-None] 8.6427ms 8.2922ms 120.5956 Ops/s 121.4720 Ops/s $\color{#d91a1a}-0.72\%$
test_td3_speed[False-backward] 14.0200ms 11.0421ms 90.5621 Ops/s 92.7506 Ops/s $\color{#d91a1a}-2.36\%$
test_td3_speed[True-None] 2.3118ms 1.7804ms 561.6735 Ops/s 573.0367 Ops/s $\color{#d91a1a}-1.98\%$
test_td3_speed[True-backward] 3.3958ms 3.3243ms 300.8173 Ops/s 299.1228 Ops/s $\color{#35bf28}+0.57\%$
test_td3_speed[reduce-overhead-None] 1.8853ms 1.7253ms 579.6110 Ops/s 577.1913 Ops/s $\color{#35bf28}+0.42\%$
test_td3_speed[reduce-overhead-backward] 3.3854ms 3.3299ms 300.3058 Ops/s 298.4906 Ops/s $\color{#35bf28}+0.61\%$
test_cql_speed[False-None] 39.0297ms 36.4959ms 27.4003 Ops/s 27.3069 Ops/s $\color{#35bf28}+0.34\%$
test_cql_speed[False-backward] 48.7369ms 46.3573ms 21.5716 Ops/s 21.4828 Ops/s $\color{#35bf28}+0.41\%$
test_cql_speed[True-None] 16.6621ms 15.8820ms 62.9645 Ops/s 62.7911 Ops/s $\color{#35bf28}+0.28\%$
test_cql_speed[True-backward] 24.3498ms 23.1349ms 43.2247 Ops/s 43.9708 Ops/s $\color{#d91a1a}-1.70\%$
test_cql_speed[reduce-overhead-None] 16.5665ms 15.7640ms 63.4357 Ops/s 62.9923 Ops/s $\color{#35bf28}+0.70\%$
test_cql_speed[reduce-overhead-backward] 24.2452ms 22.9764ms 43.5228 Ops/s 43.5238 Ops/s $-0.00\%$
test_a2c_speed[False-None] 9.5264ms 7.3495ms 136.0630 Ops/s 132.0463 Ops/s $\color{#35bf28}+3.04\%$
test_a2c_speed[False-backward] 15.8834ms 14.9122ms 67.0594 Ops/s 67.1566 Ops/s $\color{#d91a1a}-0.14\%$
test_a2c_speed[True-None] 6.2276ms 4.2137ms 237.3221 Ops/s 232.0735 Ops/s $\color{#35bf28}+2.26\%$
test_a2c_speed[True-backward] 12.0388ms 11.3849ms 87.8353 Ops/s 93.0479 Ops/s $\textbf{\color{#d91a1a}-5.60\%}$
test_a2c_speed[reduce-overhead-None] 4.6501ms 4.2134ms 237.3398 Ops/s 234.9321 Ops/s $\color{#35bf28}+1.02\%$
test_a2c_speed[reduce-overhead-backward] 12.2195ms 10.8786ms 91.9238 Ops/s 92.5469 Ops/s $\color{#d91a1a}-0.67\%$
test_ppo_speed[False-None] 9.4779ms 7.5588ms 132.2960 Ops/s 132.9064 Ops/s $\color{#d91a1a}-0.46\%$
test_ppo_speed[False-backward] 16.5039ms 15.2236ms 65.6874 Ops/s 65.6364 Ops/s $\color{#35bf28}+0.08\%$
test_ppo_speed[True-None] 4.3769ms 3.7558ms 266.2530 Ops/s 267.5949 Ops/s $\color{#d91a1a}-0.50\%$
test_ppo_speed[True-backward] 10.4010ms 9.7810ms 102.2386 Ops/s 101.0735 Ops/s $\color{#35bf28}+1.15\%$
test_ppo_speed[reduce-overhead-None] 5.9384ms 3.7364ms 267.6365 Ops/s 267.6943 Ops/s $\color{#d91a1a}-0.02\%$
test_ppo_speed[reduce-overhead-backward] 10.4601ms 9.7158ms 102.9254 Ops/s 102.1488 Ops/s $\color{#35bf28}+0.76\%$
test_reinforce_speed[False-None] 9.4842ms 6.5817ms 151.9359 Ops/s 151.4537 Ops/s $\color{#35bf28}+0.32\%$
test_reinforce_speed[False-backward] 10.0464ms 9.8809ms 101.2055 Ops/s 100.1940 Ops/s $\color{#35bf28}+1.01\%$
test_reinforce_speed[True-None] 3.1564ms 2.6511ms 377.2016 Ops/s 370.8438 Ops/s $\color{#35bf28}+1.71\%$
test_reinforce_speed[True-backward] 9.3842ms 8.6986ms 114.9609 Ops/s 112.4445 Ops/s $\color{#35bf28}+2.24\%$
test_reinforce_speed[reduce-overhead-None] 3.0548ms 2.6507ms 377.2640 Ops/s 371.9504 Ops/s $\color{#35bf28}+1.43\%$
test_reinforce_speed[reduce-overhead-backward] 9.3674ms 8.7079ms 114.8388 Ops/s 114.9172 Ops/s $\color{#d91a1a}-0.07\%$
test_iql_speed[False-None] 33.6087ms 32.0350ms 31.2159 Ops/s 30.8823 Ops/s $\color{#35bf28}+1.08\%$
test_iql_speed[False-backward] 55.0029ms 45.5246ms 21.9662 Ops/s 21.8890 Ops/s $\color{#35bf28}+0.35\%$
test_iql_speed[True-None] 11.9795ms 10.8327ms 92.3130 Ops/s 89.6102 Ops/s $\color{#35bf28}+3.02\%$
test_iql_speed[True-backward] 24.2778ms 22.0481ms 45.3554 Ops/s 45.2194 Ops/s $\color{#35bf28}+0.30\%$
test_iql_speed[reduce-overhead-None] 12.2353ms 11.0542ms 90.4632 Ops/s 88.9966 Ops/s $\color{#35bf28}+1.65\%$
test_iql_speed[reduce-overhead-backward] 23.3183ms 22.2612ms 44.9213 Ops/s 45.0677 Ops/s $\color{#d91a1a}-0.32\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.6663ms 5.0423ms 198.3230 Ops/s 187.0648 Ops/s $\textbf{\color{#35bf28}+6.02\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7496ms 0.5178ms 1.9311 KOps/s 1.9297 KOps/s $\color{#35bf28}+0.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7315ms 0.4966ms 2.0138 KOps/s 2.0393 KOps/s $\color{#d91a1a}-1.25\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.1294ms 4.8393ms 206.6404 Ops/s 203.7740 Ops/s $\color{#35bf28}+1.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2056ms 0.5134ms 1.9479 KOps/s 1.9356 KOps/s $\color{#35bf28}+0.63\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7362ms 0.4821ms 2.0744 KOps/s 2.0734 KOps/s $\color{#35bf28}+0.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.9050ms 1.6450ms 607.8923 Ops/s 603.2792 Ops/s $\color{#35bf28}+0.76\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0878ms 1.5998ms 625.0594 Ops/s 617.1638 Ops/s $\color{#35bf28}+1.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.8253ms 5.1669ms 193.5386 Ops/s 193.6550 Ops/s $\color{#d91a1a}-0.06\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.6334ms 0.6648ms 1.5041 KOps/s 1.4785 KOps/s $\color{#35bf28}+1.73\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8895ms 0.6442ms 1.5523 KOps/s 1.5874 KOps/s $\color{#d91a1a}-2.21\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4986ms 4.9747ms 201.0157 Ops/s 206.2592 Ops/s $\color{#d91a1a}-2.54\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.6707ms 0.5400ms 1.8518 KOps/s 1.9365 KOps/s $\color{#d91a1a}-4.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7629ms 0.5040ms 1.9843 KOps/s 1.9869 KOps/s $\color{#d91a1a}-0.13\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.8077ms 4.8459ms 206.3585 Ops/s 201.5649 Ops/s $\color{#35bf28}+2.38\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7582ms 0.5158ms 1.9388 KOps/s 1.9811 KOps/s $\color{#d91a1a}-2.13\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 7.6827ms 0.5045ms 1.9822 KOps/s 1.9601 KOps/s $\color{#35bf28}+1.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.4324ms 5.1485ms 194.2318 Ops/s 202.5989 Ops/s $\color{#d91a1a}-4.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1198ms 0.6630ms 1.5083 KOps/s 1.5133 KOps/s $\color{#d91a1a}-0.33\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.2530ms 0.6704ms 1.4916 KOps/s 1.5756 KOps/s $\textbf{\color{#d91a1a}-5.34\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4655s 13.5839ms 73.6168 Ops/s 243.9991 Ops/s $\textbf{\color{#d91a1a}-69.83\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.5775ms 2.4068ms 415.4972 Ops/s 38.2644 Ops/s $\textbf{\color{#35bf28}+985.86\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 3.0335ms 1.3258ms 754.2778 Ops/s 709.9051 Ops/s $\textbf{\color{#35bf28}+6.25\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 6.0323ms 4.3667ms 229.0056 Ops/s 225.4887 Ops/s $\color{#35bf28}+1.56\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.0473ms 2.3803ms 420.1082 Ops/s 422.0140 Ops/s $\color{#d91a1a}-0.45\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.6867ms 1.3885ms 720.2190 Ops/s 724.2635 Ops/s $\color{#d91a1a}-0.56\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4539s 13.7355ms 72.8043 Ops/s 214.2053 Ops/s $\textbf{\color{#d91a1a}-66.01\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.8195ms 2.6762ms 373.6631 Ops/s 393.1607 Ops/s $\color{#d91a1a}-4.96\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.9987ms 1.4477ms 690.7738 Ops/s 655.0934 Ops/s $\textbf{\color{#35bf28}+5.45\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.8131ms 11.4551ms 87.2973 Ops/s 84.4908 Ops/s $\color{#35bf28}+3.32\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.4228ms 14.6414ms 68.2995 Ops/s 67.8379 Ops/s $\color{#35bf28}+0.68\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.4507ms 20.3511ms 49.1373 Ops/s 49.5014 Ops/s $\color{#d91a1a}-0.74\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.6400ms 14.9800ms 66.7557 Ops/s 66.6334 Ops/s $\color{#35bf28}+0.18\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.4209ms 20.0952ms 49.7631 Ops/s 49.8926 Ops/s $\color{#d91a1a}-0.26\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.6858ms 16.0604ms 62.2649 Ops/s 61.7808 Ops/s $\color{#35bf28}+0.78\%$

@github-actions GitHub Actions
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: $\large\color{#35bf28}16$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7522s 0.7490s 1.3350 Ops/s 1.2876 Ops/s $\color{#35bf28}+3.68\%$
test_transformed 1.0033s 1.0009s 0.9991 Ops/s 0.9982 Ops/s $\color{#35bf28}+0.09\%$
test_serial 2.2449s 2.1627s 0.4624 Ops/s 0.4624 Ops/s $-0.01\%$
test_parallel 2.0626s 1.9647s 0.5090 Ops/s 0.5146 Ops/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[True-True-True-True-True] 0.1080ms 37.9091μs 26.3789 KOps/s 25.6129 KOps/s $\color{#35bf28}+2.99\%$
test_step_mdp_speed[True-True-True-True-False] 56.8310μs 22.5723μs 44.3021 KOps/s 44.2382 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[True-True-True-False-True] 47.7710μs 21.6783μs 46.1291 KOps/s 47.1700 KOps/s $\color{#d91a1a}-2.21\%$
test_step_mdp_speed[True-True-True-False-False] 0.1076ms 12.8006μs 78.1214 KOps/s 79.0931 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[True-True-False-True-True] 70.8110μs 41.7776μs 23.9363 KOps/s 23.9525 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[True-True-False-True-False] 48.6810μs 24.4621μs 40.8795 KOps/s 40.4370 KOps/s $\color{#35bf28}+1.09\%$
test_step_mdp_speed[True-True-False-False-True] 56.3410μs 23.5609μs 42.4432 KOps/s 41.9813 KOps/s $\color{#35bf28}+1.10\%$
test_step_mdp_speed[True-True-False-False-False] 0.1488ms 14.6480μs 68.2689 KOps/s 68.3938 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-False-True-True-True] 0.2037ms 44.3399μs 22.5531 KOps/s 22.9556 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-False-True-True-False] 53.1610μs 26.9472μs 37.1096 KOps/s 37.3911 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[True-False-True-False-True] 51.1210μs 24.1657μs 41.3809 KOps/s 42.4167 KOps/s $\color{#d91a1a}-2.44\%$
test_step_mdp_speed[True-False-True-False-False] 44.8800μs 14.7851μs 67.6358 KOps/s 67.7580 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-False-False-True-True] 83.5720μs 45.9264μs 21.7740 KOps/s 21.8200 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[True-False-False-True-False] 0.2140ms 28.9709μs 34.5174 KOps/s 34.7712 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[True-False-False-False-True] 60.1510μs 25.8316μs 38.7122 KOps/s 39.0972 KOps/s $\color{#d91a1a}-0.98\%$
test_step_mdp_speed[True-False-False-False-False] 62.6810μs 16.8008μs 59.5209 KOps/s 59.9335 KOps/s $\color{#d91a1a}-0.69\%$
test_step_mdp_speed[False-True-True-True-True] 78.9610μs 44.0397μs 22.7068 KOps/s 22.6004 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[False-True-True-True-False] 0.1099ms 26.8989μs 37.1762 KOps/s 37.7007 KOps/s $\color{#d91a1a}-1.39\%$
test_step_mdp_speed[False-True-True-False-True] 53.0600μs 27.2966μs 36.6347 KOps/s 36.0997 KOps/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[False-True-True-False-False] 42.3910μs 16.2483μs 61.5451 KOps/s 61.3603 KOps/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[False-True-False-True-True] 87.5110μs 45.2216μs 22.1133 KOps/s 21.9572 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[False-True-False-True-False] 63.9710μs 28.9380μs 34.5566 KOps/s 34.4550 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[False-True-False-False-True] 3.3642ms 29.5556μs 33.8346 KOps/s 33.4939 KOps/s $\color{#35bf28}+1.02\%$
test_step_mdp_speed[False-True-False-False-False] 51.9710μs 18.7665μs 53.2863 KOps/s 54.9871 KOps/s $\color{#d91a1a}-3.09\%$
test_step_mdp_speed[False-False-True-True-True] 91.4710μs 48.4406μs 20.6438 KOps/s 20.6953 KOps/s $\color{#d91a1a}-0.25\%$
test_step_mdp_speed[False-False-True-True-False] 63.2910μs 31.2085μs 32.0426 KOps/s 32.3314 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-False-True-False-True] 62.7810μs 29.6461μs 33.7312 KOps/s 33.8987 KOps/s $\color{#d91a1a}-0.49\%$
test_step_mdp_speed[False-False-True-False-False] 48.6110μs 18.2287μs 54.8585 KOps/s 53.6440 KOps/s $\color{#35bf28}+2.26\%$
test_step_mdp_speed[False-False-False-True-True] 94.5310μs 49.5938μs 20.1638 KOps/s 20.2098 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[False-False-False-True-False] 65.4410μs 33.0509μs 30.2564 KOps/s 30.3623 KOps/s $\color{#d91a1a}-0.35\%$
test_step_mdp_speed[False-False-False-False-True] 64.6610μs 31.1927μs 32.0588 KOps/s 32.0821 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[False-False-False-False-False] 47.6210μs 20.1675μs 49.5847 KOps/s 48.4445 KOps/s $\color{#35bf28}+2.35\%$
test_values[generalized_advantage_estimate-True-True] 25.3957ms 24.9274ms 40.1164 Ops/s 40.2177 Ops/s $\color{#d91a1a}-0.25\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1024s 2.9444ms 339.6256 Ops/s 333.0900 Ops/s $\color{#35bf28}+1.96\%$
test_values[td0_return_estimate-False-False] 0.1073ms 81.2663μs 12.3052 KOps/s 12.3761 KOps/s $\color{#d91a1a}-0.57\%$
test_values[td1_return_estimate-False-False] 55.8129ms 54.9793ms 18.1887 Ops/s 18.2496 Ops/s $\color{#d91a1a}-0.33\%$
test_values[vec_td1_return_estimate-False-False] 1.4351ms 1.0830ms 923.3689 Ops/s 931.0854 Ops/s $\color{#d91a1a}-0.83\%$
test_values[td_lambda_return_estimate-True-False] 89.4000ms 87.0071ms 11.4933 Ops/s 11.5926 Ops/s $\color{#d91a1a}-0.86\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.4318ms 1.0785ms 927.2110 Ops/s 919.5295 Ops/s $\color{#35bf28}+0.84\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.1555ms 24.7505ms 40.4032 Ops/s 41.0781 Ops/s $\color{#d91a1a}-1.64\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0353ms 0.7501ms 1.3332 KOps/s 1.3233 KOps/s $\color{#35bf28}+0.75\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8641ms 0.6783ms 1.4742 KOps/s 1.5080 KOps/s $\color{#d91a1a}-2.24\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6459ms 1.4837ms 673.9827 Ops/s 677.3083 Ops/s $\color{#d91a1a}-0.49\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.8197ms 0.6840ms 1.4621 KOps/s 1.4649 KOps/s $\color{#d91a1a}-0.20\%$
test_dqn_speed[False-None] 1.6545ms 1.4785ms 676.3648 Ops/s 674.4515 Ops/s $\color{#35bf28}+0.28\%$
test_dqn_speed[False-backward] 2.2508ms 2.1108ms 473.7450 Ops/s 477.3433 Ops/s $\color{#d91a1a}-0.75\%$
test_dqn_speed[True-None] 0.9232ms 0.5327ms 1.8773 KOps/s 1.8981 KOps/s $\color{#d91a1a}-1.10\%$
test_dqn_speed[True-backward] 1.3162ms 1.1813ms 846.5009 Ops/s 907.8906 Ops/s $\textbf{\color{#d91a1a}-6.76\%}$
test_dqn_speed[reduce-overhead-None] 0.9971ms 0.5477ms 1.8258 KOps/s 1.8643 KOps/s $\color{#d91a1a}-2.06\%$
test_dqn_speed[reduce-overhead-backward] 1.0723ms 0.9689ms 1.0321 KOps/s 935.7630 Ops/s $\textbf{\color{#35bf28}+10.30\%}$
test_ddpg_speed[False-None] 3.1908ms 2.8033ms 356.7239 Ops/s 359.8165 Ops/s $\color{#d91a1a}-0.86\%$
test_ddpg_speed[False-backward] 4.1710ms 4.0496ms 246.9370 Ops/s 240.9743 Ops/s $\color{#35bf28}+2.47\%$
test_ddpg_speed[True-None] 1.2823ms 1.0570ms 946.0337 Ops/s 950.8845 Ops/s $\color{#d91a1a}-0.51\%$
test_ddpg_speed[True-backward] 2.2373ms 2.0992ms 476.3719 Ops/s 467.1819 Ops/s $\color{#35bf28}+1.97\%$
test_ddpg_speed[reduce-overhead-None] 1.2102ms 1.0531ms 949.5911 Ops/s 944.5280 Ops/s $\color{#35bf28}+0.54\%$
test_ddpg_speed[reduce-overhead-backward] 1.7630ms 1.6218ms 616.5892 Ops/s 616.4141 Ops/s $\color{#35bf28}+0.03\%$
test_sac_speed[False-None] 8.4155ms 7.8824ms 126.8642 Ops/s 124.1291 Ops/s $\color{#35bf28}+2.20\%$
test_sac_speed[False-backward] 11.3195ms 10.8859ms 91.8618 Ops/s 89.8152 Ops/s $\color{#35bf28}+2.28\%$
test_sac_speed[True-None] 1.6727ms 1.4842ms 673.7441 Ops/s 663.0976 Ops/s $\color{#35bf28}+1.61\%$
test_sac_speed[True-backward] 3.2946ms 3.1196ms 320.5555 Ops/s 299.3784 Ops/s $\textbf{\color{#35bf28}+7.07\%}$
test_sac_speed[reduce-overhead-None] 22.1886ms 12.3791ms 80.7814 Ops/s 78.0061 Ops/s $\color{#35bf28}+3.56\%$
test_sac_speed[reduce-overhead-backward] 1.4751ms 1.3386ms 747.0416 Ops/s 660.8674 Ops/s $\textbf{\color{#35bf28}+13.04\%}$
test_redq_speed[False-None] 8.1560ms 7.3031ms 136.9282 Ops/s 131.1470 Ops/s $\color{#35bf28}+4.41\%$
test_redq_speed[False-backward] 11.8192ms 11.1381ms 89.7822 Ops/s 84.2189 Ops/s $\textbf{\color{#35bf28}+6.61\%}$
test_redq_speed[True-None] 2.1642ms 1.9291ms 518.3780 Ops/s 505.4723 Ops/s $\color{#35bf28}+2.55\%$
test_redq_speed[True-backward] 3.8073ms 3.5523ms 281.5046 Ops/s 261.8715 Ops/s $\textbf{\color{#35bf28}+7.50\%}$
test_redq_speed[reduce-overhead-None] 2.1127ms 1.9365ms 516.3850 Ops/s 503.0789 Ops/s $\color{#35bf28}+2.64\%$
test_redq_speed[reduce-overhead-backward] 3.9498ms 3.5543ms 281.3524 Ops/s 259.4699 Ops/s $\textbf{\color{#35bf28}+8.43\%}$
test_redq_deprec_speed[False-None] 9.5752ms 8.9744ms 111.4278 Ops/s 109.4980 Ops/s $\color{#35bf28}+1.76\%$
test_redq_deprec_speed[False-backward] 12.7168ms 12.0318ms 83.1131 Ops/s 80.2134 Ops/s $\color{#35bf28}+3.61\%$
test_redq_deprec_speed[True-None] 2.4437ms 2.2476ms 444.9267 Ops/s 437.3604 Ops/s $\color{#35bf28}+1.73\%$
test_redq_deprec_speed[True-backward] 3.9937ms 3.8439ms 260.1551 Ops/s 243.8149 Ops/s $\textbf{\color{#35bf28}+6.70\%}$
test_redq_deprec_speed[reduce-overhead-None] 2.5761ms 2.2874ms 437.1851 Ops/s 424.8256 Ops/s $\color{#35bf28}+2.91\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.3168ms 3.8667ms 258.6165 Ops/s 253.9723 Ops/s $\color{#35bf28}+1.83\%$
test_td3_speed[False-None] 7.7906ms 7.7217ms 129.5057 Ops/s 126.6998 Ops/s $\color{#35bf28}+2.21\%$
test_td3_speed[False-backward] 10.6857ms 10.0745ms 99.2609 Ops/s 97.4649 Ops/s $\color{#35bf28}+1.84\%$
test_td3_speed[True-None] 1.5327ms 1.5059ms 664.0460 Ops/s 649.2735 Ops/s $\color{#35bf28}+2.28\%$
test_td3_speed[True-backward] 3.2593ms 3.0414ms 328.7963 Ops/s 326.8486 Ops/s $\color{#35bf28}+0.60\%$
test_td3_speed[reduce-overhead-None] 49.7772ms 25.1276ms 39.7969 Ops/s 38.1790 Ops/s $\color{#35bf28}+4.24\%$
test_td3_speed[reduce-overhead-backward] 1.4150ms 1.2855ms 777.8880 Ops/s 767.0577 Ops/s $\color{#35bf28}+1.41\%$
test_cql_speed[False-None] 16.2210ms 15.7771ms 63.3829 Ops/s 61.4915 Ops/s $\color{#35bf28}+3.08\%$
test_cql_speed[False-backward] 21.5028ms 20.9469ms 47.7399 Ops/s 46.2299 Ops/s $\color{#35bf28}+3.27\%$
test_cql_speed[True-None] 3.0195ms 2.8272ms 353.7058 Ops/s 350.8106 Ops/s $\color{#35bf28}+0.83\%$
test_cql_speed[True-backward] 5.7613ms 4.9490ms 202.0606 Ops/s 201.1583 Ops/s $\color{#35bf28}+0.45\%$
test_cql_speed[reduce-overhead-None] 21.2549ms 12.9737ms 77.0790 Ops/s 78.4578 Ops/s $\color{#d91a1a}-1.76\%$
test_cql_speed[reduce-overhead-backward] 1.8259ms 1.6976ms 589.0573 Ops/s 591.6647 Ops/s $\color{#d91a1a}-0.44\%$
test_a2c_speed[False-None] 3.3300ms 3.1371ms 318.7700 Ops/s 315.8704 Ops/s $\color{#35bf28}+0.92\%$
test_a2c_speed[False-backward] 6.9365ms 6.3145ms 158.3649 Ops/s 156.6665 Ops/s $\color{#35bf28}+1.08\%$
test_a2c_speed[True-None] 1.1468ms 0.9664ms 1.0348 KOps/s 1.0321 KOps/s $\color{#35bf28}+0.26\%$
test_a2c_speed[True-backward] 2.9698ms 2.7645ms 361.7287 Ops/s 366.3059 Ops/s $\color{#d91a1a}-1.25\%$
test_a2c_speed[reduce-overhead-None] 0.4163s 12.4865ms 80.0862 Ops/s 85.6856 Ops/s $\textbf{\color{#d91a1a}-6.53\%}$
test_a2c_speed[reduce-overhead-backward] 1.2886ms 1.1697ms 854.9476 Ops/s 865.7283 Ops/s $\color{#d91a1a}-1.25\%$
test_ppo_speed[False-None] 3.8632ms 3.6477ms 274.1442 Ops/s 275.7809 Ops/s $\color{#d91a1a}-0.59\%$
test_ppo_speed[False-backward] 7.6581ms 7.1162ms 140.5253 Ops/s 141.0787 Ops/s $\color{#d91a1a}-0.39\%$
test_ppo_speed[True-None] 1.0794ms 0.9109ms 1.0979 KOps/s 1.0831 KOps/s $\color{#35bf28}+1.36\%$
test_ppo_speed[True-backward] 2.8097ms 2.6945ms 371.1264 Ops/s 373.5827 Ops/s $\color{#d91a1a}-0.66\%$
test_ppo_speed[reduce-overhead-None] 0.6387ms 0.4877ms 2.0505 KOps/s 1.9049 KOps/s $\textbf{\color{#35bf28}+7.65\%}$
test_ppo_speed[reduce-overhead-backward] 1.2919ms 1.1410ms 876.4090 Ops/s 1.0060 KOps/s $\textbf{\color{#d91a1a}-12.88\%}$
test_reinforce_speed[False-None] 2.3564ms 2.1886ms 456.9045 Ops/s 442.7786 Ops/s $\color{#35bf28}+3.19\%$
test_reinforce_speed[False-backward] 3.7623ms 3.3171ms 301.4649 Ops/s 304.5707 Ops/s $\color{#d91a1a}-1.02\%$
test_reinforce_speed[True-None] 0.9696ms 0.7992ms 1.2513 KOps/s 1.2401 KOps/s $\color{#35bf28}+0.91\%$
test_reinforce_speed[True-backward] 2.6634ms 2.5331ms 394.7729 Ops/s 418.6478 Ops/s $\textbf{\color{#d91a1a}-5.70\%}$
test_reinforce_speed[reduce-overhead-None] 21.6950ms 11.5555ms 86.5387 Ops/s 85.7984 Ops/s $\color{#35bf28}+0.86\%$
test_reinforce_speed[reduce-overhead-backward] 1.3705ms 1.2142ms 823.6000 Ops/s 941.1974 Ops/s $\textbf{\color{#d91a1a}-12.49\%}$
test_iql_speed[False-None] 9.5019ms 9.0112ms 110.9736 Ops/s 109.1197 Ops/s $\color{#35bf28}+1.70\%$
test_iql_speed[False-backward] 13.5727ms 13.0965ms 76.3562 Ops/s 76.6746 Ops/s $\color{#d91a1a}-0.42\%$
test_iql_speed[True-None] 1.8899ms 1.6923ms 590.9128 Ops/s 589.9482 Ops/s $\color{#35bf28}+0.16\%$
test_iql_speed[True-backward] 4.5181ms 4.3504ms 229.8639 Ops/s 232.2864 Ops/s $\color{#d91a1a}-1.04\%$
test_iql_speed[reduce-overhead-None] 19.9752ms 11.3745ms 87.9156 Ops/s 87.1470 Ops/s $\color{#35bf28}+0.88\%$
test_iql_speed[reduce-overhead-backward] 1.6536ms 1.6182ms 617.9712 Ops/s 692.5054 Ops/s $\textbf{\color{#d91a1a}-10.76\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9701ms 6.4510ms 155.0151 Ops/s 150.9438 Ops/s $\color{#35bf28}+2.70\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5733ms 0.3584ms 2.7900 KOps/s 2.8558 KOps/s $\color{#d91a1a}-2.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6029ms 0.3316ms 3.0156 KOps/s 2.9994 KOps/s $\color{#35bf28}+0.54\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.5441ms 6.2024ms 161.2287 Ops/s 158.3760 Ops/s $\color{#35bf28}+1.80\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.2456ms 0.3096ms 3.2297 KOps/s 3.0408 KOps/s $\textbf{\color{#35bf28}+6.21\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6098ms 0.3018ms 3.3129 KOps/s 3.4764 KOps/s $\color{#d91a1a}-4.70\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6893ms 1.2741ms 784.8467 Ops/s 751.1838 Ops/s $\color{#35bf28}+4.48\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5076ms 1.2240ms 816.9991 Ops/s 771.0399 Ops/s $\textbf{\color{#35bf28}+5.96\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5674ms 6.3515ms 157.4442 Ops/s 153.2108 Ops/s $\color{#35bf28}+2.76\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.8478ms 0.4753ms 2.1039 KOps/s 2.2324 KOps/s $\textbf{\color{#d91a1a}-5.75\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6647ms 0.4297ms 2.3271 KOps/s 2.3768 KOps/s $\color{#d91a1a}-2.09\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3238ms 6.1536ms 162.5068 Ops/s 156.7769 Ops/s $\color{#35bf28}+3.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.1659ms 0.3020ms 3.3111 KOps/s 3.0169 KOps/s $\textbf{\color{#35bf28}+9.75\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5716ms 0.3363ms 2.9738 KOps/s 3.3807 KOps/s $\textbf{\color{#d91a1a}-12.04\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 10.1131ms 6.1643ms 162.2237 Ops/s 157.2629 Ops/s $\color{#35bf28}+3.15\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.3557ms 0.3437ms 2.9099 KOps/s 3.6854 KOps/s $\textbf{\color{#d91a1a}-21.04\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5354ms 0.3573ms 2.7986 KOps/s 3.8222 KOps/s $\textbf{\color{#d91a1a}-26.78\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5648ms 6.3536ms 157.3916 Ops/s 156.2056 Ops/s $\color{#35bf28}+0.76\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7114ms 0.5026ms 1.9897 KOps/s 2.0187 KOps/s $\color{#d91a1a}-1.44\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 9.6735ms 0.4181ms 2.3919 KOps/s 2.3048 KOps/s $\color{#35bf28}+3.78\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1511ms 5.4301ms 184.1589 Ops/s 188.3721 Ops/s $\color{#d91a1a}-2.24\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.8696ms 1.8345ms 545.1114 Ops/s 437.1097 Ops/s $\textbf{\color{#35bf28}+24.71\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 9.0499ms 1.3205ms 757.2699 Ops/s 779.3359 Ops/s $\color{#d91a1a}-2.83\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.5075s 15.5251ms 64.4117 Ops/s 186.0675 Ops/s $\textbf{\color{#d91a1a}-65.38\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.7073ms 2.0951ms 477.3144 Ops/s 433.5415 Ops/s $\textbf{\color{#35bf28}+10.10\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.2653ms 1.2223ms 818.1461 Ops/s 968.8652 Ops/s $\textbf{\color{#d91a1a}-15.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.5333ms 5.6713ms 176.3274 Ops/s 31.7628 Ops/s $\textbf{\color{#35bf28}+455.14\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.7856ms 2.2654ms 441.4277 Ops/s 467.0143 Ops/s $\textbf{\color{#d91a1a}-5.48\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.0590ms 1.4289ms 699.8447 Ops/s 730.2922 Ops/s $\color{#d91a1a}-4.17\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.6114ms 13.1156ms 76.2450 Ops/s 75.9668 Ops/s $\color{#35bf28}+0.37\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 22.0775ms 17.5611ms 56.9441 Ops/s 58.7369 Ops/s $\color{#d91a1a}-3.05\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 17.6623ms 17.2493ms 57.9733 Ops/s 54.7237 Ops/s $\textbf{\color{#35bf28}+5.94\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.6706ms 16.9854ms 58.8740 Ops/s 57.5257 Ops/s $\color{#35bf28}+2.34\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.7576ms 17.2551ms 57.9537 Ops/s 53.6934 Ops/s $\textbf{\color{#35bf28}+7.93\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.4262ms 17.9102ms 55.8341 Ops/s 54.3181 Ops/s $\color{#35bf28}+2.79\%$

@vmoens
Update
e994649 
[ghstack-poisoned]
@vmoens vmoens merged commit e994649 into gh/vmoens/48/base Dec 12, 2024
62 of 78 checks passed
vmoens added a commit that referenced this pull request Dec 12, 2024
@vmoens
[Refactor] Refactor trees
57dc25a 
ghstack-source-id: 368ba4c4402b6db0bc8b0688802ce161db9776b7
Pull Request resolved: #2634
@vmoens vmoens deleted the gh/vmoens/48/head branch December 12, 2024 20:55
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