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

[Feature] Add include_hash_inv arg to ChessEnv #2766

Merged
merged 1 commit into from
Feb 6, 2025

Conversation

kurtamohler
Copy link
Collaborator

@kurtamohler kurtamohler commented Feb 6, 2025

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Feb 6, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2766

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

✅ You can merge normally! (4 Unrelated Failures)

As of commit 945197b with merge base 4c06ce2 (image):

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

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

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

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Feb 6, 2025
kurtamohler added a commit that referenced this pull request Feb 6, 2025
ghstack-source-id: f6920d781835902a6db02f74c5e5a3041243c5e3
Pull Request resolved: #2766
@kurtamohler kurtamohler requested a review from vmoens February 6, 2025 00:39
Copy link

github-actions bot commented Feb 6, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.5370s 0.4519s 2.2130 Ops/s 2.2314 Ops/s $\color{#d91a1a}-0.83\%$
test_transformed 1.0216s 0.9391s 1.0649 Ops/s 1.1030 Ops/s $\color{#d91a1a}-3.45\%$
test_serial 1.4691s 1.3908s 0.7190 Ops/s 0.7350 Ops/s $\color{#d91a1a}-2.17\%$
test_parallel 1.3109s 1.2051s 0.8298 Ops/s 0.8206 Ops/s $\color{#35bf28}+1.12\%$
test_step_mdp_speed[True-True-True-True-True] 0.2359ms 30.0716μs 33.2540 KOps/s 32.7213 KOps/s $\color{#35bf28}+1.63\%$
test_step_mdp_speed[True-True-True-True-False] 45.4350μs 17.7832μs 56.2328 KOps/s 55.9079 KOps/s $\color{#35bf28}+0.58\%$
test_step_mdp_speed[True-True-True-False-True] 48.0500μs 17.1858μs 58.1874 KOps/s 59.0407 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-True-True-False-False] 0.5620ms 10.0690μs 99.3143 KOps/s 98.8384 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[True-True-False-True-True] 75.5610μs 31.9181μs 31.3302 KOps/s 30.8828 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[True-True-False-True-False] 49.1220μs 19.6880μs 50.7924 KOps/s 50.4107 KOps/s $\color{#35bf28}+0.76\%$
test_step_mdp_speed[True-True-False-False-True] 61.0240μs 18.8048μs 53.1780 KOps/s 52.7558 KOps/s $\color{#35bf28}+0.80\%$
test_step_mdp_speed[True-True-False-False-False] 38.8620μs 11.8531μs 84.3660 KOps/s 83.3003 KOps/s $\color{#35bf28}+1.28\%$
test_step_mdp_speed[True-False-True-True-True] 74.9390μs 34.2944μs 29.1593 KOps/s 28.6079 KOps/s $\color{#35bf28}+1.93\%$
test_step_mdp_speed[True-False-True-True-False] 95.7080μs 21.5030μs 46.5052 KOps/s 45.9656 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[True-False-True-False-True] 89.2960μs 18.8970μs 52.9185 KOps/s 52.5986 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[True-False-True-False-False] 38.9530μs 11.8612μs 84.3088 KOps/s 83.2676 KOps/s $\color{#35bf28}+1.25\%$
test_step_mdp_speed[True-False-False-True-True] 68.5580μs 36.0001μs 27.7777 KOps/s 27.2179 KOps/s $\color{#35bf28}+2.06\%$
test_step_mdp_speed[True-False-False-True-False] 60.6930μs 23.4483μs 42.6470 KOps/s 42.3634 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[True-False-False-False-True] 62.5360μs 20.6911μs 48.3299 KOps/s 47.2193 KOps/s $\color{#35bf28}+2.35\%$
test_step_mdp_speed[True-False-False-False-False] 33.0820μs 13.7565μs 72.6927 KOps/s 72.8271 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[False-True-True-True-True] 74.5290μs 34.4069μs 29.0639 KOps/s 29.1472 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[False-True-True-True-False] 53.9310μs 21.7606μs 45.9545 KOps/s 45.5137 KOps/s $\color{#35bf28}+0.97\%$
test_step_mdp_speed[False-True-True-False-True] 60.4430μs 21.6625μs 46.1626 KOps/s 46.0803 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[False-True-True-False-False] 80.4500μs 13.2165μs 75.6628 KOps/s 74.9851 KOps/s $\color{#35bf28}+0.90\%$
test_step_mdp_speed[False-True-False-True-True] 0.5877ms 36.1051μs 27.6969 KOps/s 27.9605 KOps/s $\color{#d91a1a}-0.94\%$
test_step_mdp_speed[False-True-False-True-False] 66.1530μs 23.2445μs 43.0210 KOps/s 42.2473 KOps/s $\color{#35bf28}+1.83\%$
test_step_mdp_speed[False-True-False-False-True] 2.5595ms 23.3242μs 42.8739 KOps/s 42.2162 KOps/s $\color{#35bf28}+1.56\%$
test_step_mdp_speed[False-True-False-False-False] 47.5190μs 15.0425μs 66.4783 KOps/s 66.3644 KOps/s $\color{#35bf28}+0.17\%$
test_step_mdp_speed[False-False-True-True-True] 88.0940μs 37.6550μs 26.5569 KOps/s 26.3834 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-False-True-True-False] 52.4380μs 25.2822μs 39.5534 KOps/s 39.3545 KOps/s $\color{#35bf28}+0.51\%$
test_step_mdp_speed[False-False-True-False-True] 64.5800μs 23.3221μs 42.8778 KOps/s 42.8168 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[False-False-True-False-False] 54.8520μs 15.0901μs 66.2686 KOps/s 65.9634 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-False-False-True-True] 96.1890μs 39.2872μs 25.4536 KOps/s 25.5705 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[False-False-False-True-False] 55.8140μs 26.7400μs 37.3971 KOps/s 37.3509 KOps/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[False-False-False-False-True] 64.5700μs 24.7130μs 40.4646 KOps/s 40.2725 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[False-False-False-False-False] 44.3020μs 16.8352μs 59.3995 KOps/s 59.8915 KOps/s $\color{#d91a1a}-0.82\%$
test_values[generalized_advantage_estimate-True-True] 10.4202ms 9.8754ms 101.2616 Ops/s 104.0719 Ops/s $\color{#d91a1a}-2.70\%$
test_values[vec_generalized_advantage_estimate-True-True] 26.1825ms 24.1852ms 41.3476 Ops/s 41.5251 Ops/s $\color{#d91a1a}-0.43\%$
test_values[td0_return_estimate-False-False] 0.2498ms 0.1789ms 5.5890 KOps/s 5.6242 KOps/s $\color{#d91a1a}-0.62\%$
test_values[td1_return_estimate-False-False] 27.4190ms 24.3209ms 41.1168 Ops/s 42.1255 Ops/s $\color{#d91a1a}-2.39\%$
test_values[vec_td1_return_estimate-False-False] 26.8969ms 24.4043ms 40.9765 Ops/s 41.3138 Ops/s $\color{#d91a1a}-0.82\%$
test_values[td_lambda_return_estimate-True-False] 35.9251ms 34.7430ms 28.7828 Ops/s 29.1833 Ops/s $\color{#d91a1a}-1.37\%$
test_values[vec_td_lambda_return_estimate-True-False] 26.1902ms 24.2565ms 41.2260 Ops/s 41.2171 Ops/s $\color{#35bf28}+0.02\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.2639ms 8.5786ms 116.5693 Ops/s 118.6230 Ops/s $\color{#d91a1a}-1.73\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2596ms 1.9427ms 514.7407 Ops/s 512.6088 Ops/s $\color{#35bf28}+0.42\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5408ms 0.3607ms 2.7723 KOps/s 2.7383 KOps/s $\color{#35bf28}+1.24\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 43.7566ms 41.6840ms 23.9900 Ops/s 26.9392 Ops/s $\textbf{\color{#d91a1a}-10.95\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.2240ms 3.4286ms 291.6682 Ops/s 290.3486 Ops/s $\color{#35bf28}+0.45\%$
test_dqn_speed[False-None] 5.9116ms 1.3961ms 716.2943 Ops/s 682.5302 Ops/s $\color{#35bf28}+4.95\%$
test_dqn_speed[False-backward] 2.1289ms 1.8730ms 533.9052 Ops/s 541.0208 Ops/s $\color{#d91a1a}-1.32\%$
test_dqn_speed[True-None] 0.6636ms 0.4702ms 2.1269 KOps/s 2.0767 KOps/s $\color{#35bf28}+2.42\%$
test_dqn_speed[True-backward] 0.9592ms 0.8956ms 1.1165 KOps/s 812.4288 Ops/s $\textbf{\color{#35bf28}+37.43\%}$
test_dqn_speed[reduce-overhead-None] 0.7563ms 0.4895ms 2.0430 KOps/s 2.0717 KOps/s $\color{#d91a1a}-1.39\%$
test_dqn_speed[reduce-overhead-backward] 0.9561ms 0.8952ms 1.1171 KOps/s 1.1092 KOps/s $\color{#35bf28}+0.71\%$
test_ddpg_speed[False-None] 3.2839ms 2.8879ms 346.2742 Ops/s 352.1668 Ops/s $\color{#d91a1a}-1.67\%$
test_ddpg_speed[False-backward] 4.1250ms 4.0169ms 248.9505 Ops/s 249.7366 Ops/s $\color{#d91a1a}-0.31\%$
test_ddpg_speed[True-None] 1.7700ms 1.2215ms 818.6739 Ops/s 816.8137 Ops/s $\color{#35bf28}+0.23\%$
test_ddpg_speed[True-backward] 2.1548ms 2.1120ms 473.4872 Ops/s 431.1752 Ops/s $\textbf{\color{#35bf28}+9.81\%}$
test_ddpg_speed[reduce-overhead-None] 1.6772ms 1.2221ms 818.2644 Ops/s 803.2556 Ops/s $\color{#35bf28}+1.87\%$
test_ddpg_speed[reduce-overhead-backward] 2.2287ms 2.1189ms 471.9380 Ops/s 473.4027 Ops/s $\color{#d91a1a}-0.31\%$
test_sac_speed[False-None] 9.8288ms 7.9773ms 125.3549 Ops/s 126.3199 Ops/s $\color{#d91a1a}-0.76\%$
test_sac_speed[False-backward] 10.9528ms 10.6285ms 94.0862 Ops/s 94.8414 Ops/s $\color{#d91a1a}-0.80\%$
test_sac_speed[True-None] 3.2806ms 2.0995ms 476.2983 Ops/s 476.1499 Ops/s $\color{#35bf28}+0.03\%$
test_sac_speed[True-backward] 3.7921ms 3.7225ms 268.6345 Ops/s 265.0293 Ops/s $\color{#35bf28}+1.36\%$
test_sac_speed[reduce-overhead-None] 2.6025ms 2.0616ms 485.0705 Ops/s 477.8605 Ops/s $\color{#35bf28}+1.51\%$
test_sac_speed[reduce-overhead-backward] 3.9591ms 3.7734ms 265.0124 Ops/s 266.5401 Ops/s $\color{#d91a1a}-0.57\%$
test_redq_speed[False-None] 13.9628ms 12.9445ms 77.2526 Ops/s 78.3217 Ops/s $\color{#d91a1a}-1.36\%$
test_redq_speed[False-backward] 23.8397ms 22.1244ms 45.1990 Ops/s 45.6737 Ops/s $\color{#d91a1a}-1.04\%$
test_redq_speed[True-None] 5.7288ms 4.8347ms 206.8376 Ops/s 204.9774 Ops/s $\color{#35bf28}+0.91\%$
test_redq_speed[True-backward] 15.1795ms 12.3521ms 80.9582 Ops/s 80.9217 Ops/s $\color{#35bf28}+0.05\%$
test_redq_speed[reduce-overhead-None] 5.3993ms 4.7612ms 210.0309 Ops/s 203.6661 Ops/s $\color{#35bf28}+3.13\%$
test_redq_speed[reduce-overhead-backward] 13.1540ms 12.1263ms 82.4653 Ops/s 80.6418 Ops/s $\color{#35bf28}+2.26\%$
test_redq_deprec_speed[False-None] 14.7620ms 12.6892ms 78.8070 Ops/s 78.4187 Ops/s $\color{#35bf28}+0.50\%$
test_redq_deprec_speed[False-backward] 19.5352ms 18.3933ms 54.3676 Ops/s 54.9197 Ops/s $\color{#d91a1a}-1.01\%$
test_redq_deprec_speed[True-None] 5.3937ms 3.8744ms 258.1069 Ops/s 260.9990 Ops/s $\color{#d91a1a}-1.11\%$
test_redq_deprec_speed[True-backward] 8.7455ms 8.1063ms 123.3602 Ops/s 120.4818 Ops/s $\color{#35bf28}+2.39\%$
test_redq_deprec_speed[reduce-overhead-None] 4.4796ms 3.7750ms 264.8989 Ops/s 256.3472 Ops/s $\color{#35bf28}+3.34\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.7523ms 8.1995ms 121.9580 Ops/s 118.3994 Ops/s $\color{#35bf28}+3.01\%$
test_td3_speed[False-None] 8.1647ms 7.9124ms 126.3845 Ops/s 117.3052 Ops/s $\textbf{\color{#35bf28}+7.74\%}$
test_td3_speed[False-backward] 10.6871ms 10.2963ms 97.1221 Ops/s 96.5088 Ops/s $\color{#35bf28}+0.64\%$
test_td3_speed[True-None] 1.9424ms 1.7525ms 570.6246 Ops/s 553.5835 Ops/s $\color{#35bf28}+3.08\%$
test_td3_speed[True-backward] 3.5040ms 3.3442ms 299.0253 Ops/s 288.5816 Ops/s $\color{#35bf28}+3.62\%$
test_td3_speed[reduce-overhead-None] 1.8698ms 1.7661ms 566.2135 Ops/s 543.3626 Ops/s $\color{#35bf28}+4.21\%$
test_td3_speed[reduce-overhead-backward] 3.8307ms 3.4430ms 290.4408 Ops/s 289.0331 Ops/s $\color{#35bf28}+0.49\%$
test_cql_speed[False-None] 39.7507ms 36.7102ms 27.2404 Ops/s 27.3317 Ops/s $\color{#d91a1a}-0.33\%$
test_cql_speed[False-backward] 55.3893ms 47.1240ms 21.2206 Ops/s 20.6333 Ops/s $\color{#35bf28}+2.85\%$
test_cql_speed[True-None] 16.9043ms 15.8820ms 62.9643 Ops/s 62.0442 Ops/s $\color{#35bf28}+1.48\%$
test_cql_speed[True-backward] 23.8505ms 22.6271ms 44.1949 Ops/s 43.7433 Ops/s $\color{#35bf28}+1.03\%$
test_cql_speed[reduce-overhead-None] 17.2363ms 16.0300ms 62.3832 Ops/s 62.0594 Ops/s $\color{#35bf28}+0.52\%$
test_cql_speed[reduce-overhead-backward] 23.2356ms 22.3682ms 44.7063 Ops/s 42.2713 Ops/s $\textbf{\color{#35bf28}+5.76\%}$
test_a2c_speed[False-None] 8.5179ms 7.1521ms 139.8199 Ops/s 134.5894 Ops/s $\color{#35bf28}+3.89\%$
test_a2c_speed[False-backward] 15.1307ms 14.1377ms 70.7331 Ops/s 69.2633 Ops/s $\color{#35bf28}+2.12\%$
test_a2c_speed[True-None] 4.3841ms 3.6758ms 272.0530 Ops/s 268.9307 Ops/s $\color{#35bf28}+1.16\%$
test_a2c_speed[True-backward] 11.2564ms 10.2733ms 97.3399 Ops/s 98.4447 Ops/s $\color{#d91a1a}-1.12\%$
test_a2c_speed[reduce-overhead-None] 4.4614ms 3.6746ms 272.1413 Ops/s 268.6759 Ops/s $\color{#35bf28}+1.29\%$
test_a2c_speed[reduce-overhead-backward] 10.6447ms 10.0848ms 99.1594 Ops/s 94.2816 Ops/s $\textbf{\color{#35bf28}+5.17\%}$
test_ppo_speed[False-None] 9.1881ms 7.5359ms 132.6989 Ops/s 132.9781 Ops/s $\color{#d91a1a}-0.21\%$
test_ppo_speed[False-backward] 15.3472ms 14.6364ms 68.3226 Ops/s 65.8265 Ops/s $\color{#35bf28}+3.79\%$
test_ppo_speed[True-None] 4.8663ms 4.0527ms 246.7480 Ops/s 242.5439 Ops/s $\color{#35bf28}+1.73\%$
test_ppo_speed[True-backward] 11.3018ms 9.8878ms 101.1349 Ops/s 100.7813 Ops/s $\color{#35bf28}+0.35\%$
test_ppo_speed[reduce-overhead-None] 4.7703ms 4.0648ms 246.0160 Ops/s 244.9378 Ops/s $\color{#35bf28}+0.44\%$
test_ppo_speed[reduce-overhead-backward] 10.6498ms 9.9117ms 100.8910 Ops/s 101.0478 Ops/s $\color{#d91a1a}-0.16\%$
test_reinforce_speed[False-None] 7.6528ms 6.5199ms 153.3755 Ops/s 152.2912 Ops/s $\color{#35bf28}+0.71\%$
test_reinforce_speed[False-backward] 11.3408ms 9.8029ms 102.0107 Ops/s 102.1223 Ops/s $\color{#d91a1a}-0.11\%$
test_reinforce_speed[True-None] 3.6454ms 3.0389ms 329.0651 Ops/s 329.3249 Ops/s $\color{#d91a1a}-0.08\%$
test_reinforce_speed[True-backward] 9.4810ms 8.9422ms 111.8295 Ops/s 111.7148 Ops/s $\color{#35bf28}+0.10\%$
test_reinforce_speed[reduce-overhead-None] 3.6592ms 3.0051ms 332.7678 Ops/s 328.9259 Ops/s $\color{#35bf28}+1.17\%$
test_reinforce_speed[reduce-overhead-backward] 9.7084ms 8.8918ms 112.4635 Ops/s 111.5485 Ops/s $\color{#35bf28}+0.82\%$
test_iql_speed[False-None] 33.5744ms 32.0357ms 31.2151 Ops/s 30.8119 Ops/s $\color{#35bf28}+1.31\%$
test_iql_speed[False-backward] 46.4233ms 44.6784ms 22.3822 Ops/s 22.0762 Ops/s $\color{#35bf28}+1.39\%$
test_iql_speed[True-None] 12.2348ms 11.1340ms 89.8152 Ops/s 89.6462 Ops/s $\color{#35bf28}+0.19\%$
test_iql_speed[True-backward] 23.5671ms 21.9726ms 45.5112 Ops/s 45.8171 Ops/s $\color{#d91a1a}-0.67\%$
test_iql_speed[reduce-overhead-None] 14.4922ms 11.4292ms 87.4951 Ops/s 90.4322 Ops/s $\color{#d91a1a}-3.25\%$
test_iql_speed[reduce-overhead-backward] 26.1114ms 22.3039ms 44.8351 Ops/s 45.8275 Ops/s $\color{#d91a1a}-2.17\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.0931ms 4.8616ms 205.6939 Ops/s 200.7677 Ops/s $\color{#35bf28}+2.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8671ms 0.5330ms 1.8760 KOps/s 1.8476 KOps/s $\color{#35bf28}+1.54\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8225ms 0.5097ms 1.9619 KOps/s 1.9688 KOps/s $\color{#d91a1a}-0.35\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.0321ms 4.6417ms 215.4390 Ops/s 214.1100 Ops/s $\color{#35bf28}+0.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.5673ms 0.5239ms 1.9088 KOps/s 1.9438 KOps/s $\color{#d91a1a}-1.80\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7497ms 0.4986ms 2.0058 KOps/s 2.0151 KOps/s $\color{#d91a1a}-0.46\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.4278ms 1.7091ms 585.1071 Ops/s 566.8584 Ops/s $\color{#35bf28}+3.22\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.3591ms 1.6144ms 619.4217 Ops/s 629.6630 Ops/s $\color{#d91a1a}-1.63\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.1899ms 4.7681ms 209.7281 Ops/s 208.5346 Ops/s $\color{#35bf28}+0.57\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.7877ms 0.6668ms 1.4997 KOps/s 1.5185 KOps/s $\color{#d91a1a}-1.24\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9685ms 0.6417ms 1.5584 KOps/s 1.5632 KOps/s $\color{#d91a1a}-0.31\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.8173ms 4.6339ms 215.8021 Ops/s 214.7445 Ops/s $\color{#35bf28}+0.49\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 4.0045ms 0.5360ms 1.8656 KOps/s 1.8685 KOps/s $\color{#d91a1a}-0.15\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7303ms 0.5051ms 1.9797 KOps/s 1.9606 KOps/s $\color{#35bf28}+0.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.3160ms 4.5951ms 217.6239 Ops/s 213.4965 Ops/s $\color{#35bf28}+1.93\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8952ms 0.5260ms 1.9011 KOps/s 1.9174 KOps/s $\color{#d91a1a}-0.85\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7222ms 0.5002ms 1.9994 KOps/s 1.9794 KOps/s $\color{#35bf28}+1.01\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.7632ms 4.7787ms 209.2604 Ops/s 209.4458 Ops/s $\color{#d91a1a}-0.09\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.4596ms 0.6724ms 1.4871 KOps/s 1.5202 KOps/s $\color{#d91a1a}-2.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8510ms 0.6434ms 1.5541 KOps/s 1.5571 KOps/s $\color{#d91a1a}-0.19\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1489ms 4.2758ms 233.8752 Ops/s 251.4019 Ops/s $\textbf{\color{#d91a1a}-6.97\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.9036ms 2.4196ms 413.2860 Ops/s 453.4942 Ops/s $\textbf{\color{#d91a1a}-8.87\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0651ms 1.3301ms 751.8396 Ops/s 774.0189 Ops/s $\color{#d91a1a}-2.87\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4164s 12.4991ms 80.0056 Ops/s 35.5459 Ops/s $\textbf{\color{#35bf28}+125.08\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 5.8403ms 2.2271ms 449.0127 Ops/s 423.0968 Ops/s $\textbf{\color{#35bf28}+6.13\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.3130ms 1.4477ms 690.7643 Ops/s 716.2113 Ops/s $\color{#d91a1a}-3.55\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.1909ms 4.3964ms 227.4587 Ops/s 230.6320 Ops/s $\color{#d91a1a}-1.38\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 7.9860ms 2.5136ms 397.8364 Ops/s 398.8265 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.6037ms 1.5631ms 639.7344 Ops/s 646.5764 Ops/s $\color{#d91a1a}-1.06\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 11.9248ms 11.5724ms 86.4123 Ops/s 86.2696 Ops/s $\color{#35bf28}+0.17\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.6862ms 14.2080ms 70.3829 Ops/s 72.0401 Ops/s $\color{#d91a1a}-2.30\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.5281ms 20.4051ms 49.0073 Ops/s 48.8844 Ops/s $\color{#35bf28}+0.25\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 21.2237ms 14.5039ms 68.9469 Ops/s 70.2007 Ops/s $\color{#d91a1a}-1.79\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 20.7234ms 20.2645ms 49.3474 Ops/s 49.0690 Ops/s $\color{#35bf28}+0.57\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.1325ms 15.5693ms 64.2288 Ops/s 65.4588 Ops/s $\color{#d91a1a}-1.88\%$

Copy link

github-actions bot commented Feb 6, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}23$. Worsened: $\large\color{#d91a1a}14$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.8243s 0.7394s 1.3524 Ops/s 1.3552 Ops/s $\color{#d91a1a}-0.20\%$
test_transformed 1.3198s 1.3179s 0.7588 Ops/s 0.7456 Ops/s $\color{#35bf28}+1.77\%$
test_serial 2.1307s 2.1291s 0.4697 Ops/s 0.4631 Ops/s $\color{#35bf28}+1.42\%$
test_parallel 1.8705s 1.8247s 0.5480 Ops/s 0.5364 Ops/s $\color{#35bf28}+2.17\%$
test_step_mdp_speed[True-True-True-True-True] 0.2645ms 39.6704μs 25.2077 KOps/s 26.0690 KOps/s $\color{#d91a1a}-3.30\%$
test_step_mdp_speed[True-True-True-True-False] 57.5610μs 22.7744μs 43.9090 KOps/s 44.4130 KOps/s $\color{#d91a1a}-1.13\%$
test_step_mdp_speed[True-True-True-False-True] 59.4310μs 21.2388μs 47.0837 KOps/s 47.3486 KOps/s $\color{#d91a1a}-0.56\%$
test_step_mdp_speed[True-True-True-False-False] 37.0610μs 12.5092μs 79.9415 KOps/s 82.6048 KOps/s $\color{#d91a1a}-3.22\%$
test_step_mdp_speed[True-True-False-True-True] 73.5020μs 41.9581μs 23.8333 KOps/s 24.2081 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[True-True-False-True-False] 59.9210μs 24.9930μs 40.0111 KOps/s 40.4574 KOps/s $\color{#d91a1a}-1.10\%$
test_step_mdp_speed[True-True-False-False-True] 62.0810μs 23.8647μs 41.9029 KOps/s 41.4454 KOps/s $\color{#35bf28}+1.10\%$
test_step_mdp_speed[True-True-False-False-False] 44.8810μs 14.9355μs 66.9544 KOps/s 67.2123 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[True-False-True-True-True] 77.7410μs 44.1419μs 22.6542 KOps/s 23.1863 KOps/s $\color{#d91a1a}-2.29\%$
test_step_mdp_speed[True-False-True-True-False] 64.7820μs 27.2441μs 36.7051 KOps/s 37.3110 KOps/s $\color{#d91a1a}-1.62\%$
test_step_mdp_speed[True-False-True-False-True] 74.2510μs 24.3197μs 41.1189 KOps/s 42.1226 KOps/s $\color{#d91a1a}-2.38\%$
test_step_mdp_speed[True-False-True-False-False] 53.6010μs 14.8063μs 67.5390 KOps/s 69.7736 KOps/s $\color{#d91a1a}-3.20\%$
test_step_mdp_speed[True-False-False-True-True] 86.2820μs 46.4140μs 21.5452 KOps/s 22.2788 KOps/s $\color{#d91a1a}-3.29\%$
test_step_mdp_speed[True-False-False-True-False] 73.2820μs 29.7473μs 33.6165 KOps/s 34.5294 KOps/s $\color{#d91a1a}-2.64\%$
test_step_mdp_speed[True-False-False-False-True] 65.9720μs 26.2641μs 38.0748 KOps/s 38.7895 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[True-False-False-False-False] 45.7400μs 17.0076μs 58.7973 KOps/s 59.3951 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[False-True-True-True-True] 76.9920μs 43.7087μs 22.8788 KOps/s 23.2761 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[False-True-True-True-False] 63.2410μs 27.2194μs 36.7385 KOps/s 36.7809 KOps/s $\color{#d91a1a}-0.12\%$
test_step_mdp_speed[False-True-True-False-True] 0.1186ms 28.0145μs 35.6958 KOps/s 36.1525 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[False-True-True-False-False] 47.5810μs 16.5167μs 60.5447 KOps/s 60.7384 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[False-True-False-True-True] 81.3820μs 45.8944μs 21.7892 KOps/s 21.9720 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[False-True-False-True-False] 63.6510μs 29.5515μs 33.8392 KOps/s 34.3521 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[False-True-False-False-True] 3.2156ms 30.5733μs 32.7082 KOps/s 33.4618 KOps/s $\color{#d91a1a}-2.25\%$
test_step_mdp_speed[False-True-False-False-False] 56.5310μs 18.9726μs 52.7076 KOps/s 53.1797 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-False-True-True-True] 87.4010μs 48.3707μs 20.6737 KOps/s 20.7674 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-False-True-True-False] 61.7210μs 32.2093μs 31.0469 KOps/s 31.3772 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[False-False-True-False-True] 61.1810μs 30.4279μs 32.8646 KOps/s 33.3837 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[False-False-True-False-False] 45.7200μs 18.6734μs 53.5521 KOps/s 53.5344 KOps/s $\color{#35bf28}+0.03\%$
test_step_mdp_speed[False-False-False-True-True] 79.7410μs 50.1138μs 19.9546 KOps/s 20.1613 KOps/s $\color{#d91a1a}-1.03\%$
test_step_mdp_speed[False-False-False-True-False] 63.0810μs 34.5176μs 28.9707 KOps/s 29.5194 KOps/s $\color{#d91a1a}-1.86\%$
test_step_mdp_speed[False-False-False-False-True] 60.7910μs 32.0204μs 31.2300 KOps/s 31.8823 KOps/s $\color{#d91a1a}-2.05\%$
test_step_mdp_speed[False-False-False-False-False] 59.0620μs 20.8853μs 47.8805 KOps/s 48.6086 KOps/s $\color{#d91a1a}-1.50\%$
test_values[generalized_advantage_estimate-True-True] 25.3068ms 24.8630ms 40.2204 Ops/s 39.5760 Ops/s $\color{#35bf28}+1.63\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1144s 3.1851ms 313.9601 Ops/s 333.6514 Ops/s $\textbf{\color{#d91a1a}-5.90\%}$
test_values[td0_return_estimate-False-False] 0.1046ms 79.9914μs 12.5013 KOps/s 12.4131 KOps/s $\color{#35bf28}+0.71\%$
test_values[td1_return_estimate-False-False] 56.2586ms 55.1692ms 18.1261 Ops/s 18.0137 Ops/s $\color{#35bf28}+0.62\%$
test_values[vec_td1_return_estimate-False-False] 1.3217ms 1.0849ms 921.7310 Ops/s 920.3356 Ops/s $\color{#35bf28}+0.15\%$
test_values[td_lambda_return_estimate-True-False] 88.3942ms 87.7717ms 11.3932 Ops/s 11.3834 Ops/s $\color{#35bf28}+0.09\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2448ms 1.0776ms 927.9561 Ops/s 927.2882 Ops/s $\color{#35bf28}+0.07\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.0433ms 24.6439ms 40.5780 Ops/s 40.7245 Ops/s $\color{#d91a1a}-0.36\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0256ms 0.7502ms 1.3330 KOps/s 1.3331 KOps/s $-0.00\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7509ms 0.6692ms 1.4943 KOps/s 1.4969 KOps/s $\color{#d91a1a}-0.17\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5416ms 1.4851ms 673.3338 Ops/s 674.5500 Ops/s $\color{#d91a1a}-0.18\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7769ms 0.6921ms 1.4449 KOps/s 1.4638 KOps/s $\color{#d91a1a}-1.29\%$
test_dqn_speed[False-None] 1.6165ms 1.5240ms 656.1495 Ops/s 659.6742 Ops/s $\color{#d91a1a}-0.53\%$
test_dqn_speed[False-backward] 2.2174ms 2.1497ms 465.1891 Ops/s 465.6616 Ops/s $\color{#d91a1a}-0.10\%$
test_dqn_speed[True-None] 0.6097ms 0.5388ms 1.8561 KOps/s 1.7585 KOps/s $\textbf{\color{#35bf28}+5.55\%}$
test_dqn_speed[True-backward] 1.2464ms 1.1939ms 837.5698 Ops/s 826.0500 Ops/s $\color{#35bf28}+1.39\%$
test_dqn_speed[reduce-overhead-None] 0.6673ms 0.5723ms 1.7472 KOps/s 1.7190 KOps/s $\color{#35bf28}+1.64\%$
test_dqn_speed[reduce-overhead-backward] 1.0023ms 0.9651ms 1.0362 KOps/s 946.3387 Ops/s $\textbf{\color{#35bf28}+9.49\%}$
test_ddpg_speed[False-None] 3.2989ms 2.8771ms 347.5697 Ops/s 347.0388 Ops/s $\color{#35bf28}+0.15\%$
test_ddpg_speed[False-backward] 4.5775ms 4.1363ms 241.7645 Ops/s 234.0138 Ops/s $\color{#35bf28}+3.31\%$
test_ddpg_speed[True-None] 1.4139ms 1.3083ms 764.3230 Ops/s 754.0698 Ops/s $\color{#35bf28}+1.36\%$
test_ddpg_speed[True-backward] 2.4391ms 2.3632ms 423.1464 Ops/s 390.3694 Ops/s $\textbf{\color{#35bf28}+8.40\%}$
test_ddpg_speed[reduce-overhead-None] 1.4503ms 1.3211ms 756.9337 Ops/s 747.2667 Ops/s $\color{#35bf28}+1.29\%$
test_ddpg_speed[reduce-overhead-backward] 1.9077ms 1.8546ms 539.2066 Ops/s 495.0791 Ops/s $\textbf{\color{#35bf28}+8.91\%}$
test_sac_speed[False-None] 8.4793ms 8.0615ms 124.0460 Ops/s 123.5952 Ops/s $\color{#35bf28}+0.36\%$
test_sac_speed[False-backward] 11.6188ms 11.0004ms 90.9059 Ops/s 88.7206 Ops/s $\color{#35bf28}+2.46\%$
test_sac_speed[True-None] 1.8871ms 1.7941ms 557.3978 Ops/s 547.6464 Ops/s $\color{#35bf28}+1.78\%$
test_sac_speed[True-backward] 3.5579ms 3.4626ms 288.8044 Ops/s 268.3332 Ops/s $\textbf{\color{#35bf28}+7.63\%}$
test_sac_speed[reduce-overhead-None] 20.9698ms 11.9341ms 83.7937 Ops/s 84.0507 Ops/s $\color{#d91a1a}-0.31\%$
test_sac_speed[reduce-overhead-backward] 1.8501ms 1.7702ms 564.9133 Ops/s 551.4033 Ops/s $\color{#35bf28}+2.45\%$
test_redq_speed[False-None] 7.8818ms 7.4523ms 134.1866 Ops/s 131.5567 Ops/s $\color{#35bf28}+2.00\%$
test_redq_speed[False-backward] 12.0909ms 11.6416ms 85.8991 Ops/s 84.9582 Ops/s $\color{#35bf28}+1.11\%$
test_redq_speed[True-None] 2.4945ms 2.3553ms 424.5736 Ops/s 431.5323 Ops/s $\color{#d91a1a}-1.61\%$
test_redq_speed[True-backward] 4.0503ms 3.9089ms 255.8239 Ops/s 238.5044 Ops/s $\textbf{\color{#35bf28}+7.26\%}$
test_redq_speed[reduce-overhead-None] 2.4657ms 2.3702ms 421.8986 Ops/s 430.4906 Ops/s $\color{#d91a1a}-2.00\%$
test_redq_speed[reduce-overhead-backward] 4.4012ms 3.9367ms 254.0204 Ops/s 239.4593 Ops/s $\textbf{\color{#35bf28}+6.08\%}$
test_redq_deprec_speed[False-None] 9.9453ms 9.3937ms 106.4540 Ops/s 109.1664 Ops/s $\color{#d91a1a}-2.48\%$
test_redq_deprec_speed[False-backward] 12.8501ms 12.2298ms 81.7675 Ops/s 80.3597 Ops/s $\color{#35bf28}+1.75\%$
test_redq_deprec_speed[True-None] 2.7972ms 2.6709ms 374.4030 Ops/s 382.4544 Ops/s $\color{#d91a1a}-2.11\%$
test_redq_deprec_speed[True-backward] 4.8043ms 4.2961ms 232.7717 Ops/s 222.7261 Ops/s $\color{#35bf28}+4.51\%$
test_redq_deprec_speed[reduce-overhead-None] 2.6562ms 2.5803ms 387.5577 Ops/s 377.7275 Ops/s $\color{#35bf28}+2.60\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.4026ms 4.2197ms 236.9831 Ops/s 219.0675 Ops/s $\textbf{\color{#35bf28}+8.18\%}$
test_td3_speed[False-None] 8.0077ms 7.9634ms 125.5737 Ops/s 124.7869 Ops/s $\color{#35bf28}+0.63\%$
test_td3_speed[False-backward] 10.7245ms 10.3044ms 97.0461 Ops/s 94.3692 Ops/s $\color{#35bf28}+2.84\%$
test_td3_speed[True-None] 1.6207ms 1.5918ms 628.2077 Ops/s 604.0413 Ops/s $\color{#35bf28}+4.00\%$
test_td3_speed[True-backward] 3.1344ms 3.1021ms 322.3649 Ops/s 299.9158 Ops/s $\textbf{\color{#35bf28}+7.49\%}$
test_td3_speed[reduce-overhead-None] 48.7993ms 25.3030ms 39.5210 Ops/s 38.1183 Ops/s $\color{#35bf28}+3.68\%$
test_td3_speed[reduce-overhead-backward] 1.3605ms 1.3225ms 756.1209 Ops/s 657.6870 Ops/s $\textbf{\color{#35bf28}+14.97\%}$
test_cql_speed[False-None] 17.1884ms 16.7304ms 59.7716 Ops/s 59.3761 Ops/s $\color{#35bf28}+0.67\%$
test_cql_speed[False-backward] 22.4312ms 21.9369ms 45.5852 Ops/s 44.8131 Ops/s $\color{#35bf28}+1.72\%$
test_cql_speed[True-None] 3.2835ms 3.1645ms 316.0024 Ops/s 307.9357 Ops/s $\color{#35bf28}+2.62\%$
test_cql_speed[True-backward] 5.9125ms 5.5294ms 180.8498 Ops/s 176.7431 Ops/s $\color{#35bf28}+2.32\%$
test_cql_speed[reduce-overhead-None] 21.0308ms 13.0100ms 76.8641 Ops/s 76.6218 Ops/s $\color{#35bf28}+0.32\%$
test_cql_speed[reduce-overhead-backward] 2.1479ms 1.9874ms 503.1706 Ops/s 546.2247 Ops/s $\textbf{\color{#d91a1a}-7.88\%}$
test_a2c_speed[False-None] 3.2924ms 3.1922ms 313.2646 Ops/s 308.1099 Ops/s $\color{#35bf28}+1.67\%$
test_a2c_speed[False-backward] 7.0146ms 6.3860ms 156.5929 Ops/s 160.7292 Ops/s $\color{#d91a1a}-2.57\%$
test_a2c_speed[True-None] 1.4045ms 1.3156ms 760.1212 Ops/s 756.9634 Ops/s $\color{#35bf28}+0.42\%$
test_a2c_speed[True-backward] 3.0739ms 2.9777ms 335.8243 Ops/s 334.6147 Ops/s $\color{#35bf28}+0.36\%$
test_a2c_speed[reduce-overhead-None] 15.9089ms 8.9345ms 111.9253 Ops/s 112.9765 Ops/s $\color{#d91a1a}-0.93\%$
test_a2c_speed[reduce-overhead-backward] 1.6973ms 1.5776ms 633.8666 Ops/s 691.9908 Ops/s $\textbf{\color{#d91a1a}-8.40\%}$
test_ppo_speed[False-None] 3.9634ms 3.7351ms 267.7324 Ops/s 265.7143 Ops/s $\color{#35bf28}+0.76\%$
test_ppo_speed[False-backward] 7.5000ms 7.0883ms 141.0774 Ops/s 143.7297 Ops/s $\color{#d91a1a}-1.85\%$
test_ppo_speed[True-None] 1.5268ms 1.3755ms 726.9834 Ops/s 715.9953 Ops/s $\color{#35bf28}+1.53\%$
test_ppo_speed[True-backward] 3.0595ms 2.9834ms 335.1870 Ops/s 324.2130 Ops/s $\color{#35bf28}+3.38\%$
test_ppo_speed[reduce-overhead-None] 1.0006ms 0.9296ms 1.0757 KOps/s 1.0718 KOps/s $\color{#35bf28}+0.36\%$
test_ppo_speed[reduce-overhead-backward] 1.5236ms 1.3779ms 725.7415 Ops/s 682.2130 Ops/s $\textbf{\color{#35bf28}+6.38\%}$
test_reinforce_speed[False-None] 2.4074ms 2.2804ms 438.5140 Ops/s 424.5619 Ops/s $\color{#35bf28}+3.29\%$
test_reinforce_speed[False-backward] 3.7277ms 3.2867ms 304.2543 Ops/s 293.3690 Ops/s $\color{#35bf28}+3.71\%$
test_reinforce_speed[True-None] 1.3459ms 1.2531ms 798.0222 Ops/s 780.0635 Ops/s $\color{#35bf28}+2.30\%$
test_reinforce_speed[True-backward] 2.9338ms 2.8504ms 350.8251 Ops/s 340.8096 Ops/s $\color{#35bf28}+2.94\%$
test_reinforce_speed[reduce-overhead-None] 18.5453ms 9.9166ms 100.8413 Ops/s 102.5067 Ops/s $\color{#d91a1a}-1.62\%$
test_reinforce_speed[reduce-overhead-backward] 1.5135ms 1.4535ms 688.0079 Ops/s 663.9607 Ops/s $\color{#35bf28}+3.62\%$
test_iql_speed[False-None] 9.6687ms 9.1469ms 109.3267 Ops/s 106.2501 Ops/s $\color{#35bf28}+2.90\%$
test_iql_speed[False-backward] 13.2937ms 12.8017ms 78.1148 Ops/s 76.1449 Ops/s $\color{#35bf28}+2.59\%$
test_iql_speed[True-None] 2.3695ms 2.1566ms 463.6834 Ops/s 441.2571 Ops/s $\textbf{\color{#35bf28}+5.08\%}$
test_iql_speed[True-backward] 5.0784ms 4.6498ms 215.0631 Ops/s 203.0461 Ops/s $\textbf{\color{#35bf28}+5.92\%}$
test_iql_speed[reduce-overhead-None] 18.9681ms 11.0122ms 90.8081 Ops/s 93.6044 Ops/s $\color{#d91a1a}-2.99\%$
test_iql_speed[reduce-overhead-backward] 2.0708ms 2.0256ms 493.6687 Ops/s 469.2414 Ops/s $\textbf{\color{#35bf28}+5.21\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.7731ms 6.0720ms 164.6908 Ops/s 162.1567 Ops/s $\color{#35bf28}+1.56\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5535ms 0.3099ms 3.2273 KOps/s 3.4685 KOps/s $\textbf{\color{#d91a1a}-6.95\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7052ms 0.2965ms 3.3726 KOps/s 3.6475 KOps/s $\textbf{\color{#d91a1a}-7.54\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1821ms 5.8108ms 172.0938 Ops/s 171.2620 Ops/s $\color{#35bf28}+0.49\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1397ms 0.3057ms 3.2716 KOps/s 2.9881 KOps/s $\textbf{\color{#35bf28}+9.49\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4856ms 0.2745ms 3.6431 KOps/s 4.2437 KOps/s $\textbf{\color{#d91a1a}-14.15\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6683ms 1.3952ms 716.7381 Ops/s 742.9367 Ops/s $\color{#d91a1a}-3.53\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5391ms 1.3355ms 748.7956 Ops/s 760.9194 Ops/s $\color{#d91a1a}-1.59\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2176ms 5.9972ms 166.7449 Ops/s 165.6546 Ops/s $\color{#35bf28}+0.66\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9984ms 0.4958ms 2.0169 KOps/s 2.4617 KOps/s $\textbf{\color{#d91a1a}-18.07\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6877ms 0.4233ms 2.3623 KOps/s 2.5074 KOps/s $\textbf{\color{#d91a1a}-5.79\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.9877ms 5.8385ms 171.2762 Ops/s 170.2720 Ops/s $\color{#35bf28}+0.59\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7405ms 0.4201ms 2.3806 KOps/s 3.7903 KOps/s $\textbf{\color{#d91a1a}-37.19\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6282ms 0.3843ms 2.6019 KOps/s 3.1669 KOps/s $\textbf{\color{#d91a1a}-17.84\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.0433ms 5.7338ms 174.4056 Ops/s 169.1653 Ops/s $\color{#35bf28}+3.10\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9344ms 0.2602ms 3.8438 KOps/s 3.1494 KOps/s $\textbf{\color{#35bf28}+22.05\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5066ms 0.2418ms 4.1348 KOps/s 3.1827 KOps/s $\textbf{\color{#35bf28}+29.92\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2372ms 5.9536ms 167.9657 Ops/s 164.0682 Ops/s $\color{#35bf28}+2.38\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.6653ms 0.3996ms 2.5027 KOps/s 2.1240 KOps/s $\textbf{\color{#35bf28}+17.83\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7762ms 0.3850ms 2.5974 KOps/s 2.2319 KOps/s $\textbf{\color{#35bf28}+16.38\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.9989ms 5.3536ms 186.7914 Ops/s 185.5847 Ops/s $\color{#35bf28}+0.65\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.2330ms 2.0245ms 493.9530 Ops/s 435.6570 Ops/s $\textbf{\color{#35bf28}+13.38\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.9315ms 1.2718ms 786.2908 Ops/s 853.4159 Ops/s $\textbf{\color{#d91a1a}-7.87\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 7.8657ms 5.5009ms 181.7897 Ops/s 186.1993 Ops/s $\color{#d91a1a}-2.37\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.6875ms 2.0266ms 493.4459 Ops/s 428.5041 Ops/s $\textbf{\color{#35bf28}+15.16\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.9073ms 1.2546ms 797.0822 Ops/s 865.0116 Ops/s $\textbf{\color{#d91a1a}-7.85\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4936s 15.6554ms 63.8756 Ops/s 32.0914 Ops/s $\textbf{\color{#35bf28}+99.04\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.8732ms 2.2169ms 451.0781 Ops/s 504.6938 Ops/s $\textbf{\color{#d91a1a}-10.62\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.1304ms 1.3625ms 733.9504 Ops/s 806.4077 Ops/s $\textbf{\color{#d91a1a}-8.99\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.1877ms 12.6938ms 78.7787 Ops/s 74.0724 Ops/s $\textbf{\color{#35bf28}+6.35\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.5442ms 16.7897ms 59.5603 Ops/s 58.0754 Ops/s $\color{#35bf28}+2.56\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.0371ms 17.5158ms 57.0915 Ops/s 54.7052 Ops/s $\color{#35bf28}+4.36\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 19.2933ms 17.1075ms 58.4540 Ops/s 58.8137 Ops/s $\color{#d91a1a}-0.61\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.8116ms 17.3183ms 57.7425 Ops/s 55.5171 Ops/s $\color{#35bf28}+4.01\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.4622ms 18.1287ms 55.1612 Ops/s 54.2456 Ops/s $\color{#35bf28}+1.69\%$

@vmoens
Copy link
Contributor

vmoens commented Feb 6, 2025

cc @mikaylagawarecki

Copy link
Contributor

@vmoens vmoens left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM thanks

@kurtamohler kurtamohler merged commit 945197b into gh/kurtamohler/4/base Feb 6, 2025
71 of 75 checks passed
kurtamohler added a commit that referenced this pull request Feb 6, 2025
ghstack-source-id: f6920d781835902a6db02f74c5e5a3041243c5e3
Pull Request resolved: #2766
@kurtamohler kurtamohler deleted the gh/kurtamohler/4/head branch February 6, 2025 17:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants