+
Skip to content

Conversation

vmoens
Copy link
Collaborator

@vmoens vmoens commented Feb 20, 2025

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Feb 20, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2799

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

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 20, 2025
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: 2b5669e
Pull Request resolved: #2799
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: 2b8412f
Pull Request resolved: #2799
@vmoens vmoens added Tests Incomplete or broken unit tests Environments Adds or modifies an environment wrapper labels Feb 20, 2025
Copy link

github-actions bot commented Feb 20, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}25$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.6304s 0.5216s 1.9171 Ops/s 1.9466 Ops/s $\color{#d91a1a}-1.51\%$
test_transformed 1.1154s 1.0157s 0.9845 Ops/s 0.9986 Ops/s $\color{#d91a1a}-1.41\%$
test_serial 1.5996s 1.5040s 0.6649 Ops/s 0.6691 Ops/s $\color{#d91a1a}-0.62\%$
test_parallel 1.4270s 1.3223s 0.7562 Ops/s 0.7452 Ops/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[True-True-True-True-True] 0.1475ms 30.0696μs 33.2562 KOps/s 33.2357 KOps/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[True-True-True-True-False] 0.6196ms 17.6669μs 56.6029 KOps/s 56.2340 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[True-True-True-False-True] 80.8850μs 17.0680μs 58.5893 KOps/s 54.0345 KOps/s $\textbf{\color{#35bf28}+8.43\%}$
test_step_mdp_speed[True-True-True-False-False] 50.2240μs 9.9556μs 100.4459 KOps/s 99.8440 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[True-True-False-True-True] 0.1367ms 32.0910μs 31.1614 KOps/s 30.9012 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[True-True-False-True-False] 73.0170μs 19.5714μs 51.0950 KOps/s 51.1536 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-True-False-False-True] 61.6960μs 18.9273μs 52.8337 KOps/s 52.7399 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[True-True-False-False-False] 58.1690μs 11.8054μs 84.7072 KOps/s 84.3939 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[True-False-True-True-True] 65.9840μs 34.1592μs 29.2747 KOps/s 29.4087 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[True-False-True-True-False] 74.5400μs 21.3680μs 46.7989 KOps/s 46.5576 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-False-True-False-True] 91.2410μs 18.5942μs 53.7802 KOps/s 52.9055 KOps/s $\color{#35bf28}+1.65\%$
test_step_mdp_speed[True-False-True-False-False] 73.4580μs 11.7394μs 85.1831 KOps/s 84.4469 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[True-False-False-True-True] 83.6870μs 35.5610μs 28.1207 KOps/s 27.9610 KOps/s $\color{#35bf28}+0.57\%$
test_step_mdp_speed[True-False-False-True-False] 67.3270μs 23.1489μs 43.1985 KOps/s 43.1795 KOps/s $\color{#35bf28}+0.04\%$
test_step_mdp_speed[True-False-False-False-True] 78.4470μs 20.5790μs 48.5933 KOps/s 48.6998 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-False-False-False-False] 64.9520μs 13.6000μs 73.5293 KOps/s 74.8052 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[False-True-True-True-True] 77.0640μs 34.4003μs 29.0695 KOps/s 29.2798 KOps/s $\color{#d91a1a}-0.72\%$
test_step_mdp_speed[False-True-True-True-False] 77.6460μs 21.4297μs 46.6642 KOps/s 46.4360 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[False-True-True-False-True] 62.7880μs 21.8123μs 45.8457 KOps/s 45.7423 KOps/s $\color{#35bf28}+0.23\%$
test_step_mdp_speed[False-True-True-False-False] 0.6048ms 13.1712μs 75.9232 KOps/s 75.0733 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[False-True-False-True-True] 95.8700μs 35.5493μs 28.1299 KOps/s 27.5656 KOps/s $\color{#35bf28}+2.05\%$
test_step_mdp_speed[False-True-False-True-False] 51.0860μs 23.1775μs 43.1453 KOps/s 42.4446 KOps/s $\color{#35bf28}+1.65\%$
test_step_mdp_speed[False-True-False-False-True] 2.6877ms 23.5670μs 42.4323 KOps/s 42.0762 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[False-True-False-False-False] 57.4680μs 15.1324μs 66.0834 KOps/s 66.7722 KOps/s $\color{#d91a1a}-1.03\%$
test_step_mdp_speed[False-False-True-True-True] 93.6960μs 37.4553μs 26.6985 KOps/s 26.2973 KOps/s $\color{#35bf28}+1.53\%$
test_step_mdp_speed[False-False-True-True-False] 74.6500μs 25.2757μs 39.5637 KOps/s 39.7592 KOps/s $\color{#d91a1a}-0.49\%$
test_step_mdp_speed[False-False-True-False-True] 76.2530μs 23.3290μs 42.8652 KOps/s 42.9628 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[False-False-True-False-False] 64.3400μs 14.9137μs 67.0523 KOps/s 66.1431 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[False-False-False-True-True] 84.3580μs 39.2712μs 25.4639 KOps/s 25.4152 KOps/s $\color{#35bf28}+0.19\%$
test_step_mdp_speed[False-False-False-True-False] 77.5860μs 26.8161μs 37.2911 KOps/s 37.5867 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[False-False-False-False-True] 84.3790μs 24.8423μs 40.2539 KOps/s 40.3970 KOps/s $\color{#d91a1a}-0.35\%$
test_step_mdp_speed[False-False-False-False-False] 74.4300μs 16.5762μs 60.3276 KOps/s 60.2672 KOps/s $\color{#35bf28}+0.10\%$
test_values[generalized_advantage_estimate-True-True] 10.4519ms 9.8287ms 101.7429 Ops/s 104.4619 Ops/s $\color{#d91a1a}-2.60\%$
test_values[vec_generalized_advantage_estimate-True-True] 29.0102ms 24.6325ms 40.5967 Ops/s 38.1079 Ops/s $\textbf{\color{#35bf28}+6.53\%}$
test_values[td0_return_estimate-False-False] 0.2497ms 0.1842ms 5.4279 KOps/s 4.9612 KOps/s $\textbf{\color{#35bf28}+9.41\%}$
test_values[td1_return_estimate-False-False] 27.4072ms 24.0510ms 41.5783 Ops/s 41.8189 Ops/s $\color{#d91a1a}-0.58\%$
test_values[vec_td1_return_estimate-False-False] 26.2542ms 24.5729ms 40.6953 Ops/s 37.5330 Ops/s $\textbf{\color{#35bf28}+8.43\%}$
test_values[td_lambda_return_estimate-True-False] 35.4149ms 34.3297ms 29.1293 Ops/s 29.0910 Ops/s $\color{#35bf28}+0.13\%$
test_values[vec_td_lambda_return_estimate-True-False] 26.2393ms 24.4351ms 40.9248 Ops/s 37.3523 Ops/s $\textbf{\color{#35bf28}+9.56\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.6122ms 8.3748ms 119.4059 Ops/s 119.1189 Ops/s $\color{#35bf28}+0.24\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4349ms 1.9386ms 515.8241 Ops/s 535.8221 Ops/s $\color{#d91a1a}-3.73\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4634ms 0.3624ms 2.7594 KOps/s 2.7589 KOps/s $\color{#35bf28}+0.02\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 46.2185ms 42.7387ms 23.3980 Ops/s 23.6071 Ops/s $\color{#d91a1a}-0.89\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.2024ms 3.4555ms 289.3944 Ops/s 289.8777 Ops/s $\color{#d91a1a}-0.17\%$
test_dqn_speed[False-None] 6.3281ms 1.4229ms 702.8128 Ops/s 713.8071 Ops/s $\color{#d91a1a}-1.54\%$
test_dqn_speed[False-backward] 1.9318ms 1.8914ms 528.7070 Ops/s 512.0186 Ops/s $\color{#35bf28}+3.26\%$
test_dqn_speed[True-None] 0.7597ms 0.4898ms 2.0418 KOps/s 1.9694 KOps/s $\color{#35bf28}+3.67\%$
test_dqn_speed[True-backward] 0.9743ms 0.9120ms 1.0965 KOps/s 789.6246 Ops/s $\textbf{\color{#35bf28}+38.86\%}$
test_dqn_speed[reduce-overhead-None] 0.7653ms 0.4949ms 2.0206 KOps/s 1.9776 KOps/s $\color{#35bf28}+2.18\%$
test_dqn_speed[reduce-overhead-backward] 0.9689ms 0.8994ms 1.1118 KOps/s 1.0911 KOps/s $\color{#35bf28}+1.90\%$
test_ddpg_speed[False-None] 3.8084ms 2.8983ms 345.0344 Ops/s 344.3223 Ops/s $\color{#35bf28}+0.21\%$
test_ddpg_speed[False-backward] 4.6862ms 4.1365ms 241.7479 Ops/s 244.4349 Ops/s $\color{#d91a1a}-1.10\%$
test_ddpg_speed[True-None] 1.6967ms 1.2368ms 808.5245 Ops/s 796.5517 Ops/s $\color{#35bf28}+1.50\%$
test_ddpg_speed[True-backward] 2.2607ms 2.1658ms 461.7146 Ops/s 466.0248 Ops/s $\color{#d91a1a}-0.92\%$
test_ddpg_speed[reduce-overhead-None] 1.5713ms 1.2386ms 807.3374 Ops/s 788.9002 Ops/s $\color{#35bf28}+2.34\%$
test_ddpg_speed[reduce-overhead-backward] 2.1998ms 2.1434ms 466.5476 Ops/s 462.0632 Ops/s $\color{#35bf28}+0.97\%$
test_sac_speed[False-None] 10.3362ms 8.1833ms 122.1998 Ops/s 118.1623 Ops/s $\color{#35bf28}+3.42\%$
test_sac_speed[False-backward] 14.4202ms 10.8603ms 92.0787 Ops/s 85.9914 Ops/s $\textbf{\color{#35bf28}+7.08\%}$
test_sac_speed[True-None] 2.7350ms 2.1684ms 461.1601 Ops/s 412.7070 Ops/s $\textbf{\color{#35bf28}+11.74\%}$
test_sac_speed[True-backward] 4.3819ms 3.8627ms 258.8849 Ops/s 244.2939 Ops/s $\textbf{\color{#35bf28}+5.97\%}$
test_sac_speed[reduce-overhead-None] 2.8623ms 2.1355ms 468.2687 Ops/s 448.9159 Ops/s $\color{#35bf28}+4.31\%$
test_sac_speed[reduce-overhead-backward] 4.0260ms 3.8876ms 257.2269 Ops/s 251.6278 Ops/s $\color{#35bf28}+2.23\%$
test_redq_speed[False-None] 15.0337ms 13.2638ms 75.3930 Ops/s 73.9907 Ops/s $\color{#35bf28}+1.90\%$
test_redq_speed[False-backward] 24.6467ms 22.2711ms 44.9012 Ops/s 43.0565 Ops/s $\color{#35bf28}+4.28\%$
test_redq_speed[True-None] 8.2216ms 5.2360ms 190.9847 Ops/s 175.9853 Ops/s $\textbf{\color{#35bf28}+8.52\%}$
test_redq_speed[True-backward] 13.4383ms 12.7410ms 78.4867 Ops/s 75.4642 Ops/s $\color{#35bf28}+4.01\%$
test_redq_speed[reduce-overhead-None] 6.9863ms 5.2037ms 192.1702 Ops/s 170.5387 Ops/s $\textbf{\color{#35bf28}+12.68\%}$
test_redq_speed[reduce-overhead-backward] 14.1639ms 12.9968ms 76.9420 Ops/s 75.3892 Ops/s $\color{#35bf28}+2.06\%$
test_redq_deprec_speed[False-None] 15.7153ms 13.6294ms 73.3709 Ops/s 74.6023 Ops/s $\color{#d91a1a}-1.65\%$
test_redq_deprec_speed[False-backward] 21.6862ms 19.5251ms 51.2161 Ops/s 51.2753 Ops/s $\color{#d91a1a}-0.12\%$
test_redq_deprec_speed[True-None] 4.7655ms 3.9027ms 256.2304 Ops/s 233.9279 Ops/s $\textbf{\color{#35bf28}+9.53\%}$
test_redq_deprec_speed[True-backward] 10.6003ms 8.8644ms 112.8114 Ops/s 103.3159 Ops/s $\textbf{\color{#35bf28}+9.19\%}$
test_redq_deprec_speed[reduce-overhead-None] 5.4811ms 4.1487ms 241.0396 Ops/s 246.9984 Ops/s $\color{#d91a1a}-2.41\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.3495ms 8.7496ms 114.2904 Ops/s 109.5015 Ops/s $\color{#35bf28}+4.37\%$
test_td3_speed[False-None] 9.0255ms 8.1396ms 122.8558 Ops/s 119.6304 Ops/s $\color{#35bf28}+2.70\%$
test_td3_speed[False-backward] 12.8759ms 10.7644ms 92.8984 Ops/s 91.3842 Ops/s $\color{#35bf28}+1.66\%$
test_td3_speed[True-None] 2.3181ms 1.8444ms 542.1904 Ops/s 510.3552 Ops/s $\textbf{\color{#35bf28}+6.24\%}$
test_td3_speed[True-backward] 3.6583ms 3.5393ms 282.5388 Ops/s 241.2298 Ops/s $\textbf{\color{#35bf28}+17.12\%}$
test_td3_speed[reduce-overhead-None] 1.9626ms 1.8061ms 553.6773 Ops/s 523.4761 Ops/s $\textbf{\color{#35bf28}+5.77\%}$
test_td3_speed[reduce-overhead-backward] 3.4525ms 3.3727ms 296.4972 Ops/s 282.8166 Ops/s $\color{#35bf28}+4.84\%$
test_cql_speed[False-None] 39.7362ms 36.6963ms 27.2507 Ops/s 26.6940 Ops/s $\color{#35bf28}+2.09\%$
test_cql_speed[False-backward] 54.1792ms 47.1805ms 21.1952 Ops/s 20.8750 Ops/s $\color{#35bf28}+1.53\%$
test_cql_speed[True-None] 17.0966ms 16.2403ms 61.5754 Ops/s 58.9829 Ops/s $\color{#35bf28}+4.40\%$
test_cql_speed[True-backward] 25.0677ms 23.1249ms 43.2434 Ops/s 41.6781 Ops/s $\color{#35bf28}+3.76\%$
test_cql_speed[reduce-overhead-None] 17.6803ms 16.4881ms 60.6498 Ops/s 58.4999 Ops/s $\color{#35bf28}+3.67\%$
test_cql_speed[reduce-overhead-backward] 24.6069ms 23.4664ms 42.6141 Ops/s 42.2995 Ops/s $\color{#35bf28}+0.74\%$
test_a2c_speed[False-None] 8.9526ms 7.4557ms 134.1261 Ops/s 133.4439 Ops/s $\color{#35bf28}+0.51\%$
test_a2c_speed[False-backward] 16.5297ms 15.1118ms 66.1733 Ops/s 65.6892 Ops/s $\color{#35bf28}+0.74\%$
test_a2c_speed[True-None] 4.8123ms 3.8128ms 262.2724 Ops/s 260.0568 Ops/s $\color{#35bf28}+0.85\%$
test_a2c_speed[True-backward] 11.0808ms 10.3679ms 96.4512 Ops/s 92.1971 Ops/s $\color{#35bf28}+4.61\%$
test_a2c_speed[reduce-overhead-None] 5.3387ms 3.7982ms 263.2853 Ops/s 260.1681 Ops/s $\color{#35bf28}+1.20\%$
test_a2c_speed[reduce-overhead-backward] 11.3146ms 10.1944ms 98.0927 Ops/s 90.2045 Ops/s $\textbf{\color{#35bf28}+8.74\%}$
test_ppo_speed[False-None] 8.8585ms 7.6475ms 130.7616 Ops/s 125.0507 Ops/s $\color{#35bf28}+4.57\%$
test_ppo_speed[False-backward] 17.0527ms 15.4375ms 64.7773 Ops/s 63.4335 Ops/s $\color{#35bf28}+2.12\%$
test_ppo_speed[True-None] 4.7620ms 4.1237ms 242.4982 Ops/s 233.5102 Ops/s $\color{#35bf28}+3.85\%$
test_ppo_speed[True-backward] 10.5451ms 10.0424ms 99.5775 Ops/s 94.1600 Ops/s $\textbf{\color{#35bf28}+5.75\%}$
test_ppo_speed[reduce-overhead-None] 5.0731ms 4.1707ms 239.7661 Ops/s 230.9663 Ops/s $\color{#35bf28}+3.81\%$
test_ppo_speed[reduce-overhead-backward] 11.3670ms 10.2886ms 97.1953 Ops/s 93.8896 Ops/s $\color{#35bf28}+3.52\%$
test_reinforce_speed[False-None] 7.4628ms 6.6529ms 150.3101 Ops/s 147.4496 Ops/s $\color{#35bf28}+1.94\%$
test_reinforce_speed[False-backward] 10.1545ms 9.9397ms 100.6070 Ops/s 97.1558 Ops/s $\color{#35bf28}+3.55\%$
test_reinforce_speed[True-None] 3.5178ms 3.0986ms 322.7280 Ops/s 313.0064 Ops/s $\color{#35bf28}+3.11\%$
test_reinforce_speed[True-backward] 10.6761ms 9.1743ms 109.0001 Ops/s 104.1445 Ops/s $\color{#35bf28}+4.66\%$
test_reinforce_speed[reduce-overhead-None] 4.1635ms 3.1169ms 320.8362 Ops/s 314.3672 Ops/s $\color{#35bf28}+2.06\%$
test_reinforce_speed[reduce-overhead-backward] 10.2244ms 9.0672ms 110.2872 Ops/s 104.9281 Ops/s $\textbf{\color{#35bf28}+5.11\%}$
test_iql_speed[False-None] 33.7659ms 32.1732ms 31.0817 Ops/s 30.4498 Ops/s $\color{#35bf28}+2.08\%$
test_iql_speed[False-backward] 50.0428ms 45.7248ms 21.8700 Ops/s 21.6205 Ops/s $\color{#35bf28}+1.15\%$
test_iql_speed[True-None] 13.3021ms 11.5520ms 86.5652 Ops/s 82.8558 Ops/s $\color{#35bf28}+4.48\%$
test_iql_speed[True-backward] 24.1143ms 22.7491ms 43.9578 Ops/s 43.2840 Ops/s $\color{#35bf28}+1.56\%$
test_iql_speed[reduce-overhead-None] 12.8489ms 11.6726ms 85.6710 Ops/s 84.1220 Ops/s $\color{#35bf28}+1.84\%$
test_iql_speed[reduce-overhead-backward] 24.4892ms 22.9260ms 43.6186 Ops/s 42.3235 Ops/s $\color{#35bf28}+3.06\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.1141ms 4.9884ms 200.4645 Ops/s 196.8198 Ops/s $\color{#35bf28}+1.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8473ms 0.5424ms 1.8437 KOps/s 1.8181 KOps/s $\color{#35bf28}+1.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7785ms 0.5116ms 1.9545 KOps/s 1.9014 KOps/s $\color{#35bf28}+2.79\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.9850ms 4.8419ms 206.5288 Ops/s 204.4810 Ops/s $\color{#35bf28}+1.00\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 3.6595ms 0.5333ms 1.8751 KOps/s 1.8382 KOps/s $\color{#35bf28}+2.01\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8089ms 0.5103ms 1.9596 KOps/s 1.9751 KOps/s $\color{#d91a1a}-0.79\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.9065ms 1.7022ms 587.4708 Ops/s 576.2786 Ops/s $\color{#35bf28}+1.94\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.8308ms 1.5957ms 626.6921 Ops/s 609.7839 Ops/s $\color{#35bf28}+2.77\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.5164ms 4.9823ms 200.7093 Ops/s 193.9858 Ops/s $\color{#35bf28}+3.47\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.3192ms 0.6850ms 1.4598 KOps/s 1.4320 KOps/s $\color{#35bf28}+1.94\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0706ms 0.6573ms 1.5213 KOps/s 1.5108 KOps/s $\color{#35bf28}+0.69\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.3568ms 4.8670ms 205.4672 Ops/s 200.5548 Ops/s $\color{#35bf28}+2.45\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9486ms 0.5380ms 1.8588 KOps/s 1.8379 KOps/s $\color{#35bf28}+1.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8673ms 0.5222ms 1.9151 KOps/s 1.8957 KOps/s $\color{#35bf28}+1.03\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.9851ms 4.8375ms 206.7190 Ops/s 199.8544 Ops/s $\color{#35bf28}+3.43\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.3495ms 0.5278ms 1.8946 KOps/s 1.8812 KOps/s $\color{#35bf28}+0.71\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8572ms 0.5138ms 1.9463 KOps/s 1.9305 KOps/s $\color{#35bf28}+0.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.6684ms 4.9440ms 202.2650 Ops/s 199.3307 Ops/s $\color{#35bf28}+1.47\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.5365ms 0.6790ms 1.4727 KOps/s 1.4242 KOps/s $\color{#35bf28}+3.40\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9831ms 0.6460ms 1.5480 KOps/s 1.5496 KOps/s $\color{#d91a1a}-0.10\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.5527ms 4.2324ms 236.2733 Ops/s 218.3589 Ops/s $\textbf{\color{#35bf28}+8.20\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.2446ms 2.2385ms 446.7323 Ops/s 402.2482 Ops/s $\textbf{\color{#35bf28}+11.06\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.5228ms 1.3877ms 720.6030 Ops/s 697.4994 Ops/s $\color{#35bf28}+3.31\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4451s 13.1169ms 76.2377 Ops/s 239.6435 Ops/s $\textbf{\color{#d91a1a}-68.19\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.2021ms 2.3630ms 423.1834 Ops/s 435.0761 Ops/s $\color{#d91a1a}-2.73\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.2987ms 1.4154ms 706.5113 Ops/s 699.8734 Ops/s $\color{#35bf28}+0.95\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.1815ms 4.6654ms 214.3455 Ops/s 227.1511 Ops/s $\textbf{\color{#d91a1a}-5.64\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 6.8511ms 2.4736ms 404.2760 Ops/s 383.3785 Ops/s $\textbf{\color{#35bf28}+5.45\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.6764ms 1.4785ms 676.3525 Ops/s 574.1885 Ops/s $\textbf{\color{#35bf28}+17.79\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.9990ms 11.5171ms 86.8271 Ops/s 81.6607 Ops/s $\textbf{\color{#35bf28}+6.33\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.4290ms 14.3302ms 69.7828 Ops/s 67.7426 Ops/s $\color{#35bf28}+3.01\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 22.2536ms 20.3541ms 49.1302 Ops/s 46.6028 Ops/s $\textbf{\color{#35bf28}+5.42\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.0291ms 14.6519ms 68.2506 Ops/s 65.4711 Ops/s $\color{#35bf28}+4.25\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.2552ms 20.4383ms 48.9278 Ops/s 46.7978 Ops/s $\color{#35bf28}+4.55\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 17.7892ms 16.1755ms 61.8218 Ops/s 60.1884 Ops/s $\color{#35bf28}+2.71\%$

Copy link

github-actions bot commented Feb 20, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}11$. Worsened: $\large\color{#d91a1a}18$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.9377s 0.8470s 1.1806 Ops/s 1.2352 Ops/s $\color{#d91a1a}-4.42\%$
test_transformed 1.5480s 1.4673s 0.6815 Ops/s 0.6865 Ops/s $\color{#d91a1a}-0.72\%$
test_serial 2.4338s 2.3847s 0.4193 Ops/s 0.4248 Ops/s $\color{#d91a1a}-1.29\%$
test_parallel 1.9873s 1.9082s 0.5241 Ops/s 0.5296 Ops/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[True-True-True-True-True] 0.1821ms 39.6351μs 25.2301 KOps/s 23.8181 KOps/s $\textbf{\color{#35bf28}+5.93\%}$
test_step_mdp_speed[True-True-True-True-False] 54.6600μs 23.2720μs 42.9701 KOps/s 40.8469 KOps/s $\textbf{\color{#35bf28}+5.20\%}$
test_step_mdp_speed[True-True-True-False-True] 71.6210μs 22.3232μs 44.7965 KOps/s 43.7897 KOps/s $\color{#35bf28}+2.30\%$
test_step_mdp_speed[True-True-True-False-False] 39.8810μs 13.0021μs 76.9105 KOps/s 77.3340 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[True-True-False-True-True] 81.6510μs 41.4016μs 24.1537 KOps/s 23.4482 KOps/s $\color{#35bf28}+3.01\%$
test_step_mdp_speed[True-True-False-True-False] 60.4910μs 25.4152μs 39.3466 KOps/s 38.6941 KOps/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-True-False-False-True] 62.5010μs 24.4359μs 40.9234 KOps/s 40.4059 KOps/s $\color{#35bf28}+1.28\%$
test_step_mdp_speed[True-True-False-False-False] 48.0810μs 15.2466μs 65.5884 KOps/s 65.0333 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-False-True-True-True] 78.0610μs 44.4577μs 22.4933 KOps/s 22.2851 KOps/s $\color{#35bf28}+0.93\%$
test_step_mdp_speed[True-False-True-True-False] 77.7510μs 27.5210μs 36.3359 KOps/s 35.5862 KOps/s $\color{#35bf28}+2.11\%$
test_step_mdp_speed[True-False-True-False-True] 62.1800μs 24.9058μs 40.1513 KOps/s 40.3406 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[True-False-True-False-False] 57.4210μs 15.4336μs 64.7937 KOps/s 64.4614 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-False-False-True-True] 93.2210μs 46.9705μs 21.2900 KOps/s 20.6070 KOps/s $\color{#35bf28}+3.31\%$
test_step_mdp_speed[True-False-False-True-False] 65.1810μs 30.2703μs 33.0357 KOps/s 31.9883 KOps/s $\color{#35bf28}+3.27\%$
test_step_mdp_speed[True-False-False-False-True] 54.6310μs 26.9833μs 37.0599 KOps/s 35.7885 KOps/s $\color{#35bf28}+3.55\%$
test_step_mdp_speed[True-False-False-False-False] 52.1410μs 17.3712μs 57.5667 KOps/s 55.1513 KOps/s $\color{#35bf28}+4.38\%$
test_step_mdp_speed[False-True-True-True-True] 78.0810μs 45.2481μs 22.1004 KOps/s 22.2611 KOps/s $\color{#d91a1a}-0.72\%$
test_step_mdp_speed[False-True-True-True-False] 69.1610μs 28.3505μs 35.2728 KOps/s 34.9637 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[False-True-True-False-True] 82.1210μs 28.5832μs 34.9856 KOps/s 34.9170 KOps/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[False-True-True-False-False] 47.4310μs 17.1194μs 58.4132 KOps/s 56.3611 KOps/s $\color{#35bf28}+3.64\%$
test_step_mdp_speed[False-True-False-True-True] 82.0110μs 47.1393μs 21.2137 KOps/s 21.4418 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-True-False-True-False] 62.6010μs 30.2767μs 33.0287 KOps/s 32.5208 KOps/s $\color{#35bf28}+1.56\%$
test_step_mdp_speed[False-True-False-False-True] 3.1564ms 31.4290μs 31.8178 KOps/s 30.4741 KOps/s $\color{#35bf28}+4.41\%$
test_step_mdp_speed[False-True-False-False-False] 53.7000μs 19.4171μs 51.5010 KOps/s 48.9038 KOps/s $\textbf{\color{#35bf28}+5.31\%}$
test_step_mdp_speed[False-False-True-True-True] 84.9010μs 49.8766μs 20.0495 KOps/s 19.4828 KOps/s $\color{#35bf28}+2.91\%$
test_step_mdp_speed[False-False-True-True-False] 60.3210μs 32.6091μs 30.6663 KOps/s 29.6846 KOps/s $\color{#35bf28}+3.31\%$
test_step_mdp_speed[False-False-True-False-True] 70.3010μs 31.0346μs 32.2221 KOps/s 33.2528 KOps/s $\color{#d91a1a}-3.10\%$
test_step_mdp_speed[False-False-True-False-False] 48.9300μs 19.2720μs 51.8889 KOps/s 52.1529 KOps/s $\color{#d91a1a}-0.51\%$
test_step_mdp_speed[False-False-False-True-True] 96.6410μs 51.6025μs 19.3789 KOps/s 19.4670 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-False-False-True-False] 86.3710μs 35.0717μs 28.5130 KOps/s 28.7904 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[False-False-False-False-True] 66.8510μs 32.4852μs 30.7832 KOps/s 30.7580 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[False-False-False-False-False] 51.1700μs 21.4208μs 46.6835 KOps/s 45.8624 KOps/s $\color{#35bf28}+1.79\%$
test_values[generalized_advantage_estimate-True-True] 25.5247ms 25.0310ms 39.9504 Ops/s 40.4157 Ops/s $\color{#d91a1a}-1.15\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1061s 3.0225ms 330.8525 Ops/s 313.3181 Ops/s $\textbf{\color{#35bf28}+5.60\%}$
test_values[td0_return_estimate-False-False] 0.1078ms 80.0050μs 12.4992 KOps/s 12.3710 KOps/s $\color{#35bf28}+1.04\%$
test_values[td1_return_estimate-False-False] 56.3690ms 56.0029ms 17.8562 Ops/s 18.1018 Ops/s $\color{#d91a1a}-1.36\%$
test_values[vec_td1_return_estimate-False-False] 1.3998ms 1.0904ms 917.0944 Ops/s 922.8130 Ops/s $\color{#d91a1a}-0.62\%$
test_values[td_lambda_return_estimate-True-False] 95.6750ms 93.5213ms 10.6927 Ops/s 11.3992 Ops/s $\textbf{\color{#d91a1a}-6.20\%}$
test_values[vec_td_lambda_return_estimate-True-False] 1.3152ms 1.0868ms 920.1551 Ops/s 925.8812 Ops/s $\color{#d91a1a}-0.62\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 26.9954ms 26.5562ms 37.6560 Ops/s 40.3026 Ops/s $\textbf{\color{#d91a1a}-6.57\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0296ms 0.7570ms 1.3210 KOps/s 1.3219 KOps/s $\color{#d91a1a}-0.07\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8787ms 0.6959ms 1.4370 KOps/s 1.4919 KOps/s $\color{#d91a1a}-3.68\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5819ms 1.5089ms 662.7430 Ops/s 671.6891 Ops/s $\color{#d91a1a}-1.33\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.8472ms 0.7125ms 1.4035 KOps/s 1.4576 KOps/s $\color{#d91a1a}-3.71\%$
test_dqn_speed[False-None] 6.9982ms 1.5577ms 641.9733 Ops/s 642.3632 Ops/s $\color{#d91a1a}-0.06\%$
test_dqn_speed[False-backward] 2.2862ms 2.1774ms 459.2610 Ops/s 461.1444 Ops/s $\color{#d91a1a}-0.41\%$
test_dqn_speed[True-None] 0.7637ms 0.5914ms 1.6910 KOps/s 1.6532 KOps/s $\color{#35bf28}+2.28\%$
test_dqn_speed[True-backward] 1.3054ms 1.2509ms 799.4424 Ops/s 787.9494 Ops/s $\color{#35bf28}+1.46\%$
test_dqn_speed[reduce-overhead-None] 1.0319ms 0.6120ms 1.6340 KOps/s 1.6744 KOps/s $\color{#d91a1a}-2.42\%$
test_dqn_speed[reduce-overhead-backward] 1.2125ms 1.1299ms 885.0320 Ops/s 909.2583 Ops/s $\color{#d91a1a}-2.66\%$
test_ddpg_speed[False-None] 3.2938ms 2.9429ms 339.8023 Ops/s 339.6758 Ops/s $\color{#35bf28}+0.04\%$
test_ddpg_speed[False-backward] 4.7688ms 4.3830ms 228.1563 Ops/s 232.3434 Ops/s $\color{#d91a1a}-1.80\%$
test_ddpg_speed[True-None] 1.8053ms 1.3833ms 722.9173 Ops/s 718.6451 Ops/s $\color{#35bf28}+0.59\%$
test_ddpg_speed[True-backward] 3.0409ms 2.6426ms 378.4206 Ops/s 397.4491 Ops/s $\color{#d91a1a}-4.79\%$
test_ddpg_speed[reduce-overhead-None] 1.7966ms 1.3923ms 718.2437 Ops/s 711.1817 Ops/s $\color{#35bf28}+0.99\%$
test_ddpg_speed[reduce-overhead-backward] 2.1600ms 2.0913ms 478.1753 Ops/s 505.3717 Ops/s $\textbf{\color{#d91a1a}-5.38\%}$
test_sac_speed[False-None] 8.9235ms 8.3010ms 120.4681 Ops/s 121.7325 Ops/s $\color{#d91a1a}-1.04\%$
test_sac_speed[False-backward] 12.4012ms 11.3681ms 87.9655 Ops/s 89.9389 Ops/s $\color{#d91a1a}-2.19\%$
test_sac_speed[True-None] 2.0924ms 1.9527ms 512.1206 Ops/s 519.3546 Ops/s $\color{#d91a1a}-1.39\%$
test_sac_speed[True-backward] 4.3572ms 3.8333ms 260.8704 Ops/s 258.8099 Ops/s $\color{#35bf28}+0.80\%$
test_sac_speed[reduce-overhead-None] 21.1663ms 11.8468ms 84.4113 Ops/s 83.7801 Ops/s $\color{#35bf28}+0.75\%$
test_sac_speed[reduce-overhead-backward] 1.9254ms 1.8590ms 537.9375 Ops/s 534.9034 Ops/s $\color{#35bf28}+0.57\%$
test_redq_speed[False-None] 8.0179ms 7.5290ms 132.8203 Ops/s 129.6658 Ops/s $\color{#35bf28}+2.43\%$
test_redq_speed[False-backward] 12.3059ms 11.7615ms 85.0229 Ops/s 83.8967 Ops/s $\color{#35bf28}+1.34\%$
test_redq_speed[True-None] 2.5817ms 2.3850ms 419.2881 Ops/s 417.7325 Ops/s $\color{#35bf28}+0.37\%$
test_redq_speed[True-backward] 4.6017ms 4.3156ms 231.7194 Ops/s 230.4528 Ops/s $\color{#35bf28}+0.55\%$
test_redq_speed[reduce-overhead-None] 2.7575ms 2.4196ms 413.2995 Ops/s 404.2733 Ops/s $\color{#35bf28}+2.23\%$
test_redq_speed[reduce-overhead-backward] 4.4248ms 4.3146ms 231.7726 Ops/s 240.0891 Ops/s $\color{#d91a1a}-3.46\%$
test_redq_deprec_speed[False-None] 9.6071ms 9.1483ms 109.3096 Ops/s 109.2201 Ops/s $\color{#35bf28}+0.08\%$
test_redq_deprec_speed[False-backward] 12.9481ms 12.4235ms 80.4924 Ops/s 80.9696 Ops/s $\color{#d91a1a}-0.59\%$
test_redq_deprec_speed[True-None] 2.8339ms 2.7297ms 366.3349 Ops/s 365.7181 Ops/s $\color{#35bf28}+0.17\%$
test_redq_deprec_speed[True-backward] 5.1689ms 4.6916ms 213.1467 Ops/s 218.8794 Ops/s $\color{#d91a1a}-2.62\%$
test_redq_deprec_speed[reduce-overhead-None] 2.7803ms 2.7108ms 368.8946 Ops/s 367.1197 Ops/s $\color{#35bf28}+0.48\%$
test_redq_deprec_speed[reduce-overhead-backward] 5.0059ms 4.5905ms 217.8414 Ops/s 224.9221 Ops/s $\color{#d91a1a}-3.15\%$
test_td3_speed[False-None] 8.1272ms 8.0535ms 124.1691 Ops/s 124.0919 Ops/s $\color{#35bf28}+0.06\%$
test_td3_speed[False-backward] 11.5183ms 10.6486ms 93.9094 Ops/s 96.5986 Ops/s $\color{#d91a1a}-2.78\%$
test_td3_speed[True-None] 1.7998ms 1.7381ms 575.3507 Ops/s 574.0750 Ops/s $\color{#35bf28}+0.22\%$
test_td3_speed[True-backward] 3.8090ms 3.4745ms 287.8083 Ops/s 300.9596 Ops/s $\color{#d91a1a}-4.37\%$
test_td3_speed[reduce-overhead-None] 51.6110ms 26.3949ms 37.8862 Ops/s 37.8875 Ops/s $-0.00\%$
test_td3_speed[reduce-overhead-backward] 1.5978ms 1.5441ms 647.6439 Ops/s 689.1594 Ops/s $\textbf{\color{#d91a1a}-6.02\%}$
test_cql_speed[False-None] 17.5043ms 16.9865ms 58.8703 Ops/s 58.8054 Ops/s $\color{#35bf28}+0.11\%$
test_cql_speed[False-backward] 22.9295ms 22.4461ms 44.5511 Ops/s 44.9190 Ops/s $\color{#d91a1a}-0.82\%$
test_cql_speed[True-None] 3.4633ms 3.3656ms 297.1274 Ops/s 293.0952 Ops/s $\color{#35bf28}+1.38\%$
test_cql_speed[True-backward] 6.3552ms 5.8422ms 171.1686 Ops/s 171.1211 Ops/s $\color{#35bf28}+0.03\%$
test_cql_speed[reduce-overhead-None] 21.2860ms 13.1439ms 76.0809 Ops/s 75.1690 Ops/s $\color{#35bf28}+1.21\%$
test_cql_speed[reduce-overhead-backward] 2.2377ms 2.0581ms 485.8868 Ops/s 523.2230 Ops/s $\textbf{\color{#d91a1a}-7.14\%}$
test_a2c_speed[False-None] 3.3175ms 3.2237ms 310.1991 Ops/s 307.4703 Ops/s $\color{#35bf28}+0.89\%$
test_a2c_speed[False-backward] 6.9463ms 6.3812ms 156.7113 Ops/s 161.4950 Ops/s $\color{#d91a1a}-2.96\%$
test_a2c_speed[True-None] 1.5349ms 1.3949ms 716.9193 Ops/s 712.5063 Ops/s $\color{#35bf28}+0.62\%$
test_a2c_speed[True-backward] 3.1580ms 3.1125ms 321.2827 Ops/s 315.5400 Ops/s $\color{#35bf28}+1.82\%$
test_a2c_speed[reduce-overhead-None] 15.6837ms 8.8380ms 113.1483 Ops/s 113.1242 Ops/s $\color{#35bf28}+0.02\%$
test_a2c_speed[reduce-overhead-backward] 1.7645ms 1.6384ms 610.3486 Ops/s 600.9072 Ops/s $\color{#35bf28}+1.57\%$
test_ppo_speed[False-None] 3.8344ms 3.7435ms 267.1328 Ops/s 265.3228 Ops/s $\color{#35bf28}+0.68\%$
test_ppo_speed[False-backward] 7.5412ms 7.0885ms 141.0730 Ops/s 139.5780 Ops/s $\color{#35bf28}+1.07\%$
test_ppo_speed[True-None] 1.5532ms 1.4524ms 688.5311 Ops/s 681.6798 Ops/s $\color{#35bf28}+1.01\%$
test_ppo_speed[True-backward] 3.3320ms 3.2708ms 305.7395 Ops/s 298.6222 Ops/s $\color{#35bf28}+2.38\%$
test_ppo_speed[reduce-overhead-None] 1.0695ms 0.9951ms 1.0049 KOps/s 989.2366 Ops/s $\color{#35bf28}+1.58\%$
test_ppo_speed[reduce-overhead-backward] 1.6284ms 1.5948ms 627.0308 Ops/s 604.5981 Ops/s $\color{#35bf28}+3.71\%$
test_reinforce_speed[False-None] 2.4540ms 2.3136ms 432.2280 Ops/s 427.1992 Ops/s $\color{#35bf28}+1.18\%$
test_reinforce_speed[False-backward] 3.8455ms 3.4422ms 290.5104 Ops/s 286.5616 Ops/s $\color{#35bf28}+1.38\%$
test_reinforce_speed[True-None] 1.4303ms 1.3411ms 745.6366 Ops/s 729.2887 Ops/s $\color{#35bf28}+2.24\%$
test_reinforce_speed[True-backward] 3.1979ms 3.1300ms 319.4903 Ops/s 334.4953 Ops/s $\color{#d91a1a}-4.49\%$
test_reinforce_speed[reduce-overhead-None] 17.8992ms 9.9966ms 100.0338 Ops/s 101.4859 Ops/s $\color{#d91a1a}-1.43\%$
test_reinforce_speed[reduce-overhead-backward] 1.7817ms 1.6712ms 598.3677 Ops/s 633.5362 Ops/s $\textbf{\color{#d91a1a}-5.55\%}$
test_iql_speed[False-None] 9.7549ms 9.2961ms 107.5715 Ops/s 105.1689 Ops/s $\color{#35bf28}+2.28\%$
test_iql_speed[False-backward] 13.8000ms 13.1956ms 75.7827 Ops/s 75.7354 Ops/s $\color{#35bf28}+0.06\%$
test_iql_speed[True-None] 2.3849ms 2.3061ms 433.6372 Ops/s 423.6978 Ops/s $\color{#35bf28}+2.35\%$
test_iql_speed[True-backward] 5.2983ms 5.0222ms 199.1140 Ops/s 195.1351 Ops/s $\color{#35bf28}+2.04\%$
test_iql_speed[reduce-overhead-None] 0.4783s 12.5940ms 79.4031 Ops/s 90.6956 Ops/s $\textbf{\color{#d91a1a}-12.45\%}$
test_iql_speed[reduce-overhead-backward] 2.1839ms 2.1193ms 471.8555 Ops/s 455.2341 Ops/s $\color{#35bf28}+3.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.8842ms 6.3724ms 156.9274 Ops/s 154.7474 Ops/s $\color{#35bf28}+1.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7079ms 0.3308ms 3.0234 KOps/s 2.9057 KOps/s $\color{#35bf28}+4.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6755ms 0.3067ms 3.2602 KOps/s 3.3073 KOps/s $\color{#d91a1a}-1.42\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3446ms 6.0842ms 164.3594 Ops/s 162.9695 Ops/s $\color{#35bf28}+0.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9938ms 0.2978ms 3.3577 KOps/s 3.7501 KOps/s $\textbf{\color{#d91a1a}-10.46\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6383ms 0.2886ms 3.4653 KOps/s 3.4435 KOps/s $\color{#35bf28}+0.63\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7019ms 1.4324ms 698.1158 Ops/s 770.4619 Ops/s $\textbf{\color{#d91a1a}-9.39\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4402ms 1.2344ms 810.0805 Ops/s 809.4300 Ops/s $\color{#35bf28}+0.08\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.3735ms 6.2759ms 159.3385 Ops/s 155.9731 Ops/s $\color{#35bf28}+2.16\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9423ms 0.4433ms 2.2559 KOps/s 2.0780 KOps/s $\textbf{\color{#35bf28}+8.56\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7710ms 0.4002ms 2.4990 KOps/s 2.4062 KOps/s $\color{#35bf28}+3.86\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2978ms 6.1357ms 162.9810 Ops/s 161.7841 Ops/s $\color{#35bf28}+0.74\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.9826ms 0.3133ms 3.1916 KOps/s 3.6982 KOps/s $\textbf{\color{#d91a1a}-13.70\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6197ms 0.3545ms 2.8209 KOps/s 3.2421 KOps/s $\textbf{\color{#d91a1a}-12.99\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.2896ms 6.0526ms 165.2174 Ops/s 163.0938 Ops/s $\color{#35bf28}+1.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7238ms 0.3406ms 2.9357 KOps/s 3.5043 KOps/s $\textbf{\color{#d91a1a}-16.23\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5783ms 0.2963ms 3.3744 KOps/s 3.5109 KOps/s $\color{#d91a1a}-3.89\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4000ms 6.2434ms 160.1681 Ops/s 157.2263 Ops/s $\color{#35bf28}+1.87\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.6697ms 0.4158ms 2.4049 KOps/s 2.1242 KOps/s $\textbf{\color{#35bf28}+13.21\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5808ms 0.3825ms 2.6142 KOps/s 2.0231 KOps/s $\textbf{\color{#35bf28}+29.22\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1549ms 5.4405ms 183.8063 Ops/s 177.9420 Ops/s $\color{#35bf28}+3.30\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.1868ms 2.0591ms 485.6592 Ops/s 424.2228 Ops/s $\textbf{\color{#35bf28}+14.48\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.9669ms 1.2918ms 774.1145 Ops/s 826.4510 Ops/s $\textbf{\color{#d91a1a}-6.33\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4497s 14.4646ms 69.1342 Ops/s 179.6813 Ops/s $\textbf{\color{#d91a1a}-61.52\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.2048ms 1.9876ms 503.1251 Ops/s 426.7268 Ops/s $\textbf{\color{#35bf28}+17.90\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 8.2782ms 1.3102ms 763.2663 Ops/s 854.1413 Ops/s $\textbf{\color{#d91a1a}-10.64\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.0931ms 5.7620ms 173.5501 Ops/s 30.9455 Ops/s $\textbf{\color{#35bf28}+460.82\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.9987ms 2.3055ms 433.7498 Ops/s 531.4780 Ops/s $\textbf{\color{#d91a1a}-18.39\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.5283ms 1.4856ms 673.1491 Ops/s 813.7397 Ops/s $\textbf{\color{#d91a1a}-17.28\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.1162ms 13.4104ms 74.5688 Ops/s 70.8155 Ops/s $\textbf{\color{#35bf28}+5.30\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.0242ms 17.0278ms 58.7275 Ops/s 59.8744 Ops/s $\color{#d91a1a}-1.92\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.5108ms 17.9627ms 55.6710 Ops/s 53.7168 Ops/s $\color{#35bf28}+3.64\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 19.0364ms 17.4197ms 57.4063 Ops/s 58.2423 Ops/s $\color{#d91a1a}-1.44\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 0.3926s 25.4317ms 39.3210 Ops/s 54.8157 Ops/s $\textbf{\color{#d91a1a}-28.27\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.0199ms 18.7437ms 53.3512 Ops/s 54.4734 Ops/s $\color{#d91a1a}-2.06\%$

[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: b772c71
Pull Request resolved: #2799
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: 8838d96
Pull Request resolved: #2799
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: 68e9f0d
Pull Request resolved: #2799
[ghstack-poisoned]
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: bcbf41c
Pull Request resolved: #2799
@vmoens vmoens merged commit 89579b2 into gh/vmoens/93/base Feb 20, 2025
45 of 57 checks passed
vmoens pushed a commit that referenced this pull request Feb 20, 2025
ghstack-source-id: bcbf41c
Pull Request resolved: #2799
@vmoens vmoens deleted the gh/vmoens/93/head branch February 20, 2025 21:24
vmoens pushed a commit that referenced this pull request Mar 8, 2025
ghstack-source-id: bcbf41c
Pull Request resolved: #2799

(cherry picked from commit fb641de)
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. Environments Adds or modifies an environment wrapper Tests Incomplete or broken unit tests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载