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

[Quality] Split utils.h and utils.cpp #2348

Merged
merged 3 commits into from
Aug 2, 2024
Merged

[Quality] Split utils.h and utils.cpp #2348

merged 3 commits into from
Aug 2, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Aug 1, 2024 •
edited
Loading

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Aug 1, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2348

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

❌ 2 New Failures, 4 Unrelated Failures

As of commit 01cec2a with merge base 99332f5 (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 Aug 1, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Aug 1, 2024 •
edited
Loading

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 60.4152ms 59.2959ms 16.8646 Ops/s 16.8904 Ops/s $\color{#d91a1a}-0.15\%$
test_sync 39.5981ms 36.0616ms 27.7303 Ops/s 29.9699 Ops/s $\textbf{\color{#d91a1a}-7.47\%}$
test_async 55.2051ms 31.7438ms 31.5022 Ops/s 32.0957 Ops/s $\color{#d91a1a}-1.85\%$
test_simple 0.5469s 0.4355s 2.2962 Ops/s 2.2008 Ops/s $\color{#35bf28}+4.33\%$
test_transformed 0.7424s 0.6102s 1.6388 Ops/s 1.6433 Ops/s $\color{#d91a1a}-0.28\%$
test_serial 1.4452s 1.3136s 0.7613 Ops/s 0.7784 Ops/s $\color{#d91a1a}-2.20\%$
test_parallel 1.2863s 1.1639s 0.8592 Ops/s 0.8432 Ops/s $\color{#35bf28}+1.89\%$
test_step_mdp_speed[True-True-True-True-True] 0.1224ms 24.0877μs 41.5150 KOps/s 39.4319 KOps/s $\textbf{\color{#35bf28}+5.28\%}$
test_step_mdp_speed[True-True-True-True-False] 47.7590μs 14.8083μs 67.5297 KOps/s 68.3111 KOps/s $\color{#d91a1a}-1.14\%$
test_step_mdp_speed[True-True-True-False-True] 44.5630μs 14.2307μs 70.2706 KOps/s 69.2633 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[True-True-True-False-False] 64.5510μs 8.3393μs 119.9136 KOps/s 118.5333 KOps/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[True-True-False-True-True] 76.9730μs 26.1116μs 38.2972 KOps/s 37.5458 KOps/s $\color{#35bf28}+2.00\%$
test_step_mdp_speed[True-True-False-True-False] 42.5190μs 15.8337μs 63.1564 KOps/s 62.9235 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[True-True-False-False-True] 75.3900μs 15.4467μs 64.7386 KOps/s 63.0534 KOps/s $\color{#35bf28}+2.67\%$
test_step_mdp_speed[True-True-False-False-False] 40.4450μs 10.0968μs 99.0418 KOps/s 101.1022 KOps/s $\color{#d91a1a}-2.04\%$
test_step_mdp_speed[True-False-True-True-True] 85.1280μs 27.4961μs 36.3688 KOps/s 34.8538 KOps/s $\color{#35bf28}+4.35\%$
test_step_mdp_speed[True-False-True-True-False] 53.0790μs 17.5760μs 56.8958 KOps/s 56.7495 KOps/s $\color{#35bf28}+0.26\%$
test_step_mdp_speed[True-False-True-False-True] 75.5100μs 15.4237μs 64.8353 KOps/s 62.0853 KOps/s $\color{#35bf28}+4.43\%$
test_step_mdp_speed[True-False-True-False-False] 52.8880μs 9.9362μs 100.6421 KOps/s 100.6900 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-False-False-True-True] 86.5500μs 29.1125μs 34.3495 KOps/s 33.7897 KOps/s $\color{#35bf28}+1.66\%$
test_step_mdp_speed[True-False-False-True-False] 48.9110μs 19.0981μs 52.3612 KOps/s 52.4955 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[True-False-False-False-True] 71.9130μs 16.9738μs 58.9145 KOps/s 57.8322 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[True-False-False-False-False] 41.0360μs 11.1371μs 89.7900 KOps/s 88.5197 KOps/s $\color{#35bf28}+1.44\%$
test_step_mdp_speed[False-True-True-True-True] 84.5370μs 27.3181μs 36.6058 KOps/s 35.6868 KOps/s $\color{#35bf28}+2.58\%$
test_step_mdp_speed[False-True-True-True-False] 76.0010μs 17.5011μs 57.1391 KOps/s 56.8780 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-True-True-False-True] 66.8800μs 18.0088μs 55.5283 KOps/s 53.7950 KOps/s $\color{#35bf28}+3.22\%$
test_step_mdp_speed[False-True-True-False-False] 40.6950μs 11.0944μs 90.1354 KOps/s 91.4929 KOps/s $\color{#d91a1a}-1.48\%$
test_step_mdp_speed[False-True-False-True-True] 68.1860μs 29.1207μs 34.3398 KOps/s 33.8084 KOps/s $\color{#35bf28}+1.57\%$
test_step_mdp_speed[False-True-False-True-False] 52.9380μs 18.6296μs 53.6781 KOps/s 53.0119 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[False-True-False-False-True] 54.6810μs 19.2525μs 51.9413 KOps/s 50.2545 KOps/s $\color{#35bf28}+3.36\%$
test_step_mdp_speed[False-True-False-False-False] 40.0950μs 12.6242μs 79.2127 KOps/s 79.8683 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[False-False-True-True-True] 6.0326ms 30.7626μs 32.5070 KOps/s 32.5003 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[False-False-True-True-False] 53.6400μs 20.6565μs 48.4109 KOps/s 49.0638 KOps/s $\color{#d91a1a}-1.33\%$
test_step_mdp_speed[False-False-True-False-True] 62.6060μs 19.4716μs 51.3569 KOps/s 51.0777 KOps/s $\color{#35bf28}+0.55\%$
test_step_mdp_speed[False-False-True-False-False] 36.8590μs 12.5136μs 79.9129 KOps/s 80.6669 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[False-False-False-True-True] 80.3530μs 31.3792μs 31.8683 KOps/s 31.6132 KOps/s $\color{#35bf28}+0.81\%$
test_step_mdp_speed[False-False-False-True-False] 71.2980μs 21.4796μs 46.5558 KOps/s 46.4413 KOps/s $\color{#35bf28}+0.25\%$
test_step_mdp_speed[False-False-False-False-True] 51.3250μs 20.2095μs 49.4817 KOps/s 48.1965 KOps/s $\color{#35bf28}+2.67\%$
test_step_mdp_speed[False-False-False-False-False] 46.1060μs 13.6899μs 73.0467 KOps/s 73.0787 KOps/s $\color{#d91a1a}-0.04\%$
test_values[generalized_advantage_estimate-True-True] 13.3799ms 9.8254ms 101.7773 Ops/s 101.9188 Ops/s $\color{#d91a1a}-0.14\%$
test_values[vec_generalized_advantage_estimate-True-True] 48.1832ms 41.8458ms 23.8972 Ops/s 25.1110 Ops/s $\color{#d91a1a}-4.83\%$
test_values[td0_return_estimate-False-False] 0.3226ms 0.1779ms 5.6223 KOps/s 5.8598 KOps/s $\color{#d91a1a}-4.05\%$
test_values[td1_return_estimate-False-False] 25.4725ms 24.7621ms 40.3842 Ops/s 41.4430 Ops/s $\color{#d91a1a}-2.55\%$
test_values[vec_td1_return_estimate-False-False] 51.0007ms 44.1727ms 22.6384 Ops/s 25.5163 Ops/s $\textbf{\color{#d91a1a}-11.28\%}$
test_values[td_lambda_return_estimate-True-False] 36.3580ms 34.9622ms 28.6023 Ops/s 28.4234 Ops/s $\color{#35bf28}+0.63\%$
test_values[vec_td_lambda_return_estimate-True-False] 46.4748ms 43.4343ms 23.0233 Ops/s 25.6339 Ops/s $\textbf{\color{#d91a1a}-10.18\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.7037ms 8.3535ms 119.7110 Ops/s 118.9232 Ops/s $\color{#35bf28}+0.66\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2002ms 1.8928ms 528.3129 Ops/s 519.9742 Ops/s $\color{#35bf28}+1.60\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5906ms 0.3721ms 2.6874 KOps/s 2.6472 KOps/s $\color{#35bf28}+1.52\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 63.7024ms 56.4724ms 17.7078 Ops/s 17.1312 Ops/s $\color{#35bf28}+3.37\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.1666ms 3.0482ms 328.0633 Ops/s 318.4157 Ops/s $\color{#35bf28}+3.03\%$
test_dqn_speed 1.9497ms 1.3269ms 753.6252 Ops/s 731.8470 Ops/s $\color{#35bf28}+2.98\%$
test_ddpg_speed 3.4121ms 2.7529ms 363.2581 Ops/s 353.3714 Ops/s $\color{#35bf28}+2.80\%$
test_sac_speed 8.7048ms 8.1458ms 122.7634 Ops/s 120.6361 Ops/s $\color{#35bf28}+1.76\%$
test_redq_speed 17.3803ms 14.9203ms 67.0228 Ops/s 66.6973 Ops/s $\color{#35bf28}+0.49\%$
test_redq_deprec_speed 15.3919ms 13.1592ms 75.9923 Ops/s 71.3171 Ops/s $\textbf{\color{#35bf28}+6.56\%}$
test_td3_speed 8.4388ms 8.0287ms 124.5530 Ops/s 121.8784 Ops/s $\color{#35bf28}+2.19\%$
test_cql_speed 42.1653ms 38.7490ms 25.8071 Ops/s 25.3743 Ops/s $\color{#35bf28}+1.71\%$
test_a2c_speed 10.1761ms 7.4497ms 134.2344 Ops/s 131.4038 Ops/s $\color{#35bf28}+2.15\%$
test_ppo_speed 9.2883ms 7.6389ms 130.9082 Ops/s 127.1340 Ops/s $\color{#35bf28}+2.97\%$
test_reinforce_speed 8.3824ms 6.5257ms 153.2412 Ops/s 149.7080 Ops/s $\color{#35bf28}+2.36\%$
test_iql_speed 35.9289ms 33.5345ms 29.8200 Ops/s 28.0534 Ops/s $\textbf{\color{#35bf28}+6.30\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9146ms 4.9566ms 201.7532 Ops/s 191.3127 Ops/s $\textbf{\color{#35bf28}+5.46\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.9612ms 0.4836ms 2.0680 KOps/s 2.0442 KOps/s $\color{#35bf28}+1.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6966ms 0.4609ms 2.1696 KOps/s 2.1116 KOps/s $\color{#35bf28}+2.75\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 8.2467ms 4.9472ms 202.1348 Ops/s 193.8443 Ops/s $\color{#35bf28}+4.28\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9377ms 0.4909ms 2.0370 KOps/s 1.3838 KOps/s $\textbf{\color{#35bf28}+47.20\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6162ms 0.4500ms 2.2221 KOps/s 2.1194 KOps/s $\color{#35bf28}+4.84\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.5049ms 1.7928ms 557.7837 Ops/s 582.0679 Ops/s $\color{#d91a1a}-4.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.4616ms 1.6352ms 611.5618 Ops/s 613.5320 Ops/s $\color{#d91a1a}-0.32\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.4969ms 5.0706ms 197.2155 Ops/s 193.5208 Ops/s $\color{#35bf28}+1.91\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9039ms 0.6296ms 1.5882 KOps/s 1.5750 KOps/s $\color{#35bf28}+0.84\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8122ms 0.6025ms 1.6596 KOps/s 1.6302 KOps/s $\color{#35bf28}+1.80\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.8010ms 4.9136ms 203.5169 Ops/s 193.0906 Ops/s $\textbf{\color{#35bf28}+5.40\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7329ms 0.4966ms 2.0139 KOps/s 2.0041 KOps/s $\color{#35bf28}+0.49\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 7.9743ms 0.4682ms 2.1360 KOps/s 2.0398 KOps/s $\color{#35bf28}+4.72\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.5787ms 4.9709ms 201.1703 Ops/s 198.9382 Ops/s $\color{#35bf28}+1.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8148ms 0.4948ms 2.0211 KOps/s 2.0145 KOps/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 7.9494ms 0.4725ms 2.1166 KOps/s 2.0749 KOps/s $\color{#35bf28}+2.01\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.3194ms 5.1031ms 195.9594 Ops/s 190.6594 Ops/s $\color{#35bf28}+2.78\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7227ms 0.6207ms 1.6110 KOps/s 1.5665 KOps/s $\color{#35bf28}+2.84\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 8.2524ms 0.6319ms 1.5826 KOps/s 1.6171 KOps/s $\color{#d91a1a}-2.13\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.2452s 13.2458ms 75.4954 Ops/s 125.1330 Ops/s $\textbf{\color{#d91a1a}-39.67\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.0889ms 13.3776ms 74.7519 Ops/s 72.8933 Ops/s $\color{#35bf28}+2.55\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.9629ms 1.3856ms 721.6867 Ops/s 696.4747 Ops/s $\color{#35bf28}+3.62\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.2289s 8.6065ms 116.1908 Ops/s 132.2072 Ops/s $\textbf{\color{#d91a1a}-12.11\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.8937ms 13.4331ms 74.4431 Ops/s 73.0412 Ops/s $\color{#35bf28}+1.92\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.8349ms 1.3154ms 760.2009 Ops/s 688.6148 Ops/s $\textbf{\color{#35bf28}+10.40\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1658s 7.3560ms 135.9439 Ops/s 90.7071 Ops/s $\textbf{\color{#35bf28}+49.87\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.0335ms 13.5557ms 73.7698 Ops/s 71.9413 Ops/s $\color{#35bf28}+2.54\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.1029ms 1.6391ms 610.0869 Ops/s 654.6410 Ops/s $\textbf{\color{#d91a1a}-6.81\%}$

@github-actions GitHub Actions
Copy link

github-actions bot commented Aug 1, 2024 •
edited
Loading

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1093s 0.1088s 9.1921 Ops/s 9.1773 Ops/s $\color{#35bf28}+0.16\%$
test_sync 0.1019s 0.1004s 9.9610 Ops/s 10.4900 Ops/s $\textbf{\color{#d91a1a}-5.04\%}$
test_async 0.2564s 91.0133ms 10.9874 Ops/s 11.0887 Ops/s $\color{#d91a1a}-0.91\%$
test_single_pixels 0.1192s 0.1190s 8.4036 Ops/s 8.5015 Ops/s $\color{#d91a1a}-1.15\%$
test_sync_pixels 76.9874ms 73.7445ms 13.5603 Ops/s 13.4814 Ops/s $\color{#35bf28}+0.59\%$
test_async_pixels 0.1378s 69.7658ms 14.3337 Ops/s 14.2416 Ops/s $\color{#35bf28}+0.65\%$
test_simple 0.8007s 0.7880s 1.2690 Ops/s 1.2391 Ops/s $\color{#35bf28}+2.42\%$
test_transformed 1.1190s 1.0428s 0.9590 Ops/s 0.9860 Ops/s $\color{#d91a1a}-2.74\%$
test_serial 2.3232s 2.2545s 0.4436 Ops/s 0.4469 Ops/s $\color{#d91a1a}-0.75\%$
test_parallel 2.0263s 1.9717s 0.5072 Ops/s 0.4992 Ops/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[True-True-True-True-True] 0.1088ms 37.3798μs 26.7524 KOps/s 27.7479 KOps/s $\color{#d91a1a}-3.59\%$
test_step_mdp_speed[True-True-True-True-False] 38.0620μs 21.3127μs 46.9205 KOps/s 48.3273 KOps/s $\color{#d91a1a}-2.91\%$
test_step_mdp_speed[True-True-True-False-True] 42.4820μs 21.2174μs 47.1311 KOps/s 48.8172 KOps/s $\color{#d91a1a}-3.45\%$
test_step_mdp_speed[True-True-True-False-False] 26.4910μs 12.1359μs 82.4001 KOps/s 84.9079 KOps/s $\color{#d91a1a}-2.95\%$
test_step_mdp_speed[True-True-False-True-True] 83.7050μs 39.8086μs 25.1202 KOps/s 26.3111 KOps/s $\color{#d91a1a}-4.53\%$
test_step_mdp_speed[True-True-False-True-False] 39.4920μs 23.4346μs 42.6719 KOps/s 43.7346 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[True-True-False-False-True] 43.5420μs 23.2274μs 43.0525 KOps/s 44.9988 KOps/s $\color{#d91a1a}-4.33\%$
test_step_mdp_speed[True-True-False-False-False] 30.8420μs 14.2639μs 70.1069 KOps/s 71.4379 KOps/s $\color{#d91a1a}-1.86\%$
test_step_mdp_speed[True-False-True-True-True] 59.2030μs 41.4235μs 24.1409 KOps/s 25.3212 KOps/s $\color{#d91a1a}-4.66\%$
test_step_mdp_speed[True-False-True-True-False] 51.4430μs 25.4065μs 39.3600 KOps/s 40.5384 KOps/s $\color{#d91a1a}-2.91\%$
test_step_mdp_speed[True-False-True-False-True] 41.1420μs 23.1976μs 43.1079 KOps/s 44.8354 KOps/s $\color{#d91a1a}-3.85\%$
test_step_mdp_speed[True-False-True-False-False] 30.8220μs 14.2363μs 70.2429 KOps/s 71.9213 KOps/s $\color{#d91a1a}-2.33\%$
test_step_mdp_speed[True-False-False-True-True] 76.0540μs 43.4468μs 23.0166 KOps/s 24.0813 KOps/s $\color{#d91a1a}-4.42\%$
test_step_mdp_speed[True-False-False-True-False] 43.0430μs 27.9022μs 35.8394 KOps/s 37.3122 KOps/s $\color{#d91a1a}-3.95\%$
test_step_mdp_speed[True-False-False-False-True] 52.6130μs 25.2099μs 39.6669 KOps/s 40.9680 KOps/s $\color{#d91a1a}-3.18\%$
test_step_mdp_speed[True-False-False-False-False] 40.1230μs 16.3189μs 61.2788 KOps/s 61.9233 KOps/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[False-True-True-True-True] 66.2340μs 41.3142μs 24.2047 KOps/s 25.1588 KOps/s $\color{#d91a1a}-3.79\%$
test_step_mdp_speed[False-True-True-True-False] 52.9230μs 25.7134μs 38.8902 KOps/s 40.5463 KOps/s $\color{#d91a1a}-4.08\%$
test_step_mdp_speed[False-True-True-False-True] 47.2530μs 27.8462μs 35.9115 KOps/s 38.2202 KOps/s $\textbf{\color{#d91a1a}-6.04\%}$
test_step_mdp_speed[False-True-True-False-False] 33.8920μs 16.4678μs 60.7246 KOps/s 64.0477 KOps/s $\textbf{\color{#d91a1a}-5.19\%}$
test_step_mdp_speed[False-True-False-True-True] 70.5040μs 43.4258μs 23.0278 KOps/s 23.9608 KOps/s $\color{#d91a1a}-3.89\%$
test_step_mdp_speed[False-True-False-True-False] 65.5030μs 27.6043μs 36.2262 KOps/s 37.5196 KOps/s $\color{#d91a1a}-3.45\%$
test_step_mdp_speed[False-True-False-False-True] 47.8030μs 29.5345μs 33.8587 KOps/s 35.6110 KOps/s $\color{#d91a1a}-4.92\%$
test_step_mdp_speed[False-True-False-False-False] 34.7420μs 18.1800μs 55.0054 KOps/s 56.7852 KOps/s $\color{#d91a1a}-3.13\%$
test_step_mdp_speed[False-False-True-True-True] 4.2896ms 46.8815μs 21.3304 KOps/s 22.2004 KOps/s $\color{#d91a1a}-3.92\%$
test_step_mdp_speed[False-False-True-True-False] 55.0930μs 30.2315μs 33.0781 KOps/s 34.2949 KOps/s $\color{#d91a1a}-3.55\%$
test_step_mdp_speed[False-False-True-False-True] 47.9820μs 29.7325μs 33.6333 KOps/s 34.8342 KOps/s $\color{#d91a1a}-3.45\%$
test_step_mdp_speed[False-False-True-False-False] 35.8520μs 18.6273μs 53.6847 KOps/s 56.7258 KOps/s $\textbf{\color{#d91a1a}-5.36\%}$
test_step_mdp_speed[False-False-False-True-True] 69.9640μs 47.7950μs 20.9227 KOps/s 21.8074 KOps/s $\color{#d91a1a}-4.06\%$
test_step_mdp_speed[False-False-False-True-False] 48.0130μs 32.1882μs 31.0673 KOps/s 32.2057 KOps/s $\color{#d91a1a}-3.53\%$
test_step_mdp_speed[False-False-False-False-True] 57.5930μs 31.3276μs 31.9207 KOps/s 33.0113 KOps/s $\color{#d91a1a}-3.30\%$
test_step_mdp_speed[False-False-False-False-False] 41.8620μs 20.7030μs 48.3022 KOps/s 50.8662 KOps/s $\textbf{\color{#d91a1a}-5.04\%}$
test_values[generalized_advantage_estimate-True-True] 26.0819ms 23.9823ms 41.6975 Ops/s 41.1525 Ops/s $\color{#35bf28}+1.32\%$
test_values[vec_generalized_advantage_estimate-True-True] 91.2432ms 2.7253ms 366.9362 Ops/s 374.5840 Ops/s $\color{#d91a1a}-2.04\%$
test_values[td0_return_estimate-False-False] 94.4660μs 66.8487μs 14.9591 KOps/s 15.1845 KOps/s $\color{#d91a1a}-1.48\%$
test_values[td1_return_estimate-False-False] 58.6733ms 54.7044ms 18.2801 Ops/s 18.1938 Ops/s $\color{#35bf28}+0.47\%$
test_values[vec_td1_return_estimate-False-False] 1.3181ms 1.0832ms 923.1570 Ops/s 923.5606 Ops/s $\color{#d91a1a}-0.04\%$
test_values[td_lambda_return_estimate-True-False] 86.4644ms 86.1326ms 11.6100 Ops/s 11.4602 Ops/s $\color{#35bf28}+1.31\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2978ms 1.0801ms 925.8514 Ops/s 927.1543 Ops/s $\color{#d91a1a}-0.14\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 26.0259ms 24.3921ms 40.9968 Ops/s 41.4747 Ops/s $\color{#d91a1a}-1.15\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9596ms 0.7220ms 1.3851 KOps/s 1.3402 KOps/s $\color{#35bf28}+3.35\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7527ms 0.6701ms 1.4924 KOps/s 1.4835 KOps/s $\color{#35bf28}+0.60\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5690ms 1.4740ms 678.4291 Ops/s 679.5530 Ops/s $\color{#d91a1a}-0.17\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.8203ms 0.6971ms 1.4345 KOps/s 1.4697 KOps/s $\color{#d91a1a}-2.39\%$
test_dqn_speed 7.2118ms 1.3662ms 731.9581 Ops/s 734.1512 Ops/s $\color{#d91a1a}-0.30\%$
test_ddpg_speed 3.0094ms 2.7604ms 362.2637 Ops/s 365.6661 Ops/s $\color{#d91a1a}-0.93\%$
test_sac_speed 9.2944ms 7.9481ms 125.8169 Ops/s 127.6177 Ops/s $\color{#d91a1a}-1.41\%$
test_redq_speed 12.3908ms 10.2974ms 97.1119 Ops/s 98.1059 Ops/s $\color{#d91a1a}-1.01\%$
test_redq_deprec_speed 11.2345ms 10.8104ms 92.5037 Ops/s 93.8772 Ops/s $\color{#d91a1a}-1.46\%$
test_td3_speed 7.9879ms 7.8738ms 127.0027 Ops/s 128.0213 Ops/s $\color{#d91a1a}-0.80\%$
test_cql_speed 26.7070ms 24.9886ms 40.0183 Ops/s 40.3312 Ops/s $\color{#d91a1a}-0.78\%$
test_a2c_speed 6.2018ms 5.5858ms 179.0244 Ops/s 182.1990 Ops/s $\color{#d91a1a}-1.74\%$
test_ppo_speed 6.1741ms 5.9213ms 168.8807 Ops/s 174.2713 Ops/s $\color{#d91a1a}-3.09\%$
test_reinforce_speed 5.2342ms 4.5158ms 221.4432 Ops/s 227.0307 Ops/s $\color{#d91a1a}-2.46\%$
test_iql_speed 20.5059ms 19.6355ms 50.9281 Ops/s 51.9555 Ops/s $\color{#d91a1a}-1.98\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.9640ms 6.7162ms 148.8930 Ops/s 149.5194 Ops/s $\color{#d91a1a}-0.42\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.0180ms 0.5227ms 1.9131 KOps/s 1.9307 KOps/s $\color{#d91a1a}-0.91\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7505ms 0.4986ms 2.0055 KOps/s 2.0251 KOps/s $\color{#d91a1a}-0.97\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.8973ms 6.5881ms 151.7897 Ops/s 153.1817 Ops/s $\color{#d91a1a}-0.91\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7206ms 0.5173ms 1.9332 KOps/s 1.9672 KOps/s $\color{#d91a1a}-1.73\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7217ms 0.4942ms 2.0235 KOps/s 2.0591 KOps/s $\color{#d91a1a}-1.73\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.0781ms 1.9733ms 506.7769 Ops/s 513.3521 Ops/s $\color{#d91a1a}-1.28\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.1364ms 1.8804ms 531.7950 Ops/s 539.5035 Ops/s $\color{#d91a1a}-1.43\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.9875ms 6.8215ms 146.5954 Ops/s 148.2666 Ops/s $\color{#d91a1a}-1.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1262ms 0.6625ms 1.5095 KOps/s 1.5063 KOps/s $\color{#35bf28}+0.21\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8753ms 0.6458ms 1.5486 KOps/s 1.5693 KOps/s $\color{#d91a1a}-1.32\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.7882ms 6.6608ms 150.1318 Ops/s 152.2744 Ops/s $\color{#d91a1a}-1.41\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1424ms 0.5348ms 1.8700 KOps/s 1.9468 KOps/s $\color{#d91a1a}-3.95\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7874ms 0.5057ms 1.9775 KOps/s 2.0354 KOps/s $\color{#d91a1a}-2.84\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.8350ms 6.5667ms 152.2840 Ops/s 151.8303 Ops/s $\color{#35bf28}+0.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1255s 0.6809ms 1.4686 KOps/s 1.9661 KOps/s $\textbf{\color{#d91a1a}-25.31\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7277ms 0.4955ms 2.0183 KOps/s 2.0158 KOps/s $\color{#35bf28}+0.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.0120ms 6.8279ms 146.4574 Ops/s 148.2534 Ops/s $\color{#d91a1a}-1.21\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8064ms 0.6732ms 1.4855 KOps/s 1.2152 KOps/s $\textbf{\color{#35bf28}+22.24\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 4.4521ms 0.6567ms 1.5227 KOps/s 1.5460 KOps/s $\color{#d91a1a}-1.51\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1256s 7.5694ms 132.1103 Ops/s 129.3463 Ops/s $\color{#35bf28}+2.14\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 21.1921ms 16.3592ms 61.1278 Ops/s 61.6840 Ops/s $\color{#d91a1a}-0.90\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.2105ms 1.2686ms 788.2666 Ops/s 800.2255 Ops/s $\color{#d91a1a}-1.49\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1250s 7.5962ms 131.6451 Ops/s 130.5279 Ops/s $\color{#35bf28}+0.86\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1384s 19.0470ms 52.5016 Ops/s 61.9124 Ops/s $\textbf{\color{#d91a1a}-15.20\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.3599ms 1.3685ms 730.7317 Ops/s 790.5061 Ops/s $\textbf{\color{#d91a1a}-7.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1253s 7.7751ms 128.6149 Ops/s 128.3931 Ops/s $\color{#35bf28}+0.17\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 19.6031ms 16.7515ms 59.6961 Ops/s 60.4928 Ops/s $\color{#d91a1a}-1.32\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.7587ms 1.5420ms 648.5161 Ops/s 698.5091 Ops/s $\textbf{\color{#d91a1a}-7.16\%}$

@vmoens vmoens added the quality code quality label Aug 2, 2024
@vmoens vmoens merged commit 0029c32 into main Aug 2, 2024
69 of 71 checks passed
@vmoens vmoens deleted the split-headers-cpp branch August 2, 2024 21:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. quality code quality
Projects
None yet
Milestone
No milestone
Development

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