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

[BugFix] SliceSampler device and index mesh #1996

Merged
merged 2 commits into from
Mar 6, 2024
Merged

[BugFix] SliceSampler device and index mesh #1996

merged 2 commits into from
Mar 6, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Mar 6, 2024

No description provided.

@pytorch-bot PyTorch Bot
Copy link

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

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1996

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

❌ 4 New Failures, 15 Unrelated Failures

As of commit 3fafe1d with merge base fe6c070 (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

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 Mar 6, 2024
@vmoens vmoens added the bug Something isn't working label Mar 6, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 6, 2024

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 62.9961ms 61.4760ms 16.2665 Ops/s 16.4326 Ops/s $\color{#d91a1a}-1.01\%$
test_sync 49.7579ms 34.0542ms 29.3650 Ops/s 27.7399 Ops/s $\textbf{\color{#35bf28}+5.86\%}$
test_async 56.6022ms 30.2496ms 33.0583 Ops/s 31.6190 Ops/s $\color{#35bf28}+4.55\%$
test_simple 0.4920s 0.4287s 2.3324 Ops/s 2.3592 Ops/s $\color{#d91a1a}-1.14\%$
test_transformed 0.6397s 0.5723s 1.7472 Ops/s 1.7248 Ops/s $\color{#35bf28}+1.30\%$
test_serial 1.4452s 1.3895s 0.7197 Ops/s 0.7170 Ops/s $\color{#35bf28}+0.37\%$
test_parallel 1.4637s 1.3860s 0.7215 Ops/s 0.7315 Ops/s $\color{#d91a1a}-1.37\%$
test_step_mdp_speed[True-True-True-True-True] 0.1985ms 21.1481μs 47.2855 KOps/s 47.6051 KOps/s $\color{#d91a1a}-0.67\%$
test_step_mdp_speed[True-True-True-True-False] 66.4040μs 12.9384μs 77.2891 KOps/s 77.7090 KOps/s $\color{#d91a1a}-0.54\%$
test_step_mdp_speed[True-True-True-False-True] 54.4910μs 12.5677μs 79.5689 KOps/s 81.3900 KOps/s $\color{#d91a1a}-2.24\%$
test_step_mdp_speed[True-True-True-False-False] 52.4680μs 7.6217μs 131.2037 KOps/s 133.8963 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[True-True-False-True-True] 94.9770μs 22.5973μs 44.2531 KOps/s 44.7501 KOps/s $\color{#d91a1a}-1.11\%$
test_step_mdp_speed[True-True-False-True-False] 71.4130μs 14.2700μs 70.0773 KOps/s 71.3250 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-True-False-False-True] 40.6360μs 13.5928μs 73.5683 KOps/s 74.4573 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[True-True-False-False-False] 60.9940μs 8.7950μs 113.7015 KOps/s 113.8980 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[True-False-True-True-True] 49.6330μs 23.9433μs 41.7654 KOps/s 41.3936 KOps/s $\color{#35bf28}+0.90\%$
test_step_mdp_speed[True-False-True-True-False] 39.7440μs 15.6053μs 64.0806 KOps/s 64.1192 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[True-False-True-False-True] 62.2870μs 13.6276μs 73.3805 KOps/s 72.4266 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[True-False-True-False-False] 32.5310μs 8.7757μs 113.9511 KOps/s 113.4785 KOps/s $\color{#35bf28}+0.42\%$
test_step_mdp_speed[True-False-False-True-True] 75.0200μs 25.1166μs 39.8143 KOps/s 39.5541 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[True-False-False-True-False] 53.1290μs 16.7266μs 59.7851 KOps/s 59.3632 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[True-False-False-False-True] 54.4210μs 14.7421μs 67.8331 KOps/s 67.4891 KOps/s $\color{#35bf28}+0.51\%$
test_step_mdp_speed[True-False-False-False-False] 40.5650μs 9.9757μs 100.2437 KOps/s 99.3185 KOps/s $\color{#35bf28}+0.93\%$
test_step_mdp_speed[False-True-True-True-True] 76.4230μs 23.9350μs 41.7798 KOps/s 41.8766 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[False-True-True-True-False] 66.1530μs 16.2252μs 61.6327 KOps/s 64.1909 KOps/s $\color{#d91a1a}-3.99\%$
test_step_mdp_speed[False-True-True-False-True] 48.0700μs 15.9240μs 62.7985 KOps/s 63.1639 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[False-True-True-False-False] 54.9520μs 10.0776μs 99.2295 KOps/s 100.1830 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[False-True-False-True-True] 39.6440μs 25.2946μs 39.5342 KOps/s 39.0070 KOps/s $\color{#35bf28}+1.35\%$
test_step_mdp_speed[False-True-False-True-False] 40.1750μs 16.8182μs 59.4592 KOps/s 59.2034 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-True-False-False-True] 72.8060μs 17.0394μs 58.6874 KOps/s 58.7557 KOps/s $\color{#d91a1a}-0.12\%$
test_step_mdp_speed[False-True-False-False-False] 37.2900μs 11.2172μs 89.1484 KOps/s 88.7371 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-False-True-True-True] 86.5220μs 26.3055μs 38.0148 KOps/s 37.6238 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[False-False-True-True-False] 95.1080μs 18.1251μs 55.1721 KOps/s 55.9442 KOps/s $\color{#d91a1a}-1.38\%$
test_step_mdp_speed[False-False-True-False-True] 60.1630μs 17.1754μs 58.2228 KOps/s 59.6202 KOps/s $\color{#d91a1a}-2.34\%$
test_step_mdp_speed[False-False-True-False-False] 72.9360μs 11.2629μs 88.7868 KOps/s 87.7218 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[False-False-False-True-True] 54.0410μs 27.4214μs 36.4678 KOps/s 36.4077 KOps/s $\color{#35bf28}+0.17\%$
test_step_mdp_speed[False-False-False-True-False] 72.1750μs 19.1367μs 52.2556 KOps/s 51.7556 KOps/s $\color{#35bf28}+0.97\%$
test_step_mdp_speed[False-False-False-False-True] 46.4570μs 18.3347μs 54.5413 KOps/s 54.6506 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[False-False-False-False-False] 62.5470μs 12.4262μs 80.4749 KOps/s 80.9584 KOps/s $\color{#d91a1a}-0.60\%$
test_values[generalized_advantage_estimate-True-True] 10.3905ms 9.3929ms 106.4628 Ops/s 105.1652 Ops/s $\color{#35bf28}+1.23\%$
test_values[vec_generalized_advantage_estimate-True-True] 39.7695ms 36.2965ms 27.5509 Ops/s 26.7464 Ops/s $\color{#35bf28}+3.01\%$
test_values[td0_return_estimate-False-False] 0.2658ms 0.1826ms 5.4752 KOps/s 5.4758 KOps/s $\color{#d91a1a}-0.01\%$
test_values[td1_return_estimate-False-False] 26.4628ms 23.4999ms 42.5533 Ops/s 42.8693 Ops/s $\color{#d91a1a}-0.74\%$
test_values[vec_td1_return_estimate-False-False] 40.9860ms 36.2114ms 27.6156 Ops/s 27.5002 Ops/s $\color{#35bf28}+0.42\%$
test_values[td_lambda_return_estimate-True-False] 34.0296ms 33.4421ms 29.9024 Ops/s 29.7080 Ops/s $\color{#35bf28}+0.65\%$
test_values[vec_td_lambda_return_estimate-True-False] 42.1849ms 37.0796ms 26.9690 Ops/s 27.6241 Ops/s $\color{#d91a1a}-2.37\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.3230ms 8.1473ms 122.7406 Ops/s 120.6558 Ops/s $\color{#35bf28}+1.73\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2766ms 1.8373ms 544.2687 Ops/s 489.4462 Ops/s $\textbf{\color{#35bf28}+11.20\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4506ms 0.3512ms 2.8475 KOps/s 2.8101 KOps/s $\color{#35bf28}+1.33\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 52.7018ms 48.1687ms 20.7604 Ops/s 20.1562 Ops/s $\color{#35bf28}+3.00\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.7541ms 3.0365ms 329.3231 Ops/s 327.9858 Ops/s $\color{#35bf28}+0.41\%$
test_dqn_speed 95.4385ms 1.5313ms 653.0489 Ops/s 714.7589 Ops/s $\textbf{\color{#d91a1a}-8.63\%}$
test_ddpg_speed 3.5866ms 2.7514ms 363.4534 Ops/s 365.7790 Ops/s $\color{#d91a1a}-0.64\%$
test_sac_speed 10.0096ms 8.5654ms 116.7482 Ops/s 118.4627 Ops/s $\color{#d91a1a}-1.45\%$
test_redq_speed 15.7814ms 13.9600ms 71.6332 Ops/s 70.7170 Ops/s $\color{#35bf28}+1.30\%$
test_redq_deprec_speed 21.3648ms 13.8697ms 72.0998 Ops/s 74.0196 Ops/s $\color{#d91a1a}-2.59\%$
test_td3_speed 8.8313ms 8.3445ms 119.8390 Ops/s 120.3741 Ops/s $\color{#d91a1a}-0.44\%$
test_cql_speed 40.0265ms 37.8499ms 26.4202 Ops/s 26.8882 Ops/s $\color{#d91a1a}-1.74\%$
test_a2c_speed 8.8838ms 7.9272ms 126.1485 Ops/s 131.1811 Ops/s $\color{#d91a1a}-3.84\%$
test_ppo_speed 8.7427ms 8.1215ms 123.1296 Ops/s 127.6648 Ops/s $\color{#d91a1a}-3.55\%$
test_reinforce_speed 8.1060ms 6.8322ms 146.3648 Ops/s 150.4097 Ops/s $\color{#d91a1a}-2.69\%$
test_iql_speed 34.6321ms 33.3387ms 29.9952 Ops/s 30.3729 Ops/s $\color{#d91a1a}-1.24\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3687ms 2.2802ms 438.5551 Ops/s 422.5799 Ops/s $\color{#35bf28}+3.78\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.2679ms 0.5085ms 1.9668 KOps/s 1.9725 KOps/s $\color{#d91a1a}-0.29\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7774ms 0.4788ms 2.0884 KOps/s 2.0722 KOps/s $\color{#35bf28}+0.78\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9251ms 2.3346ms 428.3420 Ops/s 410.2267 Ops/s $\color{#35bf28}+4.42\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6705ms 0.4990ms 2.0039 KOps/s 1.9960 KOps/s $\color{#35bf28}+0.40\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.4854ms 0.4759ms 2.1014 KOps/s 2.0879 KOps/s $\color{#35bf28}+0.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.2746ms 1.2763ms 783.5391 Ops/s 775.2325 Ops/s $\color{#35bf28}+1.07\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 0.1033s 1.3605ms 735.0069 Ops/s 826.3888 Ops/s $\textbf{\color{#d91a1a}-11.06\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.9041ms 2.5110ms 398.2508 Ops/s 406.5345 Ops/s $\color{#d91a1a}-2.04\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2185ms 0.6289ms 1.5901 KOps/s 1.6009 KOps/s $\color{#d91a1a}-0.67\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8722ms 0.6011ms 1.6636 KOps/s 1.6605 KOps/s $\color{#35bf28}+0.19\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8814ms 2.3626ms 423.2614 Ops/s 413.1789 Ops/s $\color{#35bf28}+2.44\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.1019s 0.6347ms 1.5756 KOps/s 1.9715 KOps/s $\textbf{\color{#d91a1a}-20.08\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6828ms 0.4833ms 2.0691 KOps/s 1.6240 KOps/s $\textbf{\color{#35bf28}+27.41\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.8735ms 2.4478ms 408.5303 Ops/s 405.7802 Ops/s $\color{#35bf28}+0.68\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7385ms 0.5052ms 1.9796 KOps/s 1.9412 KOps/s $\color{#35bf28}+1.98\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.0382ms 0.4900ms 2.0409 KOps/s 2.0002 KOps/s $\color{#35bf28}+2.03\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.6203ms 2.3709ms 421.7847 Ops/s 396.5595 Ops/s $\textbf{\color{#35bf28}+6.36\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8769ms 0.6239ms 1.6027 KOps/s 1.5841 KOps/s $\color{#35bf28}+1.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7480ms 0.5997ms 1.6676 KOps/s 1.3748 KOps/s $\textbf{\color{#35bf28}+21.30\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1147s 6.0277ms 165.8998 Ops/s 171.8623 Ops/s $\color{#d91a1a}-3.47\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 15.1933ms 12.3402ms 81.0361 Ops/s 82.0703 Ops/s $\color{#d91a1a}-1.26\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.2968ms 1.0388ms 962.6158 Ops/s 954.2627 Ops/s $\color{#35bf28}+0.88\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 96.1777ms 7.3786ms 135.5275 Ops/s 124.5951 Ops/s $\textbf{\color{#35bf28}+8.77\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 15.3298ms 12.4075ms 80.5961 Ops/s 80.1746 Ops/s $\color{#35bf28}+0.53\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.9705ms 1.1562ms 864.8823 Ops/s 821.7037 Ops/s $\textbf{\color{#35bf28}+5.25\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1007s 7.7831ms 128.4835 Ops/s 161.4822 Ops/s $\textbf{\color{#d91a1a}-20.43\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.3159ms 12.6453ms 79.0809 Ops/s 68.9656 Ops/s $\textbf{\color{#35bf28}+14.67\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.7147ms 1.6714ms 598.2980 Ops/s 700.7349 Ops/s $\textbf{\color{#d91a1a}-14.62\%}$

@vmoens vmoens merged commit 535bd63 into main Mar 6, 2024
46 of 65 checks passed
@vmoens vmoens deleted the fix-rb-cuda branch March 6, 2024 21:15
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 6, 2024

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1126s 0.1120s 8.9295 Ops/s 9.0385 Ops/s $\color{#d91a1a}-1.21\%$
test_sync 95.1408ms 94.8632ms 10.5415 Ops/s 10.4940 Ops/s $\color{#35bf28}+0.45\%$
test_async 0.1790s 90.6332ms 11.0335 Ops/s 11.0412 Ops/s $\color{#d91a1a}-0.07\%$
test_single_pixels 0.1233s 0.1227s 8.1482 Ops/s 8.2693 Ops/s $\color{#d91a1a}-1.46\%$
test_sync_pixels 82.0177ms 80.2426ms 12.4622 Ops/s 12.3238 Ops/s $\color{#35bf28}+1.12\%$
test_async_pixels 0.1462s 73.9480ms 13.5230 Ops/s 15.6720 Ops/s $\textbf{\color{#d91a1a}-13.71\%}$
test_simple 0.8729s 0.8149s 1.2271 Ops/s 1.2385 Ops/s $\color{#d91a1a}-0.92\%$
test_transformed 1.1002s 1.0409s 0.9607 Ops/s 0.9751 Ops/s $\color{#d91a1a}-1.47\%$
test_serial 2.4409s 2.3886s 0.4187 Ops/s 0.4279 Ops/s $\color{#d91a1a}-2.16\%$
test_parallel 2.1401s 2.0475s 0.4884 Ops/s 0.4894 Ops/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[True-True-True-True-True] 80.5110μs 32.7429μs 30.5410 KOps/s 31.1412 KOps/s $\color{#d91a1a}-1.93\%$
test_step_mdp_speed[True-True-True-True-False] 55.4410μs 19.4458μs 51.4249 KOps/s 51.8333 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-True-True-False-True] 45.4500μs 18.4311μs 54.2561 KOps/s 55.0737 KOps/s $\color{#d91a1a}-1.48\%$
test_step_mdp_speed[True-True-True-False-False] 34.6500μs 10.9311μs 91.4825 KOps/s 91.6479 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-True-False-True-True] 64.6710μs 34.5279μs 28.9621 KOps/s 29.4766 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-True-False-True-False] 47.0510μs 21.1225μs 47.3429 KOps/s 47.0019 KOps/s $\color{#35bf28}+0.73\%$
test_step_mdp_speed[True-True-False-False-True] 44.8110μs 20.1740μs 49.5689 KOps/s 49.7906 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[True-True-False-False-False] 34.3300μs 12.8566μs 77.7810 KOps/s 77.9298 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[True-False-True-True-True] 79.1100μs 36.2108μs 27.6161 KOps/s 27.4812 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[True-False-True-True-False] 56.0310μs 23.0388μs 43.4050 KOps/s 43.1687 KOps/s $\color{#35bf28}+0.55\%$
test_step_mdp_speed[True-False-True-False-True] 44.3100μs 20.1881μs 49.5342 KOps/s 50.0005 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[True-False-True-False-False] 43.1410μs 12.7599μs 78.3707 KOps/s 78.4939 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[True-False-False-True-True] 0.1063ms 38.0725μs 26.2657 KOps/s 26.5046 KOps/s $\color{#d91a1a}-0.90\%$
test_step_mdp_speed[True-False-False-True-False] 87.0110μs 24.8459μs 40.2480 KOps/s 40.2563 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[True-False-False-False-True] 48.7210μs 21.7764μs 45.9213 KOps/s 46.2753 KOps/s $\color{#d91a1a}-0.77\%$
test_step_mdp_speed[True-False-False-False-False] 40.9610μs 14.5702μs 68.6331 KOps/s 67.8661 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[False-True-True-True-True] 0.2135ms 36.1620μs 27.6534 KOps/s 27.6189 KOps/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[False-True-True-True-False] 70.7420μs 23.0997μs 43.2906 KOps/s 43.2835 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[False-True-True-False-True] 80.7420μs 24.4319μs 40.9301 KOps/s 41.1140 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-True-True-False-False] 43.3400μs 14.6144μs 68.4255 KOps/s 68.4057 KOps/s $\color{#35bf28}+0.03\%$
test_step_mdp_speed[False-True-False-True-True] 69.3910μs 38.5782μs 25.9213 KOps/s 25.8437 KOps/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[False-True-False-True-False] 49.8010μs 25.1037μs 39.8347 KOps/s 39.3816 KOps/s $\color{#35bf28}+1.15\%$
test_step_mdp_speed[False-True-False-False-True] 57.8810μs 25.9000μs 38.6101 KOps/s 38.4024 KOps/s $\color{#35bf28}+0.54\%$
test_step_mdp_speed[False-True-False-False-False] 38.7100μs 16.3890μs 61.0164 KOps/s 60.5201 KOps/s $\color{#35bf28}+0.82\%$
test_step_mdp_speed[False-False-True-True-True] 71.1520μs 40.0726μs 24.9547 KOps/s 25.2636 KOps/s $\color{#d91a1a}-1.22\%$
test_step_mdp_speed[False-False-True-True-False] 91.6320μs 27.0408μs 36.9811 KOps/s 37.1950 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[False-False-True-False-True] 59.2720μs 26.2449μs 38.1026 KOps/s 38.0600 KOps/s $\color{#35bf28}+0.11\%$
test_step_mdp_speed[False-False-True-False-False] 39.0900μs 16.3664μs 61.1006 KOps/s 60.3394 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[False-False-False-True-True] 69.4610μs 41.3925μs 24.1590 KOps/s 23.9716 KOps/s $\color{#35bf28}+0.78\%$
test_step_mdp_speed[False-False-False-True-False] 95.4320μs 28.7843μs 34.7412 KOps/s 34.7112 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-False-False-False-True] 57.2510μs 28.0577μs 35.6409 KOps/s 36.2130 KOps/s $\color{#d91a1a}-1.58\%$
test_step_mdp_speed[False-False-False-False-False] 40.0700μs 18.1816μs 55.0008 KOps/s 54.1890 KOps/s $\color{#35bf28}+1.50\%$
test_values[generalized_advantage_estimate-True-True] 26.0082ms 25.6552ms 38.9784 Ops/s 39.5505 Ops/s $\color{#d91a1a}-1.45\%$
test_values[vec_generalized_advantage_estimate-True-True] 81.7782ms 3.1990ms 312.5935 Ops/s 307.2718 Ops/s $\color{#35bf28}+1.73\%$
test_values[td0_return_estimate-False-False] 98.1020μs 66.5166μs 15.0338 KOps/s 15.6933 KOps/s $\color{#d91a1a}-4.20\%$
test_values[td1_return_estimate-False-False] 55.3356ms 54.5048ms 18.3470 Ops/s 18.7074 Ops/s $\color{#d91a1a}-1.93\%$
test_values[vec_td1_return_estimate-False-False] 2.0476ms 1.7657ms 566.3383 Ops/s 569.2458 Ops/s $\color{#d91a1a}-0.51\%$
test_values[td_lambda_return_estimate-True-False] 89.7574ms 86.4390ms 11.5688 Ops/s 11.8250 Ops/s $\color{#d91a1a}-2.17\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.0585ms 1.7545ms 569.9780 Ops/s 570.8599 Ops/s $\color{#d91a1a}-0.15\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.9800ms 24.2581ms 41.2234 Ops/s 42.3039 Ops/s $\color{#d91a1a}-2.55\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9137ms 0.6983ms 1.4320 KOps/s 1.4335 KOps/s $\color{#d91a1a}-0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7149ms 0.6435ms 1.5540 KOps/s 1.5525 KOps/s $\color{#35bf28}+0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4888ms 1.4495ms 689.9007 Ops/s 691.8780 Ops/s $\color{#d91a1a}-0.29\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9579ms 0.6641ms 1.5057 KOps/s 1.5122 KOps/s $\color{#d91a1a}-0.43\%$
test_dqn_speed 9.7174ms 1.4691ms 680.6688 Ops/s 639.4608 Ops/s $\textbf{\color{#35bf28}+6.44\%}$
test_ddpg_speed 2.9463ms 2.7727ms 360.6617 Ops/s 369.5872 Ops/s $\color{#d91a1a}-2.41\%$
test_sac_speed 8.5984ms 8.1628ms 122.5068 Ops/s 125.2874 Ops/s $\color{#d91a1a}-2.22\%$
test_redq_speed 12.1594ms 10.6764ms 93.6645 Ops/s 96.1248 Ops/s $\color{#d91a1a}-2.56\%$
test_redq_deprec_speed 12.0428ms 11.4168ms 87.5906 Ops/s 89.4737 Ops/s $\color{#d91a1a}-2.10\%$
test_td3_speed 8.2290ms 8.1008ms 123.4449 Ops/s 126.0407 Ops/s $\color{#d91a1a}-2.06\%$
test_cql_speed 27.7103ms 26.3312ms 37.9777 Ops/s 38.9797 Ops/s $\color{#d91a1a}-2.57\%$
test_a2c_speed 5.7903ms 5.5517ms 180.1251 Ops/s 179.4572 Ops/s $\color{#35bf28}+0.37\%$
test_ppo_speed 6.8177ms 5.9012ms 169.4563 Ops/s 169.5330 Ops/s $\color{#d91a1a}-0.05\%$
test_reinforce_speed 4.8332ms 4.5648ms 219.0700 Ops/s 219.5670 Ops/s $\color{#d91a1a}-0.23\%$
test_iql_speed 20.4948ms 19.7483ms 50.6373 Ops/s 49.8144 Ops/s $\color{#35bf28}+1.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9454ms 2.8587ms 349.8136 Ops/s 350.6930 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8025ms 0.5608ms 1.7833 KOps/s 1.7912 KOps/s $\color{#d91a1a}-0.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.3948ms 0.5494ms 1.8200 KOps/s 1.8538 KOps/s $\color{#d91a1a}-1.82\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1982ms 2.9352ms 340.6920 Ops/s 344.4204 Ops/s $\color{#d91a1a}-1.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7560ms 0.5478ms 1.8255 KOps/s 1.8103 KOps/s $\color{#35bf28}+0.84\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.4039ms 0.5381ms 1.8585 KOps/s 1.8753 KOps/s $\color{#d91a1a}-0.90\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6723ms 1.5878ms 629.8100 Ops/s 655.8712 Ops/s $\color{#d91a1a}-3.97\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6626ms 1.5246ms 655.9095 Ops/s 683.4929 Ops/s $\color{#d91a1a}-4.04\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.2017ms 3.0087ms 332.3709 Ops/s 333.7748 Ops/s $\color{#d91a1a}-0.42\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2573ms 0.6820ms 1.4662 KOps/s 1.4701 KOps/s $\color{#d91a1a}-0.27\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8038ms 0.6624ms 1.5098 KOps/s 1.5004 KOps/s $\color{#35bf28}+0.62\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0420ms 2.8733ms 348.0316 Ops/s 350.1720 Ops/s $\color{#d91a1a}-0.61\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6653ms 0.5542ms 1.8044 KOps/s 1.8103 KOps/s $\color{#d91a1a}-0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8074ms 0.5390ms 1.8554 KOps/s 1.4794 KOps/s $\textbf{\color{#35bf28}+25.41\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0921ms 2.9181ms 342.6892 Ops/s 343.8423 Ops/s $\color{#d91a1a}-0.34\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7148ms 0.5549ms 1.8022 KOps/s 1.8193 KOps/s $\color{#d91a1a}-0.94\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8552ms 0.5345ms 1.8708 KOps/s 1.8537 KOps/s $\color{#35bf28}+0.93\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.2486ms 3.0062ms 332.6507 Ops/s 332.7203 Ops/s $\color{#d91a1a}-0.02\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3700ms 0.6835ms 1.4632 KOps/s 1.4733 KOps/s $\color{#d91a1a}-0.69\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9447ms 0.6653ms 1.5030 KOps/s 1.2506 KOps/s $\textbf{\color{#35bf28}+20.19\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1154s 9.1140ms 109.7212 Ops/s 147.7929 Ops/s $\textbf{\color{#d91a1a}-25.76\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.9849ms 14.7593ms 67.7541 Ops/s 67.3743 Ops/s $\color{#35bf28}+0.56\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.4194ms 1.1555ms 865.4051 Ops/s 906.7586 Ops/s $\color{#d91a1a}-4.56\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1038s 8.8056ms 113.5640 Ops/s 114.8954 Ops/s $\color{#d91a1a}-1.16\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.1511ms 14.7594ms 67.7534 Ops/s 67.9409 Ops/s $\color{#d91a1a}-0.28\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.1441ms 1.1339ms 881.9469 Ops/s 905.3693 Ops/s $\color{#d91a1a}-2.59\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1067s 7.2890ms 137.1932 Ops/s 138.7791 Ops/s $\color{#d91a1a}-1.14\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.3462ms 15.2350ms 65.6384 Ops/s 66.7737 Ops/s $\color{#d91a1a}-1.70\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.5227ms 1.4813ms 675.0712 Ops/s 686.6763 Ops/s $\color{#d91a1a}-1.69\%$

vmoens added a commit that referenced this pull request Mar 25, 2024
@vmoens
[BugFix] SliceSampler device and index mesh (#1996)
d17e3fc 
(cherry picked from commit 535bd63)
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
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

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