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] Call contiguous on rollout results in TestMultiStepTransform #2025

Merged
merged 1 commit into from
Mar 20, 2024
Merged

[BugFix] Call contiguous on rollout results in TestMultiStepTransform #2025

merged 1 commit into from
Mar 20, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Mar 20, 2024

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Mar 20, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2025

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

❌ 2 New Failures

As of commit 7a53f57 with merge base 9747170 (image):

NEW FAILURES - The following jobs have failed:

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 20, 2024
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 56.6619ms 55.5361ms 18.0063 Ops/s 17.2763 Ops/s $\color{#35bf28}+4.23\%$
test_sync 43.9910ms 31.0555ms 32.2004 Ops/s 31.8106 Ops/s $\color{#35bf28}+1.23\%$
test_async 72.7914ms 28.7727ms 34.7552 Ops/s 33.5962 Ops/s $\color{#35bf28}+3.45\%$
test_simple 0.4159s 0.3517s 2.8435 Ops/s 3.0401 Ops/s $\textbf{\color{#d91a1a}-6.47\%}$
test_transformed 0.4777s 0.4749s 2.1058 Ops/s 2.0883 Ops/s $\color{#35bf28}+0.84\%$
test_serial 1.2511s 1.1947s 0.8370 Ops/s 0.8384 Ops/s $\color{#d91a1a}-0.17\%$
test_parallel 1.1071s 1.0604s 0.9430 Ops/s 0.9519 Ops/s $\color{#d91a1a}-0.94\%$
test_step_mdp_speed[True-True-True-True-True] 0.2637ms 21.0645μs 47.4731 KOps/s 47.2442 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[True-True-True-True-False] 46.9670μs 12.7634μs 78.3491 KOps/s 76.7450 KOps/s $\color{#35bf28}+2.09\%$
test_step_mdp_speed[True-True-True-False-True] 37.2890μs 12.4690μs 80.1987 KOps/s 79.8558 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[True-True-True-False-False] 26.4390μs 7.4276μs 134.6332 KOps/s 131.2825 KOps/s $\color{#35bf28}+2.55\%$
test_step_mdp_speed[True-True-False-True-True] 72.8950μs 22.5179μs 44.4091 KOps/s 44.4112 KOps/s $-0.00\%$
test_step_mdp_speed[True-True-False-True-False] 37.9300μs 14.0210μs 71.3216 KOps/s 70.6120 KOps/s $\color{#35bf28}+1.00\%$
test_step_mdp_speed[True-True-False-False-True] 55.9040μs 13.6008μs 73.5252 KOps/s 73.2080 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[True-True-False-False-False] 26.3090μs 8.6664μs 115.3881 KOps/s 113.5835 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-False-True-True-True] 61.1740μs 23.7742μs 42.0623 KOps/s 41.5611 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[True-False-True-True-False] 43.5100μs 15.4562μs 64.6990 KOps/s 64.3716 KOps/s $\color{#35bf28}+0.51\%$
test_step_mdp_speed[True-False-True-False-True] 35.6760μs 13.5266μs 73.9286 KOps/s 73.7984 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[True-False-True-False-False] 42.8800μs 8.6548μs 115.5424 KOps/s 114.0213 KOps/s $\color{#35bf28}+1.33\%$
test_step_mdp_speed[True-False-False-True-True] 59.5500μs 24.7646μs 40.3802 KOps/s 40.2417 KOps/s $\color{#35bf28}+0.34\%$
test_step_mdp_speed[True-False-False-True-False] 41.9980μs 16.5244μs 60.5166 KOps/s 60.6521 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-False-False-False-True] 43.3900μs 14.6647μs 68.1910 KOps/s 68.1992 KOps/s $\color{#d91a1a}-0.01\%$
test_step_mdp_speed[True-False-False-False-False] 45.7950μs 9.8471μs 101.5528 KOps/s 101.2639 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[False-True-True-True-True] 49.7220μs 23.6367μs 42.3072 KOps/s 41.9397 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[False-True-True-True-False] 59.1090μs 15.5067μs 64.4882 KOps/s 63.9356 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[False-True-True-False-True] 33.8430μs 15.7488μs 63.4968 KOps/s 62.9406 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[False-True-True-False-False] 33.2220μs 9.9371μs 100.6330 KOps/s 100.7929 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[False-True-False-True-True] 63.2770μs 25.5909μs 39.0763 KOps/s 39.4544 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[False-True-False-True-False] 43.3900μs 16.6102μs 60.2041 KOps/s 59.5558 KOps/s $\color{#35bf28}+1.09\%$
test_step_mdp_speed[False-True-False-False-True] 57.1960μs 16.8949μs 59.1896 KOps/s 58.3723 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[False-True-False-False-False] 29.1440μs 11.2409μs 88.9609 KOps/s 89.6392 KOps/s $\color{#d91a1a}-0.76\%$
test_step_mdp_speed[False-False-True-True-True] 57.1660μs 26.0622μs 38.3698 KOps/s 38.1528 KOps/s $\color{#35bf28}+0.57\%$
test_step_mdp_speed[False-False-True-True-False] 46.3760μs 17.9862μs 55.5980 KOps/s 55.8982 KOps/s $\color{#d91a1a}-0.54\%$
test_step_mdp_speed[False-False-True-False-True] 51.0950μs 16.8000μs 59.5239 KOps/s 59.3498 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[False-False-True-False-False] 36.4380μs 11.1652μs 89.5641 KOps/s 89.7231 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[False-False-False-True-True] 59.1090μs 27.2107μs 36.7502 KOps/s 37.0140 KOps/s $\color{#d91a1a}-0.71\%$
test_step_mdp_speed[False-False-False-True-False] 68.8380μs 18.8339μs 53.0957 KOps/s 52.7721 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[False-False-False-False-True] 50.0830μs 17.7173μs 56.4421 KOps/s 54.9624 KOps/s $\color{#35bf28}+2.69\%$
test_step_mdp_speed[False-False-False-False-False] 41.6770μs 12.0393μs 83.0616 KOps/s 82.5822 KOps/s $\color{#35bf28}+0.58\%$
test_values[generalized_advantage_estimate-True-True] 12.1472ms 9.2888ms 107.6564 Ops/s 108.8071 Ops/s $\color{#d91a1a}-1.06\%$
test_values[vec_generalized_advantage_estimate-True-True] 35.9805ms 33.4959ms 29.8544 Ops/s 28.0464 Ops/s $\textbf{\color{#35bf28}+6.45\%}$
test_values[td0_return_estimate-False-False] 0.2480ms 0.1884ms 5.3091 KOps/s 5.4552 KOps/s $\color{#d91a1a}-2.68\%$
test_values[td1_return_estimate-False-False] 26.1859ms 23.0824ms 43.3230 Ops/s 42.9402 Ops/s $\color{#35bf28}+0.89\%$
test_values[vec_td1_return_estimate-False-False] 35.3786ms 33.6669ms 29.7028 Ops/s 28.0219 Ops/s $\textbf{\color{#35bf28}+6.00\%}$
test_values[td_lambda_return_estimate-True-False] 33.8930ms 33.2056ms 30.1154 Ops/s 29.9089 Ops/s $\color{#35bf28}+0.69\%$
test_values[vec_td_lambda_return_estimate-True-False] 47.0925ms 34.3422ms 29.1187 Ops/s 27.5808 Ops/s $\textbf{\color{#35bf28}+5.58\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.4241ms 8.1416ms 122.8255 Ops/s 124.9602 Ops/s $\color{#d91a1a}-1.71\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4963ms 2.0523ms 487.2501 Ops/s 510.4503 Ops/s $\color{#d91a1a}-4.55\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6326ms 0.3538ms 2.8268 KOps/s 2.8936 KOps/s $\color{#d91a1a}-2.31\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.7844ms 45.8196ms 21.8247 Ops/s 21.1260 Ops/s $\color{#35bf28}+3.31\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8318ms 3.0541ms 327.4333 Ops/s 328.8089 Ops/s $\color{#d91a1a}-0.42\%$
test_dqn_speed 1.5719ms 1.3762ms 726.6376 Ops/s 739.7155 Ops/s $\color{#d91a1a}-1.77\%$
test_ddpg_speed 3.4064ms 2.7170ms 368.0528 Ops/s 373.3620 Ops/s $\color{#d91a1a}-1.42\%$
test_sac_speed 8.9653ms 8.3425ms 119.8686 Ops/s 120.5791 Ops/s $\color{#d91a1a}-0.59\%$
test_redq_speed 15.5410ms 13.5182ms 73.9745 Ops/s 73.6713 Ops/s $\color{#35bf28}+0.41\%$
test_redq_deprec_speed 14.1531ms 13.4171ms 74.5318 Ops/s 73.3456 Ops/s $\color{#35bf28}+1.62\%$
test_td3_speed 10.7946ms 8.3783ms 119.3553 Ops/s 120.4115 Ops/s $\color{#d91a1a}-0.88\%$
test_cql_speed 37.8524ms 36.5591ms 27.3530 Ops/s 27.3048 Ops/s $\color{#35bf28}+0.18\%$
test_a2c_speed 84.5763ms 8.1365ms 122.9029 Ops/s 130.7723 Ops/s $\textbf{\color{#d91a1a}-6.02\%}$
test_ppo_speed 8.7209ms 7.9570ms 125.6755 Ops/s 125.2205 Ops/s $\color{#35bf28}+0.36\%$
test_reinforce_speed 7.5720ms 6.7231ms 148.7418 Ops/s 147.2116 Ops/s $\color{#35bf28}+1.04\%$
test_iql_speed 33.6109ms 32.6462ms 30.6315 Ops/s 30.0008 Ops/s $\color{#35bf28}+2.10\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3277ms 2.2173ms 451.0002 Ops/s 416.2244 Ops/s $\textbf{\color{#35bf28}+8.36\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8568ms 0.4994ms 2.0023 KOps/s 1.7389 KOps/s $\textbf{\color{#35bf28}+15.15\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6520ms 0.4685ms 2.1346 KOps/s 2.0824 KOps/s $\color{#35bf28}+2.51\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.7419ms 2.3550ms 424.6276 Ops/s 401.7451 Ops/s $\textbf{\color{#35bf28}+5.70\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9031ms 0.4863ms 2.0562 KOps/s 2.0154 KOps/s $\color{#35bf28}+2.02\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7703ms 0.4743ms 2.1084 KOps/s 2.0986 KOps/s $\color{#35bf28}+0.47\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.9162ms 1.3046ms 766.5136 Ops/s 781.1006 Ops/s $\color{#d91a1a}-1.87\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4212ms 1.2316ms 811.9645 Ops/s 826.9726 Ops/s $\color{#d91a1a}-1.81\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.8708ms 2.4152ms 414.0483 Ops/s 392.9853 Ops/s $\textbf{\color{#35bf28}+5.36\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0348ms 0.6137ms 1.6294 KOps/s 1.6245 KOps/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.1049s 0.6697ms 1.4933 KOps/s 1.7005 KOps/s $\textbf{\color{#d91a1a}-12.18\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.4340ms 2.2191ms 450.6331 Ops/s 416.4787 Ops/s $\textbf{\color{#35bf28}+8.20\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5874ms 0.4949ms 2.0206 KOps/s 1.9729 KOps/s $\color{#35bf28}+2.42\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.8509ms 0.4827ms 2.0716 KOps/s 2.0539 KOps/s $\color{#35bf28}+0.86\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.5763ms 2.2208ms 450.2813 Ops/s 410.1990 Ops/s $\textbf{\color{#35bf28}+9.77\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 96.0575ms 0.6317ms 1.5831 KOps/s 2.0261 KOps/s $\textbf{\color{#d91a1a}-21.86\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6449ms 0.4679ms 2.1371 KOps/s 2.0663 KOps/s $\color{#35bf28}+3.43\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4983ms 2.3348ms 428.3013 Ops/s 398.0040 Ops/s $\textbf{\color{#35bf28}+7.61\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9166ms 0.6169ms 1.6210 KOps/s 1.6253 KOps/s $\color{#d91a1a}-0.26\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 3.8521ms 0.5917ms 1.6901 KOps/s 1.6618 KOps/s $\color{#35bf28}+1.70\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 96.5178ms 7.2581ms 137.7770 Ops/s 127.7232 Ops/s $\textbf{\color{#35bf28}+7.87\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.6702ms 12.1687ms 82.1778 Ops/s 81.2938 Ops/s $\color{#35bf28}+1.09\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.4999ms 1.0313ms 969.6826 Ops/s 964.4394 Ops/s $\color{#35bf28}+0.54\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 94.0899ms 7.2040ms 138.8125 Ops/s 133.3626 Ops/s $\color{#35bf28}+4.09\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.7943ms 11.9648ms 83.5786 Ops/s 82.5912 Ops/s $\color{#35bf28}+1.20\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.4882ms 1.0233ms 977.2633 Ops/s 970.7460 Ops/s $\color{#35bf28}+0.67\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 97.7282ms 5.9745ms 167.3769 Ops/s 169.5080 Ops/s $\color{#d91a1a}-1.26\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.0547ms 12.3583ms 80.9175 Ops/s 68.7102 Ops/s $\textbf{\color{#35bf28}+17.77\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.0391ms 1.3415ms 745.4150 Ops/s 725.9782 Ops/s $\color{#35bf28}+2.68\%$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}6$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 93.2344ms 92.6323ms 10.7954 Ops/s 10.7652 Ops/s $\color{#35bf28}+0.28\%$
test_sync 84.5017ms 84.0175ms 11.9023 Ops/s 11.9680 Ops/s $\color{#d91a1a}-0.55\%$
test_async 0.1562s 68.1781ms 14.6675 Ops/s 14.5606 Ops/s $\color{#35bf28}+0.73\%$
test_single_pixels 0.1048s 0.1039s 9.6253 Ops/s 9.6407 Ops/s $\color{#d91a1a}-0.16\%$
test_sync_pixels 64.1432ms 63.5209ms 15.7429 Ops/s 15.5278 Ops/s $\color{#35bf28}+1.38\%$
test_async_pixels 0.1115s 54.0699ms 18.4946 Ops/s 18.5341 Ops/s $\color{#d91a1a}-0.21\%$
test_simple 0.6272s 0.6126s 1.6323 Ops/s 1.5942 Ops/s $\color{#35bf28}+2.39\%$
test_transformed 0.8633s 0.8104s 1.2340 Ops/s 1.2279 Ops/s $\color{#35bf28}+0.49\%$
test_serial 1.9974s 1.9305s 0.5180 Ops/s 0.5215 Ops/s $\color{#d91a1a}-0.67\%$
test_parallel 1.7476s 1.7028s 0.5873 Ops/s 0.5807 Ops/s $\color{#35bf28}+1.14\%$
test_step_mdp_speed[True-True-True-True-True] 58.5510μs 25.2067μs 39.6719 KOps/s 37.8809 KOps/s $\color{#35bf28}+4.73\%$
test_step_mdp_speed[True-True-True-True-False] 33.8710μs 15.7217μs 63.6064 KOps/s 62.2553 KOps/s $\color{#35bf28}+2.17\%$
test_step_mdp_speed[True-True-True-False-True] 35.3600μs 14.5803μs 68.5859 KOps/s 66.3966 KOps/s $\color{#35bf28}+3.30\%$
test_step_mdp_speed[True-True-True-False-False] 35.7500μs 8.9842μs 111.3069 KOps/s 107.2203 KOps/s $\color{#35bf28}+3.81\%$
test_step_mdp_speed[True-True-False-True-True] 43.4710μs 26.9366μs 37.1243 KOps/s 35.8383 KOps/s $\color{#35bf28}+3.59\%$
test_step_mdp_speed[True-True-False-True-False] 42.4200μs 17.1647μs 58.2592 KOps/s 56.9458 KOps/s $\color{#35bf28}+2.31\%$
test_step_mdp_speed[True-True-False-False-True] 33.7200μs 16.2101μs 61.6900 KOps/s 60.3666 KOps/s $\color{#35bf28}+2.19\%$
test_step_mdp_speed[True-True-False-False-False] 26.2200μs 10.4874μs 95.3526 KOps/s 92.3359 KOps/s $\color{#35bf28}+3.27\%$
test_step_mdp_speed[True-False-True-True-True] 55.5610μs 28.4935μs 35.0957 KOps/s 34.4525 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[True-False-True-True-False] 33.3810μs 18.7382μs 53.3671 KOps/s 52.2977 KOps/s $\color{#35bf28}+2.04\%$
test_step_mdp_speed[True-False-True-False-True] 32.0500μs 16.0279μs 62.3914 KOps/s 59.5713 KOps/s $\color{#35bf28}+4.73\%$
test_step_mdp_speed[True-False-True-False-False] 34.5510μs 10.4629μs 95.5759 KOps/s 91.8414 KOps/s $\color{#35bf28}+4.07\%$
test_step_mdp_speed[True-False-False-True-True] 50.2310μs 29.9069μs 33.4371 KOps/s 32.3254 KOps/s $\color{#35bf28}+3.44\%$
test_step_mdp_speed[True-False-False-True-False] 37.0200μs 20.1662μs 49.5879 KOps/s 47.8096 KOps/s $\color{#35bf28}+3.72\%$
test_step_mdp_speed[True-False-False-False-True] 36.4200μs 17.4421μs 57.3327 KOps/s 56.0089 KOps/s $\color{#35bf28}+2.36\%$
test_step_mdp_speed[True-False-False-False-False] 50.6900μs 11.9578μs 83.6275 KOps/s 79.6188 KOps/s $\textbf{\color{#35bf28}+5.03\%}$
test_step_mdp_speed[False-True-True-True-True] 47.2410μs 28.3940μs 35.2187 KOps/s 34.1682 KOps/s $\color{#35bf28}+3.07\%$
test_step_mdp_speed[False-True-True-True-False] 43.4800μs 18.7898μs 53.2203 KOps/s 52.6853 KOps/s $\color{#35bf28}+1.02\%$
test_step_mdp_speed[False-True-True-False-True] 53.7310μs 19.6856μs 50.7985 KOps/s 50.2490 KOps/s $\color{#35bf28}+1.09\%$
test_step_mdp_speed[False-True-True-False-False] 28.5500μs 11.9491μs 83.6883 KOps/s 80.5594 KOps/s $\color{#35bf28}+3.88\%$
test_step_mdp_speed[False-True-False-True-True] 48.3510μs 30.2149μs 33.0963 KOps/s 33.0683 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[False-True-False-True-False] 37.0910μs 20.4446μs 48.9128 KOps/s 47.9445 KOps/s $\color{#35bf28}+2.02\%$
test_step_mdp_speed[False-True-False-False-True] 36.2400μs 20.1433μs 49.6442 KOps/s 46.8555 KOps/s $\textbf{\color{#35bf28}+5.95\%}$
test_step_mdp_speed[False-True-False-False-False] 38.0910μs 13.4650μs 74.2665 KOps/s 72.0324 KOps/s $\color{#35bf28}+3.10\%$
test_step_mdp_speed[False-False-True-True-True] 47.5510μs 31.4814μs 31.7648 KOps/s 31.3859 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[False-False-True-True-False] 38.6600μs 22.0335μs 45.3854 KOps/s 44.9020 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[False-False-True-False-True] 34.5900μs 20.1834μs 49.5457 KOps/s 47.0864 KOps/s $\textbf{\color{#35bf28}+5.22\%}$
test_step_mdp_speed[False-False-True-False-False] 32.0900μs 13.5544μs 73.7770 KOps/s 71.1356 KOps/s $\color{#35bf28}+3.71\%$
test_step_mdp_speed[False-False-False-True-True] 48.9100μs 32.9641μs 30.3360 KOps/s 29.3691 KOps/s $\color{#35bf28}+3.29\%$
test_step_mdp_speed[False-False-False-True-False] 47.5300μs 23.3293μs 42.8645 KOps/s 41.1370 KOps/s $\color{#35bf28}+4.20\%$
test_step_mdp_speed[False-False-False-False-True] 36.4300μs 21.8334μs 45.8013 KOps/s 44.4996 KOps/s $\color{#35bf28}+2.93\%$
test_step_mdp_speed[False-False-False-False-False] 30.6600μs 15.0627μs 66.3890 KOps/s 64.9828 KOps/s $\color{#35bf28}+2.16\%$
test_values[generalized_advantage_estimate-True-True] 23.2371ms 22.3896ms 44.6636 Ops/s 43.1937 Ops/s $\color{#35bf28}+3.40\%$
test_values[vec_generalized_advantage_estimate-True-True] 84.4099ms 3.2303ms 309.5679 Ops/s 300.9314 Ops/s $\color{#35bf28}+2.87\%$
test_values[td0_return_estimate-False-False] 97.6610μs 58.1805μs 17.1879 KOps/s 17.0393 KOps/s $\color{#35bf28}+0.87\%$
test_values[td1_return_estimate-False-False] 50.6510ms 47.9036ms 20.8753 Ops/s 20.4892 Ops/s $\color{#35bf28}+1.88\%$
test_values[vec_td1_return_estimate-False-False] 2.0684ms 1.7207ms 581.1723 Ops/s 578.6049 Ops/s $\color{#35bf28}+0.44\%$
test_values[td_lambda_return_estimate-True-False] 78.8529ms 76.8419ms 13.0137 Ops/s 12.7942 Ops/s $\color{#35bf28}+1.72\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.0656ms 1.7152ms 583.0298 Ops/s 581.1917 Ops/s $\color{#35bf28}+0.32\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 21.1044ms 20.7859ms 48.1096 Ops/s 47.0026 Ops/s $\color{#35bf28}+2.36\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8576ms 0.6410ms 1.5601 KOps/s 1.5293 KOps/s $\color{#35bf28}+2.01\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6835ms 0.6066ms 1.6484 KOps/s 1.6324 KOps/s $\color{#35bf28}+0.98\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5546ms 1.4121ms 708.1846 Ops/s 708.3713 Ops/s $\color{#d91a1a}-0.03\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9019ms 0.6247ms 1.6006 KOps/s 1.5968 KOps/s $\color{#35bf28}+0.24\%$
test_dqn_speed 9.2618ms 1.2750ms 784.3416 Ops/s 786.8084 Ops/s $\color{#d91a1a}-0.31\%$
test_ddpg_speed 2.6967ms 2.4113ms 414.7160 Ops/s 410.4974 Ops/s $\color{#35bf28}+1.03\%$
test_sac_speed 7.6410ms 7.1879ms 139.1223 Ops/s 136.2460 Ops/s $\color{#35bf28}+2.11\%$
test_redq_speed 10.4316ms 9.4518ms 105.8004 Ops/s 103.9733 Ops/s $\color{#35bf28}+1.76\%$
test_redq_deprec_speed 11.0086ms 10.4439ms 95.7498 Ops/s 94.7274 Ops/s $\color{#35bf28}+1.08\%$
test_td3_speed 7.1992ms 7.1401ms 140.0550 Ops/s 136.5330 Ops/s $\color{#35bf28}+2.58\%$
test_cql_speed 24.4943ms 23.8419ms 41.9430 Ops/s 41.6250 Ops/s $\color{#35bf28}+0.76\%$
test_a2c_speed 5.5524ms 5.3473ms 187.0104 Ops/s 186.9396 Ops/s $\color{#35bf28}+0.04\%$
test_ppo_speed 5.9504ms 5.6603ms 176.6686 Ops/s 175.4454 Ops/s $\color{#35bf28}+0.70\%$
test_reinforce_speed 82.9314ms 4.6182ms 216.5344 Ops/s 229.9032 Ops/s $\textbf{\color{#d91a1a}-5.81\%}$
test_iql_speed 19.3146ms 18.4503ms 54.1998 Ops/s 48.1001 Ops/s $\textbf{\color{#35bf28}+12.68\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.6262ms 2.4697ms 404.9073 Ops/s 405.2167 Ops/s $\color{#d91a1a}-0.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7050ms 0.5110ms 1.9568 KOps/s 1.9233 KOps/s $\color{#35bf28}+1.74\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6927ms 0.4909ms 2.0369 KOps/s 1.9687 KOps/s $\color{#35bf28}+3.47\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.7218ms 2.4946ms 400.8718 Ops/s 394.8225 Ops/s $\color{#35bf28}+1.53\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6445ms 0.5044ms 1.9827 KOps/s 1.9367 KOps/s $\color{#35bf28}+2.37\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.5199ms 0.4900ms 2.0409 KOps/s 1.9879 KOps/s $\color{#35bf28}+2.67\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6486ms 1.4113ms 708.5823 Ops/s 707.8614 Ops/s $\color{#35bf28}+0.10\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5214ms 1.3332ms 750.0514 Ops/s 740.1974 Ops/s $\color{#35bf28}+1.33\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.7703ms 2.5997ms 384.6597 Ops/s 383.5063 Ops/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1997ms 0.6265ms 1.5962 KOps/s 1.5779 KOps/s $\color{#35bf28}+1.16\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8317ms 0.6071ms 1.6472 KOps/s 1.6293 KOps/s $\color{#35bf28}+1.10\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.6298ms 2.4642ms 405.8101 Ops/s 403.2420 Ops/s $\color{#35bf28}+0.64\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0816ms 0.5138ms 1.9463 KOps/s 1.9444 KOps/s $\color{#35bf28}+0.10\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6427ms 0.4944ms 2.0226 KOps/s 2.0114 KOps/s $\color{#35bf28}+0.56\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.7270ms 2.4879ms 401.9533 Ops/s 397.9534 Ops/s $\color{#35bf28}+1.01\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6620ms 0.5092ms 1.9639 KOps/s 1.9629 KOps/s $\color{#35bf28}+0.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.1062s 0.6247ms 1.6008 KOps/s 2.0052 KOps/s $\textbf{\color{#d91a1a}-20.17\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.8333ms 2.6224ms 381.3322 Ops/s 381.8014 Ops/s $\color{#d91a1a}-0.12\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3635ms 0.6353ms 1.5740 KOps/s 1.5834 KOps/s $\color{#d91a1a}-0.59\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7961ms 0.6146ms 1.6271 KOps/s 1.6366 KOps/s $\color{#d91a1a}-0.58\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1071s 8.4695ms 118.0702 Ops/s 154.8200 Ops/s $\textbf{\color{#d91a1a}-23.74\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.4479ms 11.9980ms 83.3470 Ops/s 83.5624 Ops/s $\color{#d91a1a}-0.26\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0382ms 1.0386ms 962.8134 Ops/s 947.5966 Ops/s $\color{#35bf28}+1.61\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1030s 6.4008ms 156.2294 Ops/s 122.2593 Ops/s $\textbf{\color{#35bf28}+27.79\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.5622ms 11.9895ms 83.4067 Ops/s 83.4242 Ops/s $\color{#d91a1a}-0.02\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.9118ms 1.1634ms 859.5467 Ops/s 954.8207 Ops/s $\textbf{\color{#d91a1a}-9.98\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1019s 8.5632ms 116.7791 Ops/s 151.6928 Ops/s $\textbf{\color{#d91a1a}-23.02\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 14.6045ms 12.2940ms 81.3406 Ops/s 81.3760 Ops/s $\color{#d91a1a}-0.04\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.2668ms 1.4947ms 669.0163 Ops/s 293.3783 Ops/s $\textbf{\color{#35bf28}+128.04\%}$

@vmoens vmoens added bug Something isn't working Tests Incomplete or broken unit tests labels Mar 20, 2024
@vmoens vmoens merged commit d937478 into main Mar 20, 2024
65 of 67 checks passed
@vmoens vmoens deleted the contiguous-call-multiaction-test branch March 20, 2024 10:14
vmoens added a commit that referenced this pull request Apr 7, 2024
@vmoens
[BugFix] Call contiguous on rollout results in TestMultiStepTransform (…
b2fbbe6 
…#2025)

(cherry picked from commit d937478)
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. Tests Incomplete or broken unit tests
Projects
None yet
Milestone
No milestone
Development

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