Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] inline hold_out_net #2498

Merged
merged 1 commit into from
Oct 17, 2024
Merged

[Feature] inline hold_out_net #2498

merged 1 commit into from
Oct 17, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Oct 17, 2024

Stack from ghstack (oldest at bottom):

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Oct 17, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2498

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

❌ 1 New Failure, 6 Unrelated Failures

As of commit ad3c280 with merge base d894358 (image):

NEW FAILURE - The following job has failed:

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

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

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

vmoens added a commit that referenced this pull request Oct 17, 2024
ghstack-source-id: c315202c8af55f0852195fe488ae855966386c4c
Pull Request resolved: #2498
@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 Oct 17, 2024
Copy link

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

Total Benchmarks: 143. 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_simple 0.4161s 0.4141s 2.4147 Ops/s 2.3688 Ops/s $\color{#35bf28}+1.94\%$
test_transformed 0.6879s 0.6011s 1.6637 Ops/s 1.6592 Ops/s $\color{#35bf28}+0.27\%$
test_serial 1.4212s 1.3399s 0.7463 Ops/s 0.7247 Ops/s $\color{#35bf28}+2.98\%$
test_parallel 1.3335s 1.3172s 0.7592 Ops/s 0.7421 Ops/s $\color{#35bf28}+2.31\%$
test_step_mdp_speed[True-True-True-True-True] 0.1370ms 29.5487μs 33.8425 KOps/s 34.0146 KOps/s $\color{#d91a1a}-0.51\%$
test_step_mdp_speed[True-True-True-True-False] 38.4420μs 17.5742μs 56.9017 KOps/s 57.9243 KOps/s $\color{#d91a1a}-1.77\%$
test_step_mdp_speed[True-True-True-False-True] 85.4490μs 16.3319μs 61.2299 KOps/s 60.6336 KOps/s $\color{#35bf28}+0.98\%$
test_step_mdp_speed[True-True-True-False-False] 38.4320μs 9.6987μs 103.1063 KOps/s 103.7778 KOps/s $\color{#d91a1a}-0.65\%$
test_step_mdp_speed[True-True-False-True-True] 0.1086ms 31.9378μs 31.3108 KOps/s 31.4405 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[True-True-False-True-False] 54.5510μs 19.8639μs 50.3427 KOps/s 51.3155 KOps/s $\color{#d91a1a}-1.90\%$
test_step_mdp_speed[True-True-False-False-True] 80.5100μs 18.6509μs 53.6168 KOps/s 53.6234 KOps/s $\color{#d91a1a}-0.01\%$
test_step_mdp_speed[True-True-False-False-False] 40.3040μs 11.8236μs 84.5768 KOps/s 84.3091 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-False-True-True-True] 89.6770μs 33.8693μs 29.5253 KOps/s 29.7798 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[True-False-True-True-False] 0.6267ms 22.0321μs 45.3883 KOps/s 45.9209 KOps/s $\color{#d91a1a}-1.16\%$
test_step_mdp_speed[True-False-True-False-True] 73.2960μs 18.6115μs 53.7301 KOps/s 54.1938 KOps/s $\color{#d91a1a}-0.86\%$
test_step_mdp_speed[True-False-True-False-False] 55.5130μs 11.6160μs 86.0878 KOps/s 84.8315 KOps/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[True-False-False-True-True] 0.1083ms 35.6226μs 28.0720 KOps/s 28.0541 KOps/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[True-False-False-True-False] 76.4320μs 24.0214μs 41.6296 KOps/s 42.2307 KOps/s $\color{#d91a1a}-1.42\%$
test_step_mdp_speed[True-False-False-False-True] 64.9710μs 20.4367μs 48.9315 KOps/s 48.8602 KOps/s $\color{#35bf28}+0.15\%$
test_step_mdp_speed[True-False-False-False-False] 76.2520μs 13.8051μs 72.4368 KOps/s 72.6486 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[False-True-True-True-True] 70.9020μs 33.8871μs 29.5098 KOps/s 29.6427 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-True-True-True-False] 77.3440μs 21.8068μs 45.8573 KOps/s 45.7035 KOps/s $\color{#35bf28}+0.34\%$
test_step_mdp_speed[False-True-True-False-True] 55.1030μs 21.5545μs 46.3939 KOps/s 45.1379 KOps/s $\color{#35bf28}+2.78\%$
test_step_mdp_speed[False-True-True-False-False] 66.9940μs 13.5153μs 73.9902 KOps/s 73.3821 KOps/s $\color{#35bf28}+0.83\%$
test_step_mdp_speed[False-True-False-True-True] 74.1170μs 35.8371μs 27.9041 KOps/s 28.0263 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[False-True-False-True-False] 77.1630μs 23.9103μs 41.8230 KOps/s 42.2790 KOps/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[False-True-False-False-True] 3.1575ms 23.9094μs 41.8245 KOps/s 41.8241 KOps/s $+0.00\%$
test_step_mdp_speed[False-True-False-False-False] 83.3350μs 15.6830μs 63.7631 KOps/s 64.1145 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[False-False-True-True-True] 85.1080μs 38.0172μs 26.3039 KOps/s 26.6491 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-False-True-True-False] 59.2100μs 26.1302μs 38.2699 KOps/s 38.5179 KOps/s $\color{#d91a1a}-0.64\%$
test_step_mdp_speed[False-False-True-False-True] 73.5060μs 24.3494μs 41.0688 KOps/s 42.5057 KOps/s $\color{#d91a1a}-3.38\%$
test_step_mdp_speed[False-False-True-False-False] 45.0940μs 15.5531μs 64.2960 KOps/s 63.9905 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[False-False-False-True-True] 0.6725ms 39.7733μs 25.1425 KOps/s 25.3002 KOps/s $\color{#d91a1a}-0.62\%$
test_step_mdp_speed[False-False-False-True-False] 99.4510μs 27.5801μs 36.2580 KOps/s 35.9196 KOps/s $\color{#35bf28}+0.94\%$
test_step_mdp_speed[False-False-False-False-True] 64.9200μs 24.8980μs 40.1639 KOps/s 38.7231 KOps/s $\color{#35bf28}+3.72\%$
test_step_mdp_speed[False-False-False-False-False] 53.9610μs 17.2201μs 58.0716 KOps/s 56.8088 KOps/s $\color{#35bf28}+2.22\%$
test_values[generalized_advantage_estimate-True-True] 10.4963ms 9.4298ms 106.0472 Ops/s 104.0753 Ops/s $\color{#35bf28}+1.89\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.4737ms 33.6656ms 29.7039 Ops/s 29.6545 Ops/s $\color{#35bf28}+0.17\%$
test_values[td0_return_estimate-False-False] 0.3599ms 0.1997ms 5.0087 KOps/s 5.8200 KOps/s $\textbf{\color{#d91a1a}-13.94\%}$
test_values[td1_return_estimate-False-False] 31.8813ms 24.3156ms 41.1259 Ops/s 41.9684 Ops/s $\color{#d91a1a}-2.01\%$
test_values[vec_td1_return_estimate-False-False] 36.3439ms 33.7852ms 29.5987 Ops/s 29.4504 Ops/s $\color{#35bf28}+0.50\%$
test_values[td_lambda_return_estimate-True-False] 39.2474ms 34.8835ms 28.6668 Ops/s 29.0340 Ops/s $\color{#d91a1a}-1.26\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.8607ms 33.7041ms 29.6700 Ops/s 29.6158 Ops/s $\color{#35bf28}+0.18\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 12.3438ms 8.1936ms 122.0469 Ops/s 119.9855 Ops/s $\color{#35bf28}+1.72\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4244ms 2.0342ms 491.5912 Ops/s 501.5074 Ops/s $\color{#d91a1a}-1.98\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5586ms 0.3537ms 2.8273 KOps/s 2.7734 KOps/s $\color{#35bf28}+1.95\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.0890ms 46.3088ms 21.5942 Ops/s 21.2179 Ops/s $\color{#35bf28}+1.77\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.3017ms 3.0498ms 327.8947 Ops/s 323.9125 Ops/s $\color{#35bf28}+1.23\%$
test_dqn_speed[False-None] 1.7263ms 1.3363ms 748.3322 Ops/s 714.7884 Ops/s $\color{#35bf28}+4.69\%$
test_dqn_speed[False-backward] 2.1294ms 1.8451ms 541.9831 Ops/s 537.6510 Ops/s $\color{#35bf28}+0.81\%$
test_dqn_speed[True-None] 0.6595ms 0.4589ms 2.1790 KOps/s 2.1305 KOps/s $\color{#35bf28}+2.28\%$
test_dqn_speed[True-backward] 0.9706ms 0.8749ms 1.1429 KOps/s 1.1211 KOps/s $\color{#35bf28}+1.94\%$
test_dqn_speed[reduce-overhead-None] 0.7070ms 0.4654ms 2.1487 KOps/s 2.1328 KOps/s $\color{#35bf28}+0.75\%$
test_dqn_speed[reduce-overhead-backward] 0.9420ms 0.8857ms 1.1290 KOps/s 1.1450 KOps/s $\color{#d91a1a}-1.40\%$
test_ddpg_speed[False-None] 4.1297ms 2.7864ms 358.8832 Ops/s 348.4982 Ops/s $\color{#35bf28}+2.98\%$
test_ddpg_speed[False-backward] 4.2232ms 3.9015ms 256.3123 Ops/s 251.2504 Ops/s $\color{#35bf28}+2.01\%$
test_ddpg_speed[True-None] 1.3346ms 0.9983ms 1.0018 KOps/s 992.5087 Ops/s $\color{#35bf28}+0.93\%$
test_ddpg_speed[True-backward] 2.0611ms 1.8820ms 531.3558 Ops/s 502.7271 Ops/s $\textbf{\color{#35bf28}+5.69\%}$
test_ddpg_speed[reduce-overhead-None] 1.2782ms 1.0019ms 998.1020 Ops/s 962.8307 Ops/s $\color{#35bf28}+3.66\%$
test_ddpg_speed[reduce-overhead-backward] 2.1071ms 1.9014ms 525.9327 Ops/s 521.5434 Ops/s $\color{#35bf28}+0.84\%$
test_sac_speed[False-None] 8.9232ms 7.9731ms 125.4210 Ops/s 121.4824 Ops/s $\color{#35bf28}+3.24\%$
test_sac_speed[False-backward] 13.4518ms 10.7418ms 93.0941 Ops/s 89.8491 Ops/s $\color{#35bf28}+3.61\%$
test_sac_speed[True-None] 2.9885ms 1.8533ms 539.5845 Ops/s 535.8181 Ops/s $\color{#35bf28}+0.70\%$
test_sac_speed[True-backward] 3.8703ms 3.5428ms 282.2592 Ops/s 283.9220 Ops/s $\color{#d91a1a}-0.59\%$
test_sac_speed[reduce-overhead-None] 2.4873ms 1.8807ms 531.7136 Ops/s 522.2129 Ops/s $\color{#35bf28}+1.82\%$
test_sac_speed[reduce-overhead-backward] 3.7430ms 3.5690ms 280.1936 Ops/s 277.4346 Ops/s $\color{#35bf28}+0.99\%$
test_redq_speed[False-None] 14.8044ms 13.1022ms 76.3231 Ops/s 77.3390 Ops/s $\color{#d91a1a}-1.31\%$
test_redq_speed[False-backward] 23.8131ms 22.2608ms 44.9221 Ops/s 43.9406 Ops/s $\color{#35bf28}+2.23\%$
test_redq_speed[True-None] 5.7824ms 5.0457ms 198.1870 Ops/s 201.5561 Ops/s $\color{#d91a1a}-1.67\%$
test_redq_speed[True-backward] 13.5684ms 12.8136ms 78.0422 Ops/s 79.4627 Ops/s $\color{#d91a1a}-1.79\%$
test_redq_speed[reduce-overhead-None] 6.5654ms 4.9914ms 200.3438 Ops/s 207.2214 Ops/s $\color{#d91a1a}-3.32\%$
test_redq_speed[reduce-overhead-backward] 14.5408ms 12.3878ms 80.7244 Ops/s 80.4477 Ops/s $\color{#35bf28}+0.34\%$
test_redq_deprec_speed[False-None] 17.5950ms 13.1922ms 75.8024 Ops/s 76.2168 Ops/s $\color{#d91a1a}-0.54\%$
test_redq_deprec_speed[False-backward] 21.3750ms 18.8800ms 52.9662 Ops/s 52.6615 Ops/s $\color{#35bf28}+0.58\%$
test_redq_deprec_speed[True-None] 4.7378ms 3.7571ms 266.1604 Ops/s 273.5297 Ops/s $\color{#d91a1a}-2.69\%$
test_redq_deprec_speed[True-backward] 9.3176ms 8.5459ms 117.0151 Ops/s 120.3562 Ops/s $\color{#d91a1a}-2.78\%$
test_redq_deprec_speed[reduce-overhead-None] 4.4618ms 3.6715ms 272.3690 Ops/s 275.9369 Ops/s $\color{#d91a1a}-1.29\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.9333ms 8.4971ms 117.6866 Ops/s 107.7252 Ops/s $\textbf{\color{#35bf28}+9.25\%}$
test_td3_speed[False-None] 8.4824ms 7.8674ms 127.1064 Ops/s 121.8969 Ops/s $\color{#35bf28}+4.27\%$
test_td3_speed[False-backward] 12.6613ms 10.7264ms 93.2276 Ops/s 93.5737 Ops/s $\color{#d91a1a}-0.37\%$
test_td3_speed[True-None] 1.9907ms 1.7365ms 575.8639 Ops/s 566.3217 Ops/s $\color{#35bf28}+1.68\%$
test_td3_speed[True-backward] 3.5248ms 3.3523ms 298.3038 Ops/s 295.1879 Ops/s $\color{#35bf28}+1.06\%$
test_td3_speed[reduce-overhead-None] 1.8415ms 1.7332ms 576.9556 Ops/s 561.3855 Ops/s $\color{#35bf28}+2.77\%$
test_td3_speed[reduce-overhead-backward] 3.5316ms 3.3450ms 298.9520 Ops/s 286.9940 Ops/s $\color{#35bf28}+4.17\%$
test_cql_speed[False-None] 37.5092ms 35.5191ms 28.1539 Ops/s 27.4384 Ops/s $\color{#35bf28}+2.61\%$
test_cql_speed[False-backward] 47.5973ms 45.6095ms 21.9252 Ops/s 21.3887 Ops/s $\color{#35bf28}+2.51\%$
test_cql_speed[True-None] 17.4069ms 15.9001ms 62.8928 Ops/s 60.9908 Ops/s $\color{#35bf28}+3.12\%$
test_cql_speed[True-backward] 24.2412ms 22.8718ms 43.7220 Ops/s 42.7284 Ops/s $\color{#35bf28}+2.33\%$
test_cql_speed[reduce-overhead-None] 17.4027ms 16.0626ms 62.2564 Ops/s 61.2307 Ops/s $\color{#35bf28}+1.68\%$
test_cql_speed[reduce-overhead-backward] 24.9738ms 23.1071ms 43.2767 Ops/s 44.0611 Ops/s $\color{#d91a1a}-1.78\%$
test_a2c_speed[False-None] 8.2729ms 7.5052ms 133.2415 Ops/s 133.3703 Ops/s $\color{#d91a1a}-0.10\%$
test_a2c_speed[False-backward] 15.8464ms 15.0714ms 66.3509 Ops/s 66.4428 Ops/s $\color{#d91a1a}-0.14\%$
test_a2c_speed[True-None] 3.7447ms 3.3925ms 294.7685 Ops/s 295.0607 Ops/s $\color{#d91a1a}-0.10\%$
test_a2c_speed[True-backward] 10.9028ms 10.2901ms 97.1803 Ops/s 99.7268 Ops/s $\color{#d91a1a}-2.55\%$
test_a2c_speed[reduce-overhead-None] 4.1256ms 3.4797ms 287.3824 Ops/s 291.5859 Ops/s $\color{#d91a1a}-1.44\%$
test_a2c_speed[reduce-overhead-backward] 10.7855ms 10.4293ms 95.8838 Ops/s 99.8256 Ops/s $\color{#d91a1a}-3.95\%$
test_ppo_speed[False-None] 8.5799ms 7.8533ms 127.3353 Ops/s 132.4403 Ops/s $\color{#d91a1a}-3.85\%$
test_ppo_speed[False-backward] 16.7943ms 15.5018ms 64.5085 Ops/s 65.9839 Ops/s $\color{#d91a1a}-2.24\%$
test_ppo_speed[True-None] 4.4923ms 3.7309ms 268.0300 Ops/s 266.6451 Ops/s $\color{#35bf28}+0.52\%$
test_ppo_speed[True-backward] 10.9982ms 10.0683ms 99.3217 Ops/s 98.4043 Ops/s $\color{#35bf28}+0.93\%$
test_ppo_speed[reduce-overhead-None] 4.0575ms 3.7225ms 268.6340 Ops/s 264.6415 Ops/s $\color{#35bf28}+1.51\%$
test_ppo_speed[reduce-overhead-backward] 10.5590ms 9.9186ms 100.8205 Ops/s 101.7803 Ops/s $\color{#d91a1a}-0.94\%$
test_reinforce_speed[False-None] 7.5758ms 6.5813ms 151.9446 Ops/s 151.0512 Ops/s $\color{#35bf28}+0.59\%$
test_reinforce_speed[False-backward] 11.3398ms 10.0938ms 99.0706 Ops/s 99.9132 Ops/s $\color{#d91a1a}-0.84\%$
test_reinforce_speed[True-None] 3.0759ms 2.6831ms 372.7016 Ops/s 370.7369 Ops/s $\color{#35bf28}+0.53\%$
test_reinforce_speed[True-backward] 9.8319ms 9.0416ms 110.5995 Ops/s 113.3616 Ops/s $\color{#d91a1a}-2.44\%$
test_reinforce_speed[reduce-overhead-None] 3.0437ms 2.7547ms 363.0128 Ops/s 363.9582 Ops/s $\color{#d91a1a}-0.26\%$
test_reinforce_speed[reduce-overhead-backward] 10.6045ms 8.9815ms 111.3400 Ops/s 111.0116 Ops/s $\color{#35bf28}+0.30\%$
test_iql_speed[False-None] 33.9599ms 32.4858ms 30.7827 Ops/s 30.7157 Ops/s $\color{#35bf28}+0.22\%$
test_iql_speed[False-backward] 54.4703ms 45.8698ms 21.8008 Ops/s 21.7428 Ops/s $\color{#35bf28}+0.27\%$
test_iql_speed[True-None] 12.2447ms 10.9361ms 91.4399 Ops/s 89.9486 Ops/s $\color{#35bf28}+1.66\%$
test_iql_speed[True-backward] 23.9086ms 22.7386ms 43.9781 Ops/s 43.9321 Ops/s $\color{#35bf28}+0.10\%$
test_iql_speed[reduce-overhead-None] 11.9969ms 11.0179ms 90.7613 Ops/s 90.6083 Ops/s $\color{#35bf28}+0.17\%$
test_iql_speed[reduce-overhead-backward] 23.6448ms 22.4313ms 44.5805 Ops/s 43.4647 Ops/s $\color{#35bf28}+2.57\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.2540ms 4.9038ms 203.9248 Ops/s 199.9888 Ops/s $\color{#35bf28}+1.97\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.2010ms 0.4855ms 2.0595 KOps/s 2.0300 KOps/s $\color{#35bf28}+1.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6992ms 0.4644ms 2.1534 KOps/s 2.1347 KOps/s $\color{#35bf28}+0.88\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.2972ms 4.9148ms 203.4671 Ops/s 202.1651 Ops/s $\color{#35bf28}+0.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.7785ms 0.4846ms 2.0638 KOps/s 2.0678 KOps/s $\color{#d91a1a}-0.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7557ms 0.4677ms 2.1379 KOps/s 2.1512 KOps/s $\color{#d91a1a}-0.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8835ms 1.5874ms 629.9771 Ops/s 621.5569 Ops/s $\color{#35bf28}+1.35\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.8248ms 1.5312ms 653.0948 Ops/s 641.1692 Ops/s $\color{#35bf28}+1.86\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.4644ms 5.0307ms 198.7795 Ops/s 194.9257 Ops/s $\color{#35bf28}+1.98\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.4480s 0.9724ms 1.0284 KOps/s 1.5808 KOps/s $\textbf{\color{#d91a1a}-34.94\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8462ms 0.5936ms 1.6847 KOps/s 1.5778 KOps/s $\textbf{\color{#35bf28}+6.78\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.3035ms 4.8461ms 206.3522 Ops/s 200.7369 Ops/s $\color{#35bf28}+2.80\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.7194ms 0.4902ms 2.0402 KOps/s 2.0033 KOps/s $\color{#35bf28}+1.84\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7053ms 0.4626ms 2.1619 KOps/s 2.1350 KOps/s $\color{#35bf28}+1.26\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.7734ms 4.8664ms 205.4920 Ops/s 204.3209 Ops/s $\color{#35bf28}+0.57\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0518ms 0.4723ms 2.1173 KOps/s 2.0748 KOps/s $\color{#35bf28}+2.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6421ms 0.4599ms 2.1744 KOps/s 2.0451 KOps/s $\textbf{\color{#35bf28}+6.33\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2469ms 4.9335ms 202.6966 Ops/s 198.3768 Ops/s $\color{#35bf28}+2.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.3523ms 0.6246ms 1.6010 KOps/s 1.5997 KOps/s $\color{#35bf28}+0.08\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0248ms 0.6344ms 1.5763 KOps/s 1.6391 KOps/s $\color{#d91a1a}-3.83\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4278s 12.7225ms 78.6007 Ops/s 247.1572 Ops/s $\textbf{\color{#d91a1a}-68.20\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.1245ms 2.4352ms 410.6490 Ops/s 435.7144 Ops/s $\textbf{\color{#d91a1a}-5.75\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.3364ms 1.3008ms 768.7416 Ops/s 709.7301 Ops/s $\textbf{\color{#35bf28}+8.31\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.4617ms 4.1473ms 241.1190 Ops/s 33.6762 Ops/s $\textbf{\color{#35bf28}+615.99\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 5.7600ms 2.2614ms 442.2068 Ops/s 426.9065 Ops/s $\color{#35bf28}+3.58\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.2173ms 1.3409ms 745.7811 Ops/s 763.4544 Ops/s $\color{#d91a1a}-2.31\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4016s 12.3173ms 81.1869 Ops/s 220.1523 Ops/s $\textbf{\color{#d91a1a}-63.12\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.9126ms 2.5157ms 397.5057 Ops/s 386.2671 Ops/s $\color{#35bf28}+2.91\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.2144ms 1.5021ms 665.7129 Ops/s 665.7494 Ops/s $-0.01\%$

Copy link

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

Total Benchmarks: 143. Improved: $\large\color{#35bf28}18$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7212s 0.7203s 1.3883 Ops/s 1.3757 Ops/s $\color{#35bf28}+0.92\%$
test_transformed 1.0602s 0.9807s 1.0197 Ops/s 1.0291 Ops/s $\color{#d91a1a}-0.91\%$
test_serial 2.2729s 2.1653s 0.4618 Ops/s 0.4702 Ops/s $\color{#d91a1a}-1.77\%$
test_parallel 2.0467s 1.9845s 0.5039 Ops/s 0.5033 Ops/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[True-True-True-True-True] 0.1999ms 39.5587μs 25.2789 KOps/s 25.1786 KOps/s $\color{#35bf28}+0.40\%$
test_step_mdp_speed[True-True-True-True-False] 0.2220ms 23.5744μs 42.4189 KOps/s 42.3866 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[True-True-True-False-True] 92.7220μs 21.6403μs 46.2100 KOps/s 45.9414 KOps/s $\color{#35bf28}+0.58\%$
test_step_mdp_speed[True-True-True-False-False] 38.3600μs 12.7768μs 78.2666 KOps/s 78.9355 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[True-True-False-True-True] 77.6210μs 42.2909μs 23.6458 KOps/s 23.8690 KOps/s $\color{#d91a1a}-0.94\%$
test_step_mdp_speed[True-True-False-True-False] 62.0210μs 25.4211μs 39.3373 KOps/s 39.0361 KOps/s $\color{#35bf28}+0.77\%$
test_step_mdp_speed[True-True-False-False-True] 53.7210μs 24.4896μs 40.8337 KOps/s 40.0924 KOps/s $\color{#35bf28}+1.85\%$
test_step_mdp_speed[True-True-False-False-False] 42.8900μs 15.2357μs 65.6353 KOps/s 65.0684 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[True-False-True-True-True] 95.0910μs 45.5892μs 21.9350 KOps/s 21.9836 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-False-True-True-False] 64.0000μs 28.6816μs 34.8655 KOps/s 34.6480 KOps/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[True-False-True-False-True] 0.1662ms 24.2718μs 41.2000 KOps/s 39.7545 KOps/s $\color{#35bf28}+3.64\%$
test_step_mdp_speed[True-False-True-False-False] 0.1065ms 15.2276μs 65.6702 KOps/s 64.5904 KOps/s $\color{#35bf28}+1.67\%$
test_step_mdp_speed[True-False-False-True-True] 77.3710μs 47.4290μs 21.0841 KOps/s 20.7006 KOps/s $\color{#35bf28}+1.85\%$
test_step_mdp_speed[True-False-False-True-False] 65.3410μs 30.7722μs 32.4969 KOps/s 31.5809 KOps/s $\color{#35bf28}+2.90\%$
test_step_mdp_speed[True-False-False-False-True] 61.2010μs 26.8572μs 37.2340 KOps/s 35.9841 KOps/s $\color{#35bf28}+3.47\%$
test_step_mdp_speed[True-False-False-False-False] 50.3010μs 17.6989μs 56.5007 KOps/s 55.3479 KOps/s $\color{#35bf28}+2.08\%$
test_step_mdp_speed[False-True-True-True-True] 74.6010μs 44.6447μs 22.3991 KOps/s 21.9039 KOps/s $\color{#35bf28}+2.26\%$
test_step_mdp_speed[False-True-True-True-False] 0.1142ms 28.1842μs 35.4808 KOps/s 34.4044 KOps/s $\color{#35bf28}+3.13\%$
test_step_mdp_speed[False-True-True-False-True] 83.9910μs 28.6276μs 34.9313 KOps/s 33.6374 KOps/s $\color{#35bf28}+3.85\%$
test_step_mdp_speed[False-True-True-False-False] 51.2600μs 17.7731μs 56.2649 KOps/s 55.6088 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[False-True-False-True-True] 85.1010μs 47.1061μs 21.2287 KOps/s 20.4960 KOps/s $\color{#35bf28}+3.57\%$
test_step_mdp_speed[False-True-False-True-False] 64.6510μs 30.6889μs 32.5851 KOps/s 31.8698 KOps/s $\color{#35bf28}+2.24\%$
test_step_mdp_speed[False-True-False-False-True] 3.5064ms 31.7124μs 31.5334 KOps/s 30.7968 KOps/s $\color{#35bf28}+2.39\%$
test_step_mdp_speed[False-True-False-False-False] 51.3010μs 20.0351μs 49.9123 KOps/s 48.8655 KOps/s $\color{#35bf28}+2.14\%$
test_step_mdp_speed[False-False-True-True-True] 87.6010μs 49.8841μs 20.0465 KOps/s 19.5710 KOps/s $\color{#35bf28}+2.43\%$
test_step_mdp_speed[False-False-True-True-False] 61.2910μs 33.2004μs 30.1201 KOps/s 29.4179 KOps/s $\color{#35bf28}+2.39\%$
test_step_mdp_speed[False-False-True-False-True] 69.5210μs 31.7281μs 31.5178 KOps/s 31.3196 KOps/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[False-False-True-False-False] 49.7710μs 20.0388μs 49.9031 KOps/s 48.8232 KOps/s $\color{#35bf28}+2.21\%$
test_step_mdp_speed[False-False-False-True-True] 84.4920μs 51.1188μs 19.5623 KOps/s 18.8178 KOps/s $\color{#35bf28}+3.96\%$
test_step_mdp_speed[False-False-False-True-False] 64.3910μs 35.7908μs 27.9401 KOps/s 27.2762 KOps/s $\color{#35bf28}+2.43\%$
test_step_mdp_speed[False-False-False-False-True] 69.8510μs 32.9337μs 30.3641 KOps/s 29.5464 KOps/s $\color{#35bf28}+2.77\%$
test_step_mdp_speed[False-False-False-False-False] 51.4500μs 22.4012μs 44.6405 KOps/s 44.1534 KOps/s $\color{#35bf28}+1.10\%$
test_values[generalized_advantage_estimate-True-True] 23.8170ms 23.4631ms 42.6202 Ops/s 42.4781 Ops/s $\color{#35bf28}+0.33\%$
test_values[vec_generalized_advantage_estimate-True-True] 98.5944ms 2.8435ms 351.6846 Ops/s 348.2456 Ops/s $\color{#35bf28}+0.99\%$
test_values[td0_return_estimate-False-False] 0.1067ms 64.0353μs 15.6164 KOps/s 15.9594 KOps/s $\color{#d91a1a}-2.15\%$
test_values[td1_return_estimate-False-False] 52.7155ms 52.3173ms 19.1141 Ops/s 19.0575 Ops/s $\color{#35bf28}+0.30\%$
test_values[vec_td1_return_estimate-False-False] 1.2230ms 1.0517ms 950.8004 Ops/s 946.6593 Ops/s $\color{#35bf28}+0.44\%$
test_values[td_lambda_return_estimate-True-False] 84.2217ms 83.1142ms 12.0316 Ops/s 12.0398 Ops/s $\color{#d91a1a}-0.07\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.1789ms 1.0386ms 962.7890 Ops/s 951.3495 Ops/s $\color{#35bf28}+1.20\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.5878ms 23.2097ms 43.0854 Ops/s 43.1603 Ops/s $\color{#d91a1a}-0.17\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0322ms 0.7161ms 1.3964 KOps/s 1.4094 KOps/s $\color{#d91a1a}-0.92\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7678ms 0.6318ms 1.5828 KOps/s 1.5755 KOps/s $\color{#35bf28}+0.46\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6034ms 1.4454ms 691.8601 Ops/s 691.7729 Ops/s $\color{#35bf28}+0.01\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7980ms 0.6473ms 1.5448 KOps/s 1.5416 KOps/s $\color{#35bf28}+0.21\%$
test_dqn_speed[False-None] 6.8774ms 1.3214ms 756.7932 Ops/s 680.5734 Ops/s $\textbf{\color{#35bf28}+11.20\%}$
test_dqn_speed[False-backward] 2.0016ms 1.8488ms 540.8928 Ops/s 553.9601 Ops/s $\color{#d91a1a}-2.36\%$
test_dqn_speed[True-None] 1.2056ms 0.5512ms 1.8141 KOps/s 1.7654 KOps/s $\color{#35bf28}+2.76\%$
test_dqn_speed[True-backward] 1.2558ms 1.0212ms 979.2671 Ops/s 836.0439 Ops/s $\textbf{\color{#35bf28}+17.13\%}$
test_dqn_speed[reduce-overhead-None] 0.8553ms 0.5549ms 1.8020 KOps/s 1.7648 KOps/s $\color{#35bf28}+2.11\%$
test_dqn_speed[reduce-overhead-backward] 1.1070ms 1.0207ms 979.7350 Ops/s 977.1599 Ops/s $\color{#35bf28}+0.26\%$
test_ddpg_speed[False-None] 3.0300ms 2.6882ms 371.9909 Ops/s 358.3694 Ops/s $\color{#35bf28}+3.80\%$
test_ddpg_speed[False-backward] 4.1605ms 3.9910ms 250.5667 Ops/s 252.4905 Ops/s $\color{#d91a1a}-0.76\%$
test_ddpg_speed[True-None] 1.6068ms 1.2547ms 796.9868 Ops/s 772.1505 Ops/s $\color{#35bf28}+3.22\%$
test_ddpg_speed[True-backward] 2.3438ms 2.2240ms 449.6321 Ops/s 444.4185 Ops/s $\color{#35bf28}+1.17\%$
test_ddpg_speed[reduce-overhead-None] 1.6086ms 1.2513ms 799.1561 Ops/s 792.7412 Ops/s $\color{#35bf28}+0.81\%$
test_ddpg_speed[reduce-overhead-backward] 2.5406ms 2.2413ms 446.1639 Ops/s 450.9101 Ops/s $\color{#d91a1a}-1.05\%$
test_sac_speed[False-None] 7.9915ms 7.5684ms 132.1282 Ops/s 129.5323 Ops/s $\color{#35bf28}+2.00\%$
test_sac_speed[False-backward] 11.3020ms 10.7462ms 93.0560 Ops/s 92.1105 Ops/s $\color{#35bf28}+1.03\%$
test_sac_speed[True-None] 2.4139ms 2.0560ms 486.3879 Ops/s 487.9698 Ops/s $\color{#d91a1a}-0.32\%$
test_sac_speed[True-backward] 4.3392ms 4.0353ms 247.8127 Ops/s 212.1828 Ops/s $\textbf{\color{#35bf28}+16.79\%}$
test_sac_speed[reduce-overhead-None] 2.3147ms 2.0679ms 483.5933 Ops/s 488.4371 Ops/s $\color{#d91a1a}-0.99\%$
test_sac_speed[reduce-overhead-backward] 4.1768ms 3.9991ms 250.0546 Ops/s 250.0533 Ops/s $+0.00\%$
test_redq_speed[False-None] 15.5342ms 10.5776ms 94.5397 Ops/s 87.4636 Ops/s $\textbf{\color{#35bf28}+8.09\%}$
test_redq_speed[False-backward] 19.3372ms 17.8183ms 56.1220 Ops/s 54.4975 Ops/s $\color{#35bf28}+2.98\%$
test_redq_speed[True-None] 4.2672ms 3.7750ms 264.9042 Ops/s 220.2820 Ops/s $\textbf{\color{#35bf28}+20.26\%}$
test_redq_speed[True-backward] 9.2259ms 8.8074ms 113.5413 Ops/s 106.6975 Ops/s $\textbf{\color{#35bf28}+6.41\%}$
test_redq_speed[reduce-overhead-None] 3.8961ms 3.6384ms 274.8449 Ops/s 275.6581 Ops/s $\color{#d91a1a}-0.29\%$
test_redq_speed[reduce-overhead-backward] 9.2712ms 8.8346ms 113.1909 Ops/s 113.2151 Ops/s $\color{#d91a1a}-0.02\%$
test_redq_deprec_speed[False-None] 11.2818ms 10.7566ms 92.9665 Ops/s 94.1951 Ops/s $\color{#d91a1a}-1.30\%$
test_redq_deprec_speed[False-backward] 16.0399ms 15.5789ms 64.1894 Ops/s 65.0372 Ops/s $\color{#d91a1a}-1.30\%$
test_redq_deprec_speed[True-None] 3.6273ms 3.3013ms 302.9097 Ops/s 286.5308 Ops/s $\textbf{\color{#35bf28}+5.72\%}$
test_redq_deprec_speed[True-backward] 7.6590ms 7.2204ms 138.4959 Ops/s 136.2540 Ops/s $\color{#35bf28}+1.65\%$
test_redq_deprec_speed[reduce-overhead-None] 3.7969ms 3.3335ms 299.9852 Ops/s 299.6082 Ops/s $\color{#35bf28}+0.13\%$
test_redq_deprec_speed[reduce-overhead-backward] 7.5455ms 7.2533ms 137.8686 Ops/s 136.1580 Ops/s $\color{#35bf28}+1.26\%$
test_td3_speed[False-None] 7.7213ms 7.5347ms 132.7188 Ops/s 131.5927 Ops/s $\color{#35bf28}+0.86\%$
test_td3_speed[False-backward] 10.7714ms 10.3559ms 96.5630 Ops/s 95.9742 Ops/s $\color{#35bf28}+0.61\%$
test_td3_speed[True-None] 1.9927ms 1.9409ms 515.2159 Ops/s 512.0085 Ops/s $\color{#35bf28}+0.63\%$
test_td3_speed[True-backward] 3.9858ms 3.8360ms 260.6863 Ops/s 237.9496 Ops/s $\textbf{\color{#35bf28}+9.56\%}$
test_td3_speed[reduce-overhead-None] 2.0893ms 1.9600ms 510.2144 Ops/s 517.7715 Ops/s $\color{#d91a1a}-1.46\%$
test_td3_speed[reduce-overhead-backward] 3.9189ms 3.7998ms 263.1717 Ops/s 262.4117 Ops/s $\color{#35bf28}+0.29\%$
test_cql_speed[False-None] 27.7563ms 25.5378ms 39.1577 Ops/s 39.9979 Ops/s $\color{#d91a1a}-2.10\%$
test_cql_speed[False-backward] 39.7691ms 35.0446ms 28.5351 Ops/s 29.4977 Ops/s $\color{#d91a1a}-3.26\%$
test_cql_speed[True-None] 11.7754ms 11.2094ms 89.2106 Ops/s 92.5706 Ops/s $\color{#d91a1a}-3.63\%$
test_cql_speed[True-backward] 17.7229ms 17.0581ms 58.6231 Ops/s 60.2636 Ops/s $\color{#d91a1a}-2.72\%$
test_cql_speed[reduce-overhead-None] 14.9229ms 11.4425ms 87.3934 Ops/s 90.0990 Ops/s $\color{#d91a1a}-3.00\%$
test_cql_speed[reduce-overhead-backward] 17.5704ms 17.1275ms 58.3858 Ops/s 60.1274 Ops/s $\color{#d91a1a}-2.90\%$
test_a2c_speed[False-None] 7.4464ms 5.3299ms 187.6192 Ops/s 186.1896 Ops/s $\color{#35bf28}+0.77\%$
test_a2c_speed[False-backward] 12.4034ms 11.8838ms 84.1481 Ops/s 85.0195 Ops/s $\color{#d91a1a}-1.02\%$
test_a2c_speed[True-None] 3.5268ms 3.1436ms 318.1023 Ops/s 319.9285 Ops/s $\color{#d91a1a}-0.57\%$
test_a2c_speed[True-backward] 9.0550ms 8.6005ms 116.2719 Ops/s 95.7701 Ops/s $\textbf{\color{#35bf28}+21.41\%}$
test_a2c_speed[reduce-overhead-None] 3.3578ms 3.1176ms 320.7568 Ops/s 314.8480 Ops/s $\color{#35bf28}+1.88\%$
test_a2c_speed[reduce-overhead-backward] 8.8063ms 8.5311ms 117.2176 Ops/s 116.4370 Ops/s $\color{#35bf28}+0.67\%$
test_ppo_speed[False-None] 6.0061ms 5.7381ms 174.2743 Ops/s 172.0933 Ops/s $\color{#35bf28}+1.27\%$
test_ppo_speed[False-backward] 12.9044ms 12.5558ms 79.6445 Ops/s 80.1900 Ops/s $\color{#d91a1a}-0.68\%$
test_ppo_speed[True-None] 3.6822ms 3.4939ms 286.2105 Ops/s 284.5195 Ops/s $\color{#35bf28}+0.59\%$
test_ppo_speed[True-backward] 8.6300ms 8.3066ms 120.3857 Ops/s 119.9866 Ops/s $\color{#35bf28}+0.33\%$
test_ppo_speed[reduce-overhead-None] 3.7587ms 3.4977ms 285.8984 Ops/s 285.4431 Ops/s $\color{#35bf28}+0.16\%$
test_ppo_speed[reduce-overhead-backward] 8.6080ms 8.2723ms 120.8851 Ops/s 120.3947 Ops/s $\color{#35bf28}+0.41\%$
test_reinforce_speed[False-None] 6.5676ms 4.5024ms 222.1022 Ops/s 219.3120 Ops/s $\color{#35bf28}+1.27\%$
test_reinforce_speed[False-backward] 7.6041ms 7.3020ms 136.9481 Ops/s 136.6380 Ops/s $\color{#35bf28}+0.23\%$
test_reinforce_speed[True-None] 2.6017ms 2.2873ms 437.1987 Ops/s 429.1368 Ops/s $\color{#35bf28}+1.88\%$
test_reinforce_speed[True-backward] 7.4879ms 7.1822ms 139.2336 Ops/s 136.6537 Ops/s $\color{#35bf28}+1.89\%$
test_reinforce_speed[reduce-overhead-None] 2.6927ms 2.2759ms 439.3892 Ops/s 440.4454 Ops/s $\color{#d91a1a}-0.24\%$
test_reinforce_speed[reduce-overhead-backward] 7.6413ms 7.1966ms 138.9548 Ops/s 138.0501 Ops/s $\color{#35bf28}+0.66\%$
test_iql_speed[False-None] 19.6947ms 19.0355ms 52.5335 Ops/s 50.4365 Ops/s $\color{#35bf28}+4.16\%$
test_iql_speed[False-backward] 35.4559ms 30.1845ms 33.1295 Ops/s 33.0469 Ops/s $\color{#35bf28}+0.25\%$
test_iql_speed[True-None] 7.5131ms 6.9142ms 144.6298 Ops/s 142.5205 Ops/s $\color{#35bf28}+1.48\%$
test_iql_speed[True-backward] 16.7706ms 15.8917ms 62.9261 Ops/s 61.9420 Ops/s $\color{#35bf28}+1.59\%$
test_iql_speed[reduce-overhead-None] 8.1160ms 7.0709ms 141.4247 Ops/s 145.6343 Ops/s $\color{#d91a1a}-2.89\%$
test_iql_speed[reduce-overhead-backward] 16.6603ms 15.8924ms 62.9231 Ops/s 63.1140 Ops/s $\color{#d91a1a}-0.30\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3858ms 6.1816ms 161.7704 Ops/s 162.4975 Ops/s $\color{#d91a1a}-0.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.2590ms 0.2682ms 3.7282 KOps/s 4.2027 KOps/s $\textbf{\color{#d91a1a}-11.29\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5372ms 0.2804ms 3.5669 KOps/s 4.6292 KOps/s $\textbf{\color{#d91a1a}-22.95\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.5001ms 6.1283ms 163.1783 Ops/s 165.3807 Ops/s $\color{#d91a1a}-1.33\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.0109ms 0.2709ms 3.6915 KOps/s 2.8604 KOps/s $\textbf{\color{#35bf28}+29.06\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5453ms 0.2804ms 3.5669 KOps/s 3.0040 KOps/s $\textbf{\color{#35bf28}+18.74\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.4283ms 1.1963ms 835.8935 Ops/s 710.2511 Ops/s $\textbf{\color{#35bf28}+17.69\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6339ms 1.1450ms 873.3288 Ops/s 726.1611 Ops/s $\textbf{\color{#35bf28}+20.27\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5113ms 6.2614ms 159.7088 Ops/s 160.8625 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2369ms 0.3815ms 2.6212 KOps/s 2.3271 KOps/s $\textbf{\color{#35bf28}+12.64\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6181ms 0.3583ms 2.7907 KOps/s 2.4636 KOps/s $\textbf{\color{#35bf28}+13.28\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3809ms 6.0967ms 164.0229 Ops/s 164.6405 Ops/s $\color{#d91a1a}-0.38\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.4868s 0.7726ms 1.2943 KOps/s 3.6157 KOps/s $\textbf{\color{#d91a1a}-64.20\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4546ms 0.2253ms 4.4394 KOps/s 4.1622 KOps/s $\textbf{\color{#35bf28}+6.66\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4486ms 6.1180ms 163.4520 Ops/s 161.8525 Ops/s $\color{#35bf28}+0.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7968ms 0.2376ms 4.2093 KOps/s 4.1218 KOps/s $\color{#35bf28}+2.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5849ms 0.2167ms 4.6139 KOps/s 4.4231 KOps/s $\color{#35bf28}+4.31\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4712ms 6.3099ms 158.4806 Ops/s 156.7927 Ops/s $\color{#35bf28}+1.08\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9636ms 0.3839ms 2.6048 KOps/s 2.5709 KOps/s $\color{#35bf28}+1.32\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5199ms 0.3628ms 2.7562 KOps/s 2.7413 KOps/s $\color{#35bf28}+0.54\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.7491ms 5.2126ms 191.8418 Ops/s 189.6821 Ops/s $\color{#35bf28}+1.14\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.5990ms 2.1754ms 459.6880 Ops/s 455.0754 Ops/s $\color{#35bf28}+1.01\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.2906ms 1.2617ms 792.5694 Ops/s 813.7864 Ops/s $\color{#d91a1a}-2.61\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4142s 13.3879ms 74.6941 Ops/s 189.3031 Ops/s $\textbf{\color{#d91a1a}-60.54\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.0670ms 2.0215ms 494.6732 Ops/s 448.9575 Ops/s $\textbf{\color{#35bf28}+10.18\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.5261ms 1.2204ms 819.4036 Ops/s 835.3060 Ops/s $\color{#d91a1a}-1.90\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4031s 13.3143ms 75.1074 Ops/s 186.1435 Ops/s $\textbf{\color{#d91a1a}-59.65\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.5473ms 2.1833ms 458.0310 Ops/s 414.3013 Ops/s $\textbf{\color{#35bf28}+10.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.9006ms 1.3701ms 729.8906 Ops/s 741.2467 Ops/s $\color{#d91a1a}-1.53\%$

@vmoens vmoens added the enhancement New feature or request label Oct 17, 2024
@vmoens vmoens merged commit 7c63e2e into gh/vmoens/32/base Oct 17, 2024
70 of 73 checks passed
@vmoens vmoens deleted the gh/vmoens/32/head branch October 17, 2024 13:57
@vmoens vmoens restored the gh/vmoens/32/head branch October 17, 2024 13:57
@vmoens vmoens deleted the gh/vmoens/32/head branch October 17, 2024 13:58
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. enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants