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

Deterministic DRN #42950

Merged
merged 2 commits into from
Oct 9, 2023
Merged

Conversation

ssrothman
Copy link
Contributor

PR description:

This PR addresses issue #41060 where the outputs from the photonDRN model was observed to be non-deterministic. We have determined that this is due to a problem with the scheduler in the Triton ensemble model backend. This pull request contains code changes needed to convert from the ensemble model setup to a pure pytorch combined model. A companion cms-data PR will contain the necessary changes to the model config.

PR validation:

Local testing of workflow 10805.31_SingleGammaPt35+2018_photonDRN has shown perfectly deterministic behavior.

DRN determinism test instructions

Update to combined model; cleanup prints

Further cleanup; we'll squash onto this commit
@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 4, 2023

+code-checks

Logs: https://cmssdt.cern.ch/SDT/code-checks/cms-sw-PR-42950/37096

  • This PR adds an extra 20KB to repository

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 4, 2023

A new Pull Request was created by @ssrothman (Simon Rothman) for master.

It involves the following packages:

  • PhysicsTools/PatAlgos (reconstruction, xpog)
  • RecoEgamma/EgammaTools (reconstruction)

@jfernan2, @cmsbuild, @simonepigazzini, @vlimant, @mandrenguyen can you please review it and eventually sign? Thanks.
@Senphy, @seemasharmafnal, @ram1123, @mbluj, @emilbols, @nhanvtran, @mariadalfonso, @lgray, @jdolen, @mmarionncern, @Sam-Harper, @andrzejnovak, @AnnikaStein, @AlexDeMoor, @schoef, @jdamgov, @afiqaize, @sameasy, @ahinzmann, @gkasieczka, @jainshilpi, @varuns23, @azotz, @Ming-Yan, @sobhatta, @demuller, @missirol, @a-kapoor, @hatakeyamak, @gouskos, @rappoccio, @JyothsnaKomaragiri, @Prasant1993, @gpetruc, @valsdav this is something you requested to watch as well.
@sextonkennedy, @antoniovilela, @rappoccio you are the release manager for this.

cms-bot commands are listed here

@simonepigazzini
Copy link
Contributor

please test

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 5, 2023

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-4a6996/35054/summary.html
COMMIT: 6b48c07
CMSSW: CMSSW_13_3_X_2023-10-04-2300/el8_amd64_gcc11
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/42950/35054/install.sh to create a dev area with all the needed externals and cmssw changes.

Comparison Summary

Summary:

  • You potentially removed 4 lines from the logs
  • Reco comparison results: 14 differences found in the comparisons
  • DQMHistoTests: Total files compared: 50
  • DQMHistoTests: Total histograms compared: 3356920
  • DQMHistoTests: Total failures: 9
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3356889
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.0 KiB( 49 files compared)
  • Checked 214 log files, 167 edm output root files, 50 DQM output files
  • TriggerResults: no differences found

@jfernan2
Copy link
Contributor

jfernan2 commented Oct 5, 2023

+1

@simonepigazzini
Copy link
Contributor

+1

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 9, 2023

This pull request is fully signed and it will be integrated in one of the next master IBs (tests are also fine). This pull request will now be reviewed by the release team before it's merged. @sextonkennedy, @antoniovilela, @rappoccio (and backports should be raised in the release meeting by the corresponding L2)

@mmusich
Copy link
Contributor

mmusich commented Oct 9, 2023

test parameters:

@mmusich
Copy link
Contributor

mmusich commented Oct 9, 2023

please test

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 9, 2023

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-4a6996/35100/summary.html
COMMIT: 6b48c07
CMSSW: CMSSW_13_3_X_2023-10-09-1100/el8_amd64_gcc11
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week0/cms-sw/cmssw/42950/35100/install.sh to create a dev area with all the needed externals and cmssw changes.

The following merge commits were also included on top of IB + this PR after doing git cms-merge-topic:

You can see more details here:
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-4a6996/35100/git-recent-commits.json
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-4a6996/35100/git-merge-result

Comparison Summary

Summary:

  • No significant changes to the logs found
  • Reco comparison results: 12 differences found in the comparisons
  • DQMHistoTests: Total files compared: 51
  • DQMHistoTests: Total histograms compared: 3457786
  • DQMHistoTests: Total failures: 6
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3457758
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.0 KiB( 50 files compared)
  • Checked 220 log files, 172 edm output root files, 51 DQM output files
  • TriggerResults: no differences found

@rappoccio
Copy link
Contributor

+1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants