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

Reduce the ECAL and HCAL GPU memory usage [12.5.x] #39579

Merged

Conversation

fwyzard
Copy link
Contributor

@fwyzard fwyzard commented Oct 3, 2022

PR description:

Allocate memory buffers based on the actual number of events, instead of always allocating the maximum size.

Update the HLT menus to remove the obsolete parameters, if they are present.

Reduces the total GPU memory from running the HLT with 4 jobs with 32 threads and 32 streams by about 25%:

release total reserved used free
CMSSW_12_4_9 15360 MB 449 MB 10678 - 10090 MB 4231 - 4819 MB
with #39580 15360 MB 449 MB 7366 - 8056 MB 7543 - 6853 MB

Thanks to @VinInn for finding the issue and for the changes.

PR validation:

The full HLT menu runs on GPU (with 12.4.9 plus #39580) without issues.

If this PR is a backport please specify the original PR and why you need to backport that PR. If this PR will be backported please specify to which release cycle the backport is meant for:

Backport of #39577.

VinInn and others added 2 commits October 3, 2022 14:23
Allocate memory buffers based on the actual number of events, instead of
always allocating the maximum size.
@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 3, 2022

A new Pull Request was created by @fwyzard (Andrea Bocci) for CMSSW_12_5_X.

It involves the following packages:

  • RecoLocalCalo/EcalRecProducers (reconstruction)
  • RecoLocalCalo/HcalRecProducers (reconstruction)

@cmsbuild, @mandrenguyen, @clacaputo can you please review it and eventually sign? Thanks.
@youyingli, @apsallid, @rchatter, @argiro, @missirol, @bsunanda, @thomreis, @simonepigazzini, @mariadalfonso, @abdoulline this is something you requested to watch as well.
@perrotta, @dpiparo, @rappoccio you are the release manager for this.

cms-bot commands are listed here

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 3, 2022

Pull request #39579 was updated. @cmsbuild, @missirol, @mandrenguyen, @clacaputo, @Martin-Grunewald can you please check and sign again.

@fwyzard
Copy link
Contributor Author

fwyzard commented Oct 3, 2022

please test

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 3, 2022

+1

Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-0d338d/27932/summary.html
COMMIT: af7913f
CMSSW: CMSSW_12_5_X_2022-10-02-2300/el8_amd64_gcc10
User test area: For local testing, you can use /cvmfs/cms-ci.cern.ch/week1/cms-sw/cmssw/39579/27932/install.sh to create a dev area with all the needed externals and cmssw changes.

Comparison Summary

Summary:

  • No significant changes to the logs found
  • Reco comparison results: 0 differences found in the comparisons
  • DQMHistoTests: Total files compared: 51
  • DQMHistoTests: Total histograms compared: 3699454
  • DQMHistoTests: Total failures: 2
  • DQMHistoTests: Total nulls: 0
  • DQMHistoTests: Total successes: 3699430
  • DQMHistoTests: Total skipped: 22
  • DQMHistoTests: Total Missing objects: 0
  • DQMHistoSizes: Histogram memory added: 0.0 KiB( 50 files compared)
  • Checked 212 log files, 49 edm output root files, 51 DQM output files
  • TriggerResults: no differences found

@missirol
Copy link
Contributor

missirol commented Oct 3, 2022

+hlt

@missirol
Copy link
Contributor

missirol commented Oct 3, 2022

backport of #39577

@mandrenguyen
Copy link
Contributor

+1

@cmsbuild
Copy link
Contributor

cmsbuild commented Oct 4, 2022

This pull request is fully signed and it will be integrated in one of the next CMSSW_12_5_X IBs (tests are also fine) and once validation in the development release cycle CMSSW_12_6_X is complete. This pull request will now be reviewed by the release team before it's merged. @perrotta, @dpiparo, @rappoccio (and backports should be raised in the release meeting by the corresponding L2)

@perrotta
Copy link
Contributor

perrotta commented Oct 6, 2022

+1

@cmsbuild cmsbuild merged commit 96b4264 into cms-sw:CMSSW_12_5_X Oct 6, 2022
@fwyzard fwyzard deleted the reduce_ECAL_HCAL_GPU_memory_usage_125x branch October 11, 2022 14:09
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