Instrument cmssw for nvidia nvprof/nvvm (10.0.x)

[fwyzard]

Instrument cmssw for nvprof/nvvm

• implement a Service to provide CMSSW-aware annotations to nvprof/nvvm
• highlight selected modules and delayed modules
• update for CMSSW 10.0.x

[fwyzard]

backport #21946

[cmsbuild]

A new Pull Request was created by @fwyzard (Andrea Bocci) for CMSSW_10_0_X.

It involves the following packages:

FWCore/CUDAServices

The following packages do not have a category, yet:

FWCore/CUDAServices
Please create a PR for https://github.com/cms-sw/cms-bot/blob/master/categories_map.py to assign category

@cmsbuild can you please review it and eventually sign? Thanks.
@makortel, @Martin-Grunewald, @wddgit this is something you requested to watch as well.
@davidlange6, @slava77, @fabiocos you are the release manager for this.

cms-bot commands are listed here

• Backported from Instrument cmssw for nvidia nvprof/nvvm (10.1.x) #21946

[cmsbuild]

Pull request #21947 was updated. @cmsbuild can you please check and sign again.

[cmsbuild]

Pull request #21947 was updated. @cmsbuild can you please check and sign again.

[fwyzard]

@cmsbuild, please test

[cmsbuild]

The tests are being triggered in jenkins.
https://cmssdt.cern.ch/jenkins/job/ib-any-integration/25616/console Started: 2018/01/25 10:16

[cmsbuild]

+1
Tested at: 8fd6dda
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-21947/25616/summary.html

[cmsbuild]

Comparison job queued.

[cmsbuild]

Comparison is ready
https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-21947/25616/summary.html

@slava77 comparisons for the following workflows were not done due to missing matrix map:

• /build/cmsbld/jenkins/workspace/compare-root-files-short-matrix/results/JR-comparison/PR-21947/1325.7_TTbar_13_94XNanoAODINPUT+TTbar_13_94XNanoAODINPUT+NANOEDMMC2017

Comparison Summary:

• No significant changes to the logs found
• Reco comparison results: 2 differences found in the comparisons
• DQMHistoTests: Total files compared: 26
• DQMHistoTests: Total histograms compared: 2467599
• DQMHistoTests: Total failures: 1
• DQMHistoTests: Total nulls: 0
• DQMHistoTests: Total successes: 2467429
• DQMHistoTests: Total skipped: 169
• DQMHistoTests: Total Missing objects: 0
• DQMHistoSizes: Histogram memory added: 1.00000000006 KiB( 22 files compared)
• Checked 110 log files, 9 edm output root files, 26 DQM output files

[fabiocos]

@fwyzard is this really needed in 10_0_X as well, or it is enough to integrate it in the development release?

[fwyzard]

I would rather have it in10.0.x as well, since this is the base release we are currently using for the GPU development, and because it can be used for profiling non-GPU modules as well.

[fabiocos]

+1

[fabiocos]

merge