Difference: ComputingandSoftwarePublicResults (9 vs. 10)

Revision 102018-09-17 - JaroslavGuenther

Line: 1 to 1
 
META TOPICPARENT name="WebHome"
<!--  
Line: 61 to 61
 
Changed:
<
<
The dependency of reconstruction wall time per event on the average number of interactions per bunch crossing is shown. The plot contains a selection of Tier-0 jobs reconstructing RAW data from 13 TeV pp LHC collisions in 2017. Each reconstruction job was required to run on one core of a 16-core machine with Intel(R) Xeon(R) CPU @ 2.40 GHz and memory of 4 GB/core. The red boxes refer to a special high-mu run 335302. Reconstruction jobs were configured to produce only AOD outputs, whereas standard jobs proceeded with 12 additional output types (different DRAW, DESD, DAOD and HIST), which take extra processing time.
>
>
The dependency of reconstruction wall time per event on the average number of interactions per bunch crossing (<μ>) is shown for the current Inner Detector reconstruction with default tracking cuts. The plot contains a selection of reconstructed luminosity blocks of RAW data from 13 TeV pp LHC collisions in 2017. An ATLAS luminosity block typically corresponds to one minute of data-taking. Tier-0 reconstruction jobs were required to run in single-core mode on a selected sub-cluster of 16-core machines (with Intel(R) Xeon(R) CPU E5-2630 v3 of 2.40 GHz clock speed, memory of 4 GB/core, 21 HS06/core with HT off). The typical collision runs (blue scatter plot) can be only qualitatively compared with the performance in high-μ run 335302 (red boxes), which had special data-taking conditions. Furthermore, the high-μ run jobs were configured to produce only AOD outputs, whereas standard jobs proceeded with 12 additional output types (different DRAW, DESD, DAOD and HIST), which takes extra processing time. The behaviour of the tracking reconstruction, which dominates the CPU use at high pileup, for High Luminosity LHC conditions with an upgraded tracking detector has been studied in reference [1].

[1] "Technical Design Report for the ATLAS ITk Pixel Detector", ATLAS Collaboration, CERN-LHCC-2017-021, ATLAS-TDR-030, Geneva 2018.
 
Changed:
<
<
mu_walltime_fit_combined2.png
pdf-file, png-file

The dependency of reconstruction wall time per event on the average number of interactions per bunch crossing is shown. The plot contains a selection of Tier-0 jobs reconstructing RAW data from 13 TeV pp LHC collisions in 2017. Each reconstruction job was required to run on one core of a 16-core machine with Intel(R) Xeon(R) CPU @ 2.40 GHz and memory of 4 GB/core. An exponential fit (yellow dashed line) to the typical collision runs (blue scatter plot) is being compared with the performance in special high-mu run 335302 (red boxes). The high-mu run jobs were configured to produce only AOD outputs, whereas standard jobs proceeded with 12 additional output types (different DRAW, DESD, DAOD and HIST), which take extra processing time. mu_walltime_fit_combined.png
pdf-file, png-file
>
>
reco_WtPerEvent_NOfit_revised.png
pdf-file, png-file
 
Line: 336 to 327
 
META FILEATTACHMENT attachment="mu_walltime_fit_combined.pdf" attr="h" comment="Tier0muvsWalltime" date="1511950734" name="mu_walltime_fit_combined.pdf" path="mu_walltime_fit_combined.pdf" size="23798" user="costanzo" version="1"
META FILEATTACHMENT attachment="mu_walltime_fit_combined.eps" attr="h" comment="Tier0muvsWalltime" date="1511950734" name="mu_walltime_fit_combined.eps" path="mu_walltime_fit_combined.eps" size="34561" user="costanzo" version="1"
META FILEATTACHMENT attachment="mu_walltime_fit_combined.png" attr="h" comment="Tier0muvsWalltime" date="1511950734" name="mu_walltime_fit_combined.png" path="mu_walltime_fit_combined.png" size="178347" user="costanzo" version="1"
Changed:
<
<
META FILEATTACHMENT attachment="mu_walltime_fit_combined2.pdf" attr="" comment="" date="1513159588" name="mu_walltime_fit_combined2.pdf" path="mu_walltime_fit_combined2.pdf" size="18764" user="costanzo" version="1"
>
>
META FILEATTACHMENT attachment="mu_walltime_fit_combined2.pdf" attr="" comment="" date="1537187945" name="mu_walltime_fit_combined2.pdf" path="mu_walltime_fit_combined2.pdf" size="62563" user="guenther" version="2"
 
META FILEATTACHMENT attachment="mu_walltime_fit_combined2.png" attr="h" comment="" date="1513159617" name="mu_walltime_fit_combined2.png" path="mu_walltime_fit_combined2.png" size="167623" user="costanzo" version="1"
META FILEATTACHMENT attachment="cpuHLLHC.pdf" attr="h" comment="" date="1513160035" name="cpuHLLHC.pdf" path="cpuHLLHC.pdf" size="15452" user="costanzo" version="1"
META FILEATTACHMENT attachment="cpuHLLHC.png" attr="h" comment="" date="1513160035" name="cpuHLLHC.png" path="cpuHLLHC.png" size="131654" user="costanzo" version="1"
META FILEATTACHMENT attachment="diskHLLHC.pdf" attr="h" comment="" date="1513160035" name="diskHLLHC.pdf" path="diskHLLHC.pdf" size="15583" user="costanzo" version="1"
META FILEATTACHMENT attachment="diskHLLHC.png" attr="h" comment="" date="1513160035" name="diskHLLHC.png" path="diskHLLHC.png" size="124028" user="costanzo" version="1"
Added:
>
>
META FILEATTACHMENT attachment="reco_WtPerEvent_NOfit_revised.pdf" attr="" comment="" date="1537187710" name="reco_WtPerEvent_NOfit_revised.pdf" path="reco_WtPerEvent_NOfit_revised.pdf" size="62563" user="guenther" version="1"
META FILEATTACHMENT attachment="reco_WtPerEvent_NOfit_revised.png" attr="" comment="" date="1537186820" name="reco_WtPerEvent_NOfit_revised.png" path="reco_WtPerEvent_NOfit_revised.png" size="66438" user="guenther" version="1"
META FILEATTACHMENT attachment="reco_WtPerEvent_NOfit_revised_copy.pdf" attr="" comment="" date="1537187881" name="reco_WtPerEvent_NOfit_revised_copy.pdf" path="reco_WtPerEvent_NOfit_revised_copy.pdf" size="62563" user="guenther" version="1"
 
This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2019 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback