000824330 001__ 824330
000824330 005__ 20250314084115.0
000824330 020__ $$a978-1-5090-5226-4
000824330 0247_ $$2doi$$a10.1109/vpa.2016.7
000824330 037__ $$aFZJ-2016-06939
000824330 1001_ $$0P:(DE-HGF)0$$aVierjahn, Tom$$b0$$eCorresponding author
000824330 1112_ $$aThe 3rd International Workshop on Visual Performance Analysis$$cSalt Lake City, Utah$$d2016-11-18 - 2016-11-18$$gVPA'16$$wUSA
000824330 245__ $$aUsing Directed Variance to Identify Meaningful Views in Call-path Performance Profiles
000824330 260__ $$aPiscataway, NJ, USA$$bIEEE Press$$c2016
000824330 29510 $$aProceedings of the 3rd International Workshop on Visual Performance Analysis
000824330 300__ $$a9-16
000824330 3367_ $$2ORCID$$aCONFERENCE_PAPER
000824330 3367_ $$033$$2EndNote$$aConference Paper
000824330 3367_ $$2BibTeX$$aINPROCEEDINGS
000824330 3367_ $$2DRIVER$$aconferenceObject
000824330 3367_ $$2DataCite$$aOutput Types/Conference Paper
000824330 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1480930659_8032
000824330 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000824330 520__ $$aUnderstanding the performance behaviour of massively parallel high-performance computing (HPC) applications based on call-path performance profiles is a time-consuming task. In this paper, we introduce the concept of directed variance in order to help analysts find performance bottlenecks in massive performance data and in the end optimize the application. According to HPC experts' requirements, our technique automatically detects severe parts in the data that expose large variation in an application's performance behaviour across system resources. Previously known variations are effectively filtered out. Analysts are thus guided through a reduced search space towards regions of interest for detailed examination in a 3D visualization. We demonstrate the effectiveness of our approach using performance data of common benchmark codes as well as from actively developed production codes.
000824330 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0
000824330 536__ $$0G:(DE-Juel1)jzam11_20091101$$aScalable Performance Analysis of Large-Scale Parallel Applications (jzam11_20091101)$$cjzam11_20091101$$fScalable Performance Analysis of Large-Scale Parallel Applications$$x1
000824330 536__ $$0G:(DE-Juel-1)ATMLPP$$aATMLPP - ATML Parallel Performance (ATMLPP)$$cATMLPP$$x2
000824330 7001_ $$0P:(DE-Juel1)168253$$aHermanns, Marc-André$$b1$$ufzj
000824330 7001_ $$0P:(DE-Juel1)132199$$aMohr, Bernd$$b2$$ufzj
000824330 7001_ $$0P:(DE-HGF)0$$aMüller, Matthias S.$$b3
000824330 7001_ $$0P:(DE-HGF)0$$aKuhlen, Torsten W.$$b4
000824330 7001_ $$0P:(DE-HGF)0$$aHentschel, Bernd$$b5
000824330 773__ $$a10.1109/vpa.2016.7
000824330 909CO $$ooai:juser.fz-juelich.de:824330$$pVDB
000824330 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b0$$kRWTH
000824330 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)168253$$aForschungszentrum Jülich$$b1$$kFZJ
000824330 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132199$$aForschungszentrum Jülich$$b2$$kFZJ
000824330 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000824330 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b4$$kRWTH
000824330 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b5$$kRWTH
000824330 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x0
000824330 9141_ $$y2016
000824330 915__ $$0StatID:(DE-HGF)0550$$2StatID$$aNo Authors Fulltext
000824330 920__ $$lyes
000824330 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000824330 9201_ $$0I:(DE-82)080012_20140620$$kJARA-HPC$$lJARA - HPC$$x1
000824330 980__ $$acontrib
000824330 980__ $$aVDB
000824330 980__ $$aUNRESTRICTED
000824330 980__ $$acontb
000824330 980__ $$aI:(DE-Juel1)JSC-20090406
000824330 980__ $$aI:(DE-82)080012_20140620