001019363 001__ 1019363
001019363 005__ 20250822121436.0
001019363 0247_ $$2doi$$a10.5281/ZENODO.5745504
001019363 037__ $$aFZJ-2023-05333
001019363 041__ $$aEnglish
001019363 1001_ $$00000-0002-5699-1793$$aGarcia de Gonzalo, Simon$$b0
001019363 1112_ $$aISC High Performance 2023$$cHamburg$$d2023-05-21 - 2023-05-21$$gISC23$$wGermany
001019363 245__ $$aEfficient Distributed GPU Programming for Exascale
001019363 260__ $$c2023
001019363 3367_ $$2DRIVER$$alecture
001019363 3367_ $$031$$2EndNote$$aGeneric
001019363 3367_ $$2BibTeX$$aMISC
001019363 3367_ $$0PUB:(DE-HGF)17$$2PUB:(DE-HGF)$$aLecture$$blecture$$mlecture$$s1703051177_23279$$xAfter Call
001019363 3367_ $$2ORCID$$aLECTURE_SPEECH
001019363 3367_ $$2DataCite$$aText
001019363 500__ $$aGithub repository: https://github.com/FZJ-JSC/tutorial-multi-gpu/tree/v4.0-isc23
001019363 520__ $$aOver the past years, GPUs became ubiquitous in HPC installations around the world, delivering the majority of performance of some of the largest supercomputers (e.g. Summit, Sierra, JUWELS Booster). This trend continues in the recently deployed and upcoming Pre-Exascale and Exascale systems (LUMI, Leonardo; Frontier, Perlmutter): GPUs are chosen as the core computing devices to enter this next era of HPC. To take advantage of future GPU-accelerated systems with tens of thousands of devices, application developers need to have the propers skills and tools to understand, manage, and optimize distributed GPU applications. In this tutorial, participants will learn techniques to efficiently program large-scale multi-GPU systems. While programming multiple GPUs with MPI is explained in detail, also advanced tuning techniques and complementing programming models like NCCL and NVSHMEM are presented. Tools for analysis are shown and used to motivate and implement performance optimizations. The tutorial teaches fundamental concepts that apply to GPU-accelerated systems in general, taking the NVIDIA platform as an example. It is a combination of lectures and hands-on exercises, using one of Europe's fastest supercomputers, JUWELS Booster, for interactive learning and discovery.
001019363 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001019363 536__ $$0G:(DE-HGF)POF4-5122$$a5122 - Future Computing & Big Data Systems (POF4-512)$$cPOF4-512$$fPOF IV$$x1
001019363 536__ $$0G:(DE-Juel-1)ATML-X-DEV$$aATML-X-DEV - ATML Accelerating Devices (ATML-X-DEV)$$cATML-X-DEV$$x2
001019363 588__ $$aDataset connected to DataCite
001019363 7001_ $$0P:(DE-Juel1)145478$$aHerten, Andreas$$b1$$eCorresponding author$$ufzj
001019363 7001_ $$0P:(DE-Juel1)180799$$aHrywniak, Markus$$b2$$ufzj
001019363 7001_ $$0P:(DE-Juel1)137023$$aKraus, Jiri$$b3$$ufzj
001019363 7001_ $$0P:(DE-Juel1)172093$$aOden, Lena$$b4
001019363 773__ $$a10.5281/ZENODO.5745504
001019363 8564_ $$uhttps://zenodo.org/records/7981538
001019363 909CO $$ooai:juser.fz-juelich.de:1019363$$pVDB
001019363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)145478$$aForschungszentrum Jülich$$b1$$kFZJ
001019363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180799$$aForschungszentrum Jülich$$b2$$kFZJ
001019363 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)137023$$aForschungszentrum Jülich$$b3$$kFZJ
001019363 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001019363 9131_ $$0G:(DE-HGF)POF4-512$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5122$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vSupercomputing & Big Data Infrastructures$$x1
001019363 9141_ $$y2023
001019363 920__ $$lyes
001019363 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001019363 980__ $$alecture
001019363 980__ $$aVDB
001019363 980__ $$aI:(DE-Juel1)JSC-20090406
001019363 980__ $$aUNRESTRICTED