Show simple item record

dc.contributor.authorŽivanovič, Darko
dc.contributor.authorPavlovic, Milan
dc.contributor.authorRadulovic, Milan
dc.contributor.authorShin, Hyunsung
dc.contributor.authorSon, Jongpil
dc.contributor.authorMcKee, Sally A.
dc.contributor.authorCarpenter, Paul M.
dc.contributor.authorRadojkovic, Petar
dc.contributor.authorAyguadé Parra, Eduard
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2017-03-28T12:11:53Z
dc.date.available2017-03-28T12:11:53Z
dc.date.issued2017-03
dc.identifier.citationZivanovic, D., Pavlovic, M., Radulovic, M., Shin, H., Son, J., McKee, S., Carpenter, P., Radojkovic, P., Ayguade, E. Main memory in HPC: do we need more, or could we live with less?. "ACM transactions on architecture and code optimization", Març 2017, vol. 14, núm. 1, p. 3:1-3:26.
dc.identifier.issn1544-3566
dc.identifier.urihttp://hdl.handle.net/2117/102957
dc.description.abstractAn important aspect of High-Performance Computing (HPC) system design is the choice of main memory capacity. This choice becomes increasingly important now that 3D-stacked memories are entering the market. Compared with conventional Dual In-line Memory Modules (DIMMs), 3D memory chiplets provide better performance and energy efficiency but lower memory capacities. Therefore, the adoption of 3D-stacked memories in the HPC domain depends on whether we can find use cases that require much less memory than is available now. This study analyzes the memory capacity requirements of important HPC benchmarks and applications. We find that the High-Performance Conjugate Gradients (HPCG) benchmark could be an important success story for 3D-stacked memories in HPC, but High-Performance Linpack (HPL) is likely to be constrained by 3D memory capacity. The study also emphasizes that the analysis of memory footprints of production HPC applications is complex and that it requires an understanding of application scalability and target category, i.e., whether the users target capability or capacity computing. The results show that most of the HPC applications under study have per-core memory footprints in the range of hundreds of megabytes, but we also detect applications and use cases that require gigabytes per core. Overall, the study identifies the HPC applications and use cases with memory footprints that could be provided by 3D-stacked memory chiplets, making a first step toward adoption of this novel technology in the HPC domain.
dc.description.sponsorshipThis work was supported by the Collaboration Agreement between Samsung Electronics Co., Ltd. and BSC, Spanish Government through Severo Ochoa programme (SEV-2015-0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project and by the Generalitat de Catalunya (contracts 2014-SGR-1051 and 2014-SGR-1272). This work has also received funding from the European Union’s Horizon 2020 research and innovation programme under ExaNoDe project (grant agreement No 671578). Darko Zivanovic holds the Severo Ochoa grant (SVP-2014-068501) of the Ministry of Economy and Competitiveness of Spain. The authors thank Harald Servat from BSC and Vladimir Marjanovi´c from High Performance Computing Center Stuttgart for their technical support.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
dc.subject.lcshHigh performance computing
dc.subject.otherComputer systems organization
dc.subject.otherDistributed architectures
dc.subject.otherHardware
dc.subject.otherAnalysis and design of emerging devices and systems
dc.subject.otherMemory and dense storage
dc.subject.otherMemory capacity requirements
dc.subject.otherHigh-performance computing
dc.subject.otherProduction HPC applications
dc.subject.otherHPL
dc.subject.otherHPCG
dc.titleMain memory in HPC: do we need more, or could we live with less?
dc.typeArticle
dc.subject.lemacCàlcul intensiu (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions
dc.identifier.doi10.1145/3023362
dc.relation.publisherversionhttp://dl.acm.org/citation.cfm?id=3023362
dc.rights.accessOpen Access
local.identifier.drac19786606
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/SEV-2015-0493
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/TIN2015-65316-P
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/1PE/SVP-2014-068501
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/671578/EU/European Exascale Processor Memory Node Design/ExaNoDe
local.citation.authorZivanovic, D.; Pavlovic, M.; Radulovic, M.; Shin, H.; Son, J.; McKee, S.; Carpenter, P.; Radojkovic, P.; Ayguade, E.
local.citation.publicationNameACM transactions on architecture and code optimization
local.citation.volume14
local.citation.number1
local.citation.startingPage3:1
local.citation.endingPage3:26


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder