Mostra el registre d'ítem simple
Multi-GPU parallelization of the NAS multi-zone parallel benchmarks
dc.contributor.author | González Tallada, Marc |
dc.contributor.author | Morancho Llena, Enrique |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors |
dc.date.accessioned | 2021-01-07T11:54:26Z |
dc.date.available | 2021-01-07T11:54:26Z |
dc.date.issued | 2021-01-01 |
dc.identifier.citation | González, M.; Morancho, E. Multi-GPU parallelization of the NAS multi-zone parallel benchmarks. "IEEE transactions on parallel and distributed systems", 1 Gener 2021, vol. 32, núm. 1, article 9162505, p. 229-241. |
dc.identifier.issn | 1045-9219 |
dc.identifier.uri | http://hdl.handle.net/2117/334984 |
dc.description.abstract | GPU-based computing systems have become a widely accepted solution for the high-performance-computing (HPC) domain. GPUs have shown highly competitive performance-per-watt ratios and can exploit an astonishing level of parallelism. However, exploiting the peak performance of such devices is a challenge, mainly due to the combination of two essential aspects of multi-GPU execution. On one hand, the workload should be distributed evenly among the GPUs. On the other hand, communications between GPU devices are costly and should be minimized. Therefore, a trade-of between work-distribution schemes and communication overheads will condition the overall performance of parallel applications run on multi-GPU systems. In this article we present a multi-GPU implementation of NAS Multi-Zone Parallel Benchmarks (which execution alternate communication and computational phases). We propose several work-distribution strategies that try to evenly distribute the workload among the GPUs. Our evaluations show that performance is highly sensitive to this distribution strategy, as the the communication phases of the applications are heavily affected by the work-distribution schemes applied in computational phases. In particular, we consider Static, Dynamic, and Guided schedulers to find a trade-off between both phases to maximize the overall performance. In addition, we compare those schedulers with an optimal scheduler computed offline using IBM CPLEX. On an evaluation environment composed of 2 x IBM Power9 8335-GTH and 4 x GPU NVIDIA V100 (Volta), our multi-GPU parallelization outperforms single-GPU execution from 1.48x to 1.86x (2 GPUs) and from 1.75x to 3.54x (4 GPUs). This article analyses these improvements in terms of the relationship between the computational and communication phases of the applications as the number of GPUs is increased. We prove that Guided schedulers perform at similar level as optimal schedulers. |
dc.description.sponsorship | This work was supported by the Spanish Ministry of Science and Technology (TIN2015-65316-P) and by the Generalitat de Catalunya (2014-SGR-1051). |
dc.format.extent | 13 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·leles |
dc.subject.lcsh | Graphics processing units |
dc.subject.lcsh | Parallel programming (Computer science) |
dc.subject.other | Multi-GPU parallelization |
dc.subject.other | Load balancing |
dc.subject.other | Static |
dc.subject.other | Dynamic |
dc.subject.other | Guided schedulings |
dc.title | Multi-GPU parallelization of the NAS multi-zone parallel benchmarks |
dc.type | Article |
dc.subject.lemac | Unitats de processament gràfic |
dc.subject.lemac | Programació en paral·lel (Informàtica) |
dc.contributor.group | Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions |
dc.identifier.doi | 10.1109/TPDS.2020.3015148 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/9162505 |
dc.rights.access | Open Access |
local.identifier.drac | 29925190 |
dc.description.version | Postprint (author's final draft) |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//TIN2015-65316-P/ES/COMPUTACION DE ALTAS PRESTACIONES VII/ |
dc.relation.projectid | info:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 1051 |
local.citation.author | González, M.; Morancho, E. |
local.citation.publicationName | IEEE transactions on parallel and distributed systems |
local.citation.volume | 32 |
local.citation.number | 1, article 9162505 |
local.citation.startingPage | 229 |
local.citation.endingPage | 241 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [1.049]
-
Articles de revista [382]