Por favor, use este identificador para citar o enlazar este ítem:https://uvadoc.uva.es/handle/10324/58515
Título
EPSILOD: efficient parallel skeleton for generic iterative stencil computations in distributed GPUs
Autor
Año del Documento
2023
Editorial
Springer
Descripción
Producción Científica
Documento Fuente
The Journal of Supercomputing, 2023.
Abstract
Iterative stencil computations are widely used in numerical simulations. They
present a high degree of parallelism, high locality and mostly-coalesced memory
access patterns. Therefore, GPUs are good candidates to speed up their computa-
tion. However, the development of stencil programs that can work with huge grids in
distributed systems with multiple GPUs is not straightforward, since it requires solv-
ing problems related to the partition of the grid across nodes and devices, and the
synchronization and data movement across remote GPUs. In this work, we present
EPSILOD, a high-productivity parallel programming skeleton for iterative stencil
computations on distributed multi-GPUs, of the same or different vendors that sup-
ports any type of n-dimensional geometric stencils of any order. It uses an abstract
specification of the stencil pattern (neighbors and weights) to internally derive the
data partition, synchronizations and communications. Computation is split to better
overlap with communications. This paper describes the underlying architecture of
EPSILOD, its main components, and presents an experimental evaluation to show
the benefits of our approach, including a comparison with another state-of-the-art
solution. The experimental results show that EPSILOD is faster and shows good
strong and weak scalability for platforms with both homogeneous and heterogene-
ous types of GPU
Materias Unesco
12 Matemáticas
1203.17 Informática
Palabras Clave
Distributed memory
GPU
Heterogeneous
Stencil
Parallel skeletons
ISSN
0920-8542
Revisión por pares
SI
Patrocinador
Junta de Castilla y León, Ministerio de Economía, Industria y Competitividad, y Fondo Europeo de Desarrollo Regional (FEDER): Proyecto PCAS (TIN2017-88614-R) y Proyecto PROPHET-2 (VA226P20).
Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación y “European Union NextGenerationEU/PRTR” : (MCIN/ AEI/10.13039/501100011033) - grant TED2021-130367B-I00
CTE-POWER and Minotauro and the technical support provided by Barcelona Supercomputing Center (RES-IM-2021-2-0005, RES-IM-2021-3-0024, RES- IM-2022-1-0014).
Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE
Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación y “European Union NextGenerationEU/PRTR” : (MCIN/ AEI/10.13039/501100011033) - grant TED2021-130367B-I00
CTE-POWER and Minotauro and the technical support provided by Barcelona Supercomputing Center (RES-IM-2021-2-0005, RES-IM-2021-3-0024, RES- IM-2022-1-0014).
Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE
Version del Editor
Propietario de los Derechos
© 2023 The Author(s)
Idioma
eng
Tipo de versión
info:eu-repo/semantics/publishedVersion
Derechos
openAccess
Collections
Files in this item
![Atribución 4.0 Internacional](/themes/Mirage2//images/creativecommons/cc-by.png)