Efficient data redistribution for malleable applications
![Thumbnail](/xmlui/bitstream/handle/10234/205853/88622.pdf.jpg?sequence=4&isAllowed=y)
View/ Open
Impact
![Google Scholar](/xmlui/themes/Mirage2/images/uji/logo_google.png)
![Microsoft Academico](/xmlui/themes/Mirage2/images/uji/logo_microsoft.png)
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/146069
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Efficient data redistribution for malleable applicationsDate
2023Publisher
ACM Digital Library; Association for Computing MachineryISBN
979840070785Bibliographic citation
MARTÍN ÁLVAREZ, Iker, et al. Efficient data redistribution for malleable applications. In: Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis. 2023. p. 416-426Type
info:eu-repo/semantics/conferenceObjectPublisher version
https://dl.acm.org/doi/10.1145/3624062.3624110Version
info:eu-repo/semantics/publishedVersionSubject
Abstract
Process malleability can be defined as the ability of a distributed MPI parallel job to change the number of processes on–the–fly without stopping its execution, reallocating the compute resources originally assigned ... [+]
Process malleability can be defined as the ability of a distributed MPI parallel job to change the number of processes on–the–fly without stopping its execution, reallocating the compute resources originally assigned to the job, and without storing application data to disk. MPI malleability consists of four stages: resource reallocation, process management, data redistribution and execution resuming. Among them, data redistribution is the most time-consuming and determines the reconfiguration time. In this paper, we compare different implementations of this stage using point-to-point and collective MPI operations, and discuss the impact of overlapping computation-communication. We then combine these strategies with different methods to expand/shrink jobs, using a synthetic application to emulate MPI-based codes and their malleable counterparts, in order to evaluate the effect of different malleability methods in parallel distributed applications. The results show that the use of asynchronous techniques speeds up execution by 1.14 and 1.21, depending on the network used. [-]
Description
In Workshops of The International Conference on High Performance Computing, Network, Storage,
and Analysis (SC-W 2023), November 12–17, 2023, Denver, CO, USA. ACM, New York, NY, USA.
Is part of
In: Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis. 2023. p. 416-426.Funder Name
Ministerio de Ciencia, Innovación y Universidades | Agencia Estatal de Investigación | Generalitat Valenciana | Comisión Europea | Unión Europea | Ministerio de Pesca | European Union NextGenera-tionEU/PRTR
Project code
PID2020-113656RB-C21 | ACIF/2021/260 | 955606 | PCI2021-121958
Rights
info:eu-repo/semantics/openAccess