Performance improvements of parallel applications thanks to MPI-4.0 Hints - Archive ouverte HAL Access content directly
Conference Papers Year :

Performance improvements of parallel applications thanks to MPI-4.0 Hints

(1, 2) , (3, 4, 2) , (4, 3) , (4, 3, 2) , (1, 2) , (1)
1
2
3
4

Abstract

HPC systems have experienced significant growth over the past years, with modern machines having hundreds of thousands of nodes. Message Passing Interface (MPI) is the de facto standard for distributed computing on these architectures. On the MPI critical path, the message-matching process is one of the most time-consuming operations. In this process, searching for a specific request in a message queue represents a significant part of the communication latency. So far, no miracle algorithm performs well in all cases. This paper explores potential matching specializations thanks to hints introduced in the latest MPI 4.0 standard. We propose a hash-table-based algorithm that performs constant time message-matching for no wildcard requests. This approach is suitable for intensive point-to-point communication phases in many applications (more than 50% of CORAL benchmarks). We demonstrate that our approach can improve the overall execution time of real HPC applications by up to 25%. Also, we analyze the limitations of our method and propose a strategy for identifying the most suitable algorithm for a given application. Indeed, we apply machine learning techniques for classifying applications depending on their message pattern characteristics.
Fichier principal
Vignette du fichier
SBAC_PAD_2022___IEEE_Conference_Template-1.pdf (663.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03793122 , version 1 (30-09-2022)

Identifiers

  • HAL Id : hal-03793122 , version 1

Cite

Maxim Moraru, Adrien Roussel, Hugo Taboada, Marc Pérache, Christophe Jaillet, et al.. Performance improvements of parallel applications thanks to MPI-4.0 Hints. IEEE SBAC-PAD 2022 - 34th International Symposium on Computer Architecture and High Performance Computing, Nov 2022, Bordeaux, France. ⟨hal-03793122⟩
28 View
1 Download

Share

Gmail Facebook Twitter LinkedIn More