MPI Progress For All

The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective computation and communication overlap. The opaque nature of MPI progress poses significant challenges in advancing MPI with...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis s. 425 - 435
Hlavní autori: Zhou, Hui, Latham, Robert, Raffenetti, Ken, Guo, Yanfei, Thakur, Rajeev
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 17.11.2024
Predmet:
Asynchronous communication
Complexity theory
Conferences
Engines
Guidelines
High performance computing
Message passing
mpi
mpi interoperability
mpi progress
mpi+x
mpich
Programming
Runtime
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective computation and communication overlap. The opaque nature of MPI progress poses significant challenges in advancing MPI within modern high-performance computing practices. First, the lack of clarity hinders the development of explicit guidelines for enhancing computation and communication overlap in applications. Second, it prevents MPI from seamlessly integrating with contemporary programming paradigms, such as task-based runtimes and event-driven programming. Third, it limits the extension of MPI functionality from user space. In this paper, we examine the role of MPI progress by analyzing the implementation details of MPI messaging. We then generalize the asynchronous communication pattern and identify key factors influencing application performance. Based on this analysis, we propose a set of MPI extensions designed to enable users to construct and manage an efficient progress engine explicitly. We compare our approach to previous efforts in the field, highlighting its reduced complexity and increased effectiveness.
DOI:10.1109/SCW63240.2024.00063