QMPI: A next generation MPI profiling interface for modern HPC platforms

Bengisu Elis, Dai Yang, Martin Schulz

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

1 Zitat (Scopus)

Abstract

As we approach exascale and start planning for beyond, the rising complexity of systems and applications demands new monitoring, analysis, and optimization approaches. This requires close coordination with the parallel programming system used, which for HPC in most cases includes MPI, the Message Passing Interface. While MPI provides comprehensive tool support in the form of the MPI Profiling interface, PMPI, which has inspired a generation of tools, it is not sufficient for the new arising challenges. In particular, it does not support modern software design principles nor the composition of multiple monitoring solutions from multiple agents or sources. We approach these gaps and present QMPI, as a possible successor to PMPI. In this paper, we present the use cases and requirements that drive its development, offer a prototype design and implementation, and demonstrate its effectiveness and low overhead.

OriginalspracheEnglisch
TitelProceedings of the 26th European MPI Users'' Group Meeting, EuroMPI 2019
Redakteure/-innenTorsten Hoefler, Jesper Larsson Traff
Herausgeber (Verlag)Association for Computing Machinery
ISBN (elektronisch)9781450371759
DOIs
PublikationsstatusVeröffentlicht - 11 Sept. 2019
Veranstaltung26th European MPI Users'' Group Meeting, EuroMPI 2019 - Zurich, Schweiz
Dauer: 11 Sept. 201913 Sept. 2019

Publikationsreihe

NameACM International Conference Proceeding Series

Konferenz

Konferenz26th European MPI Users'' Group Meeting, EuroMPI 2019
Land/GebietSchweiz
OrtZurich
Zeitraum11/09/1913/09/19

Fingerprint

Untersuchen Sie die Forschungsthemen von „QMPI: A next generation MPI profiling interface for modern HPC platforms“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren