MPI runtime error detection with MUST: Advances in deadlock detection

Tobias Hilbrich, Joachim Protze, Martin Schulz, Bronis R. De Supinski, Matthias S. Müller

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

46 Zitate (Scopus)

Abstract

The widely used Message Passing Interface (MPI) is complex and rich. As a result, application developers require automated tools to avoid and to detect MPI programming errors. We present the Marmot Umpire Scalable Tool (MUST) that detects such errors with significantly increased scalability. We present improvements to our graph-based deadlock detection approach for MPI, which cover future MPI extensions. Our enhancements also check complex MPI constructs that no previous graph-based detection approach handled correctly. Finally, we present optimizations for the processing of MPI operations that reduce runtime deadlock detection overheads. Existing approaches often require O(p) analysis time per MPI operation, for p processes. We empirically observe that our improvements lead to sub-linear or better analysis time per operation for a wide range of real world applications.

OriginalspracheEnglisch
Titel2012 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012
DOIs
PublikationsstatusVeröffentlicht - 2012
Extern publiziertJa
Veranstaltung2012 24th International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012 - Salt Lake City, UT, USA/Vereinigte Staaten
Dauer: 10 Nov. 201216 Nov. 2012

Publikationsreihe

NameInternational Conference for High Performance Computing, Networking, Storage and Analysis, SC
ISSN (Print)2167-4329
ISSN (elektronisch)2167-4337

Konferenz

Konferenz2012 24th International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012
Land/GebietUSA/Vereinigte Staaten
OrtSalt Lake City, UT
Zeitraum10/11/1216/11/12

Fingerprint

Untersuchen Sie die Forschungsthemen von „MPI runtime error detection with MUST: Advances in deadlock detection“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren