Making MPI intelligent
Abstract
Mapping parallel applications to multi-processor architectures requires information about the execution times of the concurrent processes to find an optimal allocation and must take into account the interprocessor communication at runtime, whose overheads have emerged as the major performance limitation. However, both information cannot be statically known in advance. In this paper we present a sophisticated approach for mapping parallel MPI applications to concurrent architectures using machine learning techniques. This automatically generates heuristics that provide the compiler with knowledge of the considered runtime behavior, hence yielding more precise heuristics than those generated by pure static analyses. The heuristics can be used to direct the runtime environment of MPI, which enables the reallocation of processes to other processors at runtime and, furthermore, results in a better initial allocation of MPI processes.
- Citation
- BibTeX
Tetzlaff, D. & Glesner, S.,
(2012).
Making MPI intelligent.
In:
Jähnichen, S., Rumpe, B. & Schlingloff, H.
(Hrsg.),
Software Engineering 2012. Workshopband.
Bonn:
Gesellschaft für Informatik e.V..
(S. 75-88).
@inproceedings{mci/Tetzlaff2012,
author = {Tetzlaff, Dirk AND Glesner, Sabine},
title = {Making MPI intelligent},
booktitle = {Software Engineering 2012. Workshopband},
year = {2012},
editor = {Jähnichen, Stefan AND Rumpe, Bernhard AND Schlingloff, Holger} ,
pages = { 75-88 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
author = {Tetzlaff, Dirk AND Glesner, Sabine},
title = {Making MPI intelligent},
booktitle = {Software Engineering 2012. Workshopband},
year = {2012},
editor = {Jähnichen, Stefan AND Rumpe, Bernhard AND Schlingloff, Holger} ,
pages = { 75-88 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Send Feedback
More Info
ISBN: 978-3-88579-293-2
ISSN: 1617-5468
xmlui.MetaDataDisplay.field.date: 2012
Language:
(en)

Content Type: Text/Conference Paper