Skip to main content

Research Repository

Advanced Search

teaMPI---replication-based resiliency without the (performance) pain

Samfass, Philipp; Weinzierl, Tobias; Hazelwood, Benjamin; Bader, Michael

teaMPI---replication-based resiliency without the (performance) pain Thumbnail


Authors

Philipp Samfass

Benjamin Hazelwood

Michael Bader



Contributors

Ponnuswamy Sadayappan
Editor

Bradford L. Chamberlain
Editor

Guido Juckeland
Editor

Hatem Ltaief
Editor

Abstract

In an era where we can not afford to checkpoint frequently, replication is a generic way forward to construct numerical simulations that can continue to run even if hardware parts fail. Yet, replication often is not employed on larger scales, as naïvely mirroring a computation once effectively halves the machine size, and as keeping replicated simulations consistent with each other is not trivial. We demonstrate for the ExaHyPE engine—a task-based solver for hyperbolic equation systems—that it is possible to realise resiliency without major code changes on the user side, while we introduce a novel algorithmic idea where replication reduces the time-to-solution. The redundant CPU cycles are not burned “for nothing”. Our work employs a weakly consistent data model where replicas run independently yet inform each other through heartbeat messages whether they are still up and running. Our key performance idea is to let the tasks of the replicated simulations share some of their outcomes, while we shuffle the actual task execution order per replica. This way, replicated ranks can skip some local computations and automatically start to synchronise with each other. Our experiments with a production-level seismic wave-equation solver provide evidence that this novel concept has the potential to make replication affordable for large-scale simulations in high-performance computing.

Citation

Samfass, P., Weinzierl, T., Hazelwood, B., & Bader, M. (2020). teaMPI---replication-based resiliency without the (performance) pain. In P. Sadayappan, B. L. Chamberlain, G. Juckeland, & H. Ltaief (Eds.), High Performance Computing: 35th International Conference, ISC High Performance 2020, Frankfurt/Main, Germany, June 22–25, 2020 ; proceedings (455-473). https://doi.org/10.1007/978-3-030-50743-5_23

Conference Name ISC High Performance
Conference Location Frankfurt
Acceptance Date May 15, 2020
Online Publication Date Jun 15, 2020
Publication Date 2020
Deposit Date May 25, 2020
Publicly Available Date Mar 28, 2024
Publisher Springer Verlag
Volume 12151
Pages 455-473
Series Title Lecture Notes in Computer Science
Book Title High Performance Computing: 35th International Conference, ISC High Performance 2020, Frankfurt/Main, Germany, June 22–25, 2020 ; proceedings.
ISBN 9783030507428
DOI https://doi.org/10.1007/978-3-030-50743-5_23
Public URL https://durham-repository.worktribe.com/output/1141068

Files

Accepted Conference Proceeding (1.6 Mb)
PDF

Copyright Statement
This a post-peer-review, pre-copyedit version of a chapter published in High Performance Computing: 35th International Conference, ISC High Performance 2020, Frankfurt/Main, Germany, June 22–25, 2020 ; proceedings. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-50743-5_23





You might also like



Downloadable Citations