Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published December 30, 2020 | Version v1
Conference paper Open

From tasks graphs to asynchronous distributed checkpointing with local restart

  • 1. University of Bordeaux, Inria Bordeaux - Sud-Ouest, Bordeaux, France

Description

The ever-increasing number of computation units assembled in current HPC platforms leads to a concerning increase in fault probability. Traditional checkpoint/restart strategies avoid wasting large amounts of computation time when such fault occurs. With the increasing amount of data dealt with by current applications, these strategies however suffer from their data transfer demand becoming unreasonable, or the entailed global synchronizations. Meanwhile, the current trend towards task-based programming is an opportunity to revisit the principles of the checkpoint/restart strategies. We here propose a checkpointing scheme which is closely tied to the execution of task graphs. We describe how it allows for completely asynchronous and distributed checkpointing, as well as localized node restart, thus opening up for very large scalability. We also show how a synergy between the application data transfers and the checkpointing transfers can lead to a reasonable additional network load, measured to be lower than +10 % on a dense linear algebra example.

Files

publication-1.pdf

Files (384.7 kB)

Name Size Download all
md5:f53e78a05c8d25c7ab18b83844c9c75c
384.7 kB Preview Download

Additional details

Funding

EXA2PRO – Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems 801015
European Commission