This short paper deals with parallel scientific applications using non-blocking and periodic coordinated checkpointing to enforce resilience. We provide a model and detailed formulas for total execution time and consumed energy. We characterize the optimal period for both objectives, and we assess the range of time/energy trade-offs to be made by instantiating the model with a set of realistic scenarios for Exascale systems. We give a particular emphasis to I/O transfers, because the relative cost of communication is expected to dramatically increase, both in terms of latency and consumed energy, for future Exascale platforms.
@article{arxiv.1310.8456,
title = {Optimal Checkpointing Period: Time vs. Energy},
author = {Guillaume Aupy and Anne Benoit and Thomas Hérault and Yves Robert and Jack Dongarra},
journal= {arXiv preprint arXiv:1310.8456},
year = {2013}
}
Comments
To be published in PMBS'13 (satellite workshop of SC'13). This work was supported in part by ANR RESCUE