Energy-Performance Modeling of Speculative Checkpointing for Exascale Systems

Muhammad ALFIAN AMRIZAL  Atsuya UNO  Yukinori SATO  Hiroyuki TAKIZAWA  Hiroaki KOBAYASHI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.12   pp.2749-2760
Publication Date: 2017/12/01
Online ISSN: 1745-1361
Type of Manuscript: Special Section PAPER (Special Section on Parallel and Distributed Computing and Networking)
Category: High performance computing
Keyword: 
checkpoint/restart,  coordinated checkpointing,  speculative checkpointing,  exascale,  performance model,  execution time,  energy consumption,  

Full Text: PDF(1.2MB)
>>Buy this Article


Summary: 
Coordinated checkpointing is a widely-used checkpoint/restart protocol for fault-tolerance in large-scale HPC systems. However, this protocol will involve massive amounts of I/O concentration, resulting in considerably high checkpoint overhead and high energy consumption. This paper focuses on speculative checkpointing, a CPR mechanism that allows for temporal distribution of checkpointings to avoid I/O concentration. We propose execution time and energy models for speculative checkpointing, and investigate energy-performance characteristics when speculative checkpointing is adopted in exascale systems. Using these models, we study the benefit of speculative checkpointing over coordinated checkpointing under various realistic scenarios for exascale HPC systems. We show that, compared to coordinated checkpointing, speculative checkpointing can achieve up to a 11% energy reduction at the cost of a relatively-small increase in the execution time. In addition, a significant energy-performance trade-off is expected when the system scale exceeds 1.2 million nodes.