Abstract

Algorithm based fault tolerance (ABFT) attracts renewed interest for its extremely low overhead and good scalability. However the fault model used to design ABFT has been either abstract, simplistic, or both, leaving a gap between what occurs at the architecture level and what the algorithm expects. As the fault model is the deciding factor in choosing an effective checksum scheme, the resulting ABFT techniques have seen limited impact in practice. In this paper we seek to close the gap by directly using a comprehensive architectural fault model and devise a comprehensive ABFT scheme that can tolerate multiple architectural faults of various kinds. We implement the new ABFT scheme into high performance linpack (HPL) to demonstrate the feasibility in large scale high performance benchmark. We conduct architectural fault injection experiments and large scale experiments to empirically validate its fault tolerance and demonstrate the overhead of error handling, respectively.

Meeting Name

25th ACM International Symposium on High-Performance Parallel and Distributed Computing, HPDC '16 (2016: May 31-Jun. 4, Kyoto, Japan)

Department(s)

Computer Science

Comments

This work is partially supported by the NSF grants CCF-1305622, ACI-1305624, CCF-1513201, the SZSTI basic research pro- gram JCYJ20150630114942313, and the Special Program for Applied Research on Super Computation of the NSFC- Guangdong Joint Fund (the second phase).

International Standard Book Number (ISBN)

978-145034314-5

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2016 Association for Computing Machinery (ACM), All rights reserved.

Publication Date

31 May 2016

Download

Full Text Link

Share

 
COinS