Contribution to a conference proceedings/Contribution to a book

FZJ-2016-05884

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Multi-versioning Performance Opportunities in BGAS System for Resilience

Dun, N. ; Pleiter, D. (Corresponding author)FZJ* ; Fang, A. ; Vandenbergen, N.FZJ* ; Chien, A. A.

2016
Springer International Publishing Cham
ISBN: 978-3-319-41320-4 (print), 978-3-319-41321-1 (electronic)

This record in other databases:    

Please use a persistent id in citations: doi:10.1007/978-3-319-41321-1_25

Abstract: Resilience has become a major concern in high-performance computing (HPC) systems. Addressing the increasing risk of latent errors (or silent data corruption) is one of the biggest challenges. Multi-version checkpointing system, which keeps multi-version of the application states, has been proposed as a solution and has been implemented in Global View Resilience (GVR). The resulting more sophisticated management of data introduces overheads and the resulting impact on performance need to be investigated. In this paper we explore the performance of GVR for an HPC system with integrated non-volatile memories, namely Blue Gene Active Storage (BGAS). Our empirical study shows that the BGAS system provides a significantly more efficient basis for flexible error recovery by using GVR multi-versioning features compared to using a standard external storage system attached to the same Blue Gene/Q installation. Using BGAS especially achieves at least 10×performance boost for random traversal across multiple versions due to significantly better performance for small random I/O operations.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 513 - Supercomputer Facility (POF3-513) (POF3-513)

Appears in the scientific report 2016

---

Database coverage:
Nationallizenz ; No Authors Fulltext ; SCOPUS

---