Fault tolerant matrix operations using checksum and reverse computation

Y. Kim; J. S. Plank; J. J. Dongarra

Fault tolerant matrix operations using checksum and reverse computation

Y. Kim
, J. S. Plank
, J. J. Dongarra

Research output: Contribution to conference › Paper › peer-review

13 Scopus citations

Abstract

In this paper, we present a technique, based on checksum and reverse computation, that enables high-performance matrix operations to be fault-tolerant with low overhead. We have implemented this technique on five matrix operations: matrix multiplication, Cholesky factorization, LV factorization, QR factorization and Hessenberg reduction. The overhead of checkpointing and recovery is analyzed both theoretically and experimentally. These analyses confirm that our technique can provide fault tolerance for these high-performance matrix operations with low overhead.

Original language	English
Pages	70-77
Number of pages	8
State	Published - 1996
Externally published	Yes
Event	Proceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96 - Annapolis, MD, USA Duration: Oct 27 1996 → Oct 31 1996

Conference

Conference	Proceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96
City	Annapolis, MD, USA
Period	10/27/96 → 10/31/96

Cite this

@conference{7181289d20454dd8abf9f10c6d40ee93,

title = "Fault tolerant matrix operations using checksum and reverse computation",

abstract = "In this paper, we present a technique, based on checksum and reverse computation, that enables high-performance matrix operations to be fault-tolerant with low overhead. We have implemented this technique on five matrix operations: matrix multiplication, Cholesky factorization, LV factorization, QR factorization and Hessenberg reduction. The overhead of checkpointing and recovery is analyzed both theoretically and experimentally. These analyses confirm that our technique can provide fault tolerance for these high-performance matrix operations with low overhead.",

author = "Y. Kim and Plank, \{J. S.\} and Dongarra, \{J. J.\}",

year = "1996",

language = "English",

pages = "70--77",

note = "Proceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96 ; Conference date: 27-10-1996 Through 31-10-1996",

}

TY - CONF

T1 - Fault tolerant matrix operations using checksum and reverse computation

AU - Kim, Y.

AU - Plank, J. S.

AU - Dongarra, J. J.

PY - 1996

Y1 - 1996

N2 - In this paper, we present a technique, based on checksum and reverse computation, that enables high-performance matrix operations to be fault-tolerant with low overhead. We have implemented this technique on five matrix operations: matrix multiplication, Cholesky factorization, LV factorization, QR factorization and Hessenberg reduction. The overhead of checkpointing and recovery is analyzed both theoretically and experimentally. These analyses confirm that our technique can provide fault tolerance for these high-performance matrix operations with low overhead.

AB - In this paper, we present a technique, based on checksum and reverse computation, that enables high-performance matrix operations to be fault-tolerant with low overhead. We have implemented this technique on five matrix operations: matrix multiplication, Cholesky factorization, LV factorization, QR factorization and Hessenberg reduction. The overhead of checkpointing and recovery is analyzed both theoretically and experimentally. These analyses confirm that our technique can provide fault tolerance for these high-performance matrix operations with low overhead.

UR - https://www.scopus.com/pages/publications/0030398726

M3 - Paper

AN - SCOPUS:0030398726

SP - 70

EP - 77

T2 - Proceedings of the 1996 6th Symposium on the Frontiers of Massively Parallel Computing, Frontiers'96

Y2 - 27 October 1996 through 31 October 1996

ER -

Fault tolerant matrix operations using checksum and reverse computation

Abstract

Conference

Other files and links

Fingerprint

Cite this