TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods

Kiril Dichev; Dimitrios S. Nikolopoulos

doi:10.1109/CLUSTER.2016.86

TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods

Kiril Dichev, Dimitrios S. Nikolopoulos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

TwinPCG pays off where relatively high soft fault rates are anticipated. We see this possibility mainly in the area of nearthreshold voltage computing. In this domain, TwinPCG, and its dual redundancy, is a better choice than more resource-intensive strategies like TMR.

Original language	English
Title of host publication	2016 IEEE International Conference on Cluster Computing (CLUSTER)
Publisher	IEEE Computer Society
Pages	162-163
Number of pages	2
DOIs	https://doi.org/10.1109/CLUSTER.2016.86
Publication status	Published - 08 Dec 2016

Publication series

Name
ISSN (Electronic)	2168-9253

Access to Document

10.1109/CLUSTER.2016.86Licence: Unspecified

Fingerprint Dive into the research topics of 'TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods'. Together they form a unique fingerprint.

2 Finished

R6520CSC: An Exascale Programming, Multi-objective Optimisation and Resilience Management Environment Based on Nested Recursive Parallelism
Nikolopoulos, D. & Trehan, A.
12/06/2015 → 30/09/2018
Project: Research
R1485CSC: SERT: Scale-free, Energy-Aware and Resilient Adaptation of CSE Applications to Mega-Core Systems
Nikolopoulos, D., Scott, S., Vandierendonck, H. & de Supinski, B.
13/11/2014 → 30/09/2018
Project: Research

Cite this

@inproceedings{4efc35a242df4411873ad013e58d1d26,

title = "TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods",

abstract = "TwinPCG pays off where relatively high soft fault rates are anticipated. We see this possibility mainly in the area of nearthreshold voltage computing. In this domain, TwinPCG, and its dual redundancy, is a better choice than more resource-intensive strategies like TMR.",

author = "Kiril Dichev and Nikolopoulos, {Dimitrios S.}",

year = "2016",

month = dec,

day = "8",

doi = "10.1109/CLUSTER.2016.86",

language = "English",

publisher = "IEEE Computer Society",

pages = "162--163",

booktitle = "2016 IEEE International Conference on Cluster Computing (CLUSTER)",

}

TY - GEN

T1 - TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods

AU - Dichev, Kiril

AU - Nikolopoulos, Dimitrios S.

PY - 2016/12/8

Y1 - 2016/12/8

N2 - TwinPCG pays off where relatively high soft fault rates are anticipated. We see this possibility mainly in the area of nearthreshold voltage computing. In this domain, TwinPCG, and its dual redundancy, is a better choice than more resource-intensive strategies like TMR.

AB - TwinPCG pays off where relatively high soft fault rates are anticipated. We see this possibility mainly in the area of nearthreshold voltage computing. In this domain, TwinPCG, and its dual redundancy, is a better choice than more resource-intensive strategies like TMR.

U2 - 10.1109/CLUSTER.2016.86

DO - 10.1109/CLUSTER.2016.86

M3 - Conference contribution

SP - 162

EP - 163

BT - 2016 IEEE International Conference on Cluster Computing (CLUSTER)

PB - IEEE Computer Society

ER -

TwinPCG: Dual Thread Redundancy with Forward Recovery for Preconditioned Conjugate Gradient Methods

Abstract

Publication series

Access to Document

R6520CSC: An Exascale Programming, Multi-objective Optimisation and Resilience Management Environment Based on Nested Recursive Parallelism

R1485CSC: SERT: Scale-free, Energy-Aware and Resilient Adaptation of CSE Applications to Mega-Core Systems

Cite this