A unified unconditionally stable split-step FDTD algorithm for modeling general dispersive electromagnetic applications
32-35
19.Cnf-58 Paper View Page
Title
A framework for transformational technique in the high performance computing systems
Authors
Dr. Hojat Hamidi, Khaje Nasir Toosi University of Technology, Tehran, Iran Mr. A. Vafaei, Khaje Nasir Toosi University of Technology, Tehran, Iran Mr. A. H. Monadjemi, Khaje Nasir Toosi University of Technology, Tehran, Iran
Abstract
The Algorithm Based Fault Tolerance (ABFT) approach transforms a system that does not tolerate a specific type of faults, called the fault-intolerant system, to a system that provides a specific level of fault tolerance, namely recovery. In this paper, we present a new approach to fault tolerance for High Performance Computing system. An important consideration in the design of high performance linear systems is to ensure the correctness of the results computed in the presence of transient failures. Concurrent error detection and correction have been applied to such systems in order to achieve reliability. Algorithm Based Fault Tolerance has been suggested as a cost-effective concurrent error detection scheme. This paper explores fault tolerance in a wide variety of matrix operations for parallel and distributed scientific computing. It proposes a novel computing paradigm to provide fault tolerance for numerical algorithms. The research reported in this paper has been motivated by the complexity involved in the analysis and design of ABFT systems. To that end, a matrix-based model has been developed and, based on that, algorithms for both the design and analysis of ABFT systems are formulated. These algorithms are less complex than the existing ones. In order to reduce the complexity further, a hierarchical approach is developed for the analysis of large systems.
@inproceedings{58CPE2011,
title={A framework for transformational technique in the high performance computing systems},
author={Hojat Hamidi, and A. Vafaei, and A. H. Monadjemi},
booktitle={2011 Global Congress on Communications, Propagation, and Electronics (GC-CPE 2011)},
year={2011},
pages={24-31},
doi={}},
organization={Mosharaka for Research and Studies}
}