Issue No. 08 - August (1993 vol. 4)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/71.238622
<p>Algorithm-based fault tolerance (ABFT) is a method for improving the reliability of parallel architectures used for computation-intensive tasks. A two-stage approach to thesynthesis of ABFT systems is proposed. In the first stage, a system-level code is chosento encode the data used in the algorithm. In the second stage, the optimal architectureto implement the scheme is chosen using dependence graphs. Dependence graphs are agraph-theoretic form of algorithm representation. The authors demonstrate that not allarchitectures are ideal for the implementation of a particular ABFT scheme. They propose new measures to characterize the fault tolerance capability of a system to better exploit the proposed synthesis method. Dependence graphs can also be used for the synthesis of ABFT schemes for non-linear problems. An example of a fault-tolerant median filter is provided to illustrate their utility for such problems.</p>
Index Termsalgorithm-based fault-tolerant systems; dependence graphs; reliability; parallelarchitectures; computation-intensive tasks; ABFT scheme; synthesis method;fault-tolerant median filter; fault tolerant computing; graph theory; parallel architectures
N. Jha and B. Vinnakota, "Synthesis of Algorithm-Based Fault-Tolerant Systems from Dependence Graphs," in IEEE Transactions on Parallel & Distributed Systems, vol. 4, no. , pp. 864-874, 1993.