International Conference on Parallel Architectures and Compilation Techniques · 2007 · 17 citations · 14 references
ComputingComputer EngineeringComputer ScienceFault-tolerant ComputingParallel AlgorithmsParallel ComputingFault Tolerance DesignFault Tolerance In Parallel SystemsFault-tolerant Parallel AlgorithmsParallel Algorithm DesignParallel ArchitecturesParallel Computing SystemsFault Tolerance MechanismsFault Tolerant AlgorithmsFault-tolerant DesignMatrix MultiplicationParallel Algorithm AnalysisParallel Matrix AlgorithmsParallel Matrix ComputationParallel Matrix Multiplication
This paper addresses the issue of fault tolerance in parallel computing, and proposes a new method named parallel recomputing. Such method achieves fault recovery automatically by using surviving processes to recompute the workload of failed processes in parallel. The paper firstly defines the fault tolerant parallel algorithm (FTPA) as the parallel algorithm which tolerates failures by parallel recomputing. Furthermore, the paper proposes the inter-process definition-use relationship analysis method based on the conventional definition-use analysis for revealing the relationship of variables in different processes. Under the guidance of this new method, principles of fault tolerant parallel algorithm design are given. At last, the authors present the design of FTPAs for matrix-matrix multiplication and NPB kernels, and evaluate them by experiments on a cluster system. The experimental results show that the overhead of FTPA is less than the overhead of checkpointing.
14
James S. Plank, Kai Li, M.A. Puening · IEEE Transactions on Parallel and Distributed Systems · 1998 · 346 citations
Automated application-level checkpointing of MPI programs
Greg Bronevetsky, Daniel Marques, Keshav Pingali et al. · 2003 · 199 citations