@INPROCEEDINGS{5090713, 
title={Fault-tolerant average execution time optimization for general-purpose multi-processor system-on-chips}, 
author={Vayrynen, M. and Singh, V. and Larsson, E.}, 
booktitle={Design, Automation & Test in Europe Conference & Exhibition, 2009. DATE '09.}, 
year={2009}, 
month={April}, 
volume={}, 
number={}, 
pages={484-489}, 
abstract={Fault-tolerance is due to the semiconductor technology development important, not only for safety-critical systems but also for general-purpose (non-safety critical) systems. However, instead of guaranteeing that deadlines always are met, it is for general-purpose systems important to minimize the average execution time (AET) while ensuring fault-tolerance. For a given job and a soft (transient) error probability, we define mathematical formulas for AET that includes bus communication overhead for both voting (active replication) and rollback-recovery with checkpointing (RRC). And, for a given multi-processor system-on-chip (MPSoC), we define integer linear programming (ILP) models that minimize AET including bus communication overhead when: (1) selecting the number of checkpoints when using RRC, (2) finding the number of processors and job-to-processor assignment when using voting, and (3) defining fault-tolerance scheme (voting or RRC) per job and defining its usage for each job. Experiments demonstrate significant savings in AET.}, 
keywords={checkpointing, fault tolerance, integer programming, linear programming, microprocessor chips, probability, safety-critical software, system buses, system-on-chipbus communication overhead, fault-tolerance, fault-tolerant average execution time optimization, general-purpose multiprocessor system-on-chips, general-purpose systems, integer linear programming models, job-to-processor assignment, rollback-recovery with checkpointing, safety-critical systems, semiconductor technology development, soft error probability, voting active replication}, 
doi={}, 
ISSN={1530-1591}, }