2002 · 16 citations · 4 references
ComputingComputer EngineeringComputer ScienceCluster ComputingMessage PassingParallel ComputingConcurrent ModelingConcurrent ProgrammingData ParallelismParallel ArchitecturesParallel ComputationTask ParallelismExecution Time AnalysisInteraction Pattern AnalysisMessage Passing InterfaceParallel Image ProcessingParallel ProcessingTask MappingTask Parallel Programming ModelsTask-level Parallelism
The efficient mapping of parallel tasks is essential in order to exploit the gain from parallelisation. In this work, we focus on modelling and mapping message-passing applications that are defined by the programmer with an arbitrary interaction pattern among tasks. A new model is proposed, known as TTIG (Temporal Task Interaction Graph), which captures not only computation and communication costs, but also the percentages of concurrency between tasks. From this model, a mapping strategy is developed that minimises expected execution time by properly exploiting task parallelism. The effectiveness of this approach has been proven for a real image-processing application on a cluster of PCs.
4
Clustering and reassignment-based mapping strategy for message-passing architectures
Miquel A. Senar, A. Ripoll, Ana Cortés et al. · 2002 · 10 citations