Performance Model for Parallel Matrix Multiplication with Dryad: Dataflow Graph Runtime

Download Now
Provided by: Indiana University
Topic: Big Data
Format: PDF
In order to meet the big data challenge of today's society, several parallel execution models on distributed memory architectures have been proposed: MapReduce, Iterative MapReduce, graph processing, and dataflow graph processing. Dryad is a distributed data-parallel execution engine that model program as dataflow graphs. In this paper, the authors evaluated the runtime and communication overhead of Dryad in realistic settings. They proposed a performance model for Dryad implementation of Parallel Matrix Multiplication (PMM) and extend the model to MPI implementations.
Download Now

Find By Topic