Issue No.04 - April (2009 vol.20)
Nikolaos Drosinos , National Technical University of Athens, Heroon Polytechniou, Zografou
Georgios Goumas , National Technical University of Athens, Heroon Polytechniou, Zografou
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPDS.2008.114
In this paper we revisit the supernode-shape selection problem, that has been widely discussed in bibliography. In general, the selection of the supernode transformation greatly affects the parallel execution time of the transformed algorithm. Since the minimization of the overall parallel execution time via an appropriate supernode transformation is very difficult to accomplish, researchers have focused on scheduling-aware supernode transformations that maximize parallelism during the execution. In this paper we argue that the communication volume of the transformed algorithm is an important criterion, and its minimization should be given high priority. For this reason we define the metric of the per process communication volume and propose a method to miminize this metric by selecting a communication-aware supernode shape. Our approach is equivalent to defining a proper Cartesian process grid with MPI_Cart_Create, which means that it can be incorporated in applications in a straightforward manner. Our experimental results illustrate that by selecting the tile shape with the proposed method, the total parallel execution time is significantly reduced due to the minimization of the communication volume, despite the fact that a few more parallel execution steps are required.
I/O and Data Communications, Load balancing and task assignment, Parallel processors, Parallel Architectures, Scheduling and task partitioning, Data communications
Nikolaos Drosinos, Georgios Goumas, "Communication-Aware Supernode Shape", IEEE Transactions on Parallel & Distributed Systems, vol.20, no. 4, pp. 498-511, April 2009, doi:10.1109/TPDS.2008.114