Network Partitioning of Data Parallel ComputationsReport
Partitioning data parallel computations across a network of heterogeneous workstations is a difficult problem for the user. We have developed a runtime partitioning method for choosing the number and type of processors to apply to a data parallel computation, and a decomposition of the data domain in order to achieve reduced completion time. The partitioning method utilizes information about the problem in the form of callback functions and uses a set of topology-specific communication functions to estimate communication costs. We show that the method makes effective partitioning decisions and has runtime overhead that is easily tolerated. In particular, we show that for two implementations of a canonical stencil application, minimum elapsed times are obtained for a range of problem sizes on a network of heterogeneous workstations 1 .
Note: Abstract extracted from PDF text
All rights reserved (no additional license for public reuse)
Weissman, Jon, and Andrew Grimshaw. "Network Partitioning of Data Parallel Computations." University of Virginia Dept. of Computer Science Tech Report (1994).
University of Virginia, Department of Computer Science