A knowledge-based operator for a genetic algorithm which optimizes the distribution of sparse matrix data

Una May O'Reilly, Nadya Bliss, Sanjeev Mohindra, Julie Mullen, Eric Robinson

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

We present the Hogs and Slackers genetic algorithm (GA) which addresses the problem of improving the parallelization efficiency of sparse matrix computations by optimally distributing blocks of matrices data. The performance of a distribution is sensitive to the non-zero patterns in the data, the algorithm, and the hardware architecture. In a candidate distributions the Hogs and Slackers GA identifies processors with many operations - hogs, and processors with fewer operations - slackers. Its intelligent operation-balancing mutation operator then swaps data blocks between hogs and slackers to explore a new data distribution.We show that the Hogs and Slackers GA performs better than a baseline GA. We demonstrate Hogs and Slackers GA's optimization capability with an architecture study of varied network and memory bandwidth and latency.

Original languageEnglish (US)
Title of host publicationParallel Architectures and Bioinspired Algorithms
Editorsde Vega Francisco Fernandez, Perez Jose Ignacio Hidalgo, Lanchares Juan
Pages219-241
Number of pages23
DOIs
StatePublished - Jun 6 2012

Publication series

NameStudies in Computational Intelligence
Volume415
ISSN (Print)1860-949X

    Fingerprint

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

O'Reilly, U. M., Bliss, N., Mohindra, S., Mullen, J., & Robinson, E. (2012). A knowledge-based operator for a genetic algorithm which optimizes the distribution of sparse matrix data. In D. V. Francisco Fernandez, P. Jose Ignacio Hidalgo, & L. Juan (Eds.), Parallel Architectures and Bioinspired Algorithms (pp. 219-241). (Studies in Computational Intelligence; Vol. 415). https://doi.org/10.1007/978-3-642-28789-3-10