Iterative solution of large, sparse linear systems on a static data flow architecture: Performance studies
Issue No. 10 - Oct. (1985 vol. 34)
Daniel A. Reed , Department of Computer Science, University of Illinois, Urbana, IL 61801
The applicability of static data flow architectures to the iterative solution of sparse linear systems of equations is investigated. An analytic performance model of a static data flow computation is developed. This model includes both spatial parallelism, concurrent execution in multiple PE's, and pipelining, the streaming of data from array memories through the PE's. The performance model is used to analyze a row partitioned iterative algorithm for solving sparse linear systems of algebraic equations. Based on this analysis, design parameters for the static data flow architecture as a function of matrix sparsity and dimension are proposed.
sparse linear systems, Algorithm analysis, data flow, parallel algorithms, performance models
D. A. Reed, "Iterative solution of large, sparse linear systems on a static data flow architecture: Performance studies," in IEEE Transactions on Computers, vol. 34, no. , pp. 874-880, 1985.