Experience Using Multiprocessor Systems—A Status Report
ACM Computing Surveys (CSUR)
Communications of the ACM - Special issue on computer architecture
Architectural mechanisms to support sparse vector processing
ISCA '89 Proceedings of the 16th annual international symposium on Computer architecture
(SM)/sup 2/-II: A Large-Scale Multiprocessor for Sparse Matrix Calculations
IEEE Transactions on Computers
(SM)2-II: a new version of the sparse matrix solving machine
ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
Hi-index | 0.01 |
In analyzing electronic circuits, it is usually necessary to solve simultaneous linear equations which provide with a sparse coefficient matrix. In order to treat these problems effectively, we propose a dedicated parallel machine called 'Sparse Matrix Solving Machine', or (SM)2 for short. (SM)2 is composed of multiple clusters, each consisting of multiple processing units (PUs) attached to a sophisticated shared memory which enables any PUs to read data from memory simultaneously without conflict. The structure of the cluster is organized so as to make the best use of the neighboring effects involved in the problems. In this paper, the characteristics of the problems to be solved and the behavior of the PUs will be discussed, and the optimum system configuration for (SM)2 will be shown and its effectiveness will be justified through behavior analysis and simulations.