Partitioned Matrix Algorithms for VLSI Arithmetic Systems

Authors:
Kai Hwang; Yeng-Heng Cheng
Affiliations:
School of Electrical Engineering, Purdue University;-
Venue:
IEEE Transactions on Computers
Year:
1982

Citing 4
Cited 4

On Stable Parallel Linear System Solvers

Journal of the ACM (JACM)
Computer Arithmetic: Principles, Architecture and Design

Computer Arithmetic: Principles, Architecture and Design
Introduction to VLSI Systems

Introduction to VLSI Systems
Decentralized parallel algorithms for matrix computation

ISCA '78 Proceedings of the 5th annual symposium on Computer architecture

PUMPS Architecture for Pattern Analysis and Image Database Management

IEEE Transactions on Computers
VLSI Array Design Under Constraint of Limited I/O Bandwidth

IEEE Transactions on Computers
Short Communication: Array size anomaly of problem-size independent systolic arrays for matrix-vector multiplication

Parallel Computing
Systolic designs for Aitken's root finding method

Parallel Computing

Quantified Score

Hi-index	14.99

Visualization

Abstract

A new class of partitioned matrix algorithms is developed for possible VLSI implementation of large-scale matrix solvers. Fast matrix solvers are higherly demanded in signal/image processing and in many real-time and scientific applications. Only a few functional types of VLSI arithmetic chips are needed for submatrix computations after partitioning. This partitioned approach is not restricted by problem sizes and thus can be applied to solve arbitrarily large linear systems of equations in an iterative fashion. The following four matrix computations are shown systematically partitionable into submatrix operations, which are feasible for direct VLSI implementation.