Performance of PGA (Programmable Graph Architecture) for Matrix Multiplications

Matrix multiplication is one of the primary operations in linear algebra and is useful in a wide spectrum of multimedia applications including signal and image processing. In this paper we review a novel computer architecture for matrix multiplications. This novel architecture is based on graph theo...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng, M., Ramani, S., Tang, K.W., Oruc, A.Y.
Format: Conference Proceeding
Language:English
Subjects:
Application software
Arithmetic
Cayley graphs
Computer architecture
Concurrent computing
Educational institutions
Electronics packaging
Image processing
Linear algebra
matrix
Matrix decomposition
multiplication
Signal processing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Matrix multiplication is one of the primary operations in linear algebra and is useful in a wide spectrum of multimedia applications including signal and image processing. In this paper we review a novel computer architecture for matrix multiplications. This novel architecture is based on graph theory, hence the name programmable graph architecture. We discuss the performance of PGA via time and space complexity and time-processor product for parallel implementation. We further compare the PGA performance with Cannon's algorithm and show that the PGA architecture outperforms the existing method for matrix with any dimension
DOI:10.1109/ICIS-COMSAR.2006.67