SLAPP: A Systolic Linear Algebra Parallel Processor

SLAPP: A Systolic Linear Algebra Parallel Processor

The SLAPP project is an effort to demonstrate the feasibility of solving real-time signal- and image-processing problems using a two-dimensional systolic array which implements a fairly wide range of linear algebra algorithms. The bitriangular unified architecture is a computationally efficient and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer (Long Beach, Calif.) Calif.), 1987-07, Vol.20 (7), p.45-49
Hauptverfasser: DRAKE, BARRYL, LUK, FRANKLINT, SPEISER, JEFFREYM, SYMANSKI, JEROMEJ
Format: Artikel
Sprache:eng
Schlagworte:
990210 - Supercomputers- (1987-1989)
ALGEBRA
ALGORITHMS
ARRAY PROCESSORS
Array signal processing
COMPUTER ARCHITECTURE
Concurrent computing
DATA PROCESSING
EFFICIENCY
GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
IMAGE PROCESSING
Least squares approximation
Linear algebra
MATRICES
Matrix decomposition
Oceans
PARALLEL PROCESSING
REAL TIME SYSTEMS
Signal processing
Signal processing algorithms
SIGNALS
Systolic arrays
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The SLAPP project is an effort to demonstrate the feasibility of solving real-time signal- and image-processing problems using a two-dimensional systolic array which implements a fairly wide range of linear algebra algorithms. The bitriangular unified architecture is a computationally efficient and cost-effective implementation of the engagement processor and the Luk QRD, SVD, and GSVD algorithms. (B.J.)
ISSN:0018-9162
1558-0814
DOI:10.1109/MC.1987.1663619