Cost functions for mapping DSP algorithms onto multiprocessors

Cost functions for mapping DSP algorithms onto multiprocessors

In this correspondence, we examine several cost functions that have been proposed for automating the mapping of algorithms onto multiprocessors. Through a case study of the recursive least squares problem, we develop improved cost functions. One of these (the Min-Max+Idle cost function) performed be...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on signal processing 1995-01, Vol.43 (1), p.369-373
Hauptverfasser: Rabideau, D.J., Steinhardt, A.O.
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Cost function
Data models
Digital signal processing
Exact sciences and technology
Frequency
Gaussian noise
Hafnium
Information, signal and communications theory
Least squares approximation
Mathematical methods
Parameter estimation
Signal processing algorithms
Signal to noise ratio
Telecommunications and information theory
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this correspondence, we examine several cost functions that have been proposed for automating the mapping of algorithms onto multiprocessors. Through a case study of the recursive least squares problem, we develop improved cost functions. One of these (the Min-Max+Idle cost function) performed better than the others and was applied to the related problem of full QR decomposition. Experiments on an iPSC/860 hypercube confirm that automated mapping can lead to lower execution times than published mappings.< >
ISSN:1053-587X
1941-0476
DOI:10.1109/78.365323