An approximate computing technique for reducing the complexity of a direct-solver for sparse linear systems in real-time video processing

Many video processing algorithms are formulated as least-squares problems that result in large, sparse linear systems. Solving such systems in real time is very demanding. This paper focuses on reducing the computational complexity of a direct Cholesky-decomposition-based solver. Our approximation s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings - ACM IEEE Design Automation Conference S. 1 - 6
Hauptverfasser: Schaffner, Michael, Gurkaynak, Frank K., Smolic, Aljosa, Kaeslin, Hubert, Benini, Luca
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2014
Schlagworte:
Accuracy
Approximate Computing
Cholesky Decomposition
Computational complexity
Equations
Hardware
Hardware Accelerator
Linear systems
Matrix decomposition
Streaming media
Video Processing
ISSN:0738-100X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Many video processing algorithms are formulated as least-squares problems that result in large, sparse linear systems. Solving such systems in real time is very demanding. This paper focuses on reducing the computational complexity of a direct Cholesky-decomposition-based solver. Our approximation scheme builds on the observation that, in well-conditioned problems, many elements in the decomposition nearly vanish. Such elements may be pruned from the dependency graph with mild accuracy degradation. Using an example from image-domain warping, we show that pruning reduces the amount of operations per solve by over 75 %, resulting in significant savings in computing time, area or energy.
ISSN:0738-100X
DOI:10.1145/2593069.2593082