A framework for self-reconfigurable DCTs based on multiobjective optimization of the Power-Performance-Accuracy space

Author

Llamocca, Daniel ; Pattichis, Marios ; Carranza, Cesar

Author_Institution

Electr. & Comput. Eng. Dept., Univ. of New Mexico, Albuquerque, NM, USA

fYear

2012

Firstpage

1

Lastpage

6

Abstract

We present a framework for the implementation of self-reconfigurable 2D Discrete Cosine Transforms (DCTs). Dynamic Partial Reconfiguration (DPR) and Dynamic Frequency Control lead to a multi-objective optimization scheme that generates Pareto-optimal realizations from the Power-Performance-Accuracy (PPA) space. The PPA space is created by evaluating the 2D DCTs realizations in terms of their power consumption, performance, and accuracy. Dynamic PPA management can then carried out by selecting Pareto-optimal realizations that meet time-varying PPA constraints.

Keywords

Pareto optimisation; discrete cosine transforms; video signal processing; 2D DCT; DPR; PPA space; Pareto-optimal realizations; digital video processing; dynamic PPA management; dynamic frequency control; dynamic partial reconfiguration; multiobjective optimization; power consumption; power-performance-accuracy space; self-reconfigurable 2D discrete cosine transforms; self-reconfigurable DCT; time-varying PPA constraints; Accuracy; Clocks; Discrete cosine transforms; Field programmable gate arrays; Frequency control; IP networks; Optimization; DCT; Dynamic Partial Reconfiguration; Field-programmable gate array (FPGA); Multi-objective Optimization;

fLanguage

English

Publisher

ieee

Conference_Titel

Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), 2012 7th International Workshop on

Conference_Location

York

Print_ISBN

978-1-4673-2570-7

Electronic_ISBN

978-1-4673-2571-4

Type

conf

DOI

10.1109/ReCoSoC.2012.6322903

Filename

6322903