Framework for High-Level Power Estimation of Signal Processing Architectures

  • Authors:
  • Achim Freimann

  • Affiliations:
  • -

  • Venue:
  • PATMOS '00 Proceedings of the 10th International Workshop on Integrated Circuit Design, Power and Timing Modeling, Optimization and Simulation
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

A framework for high-level power estimation dedicated to the design of signal processing architectures is presented in this work. A strong emphasis lies on the integration of the power estimation into the regular design-flow and on keeping the modeling overhead low. This was achieved through an object-oriented design of the estimation tool. Main features are: an easy macromodule extension, the implementation of a Verilog HDL subset, and a moderate model complexity. Estimation results obtained using the framework for development of a discrete cosine transform compare to the deviation of power consumption imposed by their data dependency.