System-Level Power Optimization of Video Codecs on Embedded Cores: A Systematic Approach

  • Authors:

  • Lode Nachtergaele;Dennis Moolenaar;Bart Vanhoof;Francky Catthoor;Hugo De Man

  • Affiliations:

  • Interuniversity Micro Electronics Centrum (IMEC), Leuven, Belgium;Interuniversity Micro Electronics Centrum (IMEC), Leuven, Belgium;Interuniversity Micro Electronics Centrum (IMEC), Leuven, Belgium;Interuniversity Micro Electronics Centrum (IMEC), Leuven, Belgium;Interuniversity Micro Electronics Centrum (IMEC), Leuven, Belgium

  • Venue:
  • Journal of VLSI Signal Processing Systems - Special issue on future directions in the design and implementations of DSP systems
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

A battery powered multimedia communication device requires avery energy efficient implementation. The required efficiencycan only be acquired by careful optimization at all levels ofthe design. System-level power optimizations have a dramatic impacton the overall power budget. We have proposeda system-level step-wise methodology to reduce the power in hardwarerealizations of data-dominated applications, which is partly supportedwith our ATOMIUM environment. In this paper, we extend the methodology tothe realization of embedded software on processor cores.Starting from a high level algorithm description (e.g., in C),a set of optimizations gradually refine the code and thecorresponding memory organization of the array data types.These array data types represent a fully detailed optimized data storage and transfer organization.Instead of creating the physical memories, a mapping can be done eitheron a general memory architecture, including a cache, or on a custom memory architecture.First, typical optimizations addressed by our methodology are applied on a didactical example.The effectiveness of this methodology is then demonstratedby the optimization of two complex applications in an embedded processorcontext: a MPEG2 and a H.263 video decoder.The impact of the power optimizations on the typical powerconsumption is demonstrated by simulating the optimizeddecoders with real video streams.