Affordable Access

Fast Huffman decoding by exploiting data level parallelism

IEEE Service Center
Publication Date
  • Computer Science


Fast Huffman Decoding by Exploiting Data Level Parallelism Tim Drijvers∗†, Carlos Alba Pinto†, Henk Corporaal∗, Bart Mesman∗, Gert-Jan van den Braak∗ ∗Department of Electrical Engineering Eindhoven University of Technology, The Netherlands Email: {h.corporaal,b.mesman,[email protected] †Silicon Hive Eindhoven, The Netherlands Abstract—The frame rates and resolutions of digital videos are on the rising edge. Thereby, pushing the compression ratios of video coding standards to their limits, resulting in more complex and computational power hungry algorithms. Programmable solutions are gaining interest to keep up the pace of the evolving video coding standards, by reducing the time- to-market of upcoming video products. However, to compete with hardwired solutions, parallelism needs to be exploited on as many levels as possible. In this paper the focus will be on data level parallelism. Huffman coding is proven to be very efficient and therefore commonly applied in many coding standards. However, due to the inherently sequential nature, parallelization of the Huffman decoding is considered hard. The proposed fully flexible and programmable acceleration exploits available data level parallelism in Huffman decoding. Our implementation achieves a decoding speed of 106 MBit/s while running on a 250 MHz processor. This is a speed-up of 24× compared to our sequential reference implementation. I. INTRODUCTION Modern video coding standards are becoming more compu- tational power, bandwidth and hardware resource demanding. These standards are driven by an active research area in displays, a requiring consumer market and a still rising number of videos on the Internet. Providing faster frame rates and larger resolutions in a space efficient manner is key to success of these coding standards. New optical storage systems, such as Blu-ray and HD-DVD, are introduced to cope with the call for more bandwidth and storage space, thereby also pushing the compression ratios of video coding standards

There are no comments yet on this publication. Be the first to share your thoughts.