Design of low power variable length decoder using fine grain non-uniform table partitioning

Variable length coding is a widely used technique in digital video compression systems. Previous work related to variable length decoders are primarily aimed at high throughput applications, but the increased demand for portable multimedia systems has made power a very important factor. In this paper a data driven variable length decoding algorithm is presented, which exploits the signal statistics of variable length codes to reduce power. It uses fine grain lookup table partitioning based on codeword frequency. An order magnitude of power reduction is possible compared to conventional parallel decoding scheme with a single lookup table.

[1]  Mostafa A. Bassiouni,et al.  Efficient VLSI designs for data transformation of tree-based codes , 1991 .

[2]  R. Hashemian.  Design and Hardware Construction of a High Speed and Memory Efficient Huffman Decoding , 1994, IEEE International Conference on Consumer Electronics.

[3]  Shawmin Lei,et al.  An entropy coding system for digital HDTV applications , 1991, IEEE Trans. Circuits Syst. Video Technol..

[4]  Moon Ho Lee,et al.  High speed pattern matching for a fast Huffman decoder , 1995 .

[5]  Lars Wanhammar,et al.  New approaches to high speed Huffman decoding , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[6]  D. Huffman.  A Method for the Construction of Minimum-Redundancy Codes , 1952 .

[7]  Y. Ooi,et al.  A 162 Mbit/s variable length decoding circuit using an adaptive tree search technique , 1994, Proceedings of IEEE Custom Integrated Circuits Conference - CICC '94.