Time distributed DCT architecture for multimedia applications

This paper presents the design of a new time distributed architecture (TDA), which outlines architecture submitted to MPEG4 Part9 committee ISO/IEC JTC1/SC29/WG11 MPEG2002/M8565. The proposed TDA optimizes the 2D-DCT performance. It uses a time distribution mechanism to exploit the computational redundancy within the inner product computation module. It schedules the computation to meet the application specific requirements of input, output and coefficients word length. The Coefficient matrix uses linear mappings to assign necessary computation to processor elements in the space and the time domains. The performance analysis shows a performance savings in excess of 71% as compared to the current optimized general and application specific architectures for DCT is achieved.

[1]  Discrete Cosine Transform Basics 1 Discrete Cosine Transform Basics , .

[2]  Earl E. Swartzlander,et al.  DCT Implementation with Distributed Arithmetic , 2001, IEEE Trans. Computers.

[3]  H. C. Karathanasis,et al.  A low ROM distributed arithmetic implementation of the forward/inverse DCT/DST using rotations , 1995 .

[4]  Magdy A. Bayoumi,et al.  A low power high performance distributed DCT architecture , 2002, Proceedings IEEE Computer Society Annual Symposium on VLSI. New Paradigms for VLSI Systems Design. ISVLSI 2002.

[5]  Alan N. Willson,et al.  A 100 MHz 2-D 8×8 DCT/IDCT processor for HDTV applications , 1995, IEEE Trans. Circuits Syst. Video Technol..

[6]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[7]  Peter A. Ruetz,et al.  A high-performance full-motion video compression chip set , 1992, IEEE Trans. Circuits Syst. Video Technol..