MFAST: a single chip highly parallel image processing architecture

IBM Mwave/sup TM/ has developed a radically new approach for real-time video and graphics processing. A scalable array of processing elements (PEs) is configured as a "folded array" for effective execution of matrix and transpose operations. The single chip Mwave Folded Array Signal Transform processor (MFAST) is a scalable DSP that provides 10+ billion 16-bit operations-per-second@50 MHz, sustainable during algorithm execution. This paper describes key M.F.A.S.T. elements and a bounded 18-22 cycle 8/spl times/8-pixel 2-D discrete cosine transform (DCT) program, verified on VHDL and functional simulator models.

[1]  Chuck H. Ngai,et al.  Architecture and VLSI Implementation of the MPEG-2:MP@ML Video Decoding Process , 1995 .

[2]  Stamatis Vassiliadis,et al.  Multiple-fold clustered processor mesh array , 1993 .

[3]  Stamatis Vassiliadis,et al.  A massively parallel diagonal-fold array processor , 1993, Proceedings of International Conference on Application Specific Array Processors (ASAP '93).

[4]  MUNSI ALAUL HAQUE,et al.  A two-dimensional fast cosine transform , 1985, IEEE Trans. Acoust. Speech Signal Process..

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