A new architecture for FPGA implementation of a MAC unit for digital signal processors using mixed number system

Execution of arithmetic operations at very high speed in real time is the major concern in digital signal processing (DSP) because DSP algorithms are computation intensive. In recent times, Residue Number Systems (RNS) are considered as alternative to binary number system because of their capabilities of performing "carry-free" addition and Multiplication. Double Base Number Systems (DBNS), another non-binary number systems are also increasingly becoming attractive for signal processing applications due to their capabilities of handling arithmetic operations, particularly multiplication efficiently. However, the complexity involved in converting binary to DBNS becomes a major bottleneck and the efficiency of performance decreases considerably due to large conversion time. So RNS Adder and DBNS Multiplier can be used to implement multiply & accumulate (MAC) units. Because RNS adders are less complex and faster compared to DBNS and DBNS multipliers are efficient compared to RNS multiplier. MAC units are the key units in Digital Signal Processors. In this paper we have shown how FIR filter can be implemented using the proposed "Mixed Number System MAC units".

[1]  M. Omair Ahmad,et al.  Moduli selection in RNS for efficient VLSI implementation , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[2]  Graham A. Jullien,et al.  Theory and Applications of the Double-Base Number System , 1999, IEEE Trans. Computers.

[3]  Sanjit K. Mitra,et al.  Digital Signal Processing: A Computer-Based Approach , 1997 .

[4]  B. Lee.  A new algorithm to compute the discrete cosine Transform , 1984 .

[5]  Stephen A. Dyer,et al.  Digital signal processing , 2018, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[6]  Amitabha Sinha,et al.  A novel architecture for conversion of binary to single digit double base numbers , 2010, CARN.

[8]  P. Siy,et al.  A new moduli set selection technique to improve sign detection and number comparison in residue number system (RNS) , 2005, NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society.

[9]  F. J. Taylor,et al.  Residue Arithmetic A Tutorial with Examples , 1984, Computer.

[10]  W.C. Miller,et al.  On efficient techniques for difficult operations in one and two-digit DBNS index calculus , 2000, Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154).

[11]  Majid Ahmadi,et al.  A hybrid DBNS processor for DSP computation , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[12]  Ronald Smith,et al.  Computer Organization , 1965, SIGCPR '65.

[13]  Roberto Muscedere,et al.  A 2-digit DBNS filter architecture , 2000, 2000 IEEE Workshop on SiGNAL PROCESSING SYSTEMS. SiPS 2000. Design and Implementation (Cat. No.00TH8528).

[14]  Aniruddha Ghosh,et al.  A Novel Architecture of “Mixed Number System MAC Unit” for Digital Signal Processors , 2010 .

[15]  Graham A. Jullien,et al.  Near canonic double-based number system (DBNS) with applications in digital signal processing , 1996, Optics & Photonics.

[16]  Russell Tessier,et al.  c ○ 2001 Kluwer Academic Publishers. Manufactured in The Netherlands. Reconfigurable Computing for Digital Signal Processing: A Survey ∗ , 1999 .