Jianhua Liu
ABSTRACT
Division is one of the most complicated and expensive arithmetic operations. Both clock frequency and operation delay are limited by the memory wall, even in LUT-based FPGA devices. To conquer the memory limitation, we propose a hybrid division algorithm which employs Prescaling, Series expansion and Taylor expansion (PST) algorithms. The proposed algorithm boosts very-high radix division efficiently. The algorithm is multiplicative, and feasible for the modern FPGA devices with build-in multipliers. The algorithm is implemented in Altera StratixII FPGA devices and compared with the division IP core generated by MegaWizard. The result shows that the PST algorithm has higher clock frequency, lower execution time and also lower power consumption.
- Robertson J, "A New Class of Digital Division Methods", IRE Trans. on Electronic Computers, vol. 7, 1958, pp. 218--222.Google Scholar
Cross Ref
- Tocher T, "Techniques of Multiplication and Division for Automatic Binary Computers", Quarterly J. Mech. App. Math., vol. 2, pt. 3, 1958, pp. 364--384.Google ScholarCross Ref
- Coe T, Tang P, "It takes six ones to reach a flaw {Pentium processor}", Computer Arithmetic, 1995., Proceedings of the 12th Symposium on 19-21 July 1995 Page(s):140--146. Google ScholarDigital Library
- Svoboda A, "An Algorithm for Division", Information Processing Machines, vol. 9, 1963, pp. 183--190.Google Scholar
- Tung C, "A Division Algorithm for Signed-Digit Arithmetic", IEEE Trans. on Computers, vol.17, 1968, pp. 887--889.Google ScholarDigital Library
- Oberman S, Flynn M, "Division Algorithms and Implementations", IEEE Trans. on Computers, vol. 46, NO. 8, 1997, pp. 833--854. Google ScholarDigital Library
- Goldschmidt R, "Applications of Division by Convergence", MS thesis, Dept. of Electrical Eng., Massachusetts Inst. of Technology, Cambridge, Mass., June 1964.Google Scholar
- Hung P, Fahmy H, Mencer O, Flynn M, "Fast Division Algorithm with a Small Lookup Table", Conference Record of the 33rd Asilomar conference on Signals, Systems, and Computers, IEEE. Part vol. 2, 1999, pp. 1465--1468.Google Scholar
- Markstein P, "Computation of Elementary Functions on the IBM RISC System/6000 Processor", IBM J. Research and Development, vol. 34, no. 1, pp.111--119, Jan. 1990. Google ScholarDigital Library
- Oberman S, "Floating Point Division and Square Root Algorithms and Implementation in the AMD-K7 Microprocessor", Proc. 14th IEEE Symp. Computer Arithmetic, I. Koren and P. Kornerup, eds., pp. 106--115, Apr. 1999. Google ScholarDigital Library
- Ibrahem AA, Elsimary HA, Salama AE, "FPGA implementation of fast radix 4 division algorithm", 4th IEEE International Workshop on System-on-Chip for Real-Time Applications. IEEE Comput. Soc. 2004, pp.69--72. Los Alamitos, CA, USA. Google ScholarDigital Library
- Sutter G, Bioul G, Deschamps J-P, "Comparative study of SRT-dividers in FPGA", Field-Programmable Logic and Applications. 14th International Conference, FPL 2004. Proceedings (Lecture Notes in Comput. Sci. Vol.3203). Springer-Verlag. 2004, pp.209--20. Berlin, Germany.Google Scholar
- Altera Documentation Group, "Stratix II Device Handbook"', Altera Corporation, July 2005.Google Scholar
Index Terms
- An iterative division algorithm for FPGAs
Recommendations
Pipelining of double precision floating point division and square root operations
ACM-SE 44: Proceedings of the 44th annual Southeast regional conferenceSpace applications rely increasingly on high data rate DSP algorithms. These algorithms use double precision floating point arithmetic operations. While most DSP applications can be compiled on DSP processors, high data rate DSP computations require ...
An Unified Architecture for Single, Double, Double-Extended, and Quadruple Precision Division
A hardware architecture for quadruple precision floating point division arithmetic with multi-precision support is presented. Division is an important yet far more complex arithmetic operation than addition and multiplication, which demands significant ...
Power and energy efficiency evaluation for HW and SW implementation of nxn matrix multiplication on Altera FPGAs
FPGAworld '09: Proceedings of the 6th FPGAworld ConferenceMatrix multiplication is most often involved in graphics, image processing, digital signal processing, robotics and control engineering applications. In this paper we compared and analyzed the power and energy consumption in three different designs, ...
Comments