Subscribe

Issue No.11 - November (2008 vol.57)

pp: 1561-1570

Paul D. Fiore , MIT Lincoln Laboratory, Lexington

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TC.2008.87

ABSTRACT

In this paper, the problem of bounding the performance of good wordlength combinations for fixed-point digital signal processing flowgraphs is addressed. By formulating and solving an approximate optimization problem, a lower bounding curve on attainable cost/quality combinations is rapidly calculated. This curve and the associated wordlength combinations are useful in several situations, and can serve as starting points for real design searches. A detailed design example that utilizes these concepts is given.

INDEX TERMS

Signal processing systems, Reconfigurable hardware, Tradeoffs between Complexity Measures, Multiple precision arithmetic, Constrained optimization

CITATION

Paul D. Fiore, "Efficient Approximate Wordlength Optimization",

*IEEE Transactions on Computers*, vol.57, no. 11, pp. 1561-1570, November 2008, doi:10.1109/TC.2008.87REFERENCES

- [3] G.A. Constantinides, “Perturbation Analysis for Word-Length Optimization,”
Proc. 11th IEEE Symp. Field-Programmable Custom Computing Machines (FCCM), 2003.- [9] P.D. Fiore, “A Custom Computing Framework for Orientation and Photogrammetry,” PhD dissertation, Massachusetts Inst. of Technology, http:/dspace.mit.edu/, Apr. 2000.
- [11]
Proc. First NASA/ESA Conf. Adaptive Hardware and Systems (AHS'06), A. Stoica et al., eds., June 2006.- [13] D.A. Brown, “ELINT Signal Processing on Reconfigurable Computers for Detection and Classification of LPI Emitters,” PhD dissertation, Naval Postgraduate School, Monterey, Calif., June 2006.
- [14] A.V. Oppenheim and R.W. Schafer,
Digital Signal Processing. Prentice Hall, 1975.- [15] G.A. Constantinides, P.Y.K. Cheung, and W. Luk, “Truncation Noise in Fixed-Point SFGs,”
IEE Electronics Letter, vol. 35, no. 23, pp. 2012-2014, 1999.- [18] M.-A. Cantin, “Methode de Determination Automatique de la Taille des Chemins de Donnees,” PhD dissertation, Univ. of Montreal, June 2005.
- [19] G.A. Constantinides, P.Y.K. Cheung, and W. Luk,
Synthesis and Optimization of DSP Algorithms. Kluwer Academic Publishers, 2004.- [20] S.C. Chan and K.M. Tsui, “Wordlength Determination Algorithms for Hardware Implementation of Linear Time Invariant Systems with Prescribed Output Accuracy,”
Proc. IEEE Int'l Symp. Circuits and Systems (ISCAS '05), vol. 3, pp. 2607-2610, May 2005.- [24] P.D. Fiore, C.S. Myers, J.M. Smith, and E.K. Pauer, “Rapid Implementation of Mathematical and DSP Algorithms in Configurable Computing Devices,”
Proc. Configurable Computing: Technology and Applications, Part of SPIE Int'l Symp. Voice, Video and Data Comm., pp. 178-189, Nov. 1998.- [26] E.M. Panainte, K. Bertels, and S. Vassiliadis, “Compiler-Driven FPGA-Area Allocation for Reconfigurable Computing,”
Proc. Design, Automation and Test in Europe (DATE '06), Mar. 2006.- [30] J. Stoer and R. Bulirsch,
Introduction to Numerical Analysis, second ed. Springer, 1993.- [31] A.A. Gaffar, O. Mencer, W. Luk, and P.Y.K. Cheung, “Unifying Bit-Width Optimisation for Fixed-Point and Floating-Point Designs,”
Proc. 12th IEEE Symp. Field-Programmable Custom Computing Machines (FCCM '04), Apr. 2004.- [33] M.M. Strout and P. Hovland, “Linearity Analysis for Automatic Differentiation,”
Proc. Int'l Workshop Automatic Differentiation Tools and Applications (ADTA '06), May 2006.- [36] C. Shi and R.W. Brodersen, “A Perturbation Theory on Statistical Quantization Effects in Fixed-Point DSP with Non-Stationary Inputs,”
Proc. IEEE Int'l Symp. Circuits and Systems (ISCAS '04), vol. 3, pp. 373-376, 2004.- [37] P.D. Fiore, “Efficient Wordlength Reduction Techniques for DSP Applications,”
J. VLSI Signal Processing, vol. 24, no. 1, pp. 9-18, Feb. 2000.- [38] D. Bertsekas,
Nonlinear Programming. Athena Scientific, 1995.- [39] D.G. Luenberger,
Introduction to Dynamic Systems. John Wiley & Sons, 1979.- [40] G.W. Stewart and J. Sun,
Matrix Perturbation Theory. Academic Press, 1990.- [41] H.L. Van Trees,
Optimum Array Processing. Wiley Interscience, 2002. |