Implementation and analysis of numerical components for reconfigurable computing
作者： W.B. Ligon , G. Monn , D. Stanzione , F. Stivers , K.D. Underwood
关键词:
摘要: In the past, reconfigurable computing has not been an option for accelerating scientific algorithms (which require complex floating-point operations) and other similar applications due to limited FPGA density. However, rapid increase of densities over past several years altered this situation. The central goal Reconfigurable Computing Application Development Environment (RCADE) is capitalize on these improvements. Through RCADE, algorithm translated into a data flow design, which then implemented platform using "toolbox" components. This paper expands library components by implementing following IEEE single precision functions: sine, cosine, arctangent, arcsine, arccosine, square root natural logarithm. Each component designed around CORDIC shift-and-add algorithms. A discussion how each operation followed analysis space requirements current future Xilinx FPGAs. Performance results are compared individually two example equations against workstations.
sci-hub.se 参考文章(13)
Brian Boysen, Nathan DeBardeleben, Kim M. Hazelwood, Walter B. Ligon III, Ron Sass, Dan C. Stanzione, Jr., Keith D. Underwood, Development environment for configurable computing Configurable Computing: Technology and Applications. ,vol. 3526, pp. 103- 112 ,(1998) , 10.1117/12.327038
J. S. Walther, A unified algorithm for elementary functions Proceedings of the May 18-20, 1971, spring joint computer conference on - AFIPS '71 (Spring). pp. 379- 385 ,(1971) , 10.1145/1478786.1478840
Y.H. Hu, S. Naganathan, A novel implementation of a chirp Z-transform using a CORDIC processor IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 38, pp. 352- 354 ,(1990) , 10.1109/29.103071
Ray Andraka, A survey of CORDIC algorithms for FPGA based computers field programmable gate arrays. pp. 191- 200 ,(1998) , 10.1145/275107.275139
M. Dao, T.A. Cook, D. Silver, P.S. D'Urbano, Acceleration of template-based ray casting for volume visualization using FPGAs field-programmable custom computing machines. pp. 116- 124 ,(1995) , 10.1109/FPGA.1995.477417
W.B. Ligon, S. McMillan, G. Monn, K. Schoonover, F. Stivers, K.D. Underwood, A re-evaluation of the practicality of floating-point operations on FPGAs field-programmable custom computing machines. pp. 206- 215 ,(1998) , 10.1109/FPGA.1998.707898
Villasenor, Schoner, Kang-Ngee Chia, Zapata, Hea Joung Kim, Jones, Lansing, Mangione-Smith, Configurable computing solutions for automatic target recognition field-programmable custom computing machines. pp. 70- 79 ,(1996) , 10.1109/FPGA.1996.564749
A.L. Abbott, P.M. Athanas, L. Chen, R.L. Elliott, Finding lines and building pyramids with SPLASH 2 field programmable gate arrays. pp. 155- 163 ,(1994) , 10.1109/FPGA.1994.315608
Jack E. Volder, The CORDIC Trigonometric Computing Technique Ire Transactions on Electronic Computers. ,vol. 8, pp. 330- 334 ,(1959) , 10.1109/TEC.1959.5222693
N. Shirazi, A. Walters, P. Athanas, Quantitative analysis of floating point arithmetic on FPGA based custom computing machines field-programmable custom computing machines. pp. 155- 162 ,(1995) , 10.1109/FPGA.1995.477421