Stochastic computing implementation of trigonometric and hyperbolic functions

Lian Huai; Peng Li; Gerald E. Sobelman; David J. Lilja

doi:10.1109/ASICON.2017.8252535

Stochastic computing implementation of trigonometric and hyperbolic functions

Lian Huai, Peng Li, Gerald E. Sobelman, David J. Lilja

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

High performance implementations of trigonometric and hyperbolic functions are important in many application areas. This paper presents an FPGA implementation of these functions using the stochastic computing methodology. The results are compared to the well-known CORDIC approach. All of the designs are synthesized and implemented on a Xilinx Virtex-5 FPGA. The results are compared in terms of delay and area for various input data widths. The results show that the proposed design method has advantages in the delay-area product and in soft error tolerance compared to CORDIC designs.

Original language	English (US)
Title of host publication	Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017
Editors	Yajie Qin, Zhiliang Hong, Ting-Ao Tang
Publisher	IEEE Computer Society
Pages	553-556
Number of pages	4
ISBN (Electronic)	9781509066247
DOIs	https://doi.org/10.1109/ASICON.2017.8252535
State	Published - Jul 1 2017
Event	12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017 - Guiyang, China Duration: Oct 25 2017 → Oct 28 2017

Publication series

Name	Proceedings of International Conference on ASIC
Volume	2017-October
ISSN (Print)	2162-7541
ISSN (Electronic)	2162-755X

Other

Other	12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017
Country/Territory	China
City	Guiyang
Period	10/25/17 → 10/28/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Access

10.1109/ASICON.2017.8252535

OpenUrl availability

Full text

Cite this

Huai, L., Li, P., Sobelman, G. E., & Lilja, D. J. (2017). Stochastic computing implementation of trigonometric and hyperbolic functions. In Y. Qin, Z. Hong, & T.-A. Tang (Eds.), Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017 (pp. 553-556). (Proceedings of International Conference on ASIC; Vol. 2017-October). IEEE Computer Society. https://doi.org/10.1109/ASICON.2017.8252535

Stochastic computing implementation of trigonometric and hyperbolic functions. / Huai, Lian; Li, Peng; Sobelman, Gerald E. et al.
Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. ed. / Yajie Qin; Zhiliang Hong; Ting-Ao Tang. IEEE Computer Society, 2017. p. 553-556 (Proceedings of International Conference on ASIC; Vol. 2017-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Huai, L, Li, P, Sobelman, GE & Lilja, DJ 2017, Stochastic computing implementation of trigonometric and hyperbolic functions. in Y Qin, Z Hong & T-A Tang (eds), Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017. Proceedings of International Conference on ASIC, vol. 2017-October, IEEE Computer Society, pp. 553-556, 12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017, Guiyang, China, 10/25/17. https://doi.org/10.1109/ASICON.2017.8252535

@inproceedings{6d067a35c0f0496a86cd2098a23568f2,

title = "Stochastic computing implementation of trigonometric and hyperbolic functions",

abstract = "High performance implementations of trigonometric and hyperbolic functions are important in many application areas. This paper presents an FPGA implementation of these functions using the stochastic computing methodology. The results are compared to the well-known CORDIC approach. All of the designs are synthesized and implemented on a Xilinx Virtex-5 FPGA. The results are compared in terms of delay and area for various input data widths. The results show that the proposed design method has advantages in the delay-area product and in soft error tolerance compared to CORDIC designs.",

author = "Lian Huai and Peng Li and Sobelman, {Gerald E.} and Lilja, {David J.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017 ; Conference date: 25-10-2017 Through 28-10-2017",

year = "2017",

month = jul,

day = "1",

doi = "10.1109/ASICON.2017.8252535",

language = "English (US)",

series = "Proceedings of International Conference on ASIC",

publisher = "IEEE Computer Society",

pages = "553--556",

editor = "Yajie Qin and Zhiliang Hong and Ting-Ao Tang",

booktitle = "Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017",

}

TY - GEN

T1 - Stochastic computing implementation of trigonometric and hyperbolic functions

AU - Huai, Lian

AU - Li, Peng

AU - Sobelman, Gerald E.

AU - Lilja, David J.

PY - 2017/7/1

Y1 - 2017/7/1

N2 - High performance implementations of trigonometric and hyperbolic functions are important in many application areas. This paper presents an FPGA implementation of these functions using the stochastic computing methodology. The results are compared to the well-known CORDIC approach. All of the designs are synthesized and implemented on a Xilinx Virtex-5 FPGA. The results are compared in terms of delay and area for various input data widths. The results show that the proposed design method has advantages in the delay-area product and in soft error tolerance compared to CORDIC designs.

AB - High performance implementations of trigonometric and hyperbolic functions are important in many application areas. This paper presents an FPGA implementation of these functions using the stochastic computing methodology. The results are compared to the well-known CORDIC approach. All of the designs are synthesized and implemented on a Xilinx Virtex-5 FPGA. The results are compared in terms of delay and area for various input data widths. The results show that the proposed design method has advantages in the delay-area product and in soft error tolerance compared to CORDIC designs.

UR - http://www.scopus.com/inward/record.url?scp=85044743303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044743303&partnerID=8YFLogxK

U2 - 10.1109/ASICON.2017.8252535

DO - 10.1109/ASICON.2017.8252535

M3 - Conference contribution

AN - SCOPUS:85044743303

T3 - Proceedings of International Conference on ASIC

SP - 553

EP - 556

BT - Proceedings - 2017 IEEE 12th International Conference on ASIC, ASICON 2017

A2 - Qin, Yajie

A2 - Hong, Zhiliang

A2 - Tang, Ting-Ao

PB - IEEE Computer Society

T2 - 12th IEEE International Conference on Advanced Semiconductor Integrated Circuits, ASICON 2017

Y2 - 25 October 2017 through 28 October 2017

ER -

Stochastic computing implementation of trigonometric and hyperbolic functions

Abstract

Publication series

Other

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this