Designing of single precision floating point DSP co-processor

Evgeni R. Overchick; Binyamin Abramov

doi:10.1109/eeei.2014.7005864

Designing of single precision floating point DSP co-processor

Evgeni R. Overchick, Binyamin Abramov

Dept. Electrical Engineering, Afeka College of Engineering

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

1 Scopus citations

Abstract

In this paper, we show that using FPGA as a CoProcessor with floating point arithmetic can enhance DSP system performance levels through optimized core implementation of critical compute-intensive digital signal processing algorithms such as Fast Fourier Transform (FFT). Our approach is based on building basic building blocks, by implementing optimized, multi-cycle, floating point arithmetic core, which are then used to implement much complex layers of logic such as FFT butterfly, complex multiplier and a DFT block. We present performance results to show that a speedup of 10-19X can be achieved over an optimized FFT DSP Coprocessor implementation on a low cost FPGA such as Cyclone IV.

Original language	English
Title of host publication	2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479959877
DOIs	https://doi.org/10.1109/eeei.2014.7005864
State	Published - 2014
Externally published	Yes
Event	2014 28th IEEE Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014 - Eilat, Israel Duration: 3 Dec 2014 → 5 Dec 2014

Publication series

Name	2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014

Conference

Conference	2014 28th IEEE Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014
Country/Territory	Israel
City	Eilat
Period	3/12/14 → 5/12/14

Bibliographical note

Publisher Copyright:
© Copyright 2015 IEEE All rights reserved.

Keywords

DSP coprocessor
FFT
FPGA
IEEE754
Single precision floating point numbers

Access to Document

10.1109/eeei.2014.7005864

Cite this

Overchick, E. R., & Abramov, B. (2014). Designing of single precision floating point DSP co-processor. In 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014 Article 7005864 (2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/eeei.2014.7005864

@inproceedings{90ce230a23204bedb4fcae7ad4948f19,

title = "Designing of single precision floating point DSP co-processor",

abstract = "In this paper, we show that using FPGA as a CoProcessor with floating point arithmetic can enhance DSP system performance levels through optimized core implementation of critical compute-intensive digital signal processing algorithms such as Fast Fourier Transform (FFT). Our approach is based on building basic building blocks, by implementing optimized, multi-cycle, floating point arithmetic core, which are then used to implement much complex layers of logic such as FFT butterfly, complex multiplier and a DFT block. We present performance results to show that a speedup of 10-19X can be achieved over an optimized FFT DSP Coprocessor implementation on a low cost FPGA such as Cyclone IV.",

keywords = "DSP coprocessor, FFT, FPGA, IEEE754, Single precision floating point numbers",

author = "Overchick, {Evgeni R.} and Binyamin Abramov",

note = "Publisher Copyright: {\textcopyright} Copyright 2015 IEEE All rights reserved.; 2014 28th IEEE Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014 ; Conference date: 03-12-2014 Through 05-12-2014",

year = "2014",

doi = "10.1109/eeei.2014.7005864",

language = "אנגלית",

series = "2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014",

address = "ארצות הברית",

}

Overchick, ER & Abramov, B 2014, Designing of single precision floating point DSP co-processor. in 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014., 7005864, 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014, Institute of Electrical and Electronics Engineers Inc., 2014 28th IEEE Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014, Eilat, Israel, 3/12/14. https://doi.org/10.1109/eeei.2014.7005864

Designing of single precision floating point DSP co-processor. / Overchick, Evgeni R.; Abramov, Binyamin.
2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 7005864 (2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014).

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

TY - GEN

T1 - Designing of single precision floating point DSP co-processor

AU - Overchick, Evgeni R.

AU - Abramov, Binyamin

PY - 2014

Y1 - 2014

N2 - In this paper, we show that using FPGA as a CoProcessor with floating point arithmetic can enhance DSP system performance levels through optimized core implementation of critical compute-intensive digital signal processing algorithms such as Fast Fourier Transform (FFT). Our approach is based on building basic building blocks, by implementing optimized, multi-cycle, floating point arithmetic core, which are then used to implement much complex layers of logic such as FFT butterfly, complex multiplier and a DFT block. We present performance results to show that a speedup of 10-19X can be achieved over an optimized FFT DSP Coprocessor implementation on a low cost FPGA such as Cyclone IV.

AB - In this paper, we show that using FPGA as a CoProcessor with floating point arithmetic can enhance DSP system performance levels through optimized core implementation of critical compute-intensive digital signal processing algorithms such as Fast Fourier Transform (FFT). Our approach is based on building basic building blocks, by implementing optimized, multi-cycle, floating point arithmetic core, which are then used to implement much complex layers of logic such as FFT butterfly, complex multiplier and a DFT block. We present performance results to show that a speedup of 10-19X can be achieved over an optimized FFT DSP Coprocessor implementation on a low cost FPGA such as Cyclone IV.

KW - DSP coprocessor

KW - FFT

KW - FPGA

KW - IEEE754

KW - Single precision floating point numbers

UR - http://www.scopus.com/inward/record.url?scp=84941254855&partnerID=8YFLogxK

U2 - 10.1109/eeei.2014.7005864

DO - 10.1109/eeei.2014.7005864

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84941254855

T3 - 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014

BT - 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 28th IEEE Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014

Y2 - 3 December 2014 through 5 December 2014

ER -

Overchick ER, Abramov B. Designing of single precision floating point DSP co-processor. In 2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 7005864. (2014 IEEE 28th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2014). doi: 10.1109/eeei.2014.7005864

Designing of single precision floating point DSP co-processor

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this