Energy Efficient FPGA based Hardware Accelerators for Financial Applications

Jakob Kenn Toft; Alberto Nannarelli

doi:10.1109/NORCHIP.2014.7004741

Energy Efficient FPGA based Hardware Accelerators for Financial Applications

Jakob Kenn Toft, Alberto Nannarelli

Technical University of Denmark

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

1334 Downloads (Pure)

Abstract

Field Programmable Gate Arrays (FPGAs) based accelerators are very suitable to implement application-specific processors using uncommon operations or number systems. In this work, we design FPGA-based accelerators for two financial computations with different characteristics and we compare the accelerator performance and energy consumption to a software execution of the application. The experimental results show that significant speed-up and energy savings, can be obtained for large data sets by using the accelerator at expenses of a longer development time.

Original language	English
Title of host publication	Proceedings of 32nd NORCHIP Conference
Number of pages	6
Publisher	IEEE
Publication date	2014
ISBN (Print)	978-1-4799-6890-9
DOIs	https://doi.org/10.1109/NORCHIP.2014.7004741
Publication status	Published - 2014
Event	2014 IEEE 32nd NORCHIP Conference - Tampere, Finland Duration: 27 Oct 2014 → 28 Oct 2014 Conference number: 32 https://ieeexplore.ieee.org/xpl/conhome/6962987/proceeding

Conference

Conference	2014 IEEE 32nd NORCHIP Conference
Number	32
Country/Territory	Finland
City	Tampere
Period	27/10/2014 → 28/10/2014
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6962987/proceeding

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/NORCHIP.2014.7004741

PID3410305 final 1

OpenUrl availability

Full text

Cite this

@inproceedings{8abf7160359b40cba952966c8d0d3dab,

title = "Energy Efficient FPGA based Hardware Accelerators for Financial Applications",

abstract = "Field Programmable Gate Arrays (FPGAs) based accelerators are very suitable to implement application-specific processors using uncommon operations or number systems. In this work, we design FPGA-based accelerators for two financial computations with different characteristics and we compare the accelerator performance and energy consumption to a software execution of the application. The experimental results show that significant speed-up and energy savings, can be obtained for large data sets by using the accelerator at expenses of a longer development time.",

author = "{Kenn Toft}, Jakob and Alberto Nannarelli",

year = "2014",

doi = "10.1109/NORCHIP.2014.7004741",

language = "English",

isbn = "978-1-4799-6890-9",

booktitle = "Proceedings of 32nd NORCHIP Conference",

publisher = "IEEE",

address = "United States",

note = "2014 IEEE 32nd NORCHIP Conference, NORCHIP 2014 ; Conference date: 27-10-2014 Through 28-10-2014",

url = "https://ieeexplore.ieee.org/xpl/conhome/6962987/proceeding",

}

TY - GEN

T1 - Energy Efficient FPGA based Hardware Accelerators for Financial Applications

AU - Kenn Toft, Jakob

AU - Nannarelli, Alberto

N1 - Conference code: 32

PY - 2014

Y1 - 2014

N2 - Field Programmable Gate Arrays (FPGAs) based accelerators are very suitable to implement application-specific processors using uncommon operations or number systems. In this work, we design FPGA-based accelerators for two financial computations with different characteristics and we compare the accelerator performance and energy consumption to a software execution of the application. The experimental results show that significant speed-up and energy savings, can be obtained for large data sets by using the accelerator at expenses of a longer development time.

AB - Field Programmable Gate Arrays (FPGAs) based accelerators are very suitable to implement application-specific processors using uncommon operations or number systems. In this work, we design FPGA-based accelerators for two financial computations with different characteristics and we compare the accelerator performance and energy consumption to a software execution of the application. The experimental results show that significant speed-up and energy savings, can be obtained for large data sets by using the accelerator at expenses of a longer development time.

U2 - 10.1109/NORCHIP.2014.7004741

DO - 10.1109/NORCHIP.2014.7004741

M3 - Article in proceedings

SN - 978-1-4799-6890-9

BT - Proceedings of 32nd NORCHIP Conference

PB - IEEE

T2 - 2014 IEEE 32nd NORCHIP Conference

Y2 - 27 October 2014 through 28 October 2014

ER -

Energy Efficient FPGA based Hardware Accelerators for Financial Applications

Abstract

Conference

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this