High performance biological pairwise sequence alignment: FPGA versus GPU versus cell BE versus GPP

Khaled Benkrid, Ali Akoglu, Cheng Ling, Yang Song, Ying Liu, Xiang Tian

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

This paper explores the pros and cons of reconfigurable computing in the form of FPGAs for high performance efficient computing. In particular, the paper presents the results of a comparative study between three different acceleration technologies, namely, Field Programmable Gate Arrays (FPGAs), Graphics Processor Units (GPUs), and IBM's Cell Broadband Engine (Cell BE), in the design and implementation of the widely-used Smith-Waterman pairwise sequence alignment algorithm, with general purpose processors as a base reference implementation. Comparison criteria include speed, energy consumption, and purchase and development costs. The study shows that FPGAs largely outperform all other implementation platforms on performance per watt criterion and perform better than all other platforms on performance per dollar criterion, although by a much smaller margin. Cell BE and GPU come second and third, respectively, on both performance per watt and performance per dollar criteria. In general, in order to outperform other technologies on performance per dollar criterion (using currently available hardware and development tools), FPGAs need to achieve at least two orders of magnitude speed-up compared to general-purpose processors and one order of magnitude speed-up compared to domain-specific technologies such as GPUs.

Original languageEnglish (US)
Article number752910
JournalInternational Journal of Reconfigurable Computing
Volume2012
DOIs
StatePublished - 2012

Fingerprint

Field programmable gate arrays (FPGA)
Engines
Energy utilization
Hardware
Costs

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

High performance biological pairwise sequence alignment : FPGA versus GPU versus cell BE versus GPP. / Benkrid, Khaled; Akoglu, Ali; Ling, Cheng; Song, Yang; Liu, Ying; Tian, Xiang.

In: International Journal of Reconfigurable Computing, Vol. 2012, 752910, 2012.

Research output: Contribution to journalArticle

@article{0ec52c8eaccd453990ec9b0cec44b317,
title = "High performance biological pairwise sequence alignment: FPGA versus GPU versus cell BE versus GPP",
abstract = "This paper explores the pros and cons of reconfigurable computing in the form of FPGAs for high performance efficient computing. In particular, the paper presents the results of a comparative study between three different acceleration technologies, namely, Field Programmable Gate Arrays (FPGAs), Graphics Processor Units (GPUs), and IBM's Cell Broadband Engine (Cell BE), in the design and implementation of the widely-used Smith-Waterman pairwise sequence alignment algorithm, with general purpose processors as a base reference implementation. Comparison criteria include speed, energy consumption, and purchase and development costs. The study shows that FPGAs largely outperform all other implementation platforms on performance per watt criterion and perform better than all other platforms on performance per dollar criterion, although by a much smaller margin. Cell BE and GPU come second and third, respectively, on both performance per watt and performance per dollar criteria. In general, in order to outperform other technologies on performance per dollar criterion (using currently available hardware and development tools), FPGAs need to achieve at least two orders of magnitude speed-up compared to general-purpose processors and one order of magnitude speed-up compared to domain-specific technologies such as GPUs.",
author = "Khaled Benkrid and Ali Akoglu and Cheng Ling and Yang Song and Ying Liu and Xiang Tian",
year = "2012",
doi = "10.1155/2012/752910",
language = "English (US)",
volume = "2012",
journal = "International Journal of Reconfigurable Computing",
issn = "1687-7195",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - High performance biological pairwise sequence alignment

T2 - FPGA versus GPU versus cell BE versus GPP

AU - Benkrid, Khaled

AU - Akoglu, Ali

AU - Ling, Cheng

AU - Song, Yang

AU - Liu, Ying

AU - Tian, Xiang

PY - 2012

Y1 - 2012

N2 - This paper explores the pros and cons of reconfigurable computing in the form of FPGAs for high performance efficient computing. In particular, the paper presents the results of a comparative study between three different acceleration technologies, namely, Field Programmable Gate Arrays (FPGAs), Graphics Processor Units (GPUs), and IBM's Cell Broadband Engine (Cell BE), in the design and implementation of the widely-used Smith-Waterman pairwise sequence alignment algorithm, with general purpose processors as a base reference implementation. Comparison criteria include speed, energy consumption, and purchase and development costs. The study shows that FPGAs largely outperform all other implementation platforms on performance per watt criterion and perform better than all other platforms on performance per dollar criterion, although by a much smaller margin. Cell BE and GPU come second and third, respectively, on both performance per watt and performance per dollar criteria. In general, in order to outperform other technologies on performance per dollar criterion (using currently available hardware and development tools), FPGAs need to achieve at least two orders of magnitude speed-up compared to general-purpose processors and one order of magnitude speed-up compared to domain-specific technologies such as GPUs.

AB - This paper explores the pros and cons of reconfigurable computing in the form of FPGAs for high performance efficient computing. In particular, the paper presents the results of a comparative study between three different acceleration technologies, namely, Field Programmable Gate Arrays (FPGAs), Graphics Processor Units (GPUs), and IBM's Cell Broadband Engine (Cell BE), in the design and implementation of the widely-used Smith-Waterman pairwise sequence alignment algorithm, with general purpose processors as a base reference implementation. Comparison criteria include speed, energy consumption, and purchase and development costs. The study shows that FPGAs largely outperform all other implementation platforms on performance per watt criterion and perform better than all other platforms on performance per dollar criterion, although by a much smaller margin. Cell BE and GPU come second and third, respectively, on both performance per watt and performance per dollar criteria. In general, in order to outperform other technologies on performance per dollar criterion (using currently available hardware and development tools), FPGAs need to achieve at least two orders of magnitude speed-up compared to general-purpose processors and one order of magnitude speed-up compared to domain-specific technologies such as GPUs.

UR - http://www.scopus.com/inward/record.url?scp=84862285770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862285770&partnerID=8YFLogxK

U2 - 10.1155/2012/752910

DO - 10.1155/2012/752910

M3 - Article

AN - SCOPUS:84862285770

VL - 2012

JO - International Journal of Reconfigurable Computing

JF - International Journal of Reconfigurable Computing

SN - 1687-7195

M1 - 752910

ER -