Accelerating Join Operation for Relational Databases with FPGAs

Author

Halstead, Robert J. ; Sukhwani, Bharat ; Hong Min ; Thoennes, Mathew ; Dube, Parijat ; Asaad, Sameh ; Iyer, Brijesh

Author_Institution

Dept. Comput. Sci., Univ. of California, Riverside, Riverside, CA, USA

fYear

2013

fDate

28-30 April 2013

Firstpage

17

Lastpage

20

Abstract

In this paper, we investigate the use of field programmable gate arrays (FPGAs) to accelerate relational joins. Relational join is one of the most CPU-intensive, yet commonly used, database operations. Hashing can be used to reduce the time complexity from quadratic (naïve) to linear time. However, doing so can introduce false positives to the results which must be resolved. We present a hash-join engine on FPGA that performs hashing, conflict resolution, and joining on a PCIe-attached system, achieving greater than 11x speedup over software.

Keywords

computational complexity; field programmable gate arrays; peripheral interfaces; relational databases; CPU-intensive; FPGA; PCIe-attached system; conflict resolution; false positives; field programmable gate arrays; hash-join engine; linear time; relational databases; relational joins; time complexity; Benchmark testing; Databases; Field programmable gate arrays; Pipelines; Probes; Software; Vectors; FPGA; Relational database; analytics; database join; hardware aceleration;

fLanguage

English

Publisher

ieee

Conference_Titel

Field-Programmable Custom Computing Machines (FCCM), 2013 IEEE 21st Annual International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

978-1-4673-6005-0

Type

conf

DOI

10.1109/FCCM.2013.17

Filename

6545988