Detail publikace

Evolutionary design of hash function pairs for network filters

DOBAI, R. KOŘENEK, J. SEKANINA, L.

Originální název

Evolutionary design of hash function pairs for network filters

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

Network filtering is a challenging area in high-speed computer networks, mostly because lots of filtering rules are required and there is only a limited time available for matching these rules. Therefore, network filters accelerated by field-programmable gate arrays (FPGAs) are becoming common where the fast lookup of filtering rules is achieved by the use of hash tables. It is desirable to be able to fill-up these tables efficiently, i.e. to achieve a high table-load factor in order to reduce the offline time of the network filter due to rehashing and/or table replacement. A parallel reconfigurable hash function tuned by an evolutionary algorithm (EA) is proposed in this paper for Internet Protocol (IP) address filtering in FPGAs. The EA fine-tunes the reconfigurable hash function for a given set of IP addresses. The experiments demonstrate that the proposed hash function provides high-speed lookup and achieves a higher table-load factor in comparison with conventional solutions.

Klíčová slova

evolution, hash function, network filter, field-programmable gate array, cuckoo

Autoři

DOBAI, R.; KOŘENEK, J.; SEKANINA, L.

Vydáno

6. 3. 2017

ISSN

1568-4946

Periodikum

APPLIED SOFT COMPUTING

Ročník

56

Číslo

7

Stát

Nizozemsko

Strany od

173

Strany do

181

Strany počet

9

URL

BibTex

@article{BUT134465,
  author="Roland {Dobai} and Jan {Kořenek} and Lukáš {Sekanina}",
  title="Evolutionary design of hash function pairs for network filters",
  journal="APPLIED SOFT COMPUTING",
  year="2017",
  volume="56",
  number="7",
  pages="173--181",
  doi="10.1016/j.asoc.2017.03.009",
  issn="1568-4946",
  url="http://dx.doi.org/10.1016/j.asoc.2017.03.009"
}