Building a Parallel Computer System for \$18,000 that
Performs a Half Peta-Flop per Day
F. Bennett III, J. Koza, J. Shipman, und O. Stiffelman. Proceedings of the Genetic and Evolutionary
Computation Conference, 2, Seite 1484--1490. Orlando, Florida, USA, Morgan Kaufmann, (13-17 July 1999)
Zusammenfassung
Techniques of evolutionary computation generally
require significant computational resources to solve
non-trivial problems of interest. Increases in
computing power can be realized either by using a
faster computer or by parallelizing the application.
Techniques of evolutionary computation are especially
amenable to parallelization. This paper describes how
to build a 10-node Beowulf-style parallel computer
system for $18,000 that delivers about a half peta-flop
(1015 floating-point operations) per day on runs of
genetic programming. Each of the 10 nodes of the system
contains a 533 MHz Alpha processor and runs with the
Linux operating system. This amount of computational
power is sufficient to yield solutions (within a couple
of days per problem) to 14 published problems where
genetic programming has produced results that are
competitive with human-produced results.
Proceedings of the Genetic and Evolutionary
Computation Conference
Jahr
1999
Monat
13-17 July
Seiten
1484--1490
Verlag
Morgan Kaufmann
Band
2
publisher_address
San Francisco, CA 94104, USA
isbn
1-55860-611-4
notes
GECCO-99 A joint meeting of the eighth international
conference on genetic algorithms (ICGA-99) and the
fourth annual genetic programming conference (GP-99)
%0 Conference Paper
%1 bennett:1999:BPCSPHPD
%A Bennett III, Forrest H
%A Koza, John R.
%A Shipman, James
%A Stiffelman, Oscar
%B Proceedings of the Genetic and Evolutionary
Computation Conference
%C Orlando, Florida, USA
%D 1999
%E Banzhaf, Wolfgang
%E Daida, Jason
%E Eiben, Agoston E.
%E Garzon, Max H.
%E Honavar, Vasant
%E Jakiela, Mark
%E Smith, Robert E.
%I Morgan Kaufmann
%K algorithms, applications genetic programming, real world
%P 1484--1490
%T Building a Parallel Computer System for \$18,000 that
Performs a Half Peta-Flop per Day
%U http://www.cs.bham.ac.uk/~wbl/biblio/gecco1999/RW-788.ps
%V 2
%X Techniques of evolutionary computation generally
require significant computational resources to solve
non-trivial problems of interest. Increases in
computing power can be realized either by using a
faster computer or by parallelizing the application.
Techniques of evolutionary computation are especially
amenable to parallelization. This paper describes how
to build a 10-node Beowulf-style parallel computer
system for $18,000 that delivers about a half peta-flop
(1015 floating-point operations) per day on runs of
genetic programming. Each of the 10 nodes of the system
contains a 533 MHz Alpha processor and runs with the
Linux operating system. This amount of computational
power is sufficient to yield solutions (within a couple
of days per problem) to 14 published problems where
genetic programming has produced results that are
competitive with human-produced results.
%@ 1-55860-611-4
@inproceedings{bennett:1999:BPCSPHPD,
abstract = {Techniques of evolutionary computation generally
require significant computational resources to solve
non-trivial problems of interest. Increases in
computing power can be realized either by using a
faster computer or by parallelizing the application.
Techniques of evolutionary computation are especially
amenable to parallelization. This paper describes how
to build a 10-node Beowulf-style parallel computer
system for $18,000 that delivers about a half peta-flop
(1015 floating-point operations) per day on runs of
genetic programming. Each of the 10 nodes of the system
contains a 533 MHz Alpha processor and runs with the
Linux operating system. This amount of computational
power is sufficient to yield solutions (within a couple
of days per problem) to 14 published problems where
genetic programming has produced results that are
competitive with human-produced results.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Orlando, Florida, USA},
author = {{Bennett III}, Forrest H and Koza, John R. and Shipman, James and Stiffelman, Oscar},
biburl = {https://www.bibsonomy.org/bibtex/25e1ceb7170915ffc751c06422e084878/brazovayeye},
booktitle = {Proceedings of the Genetic and Evolutionary
Computation Conference},
editor = {Banzhaf, Wolfgang and Daida, Jason and Eiben, Agoston E. and Garzon, Max H. and Honavar, Vasant and Jakiela, Mark and Smith, Robert E.},
interhash = {27bc7737a19dc6031b7814cda30ce0ee},
intrahash = {5e1ceb7170915ffc751c06422e084878},
isbn = {1-55860-611-4},
keywords = {algorithms, applications genetic programming, real world},
month = {13-17 July},
notes = {GECCO-99 A joint meeting of the eighth international
conference on genetic algorithms (ICGA-99) and the
fourth annual genetic programming conference (GP-99)},
pages = {1484--1490},
publisher = {Morgan Kaufmann},
publisher_address = {San Francisco, CA 94104, USA},
timestamp = {2008-06-19T17:36:25.000+0200},
title = {Building a Parallel Computer System for \$18,000 that
Performs a Half Peta-Flop per Day},
url = {http://www.cs.bham.ac.uk/~wbl/biblio/gecco1999/RW-788.ps},
volume = 2,
year = 1999
}