A Many Threaded CUDA Interpreter for Genetic Programming

Research output: Chapter in Book/Report/Conference proceedingConference paper

37 Citations (Scopus)

Abstract

A Single Instruction Multiple Thread CUDA interpreter provides SIMD like parallel evaluation of the whole GP population of million reverse polish notation (RPN) expressions on graphics cards and nVidia Tesla. Using sub-machine code tree GP a sustain peak performance of 665 billion GP operations per second (10,000 speed up) and an average of 22 peta GP ops per day is reported for a single GPU card on a Boolean induction benchmark never attempted before, let alone solved.
Original languageEnglish
Title of host publicationUnknown
Place of PublicationBERLIN
PublisherSpringer
Pages146 - 158
Number of pages13
Volume6021 LNCS
ISBN (Print)978-3-642-12147-0
Publication statusPublished - 2010
Event13th European Conference on Genetic Programming - Istanbul, Turkey
Duration: 7 Apr 20109 Apr 2010

Publication series

NameGENETIC PROGRAMMING, PROCEEDINGS

Conference

Conference13th European Conference on Genetic Programming
Country/TerritoryTurkey
CityIstanbul
Period7/04/20109/04/2010

Fingerprint

Dive into the research topics of 'A Many Threaded CUDA Interpreter for Genetic Programming'. Together they form a unique fingerprint.

Cite this