Genetically Improved CUDA kernels for StereoCamera
Created by W.Langdon from
gp-bibliography.bib Revision:1.8010
- @TechReport{Langdon_RN1402,
-
author = "W. B. Langdon and M. Harman",
-
title = "Genetically Improved {CUDA} kernels for
{StereoCamera}",
-
institution = "Department of Computer Science, University College
London",
-
year = "2014",
-
type = "Research Note",
-
number = "RN/14/02",
-
address = "Gower Street, London WC1E 6BT, UK",
-
month = "20 " # feb,
-
keywords = "genetic algorithms, genetic programming, genetic
improvement, GI, GP, gismoe, SBSE, software
optimisation, nVidia, GPU, GPGPU, Tesla, GeForce GTX
580, evolutionary programming, software engineering",
-
URL = "http://www.cs.ucl.ac.uk/fileadmin/UCL-CS/research/Research_Notes/Langdon_RN1402.pdf",
-
size = "24 pages",
-
abstract = "Genetic Programming (GP) may dramatically increase the
performance of software written by domain experts. GP
and autotuning are used to optimise and refactor legacy
GPGPU C code for modern parallel graphics hardware and
software. Speed ups of more than six times on recent
nVidia GPU cards are reported compared to the original
kernel on the same hardware.",
-
notes = "
GP code
ftp://ftp.cs.ucl.ac.uk//genetic/gp-code/StereoCamera_1_1.tar.gz
Training images
ftp://ftp.cs.ucl.ac.uk//genetic/gp-code/StereoImages.tar.gz
StereoCamera v1.0b with bugfix and tuned for K20c Tesla
at
ftp://ftp.cs.ucl.ac.uk//genetic/gp-code/StereoCamera_v1_1c.zip
Cf \cite{langdon:2014:EuroGP}",
- }
Genetic Programming entries for
William B Langdon
Mark Harman
Citations