Evolving a CUDA Kernel from an nVidia Template

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "W. B. Langdon and M. Harman",
  title =        "Evolving a {CUDA} Kernel from an {nVidia} Template",
  booktitle =    "2010 IEEE World Congress on Computational
  year =         "2010",
  editor =       "Pilar Sobrevilla",
  pages =        "2376--2383",
  address =      "Barcelona",
  month =        "18-23 " # jul,
  organisation = "IEEE Computational Intelligence Society",
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming, GPU, grammar,
  isbn13 =       "978-1-4244-6910-9",
  URL =          "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/langdon_2010_cigpu.pdf",
  URL =          "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/langdon_2010_cigpu.ps.gz",
  DOI =          "doi:10.1109/CEC.2010.5585922",
  size =         "8 pages",
  abstract =     "Rather than attempting to evolve a complete program
                 from scratch we demonstrate genetic interface
                 programming by automatically generating a parallel CUDA
                 kernel with identical functionality to existing highly
                 optimised ancient sequential C code. Generic GPGPU
                 nVidia kernel C++ code is converted into a BNF grammar.
                 Strongly typed genetic programming uses the BNF to
                 generate compilable and executable graphics card
                 kernels. Their fitness is given by running the
                 population on a GPU with randomised subsets of training
                 data itself given by running the original code's test
  notes =        "BNF grammar and training examples
                 WCCI 2010. CEC 2010. Also known as \cite{5585922} Cited
                 by \cite{Langdon:2016:GPEM}",

Genetic Programming entries for William B Langdon Mark Harman