- author = "W. B. Langdon",
- title = "Large Scale Bioinformatics Data Mining with Parallel Genetic Programming on Graphics Processing Units",
- booktitle = "Parallel and Distributed Computational Intelligence",
- publisher = "Springer",
- year = "2010",
- editor = "Francisco {Fernandez de Vega} and Erick Cantu-Paz",
- volume = "269",
- series = "Studies in Computational Intelligence",
- chapter = "5",
- pages = "113--141",
- month = jan,
- keywords = "genetic algorithms, genetic programming, GPU",
- isbn13 = "978-3642106743",
-
URL = "
http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/langdon_2009_pdci.pdf",
-
URL = "
http://www.springer.com/engineering/book/978-3-642-10674-3",
-
DOI = "
doi:10.1007/978-3-642-10675-0_6",
-
abstract = "A suitable single instruction multiple data GP
interpreter can achieve high (Giga GPop/second)
performance on a SIMD GPU graphics card by
simultaneously running multiple diverse members of the
genetic programming population. SPMD dataflow
parallelisation is achieved because the single
interpreter treats the different GP programs as data.
On a single 128 node parallel nVidia GeForce 8800 GTX
GPU, the interpreter can out run a compiled approach,
where data parallelisation comes only by running a
single program at a time across multiple inputs.
The RapidMind GPGPU Linux C++ system has been demonstrated by predicting ten year+ outcome of breast cancer from a dataset containing a million inputs. NCBI GEO GSE3494 contains hundreds of Affymetrix \mbox{HG-U133A} and HG-U133B GeneChip biopsies. Multiple GP runs each with a population of five million programs winnow useful variables from the chaff at more than 500 million GPops per second. Sources available via \href{http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/gp-code/gpu_gp_2.tar.gz} {FTP}.",
- notes = "part of \cite{FernandezdeVega:pdci}",
- size = "28 pages",
