Abstract
We demonstrate a SIMD C++ genetic programming system
on a single 128 node parallel nVidia GeForce 8800 GTX
GPU under RapidMind's GPGPU Linux software by
predicting ten year+ outcome of breast cancer from a
dataset containing a million inputs. NCBI GEO GSE3494
contains hundreds of Affymetrix HG-U133A and HG-U133B
GeneChip biopsies. Multiple GP runs each with a
population of 5 million programs winnow useful
variables from the chaff at more than 500 million GPops
per second. Sources available via FTP.
- 1,
- affymetrix
- algorithm,
- algorithms,
- biopsy,
- breast
- c++
- c17orf81,
- cancer,
- computing,
- consumer
- data
- decorin,
- evolutionary
- fibulin
- gcc
- genetic
- geo
- gpu,
- graphics
- gse3494
- hardware,
- hg-u133a,
- hg-u133b,
- hydrolase,
- lance
- miller's
- mining,
- parallel
- processing
- programming,
- rapidmind
- s-adenosylhomocysteine
- simd,
- soft
- tumour
- ubuntu
- unit,
- uppsala
Users
Please
log in to take part in the discussion (add own reviews or comments).