Abstract A top end graphics card (GPU) plus a suitable SIMD interpreter, can deliver a several hundred fold speed up, yet cost less than the computer holding it. We give highlights of AI and computational intelligence applications in the new field of general purpose computing on graphics hardware (GPGPU). In particular we survey genetic programming (GP) use with GPU. We give several applications from Bioinformatics and show how the fastest GP is based on an interpreter rather than compilation. Finally using GP to generate GPU CUDA kernel C++ code is sketched. Peak single precision GFlop/seccond

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 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 FTP. 1