Evolving a CUDA kernel from an nVidia template

Rather than attempting to evolve a complete program from scratch we demonstrate genetic interface programming (GIP) by automatically generating a parallel CUDA kernel with identical functionality to existing highly optimised ancient sequential C code (gzip). 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 derived from gzip's SIR test suite. Backto-back validation uses the original code as a test oracle.

• Type: Conference
• Year: 2010
• Where: CEC
• Authors: William B. Langdon, Mark Harman
• Keywords: Artificial Intelligence, CEC 2010, Genetic Interface Programming, Kernel C++ Code, Parallel Cuda Kernel