Evolving a CUDA kernel from an nVidia template
Authors:
- 1 July 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1089778X,p. 1-8
Abstract
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. Back-to-back validation uses the original code as a test oracle.Keywords
This publication has 11 references indexed in Scilit:
- A genetic programming approach to automated software repair2009
- Automatically finding patches using genetic programming2009
- A novel co-evolutionary approach to automatic software bug fixing2008
- Generalisation of the limiting distribution of program sizes in tree-based genetic programming and analysis of its effects on bloat2007
- Visualizing Tree Structures in Genetic ProgrammingGenetic Programming and Evolvable Machines, 2005
- Experiments on the effectiveness of dataflow- and control-flow-based test adequacy criteria2002
- Foundations of Genetic Programming2002
- Size Fair and Homologous Tree Crossovers for Tree Genetic ProgrammingGenetic Programming and Evolvable Machines, 2000
- Genetic Programming and Data Structures1998
- Strongly Typed Genetic ProgrammingEvolutionary Computation, 1995