GPUs for Genetic and Evolutionary Computation

The Goal

This competition focuses on the applications of genetic and evolutionary computation that can maximally exploit the parallelism provided by low-cost consumer graphical cards. The competition will award the best applications both in terms of degree of parallelism obtained, in terms of overall speed-up, and in terms of programming style.

The Competition

We had 10 excellent submissions that have now been reviewed by our panel. At the CIGPU workshop and during the competition slot, the best 3 entrants will be given time to present their work. During the competition session, ballot papers will be distributed for selecting the overall winner.

Download flyer in PDF format

Download information in text format

The Submissions

Winning entry

Nicholas A. Sinnott-Armstrong, Casey S. Greene and Jason H. Moore - Using Evolutionary Computing on Consumer Graphics Hardware for Epistasis Analysis in Human Genetics

Runners up

Luca Mussi and Stefano Cagnoni - Particle Swarm Optimization within the CUDA Architecture

Steve Worley - Optimization of Primality Testing Methods by GPU Evolutionary Search

Other entries

Avi Dullu - A Framework for Genetic Algorithms for GPGPUs

Stefano Debattisti, Nicola Marlat, Luca Mussi and Stefano Cagnoni - Implementation of a Simple Genetic Algorithm within the CUDA Architecture

Ying-Shiuan You - Parallel Ant System for Traveling Salesman Problem on GPUs

William Langdon - A CUDA SIMT Interpreter for Genetic Programming

Petr Pospichal and Jiri Jaros - The GPU-based Acceleration of the Genetic Algorithm

Marc Ebner - A GPU Accelerated Evolutionary Computer Vision System

Noriyuki Fujimoto and Shigeyoshi Tsutsui - A QAP Solver with CUDA GPU Computing Architecture

On behalf of the organisers, I would like to offer a big thank you to all those who entered. (Simon Harding)