Accelerating evolutionary computation with graphics processing units
Wolfgang Banzhaf, Simon Peter Harding · 2009
Graphics Processing Units (GPUs) have become a major source of computational power for numerical applications. Originally designed for application of time-consuming graphics operations, GPUs are stream processors that implement the SIMD paradigm. Modern programming tools allow developers to access the parallelism of the GPU in a flexible and convenient way, hiding many low level details from the user.