Differential Evolution with parallelised objective functions using CUDA

Primoz Kralj
FERI, University of Maribor
University of Maribor, 2013


   title={Differential Evolution with parallelised objective functions using CUDA},

   author={Kralj, Primoz},



Download Download (PDF)   View View   Source Source   



Differential Evolution (DE) algorithms can be used in various fields for problem solving where we need to find an optimal (or close to optimal) solution but we don’t have a clear, straightforward method to compute it. Unfortunately it can take a very long time to produce such a solution when implemented serially or even parallel on a Central Processing Unit (CPU). To reduce computation time we can utilise the power of Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA) technology. Since GPUs are designed purely for computational tasks as opposed to CPUs which are more general-work oriented they can provide a great architecture for parallelising our DE method.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: