ILCS is a highly-scalable parallelization framework for running iterative local champion searches on heterogeneous HPC platforms. The user only needs to provide serial CPU or single-GPU code that implements a simple interface. The framework then executes this code in parallel using MPI between compute nodes and OpenMP and multi-GPU support within nodes. It handles all parallelization aspects, seed distribution and program termination, and it regularly records the currently best solution.
The source code can be requested via email from firstname.lastname@example.org. A description of the ILCS framework and its usage is available here. Note that ILCS is protected by this license and that by obtaining ILCS you agree to the terms and conditions set forth in this license.
More information will follow later.
M. Burtscher and H. Rabeti. "A Scalable Heterogeneous Parallelization Framework for Iterative Local Searches." 27th IEEE International Parallel & Distributed Processing Symposium. May 2013. [pdf] [pptx]