GPU Revised Simplex Solver
Description #
In a team of 5 people we implemented multiple variants of the Revised Simplex Method on an NVIDIA GPU and compared the variants to existing LP solvers.
For the implementation we used different CUDA kernels as well as implemented our own. The final benchmarks were performed on a local machine that was made accessible to all participants using docker to ensure system separation.
As the final paper was part of the performance assessment of the course a copy can be provided on request.