Porting Nahuj To Cuda
Evghenii Gaburov · Zenodo (CERN European Organization for Nuclear Research) · 2013
This white-paper reports on an enabling e ort that involves porting a legacy 2D uid dynamics Fortran code to NVIDIA GPUs. Given the complexity of both code and underlying (custom) numerical method, the natural choice was to use NVIDIA CUDA C to achieve the best possible performance. We achieved over 4.5x speed-up on a single K20 compared to the original code executed on a dual-socket E5-2687W.1