CUDA and OpenACC Training

BSC, in association with Universitat Politècnica de Catalunya (UPC) was designated by NVIDIA as a GPU Center of Excellence (GCOE) in 2011 in recognition of their role as leading institutions at the forefront of parallel computing research.  

Together, BSC and UPC have built an Education Programme on Parallel Programming using CUDA and OpenACC in order to provide a cluster-aware programming environment for GPUs, to optimise mutlti-GPU runtime management with GMAC, to support GPU acceleration from the task-based StarSs programming model and its OmpSs implementation and to build a new GPU-based cluster prototype system to explore the potential of low-power GPU clusters as High Performance Computing platforms.