Multi-GPU programming with OpenACC and MPI
Résumé
In this session you will learn how to program multi GPU systems or GPU clusters using the Message Passing Interface (MPI) and OpenACC. The session starts by giving a quick introduction to MPI and how a CUDA-aware MPI implementation can be used with OpenACC. Other topics covered are: how to handle GPU affinity in multi GPU systems, overlapping communication with computation to hide communication times and using the NVIDIA performance analysis tools. As we'll be using GPUs hosted in the cloud, all you are required to bring is a laptop with a modern browser.