GPUs for high performance computing, Deep learning and beyond

Abstract

After an impressive evolution within the last decade, Graphics Processing Units (GPUs) constitute nowadays a solid trend to accelerate scientific applications. This talk unveils the GPU architecture from an applied perspective, which makes it the cornerstone for Deep Learning, Big Data, Real-Time and Low-Power applications. We will pay a closer attention to Nvidia developments, the leading manufacturer in the HPC marketplace, focusing on the latest Volta and Turing designs.