Agenda

Due to COVID-19 travel restrictions, we decided to organize the ACACES 2020 summer school as a VIRTUAL summer school. The virtual ACACES 2020 summer school is a two-week event for computer architects and tool builders working in the field of embedded systems, computer architecture, and compilation. A distinguishing feature of this Summer School is its broad scope ranging from low-level technological issues to advanced compilation techniques and entrepreneurship. In the design of modern computer systems one has to be knowledgeable about hardware as well as about software and the market needs. This summer school offers the ideal mix, both at the entry level and at the most advanced level. The ACACES Summer School is organized by the HiPEAC Network (www.HiPEAC.net) in collaboration with the TETRAMAX Innovation Action (www.tetramax.eu) but it is open to everybody.

HPC Architectures for AI and Dedicated Applications

Proteins and their intricate network of interactions are the mainstay of any cellular process. Dissecting these networks at atomic detail is invaluable, as this paves the route to a mechanistic understanding of biological function and provides the first essential step toward the development of new drugs. Because of the challenges associated with experimental techniques, structural biologists have to resort more and more these days to complementary computational methods.

During the last years, the computing ecosystem is becoming more and more heterogeneous. On the one hand, trends in computer architectures focus on providing different computing devices (CPUs, GPUs and FPGAs) and memories in a single chip or computing node, with the aim of providing better computing devices for the different types of algorithms and applications. On the other hand, distributed platforms such as Clusters, Grids and Clouds, which have been traditionally composed by many homogeneous nodes, are starting to be composed of heterogeneous nodes including processors with different cores, accelerators and memory capacities. This heterogeneity is required to achieve better computing performance with lower energy consumption and must be managed at different levels.