DescriptionAs we approach the end of lithographic/Dennard scaling, the HPC community needs a way to continue performance scaling. One way of providing that scaling is an increase in the number and diversity of specialized architectures tailored for specific applications. To accelerate the architecture specification and verification of these new architectures, more rapid prototyping methods are needed. At the same time, these new architectures need software stacks and programming models to be able to actually use these new designs.
In concert with this increase in architecture heterogeneity, there has been a consistent march toward development of open source based hardware and software solutions for each of these components to be used in lieu of existing closed source solutions.
We present the proposed third installment of OpenSuCo: Workshop for Open Source Supercomputing. We aim to continue the previous two workshops' focus on exploring and collaborating on building HPC systems using open-source hardware and system software IP. The goal is to engage the HPC community and explore open source solutions across the system stack – from silicon to applications.