Abstract: In this talk I’ll review several research activities at Arm that relate to distributed systems and more specifically the edge computing and high-performance computing segments. I’ll discuss our work at looking at how to adapt cloud native software architectures and infrastructure to edge computing stacks, covering our recently completed work on addressing static and dynamic heterogeneity present in such systems. I’ll also discuss our work on addressing contention from executing machine learning inference and multi-model both inside constrained systems and at scale. Finally, I’ll cover work we have been doing at addressing privacy and confidentially concerns for machine learning workloads using confidential computing architectures.
Bio: Eric is currently a fellow in the Architecture division at Arm in Austin, TX leading the systems research group. The group’s activities include exploring the place of Arm within edge computing, data centers, HPC, and investigating next generation concepts in security, systems software, and distributed systems.