Distinguished Lecture - Joe Hellerstein: Advance Calmly: Serverless Computing and Cloud Programming
Major shifts in computing platforms are typically accompanied by major shifts in programming models. The public cloud emerged as a new computing platform a decade ago, but we have yet to see a new generation of programming platforms arise in response. All the traditional challenges of distributed programming are present in the cloud, only they are now ubiquitous and more severe. Added to these challenges are new Serverless Computing desires for consumption-based pricing and autoscaling.
This talk will highlight some key principles for cloud programming, including the CALM Theorem and constructive approaches to monotonic coordination-free consistency. I will discuss a new platform called Hydro that we are building at Berkeley's RISElab to take the best of these ideas and combine them into a polyglot, pay-as-you-go platform for cloud programming and deployment. Early results on Hydro---and its underlying database, Anna---suggest that research can offer major improvements to the Serverless Computing systems currently being deployed by the cloud vendors.
Joe Hellerstein is a Madison native, with a Ph.D. in Computer Science and a Minor in Music from the University of Wisconsin. The remainder of the bio is left as an exercise for the reader.
Coffee and cookies will be provided.