INGI Seminar

The road to continuous deep analytics: Apache Flink and Beyond

by Paris Carbone, research group leader of the Distributed Computing group at RISE SICS

Data-stream management systems have for long been considered as a promising architecture for fast data management. The stream processing paradigm poses an attractive means of declaring persistent application logic coupled with state over evolving data.
This talk will start with recent research findings from our distributed computing group that showcase how this architecture can enable the composition of reliable, reconfigurable services and complex applications that go even beyond the needs of scalable data analytics, a major trend in the past decade. Next, I am going to talk about how we envision taking this system architecture to the next level in order to support diverse workloads such as applying large scale ML and AI algorithms while also exploiting modern and heterogeneous application accelerators such as GPUs and Spatial hardware available.

Paris is research group leader of the Distributed Computing group at RISE SICS. He holds a PhD in Distributed Systems from KTH and has been a core open source committer for Apache Flink, a leading system in data stream processing. His research interests span several domains of computer science from distributed algorithms, databases and data management to declarative programming support for data analytics and AI.