BIFOLD Colloquium 04/24/2023

Cloud-native Data Systems for the Post-Moore Era

Abstract: Cloud-native data systems today need to address a number of pressing challenges: from handling massive amounts of data using different cloud form factors, to  efficiently managing a pool of disaggregated hardware resources. This is a non-trivial undertaking, especially in the post-Moore era of increased hardware heterogeneity that opens the potential to offload compute closer to data (e.g., storage) or push operations down to where the data moves (e.g., on the network cards or switches). While this opens a number of exciting opportunities, it is not clear on what the best way forward is to absorb the increased complexity.

In her talk, Jana Giceva argues that addressing such a range of challenges, requires an effort that is beyond what can be typically done within a single layer of the system stack. Her proposal calls for a holistic approach that opens up the data system interfaces, embraces the synergy with compilers, and revisits the underlying system support for modern data workloads in virtualized environments.

Register: pr@bifold.berlin

Speaker: Jana Giceva is an Assistant Professor for Computer Scienceat the Department of Computer Science, TU Munich. Before joining TUM in 2020, she was a Lecturer (Assistant Professor) in the Department of Computing at Imperial College London. She completed her PhD at ETH Zurich in 2017, where she was advised by Gustavo Alonso and Timothy Roscoe. She also held roles at Microsoft Research and Oracle Labs.