Logical Aspects of Massively Parallel and Distributed Systems

Abstract

Database research has witnessed a renewed interest for data processing in distributed and parallel settings. While distributed and parallel data management systems have been around for quite some time, it is the rise of cloud computing and the advent of Big Data that presents the community with new challenges. This paper highlights recent research concerning the logical foundations of massively parallel and distributed systems. The first part of the paper concerns massively parallel systems where computation proceeds in a number of synchronized rounds. Here, the focus is on evaluation algorithms for conjunctive queries as well as on reasoning about correctness and optimization of such algorithms. The second part of the paper addresses a distributed asynchronous setting where eventual consistency comes into play. Here, the focus is on coordination-free computation and its relationship to logical monotonicity and Datalog programs.