High-speed graph analytics with the galois system

Abstract

The Galois project at UT Austin has developed a high-level programming model and a lightweight parallel execution engine that enable application writers to write and tune complex parallel applications at a high level of abstraction. This talk describes the experiences of our group and of our industrial collaborators in using the Galois system for "big data" graph analytics. We show that (i) the rich programming model of Galois enables application programmers to write sophisticated graph analytics algorithms that cannot be expressed directly in current graph analytics DSLs, (ii) even when the same algorithm is used, the lightweight execution engine permits Galois programs to run much faster than programs in other DSLs, and (iii) the APIs of most current graph analytics DSLs can be implemented on top of the Galois system in a few hundred lines of code.