Distributed Triangle Counting in the Graphulo Matrix Math Library

TL;DR

This paper adapts two triangle counting algorithms for large graphs to the Graphulo library within Apache Accumulo, enabling distributed, server-side processing and analyzing their performance on power law graphs.

Contribution

It introduces adaptations of adjacency and incidence matrix-based triangle counting algorithms to Graphulo for distributed graph analysis inside Accumulo.

Findings

Similar performance profiles for both algorithms on power law graphs

Data skew increasingly affects performance

Motivates development of skew-aware hybrid algorithms

Abstract

Triangle counting is a key algorithm for large graph analysis. The Graphulo library provides a framework for implementing graph algorithms on the Apache Accumulo distributed database. In this work we adapt two algorithms for counting triangles, one that uses the adjacency matrix and another that also uses the incidence matrix, to the Graphulo library for server-side processing inside Accumulo. Cloud-based experiments show a similar performance profile for these different approaches on the family of power law Graph500 graphs, for which data skew increasingly bottlenecks. These results motivate the design of skew-aware hybrid algorithms that we propose for future work.