A Fast and Scalable Graph Coloring Algorithm for Multi-core and Many-core Architectures

TL;DR

This paper introduces an improved, scalable graph coloring algorithm optimized for multi-core and many-core architectures, reducing conflicts and synchronization to enhance performance in irregular parallel applications.

Contribution

An enhanced graph coloring algorithm that runs more efficiently with fewer conflicts and better scalability on modern multi-core and many-core systems.

Findings

Up to 1.5x faster performance on high-degree graphs

Reduces thread synchronization and conflicts

Maintains near-optimal number of colors

Abstract

Irregular computations on unstructured data are an important class of problems for parallel programming. Graph coloring is often an important preprocessing step, e.g. as a way to perform dependency analysis for safe parallel execution. The total run time of a coloring algorithm adds to the overall parallel overhead of the application whereas the number of colors used determines the amount of exposed parallelism. A fast and scalable coloring algorithm using as few colors as possible is vital for the overall parallel performance and scalability of many irregular applications that depend upon runtime dependency analysis. Catalyurek et al. have proposed a graph coloring algorithm which relies on speculative, local assignment of colors. In this paper we present an improved version which runs even more optimistically with less thread synchronization and reduced number of conflicts compared to Catalyurek et al.'s algorithm. We show that the new technique scales better on multi-core and many-core systems and performs up to 1.5x faster than its predecessor on graphs with high-degree vertices, while keeping the number of colors at the same near-optimal levels.