Improving graph coloring on distributed-memory parallel computers

Graph coloring is a combinatorial optimization problem that classically appears in distributed computing to identify the sets of tasks that can be safely performed in parallel. Despite many existing efficient sequential algorithms being known for this NP-Complete problem, distributed variants are challenging. Building on an existing distributed-memory graph coloring framework, we investigate two techniques in this paper. First, we investigate the application of two different vertex-visit orderings, namely Largest First and Smallest Last, in a distributed context and show that they can help to significantly decrease the number of colors, on small-to medium-scale parallel architectures. Second, we investigate the use of a distributed post-processing operation, called recoloring, which further drastically improves the number of colors while not increasing the runtime more than twofold on large graphs. We also investigate the use of multicore architectures for distributed graph coloring algorithms.