Graph processing exists in many practical problems in computer science. Most graphs from real applications, such as transportation routes and social network analysis, are large scale and complex structured. This nature makes high performance graph processing on modern heterogeneous parallel devices more interesting.
This Master project will first select two or three recently developed open-source parallel graph processing libraries (i.e., BGL, Pregel, GraphLab, PowerGraph, Ligra, Galois and Gunrock) and empirically identify several major shortcomings through extensive benchmarks on parallel platforms at HPC-Lab.
The experiments will be done on the latest Intel/AMD CPUs and NVIDIA GPUs with Linux OS installed.
In the subsequent work for the Master thesis, the student will be encouraged to find for potential opportunities for faster graph processing methods applied to, for instance breadth-first search or single source shortest path.
Co-supervisor: Dr. Weifeng Liu, MSCA Post Doc, HPC-Lab