Graph analytics in the exascale era

Emergence of large-scale data sets has ushered in a new era of data-driven discovery in science and beyond that is enabled by advances in artificial intelligence techniques and high-performance computing. Graph analytics is a rapidly emerging area of research and application that enables several classes of applications. Generalization of graph algorithms in the form of combinatorial optimization has numerous applications in scientific computing and data-driven discovery. Despite widespread use, efficient parallel tools for graph analytics are hard to come by, especially when targeting the hybrid CPU-Graphics Processing Unit architectures at extreme scales. In this talk, we will present our ongoing work on distributed multi-GPU systems for two prototypical graph problems: graph clustering and influence maximization. We will demonstrate substantial gains in performance not only on PNNL systems but also on the current # 2 supercomputer, Summit. We will also present case studies from several scientific domains of importance to the DOE.