Performance evaluation of scale-free graph algorithms




Abstract: In this work, we quantitatively assess the performance of graph processing algorithms for large scale-free graphs residing in byte-addressable Non-Volatile Memory (NVM). Our goal is to assess the performance impact of NVM latencies, with ("semi-external") and without ("fully external") an application-specific scratchpad for the in-flight data structures present within these graph processing algorithms. We use an NVM hardware emulator from Intel for our evaluation.

Bio: Manu Shantharam is a Computational Scientist in the San Diego Supercomputer Center. Manu received his Ph.D. in Computer Science and Engineering from The Pennsylvania State University in 2012. His research interests include performance analysis of HPC applications, sparse scientific computations, scheduling HPC workloads, and resiliency in HPC.