Data Centers

HierKNEM: An Adaptive Framework for Kernel-Assisted and Topology-Aware Collective Communications on Many-Core Clusters

Free registration required

Executive Summary

Multicore Clusters, which have become the most prominent form of High Performance Computing (HPC) systems, challenge the performance of MPI applications with non uniform memory accesses and shared caches hierarchies. Recent advances in MPI collective communications have alleviated the performance issue exposed by deep memory hierarchies by carefully considering the mapping between the collective topology and the core distance, as well as the use of single-copy kernel assisted mechanisms. However, on distributed environments, a single level approach cannot encompass the extreme variations not only in bandwidth and latency capabilities, but also in the aptitude to support duplex communications or operate multiple concurrent copies simultaneously.

  • Format: PDF
  • Size: 165.9 KB