‹ Back to Video Series: Programming Models for Intel® Xeon Phi™ Coprocessors

Part 8: Heterogeneous Programming with Coprocessors using MPI

  • Overview
  • Resources

In this episode, we will be talking about using multiple coprocessors in a cluster environment. Consider a cluster, which has multiple machines, called compute nodes, with one or several coprocessors per node, connected into a common network. As we know from earlier episodes, we can use a parallel framework called MPI to scale an application across these compute nodes.