MPC: A Unified Parallel Runtime for Clusters of NUMA Machines

Over the last decade, Message Passing Interface (MPI) has become a very successful parallel programming environment for distributed memory architectures such as clusters. However, the architecture of cluster node is currently evolving from small symmetric shared memory multiprocessors towards massively multicore, Non-Uniform Memory Access (NUMA) hardware. Although regular MPI implementations are using numerous optimizations to realize zero copy cacheoblivious data transfers within shared-memory nodes, they might prevent applications from achieving most of the hardware's performance simply because the scheduling of heavyweight processes is not flexible enough to dynamically fit the underlying hardware topology. This explains why several research efforts have investigated hybrid approaches mixing message passing between nodes and memory sharing inside nodes, such as MPI+OpenMP solutions [1,2]. However, these approaches require lots of programming efforts in order to adapt/rewrite ex...

• Type: Conference
• Year: 2008
• Where: EUROPAR
• Authors: Marc Pérache, Hervé Jourdren, Raymond Namyst
• Keywords: Distributed And Parallel Computing, EUROPAR 2008, MPI Applications, Regular Mpi, Regular Mpi Implementations