Fabric Collective Accelerator (FCA)

Overview

To meet the needs of scientific research and engineering simulations, supercomputers are growing at an unrelenting rate. As supercomputers increase in size from mere thousands to hundreds-of-thousands of processor cores, new performance and scalability challenges have emerged. FCA is a Mellanox MPI-integrated software package that utilizes CORE-Direct technology for implementing the MPI collectives communications. FCA can be used with all major commercial and open-source MPI solutions that exist and being used for high-performance applications. FCA with CORE-Direct technology accelerates the MPI collectives runtime, increases the CPU availability to the application and allows overlap of communications and computations with asynchronous collective operations.

  • Significantly reduce MPI collective operations runtime
  • Efficient collective communication flow optimized to job and topology
  • Increase CPU availability and efficiency
  • Eliminate congestion caused by collective traffic
  • No need for any additional hardware to install or manage
  • No space/power/cooling penalty
  • Seamless integration with MPI libraries and job schedulers
  • Future proof with embedded support for MPI-3