Parallel programming: classic track (MPI & OpenMP) 1
  • David Henty, PRACE, XSEDE, RIKEN, Compute Canada
  • June 2016

Slide contents

  • Traffic Model
  • MPI / OpenMP Track IHPCSS 2016, Ljubljana
  • Who am I?
  • Edinburgh
  • ARCHER
  • Overview
  • Materials
  • Timetable: Monday
  • Timetable: Tuesday
  • Lecture / practical rationale
  • Message-Passing
  • Outline
  • Analogy
  • Process communication
  • Synchronisation
  • Communication modes
  • Synchronous send
  • Asynchronous send
  • Point-to-Point Communications
  • Collective Communications
  • Broadcast: one to all communication
  • Broadcast
  • Scatter
  • Gather
  • Reduction Operations
  • Reduction
  • Hardware
  • Practicalities
  • Message Passing on Shared Memory
  • Issues
  • Summary (i)
  • Summary (ii)
  • Exercise: computing pi