Frequently Asked Questions

FAQ categories:

• Rollup of ALL FAQ categories and questions
• General information about the Open MPI Project
  • General information about the Open MPI Project
  • What kinds of systems / networks / run-time environments does Open MPI support?
  • Contributing to the Open MPI project
  • Developer-level technical information on the internals of Open MPI
  • System administrator-level technical information about Open MPI
  • Fault tolerance for parallel MPI jobs
• Building
  • Building Open MPI
  • Removed MPI constructs
  • Compiling MPI applications
• Running Jobs with Open MPI
  • Running MPI jobs
  • Troubleshooting building and running MPI jobs
  • Debugging applications in parallel
  • Running jobs under rsh/ssh
  • Running jobs under BProc
  • Running jobs under Torque / PBS Pro
  • Running jobs under Slurm
  • Running jobs under SGE
  • Running on large clusters
• Tuning
  • General run-time tuning
  • Tuning the run-time characteristics of MPI shared memory communications
  • Tuning the run-time characteristics of MPI TCP communications
  • Tuning the run-time characteristics of MPI InfiniBand, RoCE, and iWARP communications
  • Tuning the run-time characteristics of MPI Omni-Path communications
  • Performance analysis tools
  • Tuning the OMPIO parallel I/O component
  • Tuning the run-time characteristics of MPI UDAPL communications
  • Tuning the run-time characteristics of MPI Myrinet communications
• Platform Specific Questions
  • OS X
  • AIX (unsupported)
• Contributed Software
  • VampirTrace Integration
• Languages
  • Java
• CUDA-aware Support
  • Building CUDA-aware Open MPI
  • Running CUDA-aware Open MPI