Lesson 12 Date: 4/16/2014

High Performance Computing (part I)

Linux for Engineering and IT applications

What is High Performance Computing Serial computing Computational tasks are processed in sequential order on one CPU. Most of the generic software was developed for serial computing. Doesn't take advantage of the modern multi-core architectures. Parallel (High Performance) Computing Computational tasks are processed concurrently on the different CPUs or cores. The platform can be a single multi-core host or a computational cluster of network interconnected hosts or combination of both. Special programming methods and software are required, for example, OpenMP or MPI.

Parallel Computing HPC paradigms Amdahl's law OpenMP Parallel regions and loops Parallel sections Synchronization Constructs Message Passing Interface (MPI) General MPI Program Structure Point to Point Communication MPI Standard Data Types MPI Send/Receive example MPI Collective Communications Collective Communication Example Master-Slave Task Farming Computing Partial Sums VM for MPI cluster OpenMPI installation MPI code compilation and run in OpenMPI References Take me to the Course Website