Parallel computing performs multiple actions at the same time, allowing you to to execute code efficiently and save time. It can therefore scale and solve larger problems than sequential programming.

This four-day school covers topics essential to parallel programming. Topics include:

• General parallel computing - performance measurement and factors affecting performance, I/O and data movement, schedulers and “embarrassingly parallel” jobs
  
• OpenMP, shared memory and threads
• Message Passing Interface (MPI)
• GPGPU - CUDA

Details and prerequisites.

The school is designed for participants familiar with the Unix command line and who have some level of programming experience. Completion of the ACENET Basics Series, or equivalent experience, is strongly recommended. The mornings will consist of lectures, with the afternoons following a lab format, where participants will be given exercises, or can bring specific problems to instructors related to their research.

Seating is limited so please register early.