Introduction to mixed parallel programming using MPI and OpenMP
PICSciE is pleased to announce a two-hour mini-course on mixed parallel programming. Participants will learn to exploit the power of parallel computing on distributed memory systems using message passing (MPI) combined with shared memory multi-threaded parallelism using OpenMP directives on multicore processors.
Mixing these two methods together allows for very high scalability on the largest computers currently available. GPU programming with recently-developed OpenACC directives will also be discussed.
No previous experience with parallel programming is assumed, but participants are expected to be familiar with C or Fortran.
Dr. Stéphane Ethier is the Deputy Head of Computational Plasma Physics Group at the Princeton Plasma Physics Laboratory (PPPL). He received his Ph.D. in theoretical plasma physics from the Department of Energy and Materials of the Institut National de la Recherche Scientifique (INRS) in Montreal, Canada. His current research involves all aspects of high-performance computing for large-scale gyrokinetic particle-in-cell simulations of microturbulence in magnetic confinement fusion devices. Dr. Ethier has been involved in several projects funded by the Department of Energy's Scientific Discovery through Advanced Computing (SciDAC) as well as a new Exascale Software stack project funded by the office of Advanced Scientific Computing Research.
Audience: Graduate students, researchers and technical staff
Location: E-Classroom, 225 Lewis Science Library
Date/Time: 12/05/13 at 4:30 pm - 12/05/13 at 6:30 pm