Dear NERSC users, The OpenMP API is the de facto standard for writing parallel applications for shared memory computers supported by multiple scientific compilers on CPU and GPU architectures. MPI+OpenMP for CPUs and OpenMP device offload for GPUs are recommended portable programming models on Perlmutter. Calling all programmers! Whether you're new to parallel programming, new to OpenMP or OpenMP device offload, or want a refresher on the basics or explore advanced features, our OpenMP monthly training series is for you. The series runs from May to October 2024, and you're welcome to attend all sessions or just the ones that interest you most. Join the training series led by OpenMP experts Michael Klemm (AMD OpenMP ARB) and Christian Terboven (RWTH Aachen University)! A wide range of topics to be covered includes OpenMP basics, parallel worksharing, tasking, memory management and affinity, vectorization, correctness, performance, GPU offloading, and MPI/OpenMP hybrid programming. The format of each training session will be presentations followed by homework assignments using Perlmutter. Homework solutions will be reviewed at the start of the next session. - Session 1: Monday, May 6. OpenMP Introduction - Session 2: Monday, June 10. Tasking - Session 3: Monday, July 8. Optimization for NUMA and SIMD - Session 4: Monday, August 5. What Could Possibly Go Wrong Using OpenMP (by Ruud van der Pas, Oracle) - Session 5: Wednesday, September 4. Introduction to Offloading with OpenMP - Session 6: Monday, October 7. Advanced OpenMP Offloading Topics - Session 7: Monday, October 28. Selected / Remaining Topics For detailed session topics and to register, please visit https://www.nersc.gov/openmp-training-series-may-oct-2024/. Best Regards, Helen He NERSC Training > _______________________________________________ Users mailing list Users@nersc.gov