- Venue: Barcelona, SPAIN
- Event date: October 18-20th, 2018
- Speakers: Xavier Teruel & Xavier Martorell
Description
The objectives of this course are to understand the fundamental concepts supporting message-passing and shared memory programming models. The course covers the two widely used programming models: MPI for the distributed-memory environments, and OpenMP for the shared-memory architectures. It also presents the main tools developed at BSC to get information and analyze the execution of parallel applications, Paraver and Extrae. Moreover it sets the basic foundations related with task decomposition and parallelization inhibitors, using a tool to analyze potential parallelism and dependences, Tareador.
Agenda
Day 1 (Wednesday) 2:00 pm - 5:30 pm:
- Shared-memory programming models, OpenMP fundamentals
- Parallel regions and work sharing constructs
- Synchronization mechanisms in OpenMP
- Practical: heat diffusion in OpenMP
Day 2 (Thursday) 9:30am – 1:00 pm:
- Tasking in OpenMP 3.0/4.0/4.5
- Programming using a hybrid MPI/OpenMP approach
- Practical: multisort in OpenMP and hybrid MPI/OpenMP
Day 2 (Thursday) 2:00am – 5:30 pm:
- Parallware: guided parallelization
- Practical session with Parallware examples
Day 3 (Friday) 9:30 am – 1:00 pm:
- Introduction to the OmpSs programming model
- Practical: heat equation example and divide-and-conquer
Day 3 (Friday) 2:00pm – 5:30 pm
- Programming using a hybrid MPI/OmpSs approach
- Practical: heat equation example and divide-and-conquer