From scratch, Alya was specially designed for massively parallel supercomputers, and the parallelization embraces four levels of the computer hierarchy. 1) A substructuring technique with MPI as the message passing library is used for distributed memory supercomputers. 2) At the node level, both loop and task parallelisms are considered using OpenMP as an alternative to MPI. Dynamic load balance techniques have been introduced as well to better exploit computational resources at the node level. 3) At the CPU level, some kernels are also designed to enable automatic vectorization. 4) Finally, accelerators like GPU are also partially exploited through OpenACC pragmas or with CUDA to further enhance the performance of the code on heterogeneous computers.
The scientific tasks of the candidate will involve optimizing and parallelizing computationally expensive portions of Alya for execution on GPUs using OpenACC. The focus is on leveraging hardware accelerators to enhance performance and scalability, ensuring efficient utilization of modern heterogeneous supercomputing resources involving accelerators.
Key Duties
- Performance analysis and profiling
- Porting to GPU of given kernels of Alya to GPU
- Documentation
- Benchmarking
Data de tancament: Dijous, 30 Gener, 2025
Més posts de Recerca
Cap comentari:
Publica un comentari a l'entrada