Optimization of Finite-Differencing Kernels for Numerical Relativity Applications
A simple optimization strategy for the computation of 3D finite-differencing kernels on many-cores architectures is proposed. The 3D finite-differencing computation is split direction-by-direction and exploits two level of parallelism: in-core vectorization and multi-threads shared-memory paralleliz...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
MDPI AG
2018-05-01
|
| coleção: | Journal of Low Power Electronics and Applications |
| Assuntos: | |
| Acesso em linha: | http://www.mdpi.com/2079-9268/8/2/15 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|