Improving the Scalability of an Operational Scientific Application in a Large Multi-core Cluster

  • Alvaro L. Fazenda UNIFESP
  • Eduardo Rocha Rodrigues IBM Research Brazil
  • Simone S. Tomita INPE
  • Jairo Panetta INPE
  • Celso L. Mendes UIUC

Resumo


Currently, High-Performance Computers use nodes with a tendency of an increasing number of cores per chip. In this scenario, enhancing scalability of an existing application requires a comprehensive approach, since system parameters such as memory per core and I/O speeds increase slower with time than cores per chip. This work describes the enhancements incorporated in BRAMS - a regional weather forecasting model - to reach a target execution time using 9,600 cores. We show that some common coding techniques may prevent scalability and that I/O and memory are constraints as core counts increase.
Palavras-chave: Scalability, Parallel IO, Numerical Weather Forecast Model, Large multi-core cluster
Publicado
17/10/2012
FAZENDA, Alvaro L.; RODRIGUES, Eduardo Rocha; TOMITA, Simone S.; PANETTA, Jairo; MENDES, Celso L.. Improving the Scalability of an Operational Scientific Application in a Large Multi-core Cluster. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 13. , 2012, Petrópolis. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2012 . p. 126-132.