Idioma:

Communication-Avoiding for Dynamical Core of Atmospheric General Circulation Model

Xiao, Junmin ; Li, Shigang ; Wu, Baodong ; Zhang, He ; Li, Kun ; Yao, Erlin ; Zhang, Yunquan ; Tan, Guangming

Proceedings of the 47th International Conference on Parallel Processing, 2018, p.1-10

New York, NY, USA: ACM

Texto completo disponível

Citações Citado por

Enviar para

Título:
Communication-Avoiding for Dynamical Core of Atmospheric General Circulation Model
Autor: Xiao, Junmin ; Li, Shigang ; Wu, Baodong ; Zhang, He ; Li, Kun ; Yao, Erlin ; Zhang, Yunquan ; Tan, Guangming
Assuntos: Applied computing -- Physical sciences and engineering -- Earth and atmospheric sciences ; Applied computing -- Physical sciences and engineering -- Earth and atmospheric sciences -- Environmental sciences ; Computing methodologies -- Parallel computing methodologies -- Parallel algorithms ; Computing methodologies -- Parallel computing methodologies -- Parallel algorithms -- Massively parallel algorithms
É parte de: Proceedings of the 47th International Conference on Parallel Processing, 2018, p.1-10
Descrição: Dynamical core is one of the most time-consuming parts in the global atmospheric general circulation model, which is widely used for the numerical simulation of the dynamic evolution process of global atmosphere. Due to its complicated calculation procedures and the non-uniformity of latitude-longitude mesh, the parallelization suffers from high communication overhead. In this paper, we deduce the operator form of the calculating flow in the dynamical core. Furthermore, it is abstracted out that the stencil and collection alternate action is the basic operation in the dynamic core. Based on the operator form of the calculation flow, we propose the corresponding optimization strategy for each operator. In the end, we develop a communication-avoiding algorithm to reduce communication overhead in the dynamic core. Our experiments show that the communication-avoiding algorithm reduces the total runtime by 54% at most for a 50 km resolution model running 10 years. Especially for communication reduction, the new algorithm achieves 1.4x speedup on average for the collective communication and 3.9x speedup on average for the communication involved in the stencil computation.
Editor: New York, NY, USA: ACM
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Communication-Avoiding for Dynamical Core of Atmospheric General Circulation Model

Xiao, Junmin ; Li, Shigang ; Wu, Baodong ; Zhang, He ; Li, Kun ; Yao, Erlin ; Zhang, Yunquan ; Tan, Guangming

New York, NY, USA: ACM

Buscando em bases de dados remotas. Favor aguardar.