POM.gpu-v1.0: a GPU-based Princeton Ocean Model

POM.gpu-v1.0: a GPU-based Princeton Ocean Model
复制标题

POM.gpu-v1.0:基于 GPU 的普林斯顿海洋模型

DOI:
10.5194/gmd-8-2815-2015
复制
发表时间:
2015-09
影响因子:
5.1
通讯作者:
Yang G.
Yang G.
中科院分区:
地球科学2区
文献类型:
--
作者:
Xu S.;Huang X.;Oey L. -Y.;Xu F.;Fu H.;Zhang Y.;Yang G.

文献摘要

参考文献

被引文献

相似文献

摘要图形处理器(GPU)因其高性能而成为许多科学应用中极具吸引力的解决方案。然而,大多数现有的气候模型 GPU 转换仅在少数计算密集型区域使用 GPU。在
Abstract. Graphics processing units (GPUs) are an attractive solution in many scientific applications due to their high performance. However, most existing GPU conversions of climate models use GPUs for only a few computationally intensive regions. In the present study, we redesign the mpiPOM (a parallel version of the Princeton Ocean Model) with GPUs. Specifically, we first convert the model from its original Fortran form to a new Compute Unified Device Architecture C (CUDA-C) code, then we optimize the code on each of the GPUs, the communications between the GPUs, and the I / O between the GPUs and the central processing units (CPUs). We show that the performance of the new model on a workstation containing four GPUs is comparable to that on a powerful cluster with 408 standard CPU cores, and it reduces the energy consumption by a factor of 6.8.
DOI: 10.1007/s10236-011-0519-z
发表时间: 2012-01
期刊: Ocean Dynamics
影响因子: 2.3
作者:
A. Isobe;Shin’ichiro Kako;Xinyu Guo;H. Takeoka
通讯作者: A. Isobe;Shin’ichiro Kako;Xinyu Guo;H. Takeoka
DOI: 10.23919/oceans.2011.6107199
发表时间: 2011-12
期刊: OCEANS'11 MTS/IEEE KONA
影响因子: --
作者:
J. Mak;P. Choboter;C. Lupo
通讯作者: J. Mak;P. Choboter;C. Lupo
DOI: 10.1145/1654059.1654067
发表时间: 2009-11
期刊: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis
影响因子: --
作者:
J. C. Linford;J. Michalakes;Manish Vachharajani;Adrian Sandu
通讯作者: J. C. Linford;J. Michalakes;Manish Vachharajani;Adrian Sandu
DOI: 10.1007/s10872-009-0063-3
发表时间: 2009-12-01
影响因子: 2.3
作者:
Miyazawa, Yasumasa;Zhang, Ruochao;Komatsu, Kosei
通讯作者: Komatsu, Kosei
DOI: 10.1175/1520-0485(1985)015
发表时间: 1985-05
影响因子: 3.5
作者:
E. Kunze
通讯作者: E. Kunze