A Heterogeneous CPU-GPU Implementation for Discrete Elements Simulation with Multiple GPUs
文献类型：会议论文
| 作者 | Tian, Yuan1 ; Qi, Ji1; Lai, Junjie2; Zhou, Qingguo3; Yang, Lei1; IEEE
|
| 出版日期 | 2013 |
| 关键词 | heterogeneous DEM GPU multi-GPU MPI |
| 页码 | 547-+ |
| 英文摘要 | To calculate the large number of particles in discrete elements simulation, a heterogeneous CPU-GPU implementation with multiple GPUs is developed. The implementation is achieved by combining two different parallel programming languages so that it can be assigned to a CPU-GPU cluster. The communication between nodes uses Massage Passing Interface (MPI) implementation for dynamic domain decomposition, particles re-mapping and data copying of overlapping areas. Other works are assigned to GPUs to obtain a high computational speed. The results of strong and weak scalability tests are analyzed for different number of GPUs. Last, the LAMMPS is used as CPU platform to compare with multi-GPU application for reflecting the superiority of using heterogeneous implementation. |
| 会议录 | 2013 INTERNATIONAL JOINT CONFERENCE ON AWARENESS SCIENCE AND TECHNOLOGY & UBI-MEDIA COMPUTING (ICAST-UMEDIA)
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | 345 E 47TH ST, NEW YORK, NY 10017 USA |
| 语种 | 英语 |
| 资助项目 | China National Natural Science Foundation[91026005] |
| WOS研究方向 | Computer Science ; Engineering |
| WOS记录号 | WOS:000349913600089 |
| 源URL | [http://119.78.100.186/handle/113462/57568]  |
| 专题 | 中国科学院近代物理研究所 |
| 通讯作者 | Tian, Yuan |
| 作者单位 | 1.Chinese Acad Sci, Inst Modern Phys, Dept Spallt Target, Beijing 100864, Peoples R China 2.nVIDIA Corp, Beijing, Peoples R China 3.Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tian, Yuan,Qi, Ji,Lai, Junjie,et al. A Heterogeneous CPU-GPU Implementation for Discrete Elements Simulation with Multiple GPUs[C]. 见:. |
入库方式： OAI收割
来源：近代物理研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。