期刊
出版社
IEEE
DOI: 10.1145/2503210.2503300
关键词
SCEC; seismic hazard analysis; earthquake ground motions; weak scaling; GPU; CyberShake; hybrid heterogeneous
资金
- Department of Energy (DOE) [DE-AC05-00OR22725]
- Innovative and Novel Computational Impact on Theory and Experiment (INCITE)
- XSEDE under NSF [OCI-1053575]
- NSF [OCI-0832698, EAR-0529922]
- Community Computational Platforms for Developing Three-Dimensional Models of Earth Structure [EAR-1226343]
- NSF Software Environment for Integrated Seismic Modeling [OCI-1148493]
- SCEC
- USGS [07HQAG0008]
We have developed a highly scalable and efficient GPU-based finite-difference code (AWP) for earthquake simulation that implements high throughput, memory locality, communication reduction and communication / computation overlap and achieves linear scalability on Cray XK7 Titan at ORNL and NCSA's Blue Waters system. We simulate realistic 0-10 Hz earthquake ground motions relevant to building engineering design using high-performance AWP. Moreover, we show that AWP provides a speedup by a factor of 110 in key strain tensor calculations critical to probabilistic seismic hazard analysis (PSHA). These performance improvements to critical scientific application software, coupled with improved co-scheduling capabilities of our workflow-managed systems, make a statewide hazard model a goal reachable with existing supercomputers. The performance improvements of GPU-based AWP arc expected to save millions of core-hours over the next few years as physics-based seismic hazard analysis is developed using heterogeneous petascale supercomputers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据