Performance Characterization for Fusion Co-design Applications

Conference · Sun May 01 00:00:00 EDT 2011

OSTI ID:1407103

Narayanan, Praveen ^[1]; Koniges, Alice ^[1]; Oliker, Leonid ^[1]; Preissl, Robert ^[1]; Williams, Samuel ^[1]; Wright, Nicholas J. ^[1]; Umansky, Maxim ^[2]; Xu, Xueqiao ^[2]; Ethier, Stephanie ^[3]; Wang, Weixing ^[3]; Candy, Jeff ^[4]; Cary, John R. ^[5]; Dudson, Benjamin ^[6]

---

1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
2. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
3. Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
4. General Atomics, San Diego, CA (United States)
5. Tech-X, Boulder, CO (United States)
6. Univ. of York (United Kingdom)

Magnetic fusion is a long-term solution for producing electrical power for the world, and the large thermonuclear international device (ITER) being constructed will produce net energy and a path to fusion energy provided the computer modeling is accurate. To effectively address the requirements of the high-end fusion simulation community, application developers, algorithm designers, and hardware architects must have reliable simulation data gathered at scale for scientifically valid configurations. This paper presents detailed benchmarking results for a set of magnetic fusion applications with a wide variety of underlying mathematical models including both particle-in-cell and Eulerian codes using both implicit and explicit numerical solvers. Our evaluation on a petascale Cray XE6 platform focuses on profiling these simulations at scale identifying critical performance characteristics, including scalability, memory/network bandwidth limitations, and communication overhead. Overall results are a key in improving fusion code design, and are a critical first step towards exascale hardware-software co-design — a process that tightly couples applications, algorithms, imple- mentation, and computer architecture.

• Research Organization: Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
• DOE Contract Number: AC02-05CH11231
• OSTI ID: 1407103
• Resource Relation: Conference: Cray Users Group 2011 (CUG11), Fairbanks, AK (United States), 23-26 May 2011
• Country of Publication: United States
• Language: English

Related Subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY
application benchmarking
profiling
performance characterization
magnetic fusion