After a decade where HEC (high-end computing) capability was dominated by the rapid pace of improvements to CPU clock frequency, the performance of next-generation supercomputers is increasingly differentiated by varying interconnect designs and levels of integration. Understanding the tradeoffs of these system designs, in the context of high-end numerical simulations, is a key step towards making effective petascale computing a reality. This work represents one of the most comprehensive performance evaluation studies to date on modern HEC systems, including the IBM Power5, AMD Opteron, IBM BG/L, and Cray X1E. A novel aspect of our study is the emphasis on full applications, with real input data at the scale desired by computational scientists in their unique domain. We examine five candidate ultra-scale applications, representing a broad range of algorithms and computational structures. Our work includes the highest concurrency experiments to date on five of our six applications, including 32K processor scalability for two of our codes and describe several successful optimizations strategies on BG/L, as well as improved X1E vectorization. Overall results indicate that our evaluated codes have the potential to effectively utilize petascale resources; however, several applications will require reengineering to incorporate the additional levels of parallelism necessary to utilize the vast concurrency of upcoming ultra-scale systems. 0-8493-0052-5/00/$0.00+$.50 c © 2001 by CRC Press LLC 3 4 Performance Characteristics of Potential Petascale Scientific Applications
[1]
I. Karlin,et al.
Stabilization of the lattice boltzmann method by the H theorem: A numerical test
,
2000,
Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.
[2]
John B. Bell,et al.
Parallelization of structured, hierarchical adaptive mesh refinement algorithms
,
2000
.
[3]
Lin,et al.
Method for solving the gyrokinetic Poisson equation in general geometry.
,
1995,
Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.
[4]
E. Seidel,et al.
Towards an understanding of the stability properties of the 3+1 evolution equations in general relativity.
,
1999,
gr-qc/9908079.
[5]
Lin-wang Wang,et al.
Parallel Empirical Pseudopotential Electronic Structure Calculations for Million Atom Systems
,
2000
.
[6]
John Shalf,et al.
The Cactus Framework and Toolkit: Design and Applications
,
2002,
VECPAR.
[7]
T. Hahm,et al.
Turbulent transport reduction by zonal flows: massively parallel simulations
,
1998,
Science.
[8]
J. Haas,et al.
Interaction of weak shock waves with cylindrical and spherical gas inhomogeneities
,
1987,
Journal of Fluid Mechanics.