Predictive performance and scalability modeling of a large-scale application.

Kerbyson, D. J. ; Alme, H. J.

Technical Information Center Oak Ridge Tennessee

关键词: Performance;    Computer Architecture;    Parallel processing;    Scalability;   

RP-ID  :  DE2001780579

学科分类：工程和技术（综合）

美国|英语

来源: National Technical Reports Library

【 摘 要 】

In this work we present an analytical model that encompasses the performance and scaling characteristics of an important ASCI application. SAGE (SAIC's Adaptive Grid Eulerian hydrocode) is a multidimensional hydrodynamics code with adaptive mesh refinement. The model is validated against measurements on several systems including ASCI Blue Mountain, and a yet to be announced Compaq System showing high accuracy. It is parametric-basic machine performance numbers (latency, MFLOPS rate, bandwidth) and application characteristics (problem size, decomposition method, etc.) serve as input. The model adds insight into the performance of current systems, revealing bottlenecks, and is able to show where tuning efforts would be effective. It also allows prediction of performance on future systems which is important for both application and system architecture design as well as for the procurement of supercomputer architectures.