A Statistical-Empirical Hybrid Approach to Hierarchical Memory Analysis

A hybrid approach that utilizes both statistical techniques and empirical methods seeks to provide more information about the performance of an application. In this paper, we present a general approach to creating hybrid models of this type. We show that for the scienti c applications of interest, the scaled performance is somewhat predictable due to the regular characteristics of the measured codes. Furthermore, the resulting method encourages streamlined performance evaluation by determining which analysis steps may provide further insight to code performance.

• Type: Conference
• Year: 2000
• Where: EUROPAR
• Authors: Xian-He Sun, Kirk W. Cameron
• Keywords: Distributed And Parallel Computing, Encourages Streamlined Performance, EUROPAR 2000, Hybrid Approach, Scaled Performance