Performance Coupling: A Methodology for Predicting Application Performance Using Kernel Performance.
Jonathan Geisler, Valerie Taylor · 1999
Traditional performance optimization techniques have focused on finding the kernel in a program that is the most time consuming and attempting to optimize it. We introduce a methodology for measuring and representing the interaction, or coupling, between kernels that improves upon the accuracy of the traditional method. Then we demonstrate the benefits of using the new methodology by developing a new hybrid algorithm for the conjugate gradient application that results in fewer cache misses than the other algorithms studied.