An Analysis of Program Phase Behavior and its Predictability

Abstract

The execution of a computer program typically consists of a number of phases where each phase exhibits its own behavior. This phase behavior can be exploited for various purposes such as hardware adaptation, performance modeling, etc. Recently, a number of phase identification and classification schemes have been proposed to capture this phase behavior. For some of these phase classification schemes, phase predictors are needed to accurately predict phase transitions.In this paper, we analyze program phase behavior by constructing a model for representing the phase sequence of a program execution. We validate this model by generating a probabilistic phase sequence from it and by comparing the phase prediction accuracy of this phase sequence with the original program phase sequence for a number of phase predictors. From this model, we derive a compact model which we use to evaluate the performance of various types of phase predictors. This gives us a better understanding in program phase behavior.

Synthetic traffic generation as a tool for dynamic interconnect evaluation

“…One problem may be that the network traffic behavior changes throughout the execution of the program, and that just one traffic profile does not suffice. Using known program phase behavior techniques [8] we will investigate this, and explore the benefits of using multiple traffic profiles for each benchmark application, one per program phase, and average the results according to the relative occurrences of each phase.…”