Power invariant vector sequence compaction

TL;DR: This work proposes a novel method to compact a given input vector sequence to improve on the existing techniques, and proposes a graph model to transform the problem to the problem of finding a heaviest weighted trail in a directed graph.

Abstract: Simulation-based power estimation is commonly used for its high accuracy, despite excessive computation times. Techniques have been proposed to speed it up by transforming a given sequence into a shorter one while preserving the power consumption characteristics of the original sequence. This work proposes a novel method to compact a given input vector sequence to improve on the existing techniques. We propose a graph model to transform the problem to the problem of finding a heaviest weighted trail in a directed graph. We also propose a heuristic based on min-cost flow algorithms, using the graph model. Furthermore, we show that generating multiple input sequences yields better solutions in terms of both accuracy and simulation time. Experiments showed that significant reduction in simulation times can be achieved with extremely accurate results. Experiments also showed that the generation of multiple sequences improved the results further both in terms of accuracy and simulation time.