An Improved Machine Learning Approach for Selecting a Polyhedral Model Transformation

Abstract

Algorithms in fields like image manipulation, signal processing, and statistics frequently employ tight CPU-bound loops, whose performance is highly dependent on efficient utilization of the CPU and memory bus. The polyhedral model allows the automatic generation of loop nest transformations that are semantically equivalent to the original. The challenge, however, is to select the transformation that gives the highest performance on a given architecture. In this paper, we present an improved machine learning approach to select the best transformation. Our approach can be used as a stand-alone method that yields accuracy comparable to the best previous approach but offers a substantially faster selection process. As well, our approach can be combined with the best previous approach into a higher level selection process that is more accurate than either method alone. Compared to prior work, the key distinguishing characteristics to our approach are formulating the problem as a classification problem rather than a regression problem, using static structural features in addition to dynamic performance counter features, performing feature selection, and using ensemble methods to boost the performance of the classifier.