A cross-input adaptive framework for GPU programs optimization

Abstract—Recent years have seen a trend in using graphic pro-cessing units (GPU) as accelerators for general-purpose comput-ing. The inexpensive, single-chip, massively parallel architecture of GPU has evidentially brought factors of speedup to many nu-merical applications. However, the development of a high-quality GPU application is challenging, due to the large optimization space and complex unpredictable effects of optimizations on GPU program performance. Recently, several studies have attempted to use empiri-cal search to help the optimization. Although those studies have shown promising results, one important factor—program inputs—in the optimization has remained unexplored. In this work, we initiate the exploration in this new dimension. By conducting a series of measurement, we find that the ability to adapt to program inputs is important for some applications to achieve their best performance on GPU. In light of the findings, we develop an input-adaptive optimization framework, namely G-ADAPT, to address the influence by constructing cross-input predictive models for automatically predicting the (near-)optimal configurations for an arbitrary input to a GPU program. The results demonstrate the promise of the framework in serving as a tool to alleviate the productivity bottleneck in GPU programming