Revisiting hash join on graphics processors: a decade later

摘要

Over the last decade, significant research effort has been put into improving the performance of hash join operation on GPUs. Over the same period, there have been significant changes to the GPU architecture. Hence in this paper, we first revisit the major GPU hash join implementations in the last decade and detail how they take advantage of different GPU architecture features. We then perform a comprehensive performance evaluation of these implementations using different generations of GPUs released over the last decade, which helps to shed light on the impact of different architecture features and to identify the factors guiding the choice of these features. We then study how data characteristics like skew and match rate impact the performance of GPU hash join implementations and propose techniques to improve the performance of existing implementations under such conditions. Finally, we perform an in-depth comparison of the performance and cost-efficiency of GPU hash join implementations against state-of-the-art CPU implementation.