一种适应GPU的混合OLAP查询处理模型

GPU Adaptive Hybrid OLAP Query Processing Model

通用GPU因其强大的并行计算能力成为新兴的高性能计算平台,并逐渐成为近年来学术界在高性能数据库实现技术领域的研究热点.但当前GPU数据库领域的研究沿袭的是ROLAP(relational OLAP)多维分析模型,研究主要集中在关系操作符在GPU平台上的算法实现和性能优化技术,以哈希连接的GPU并行算法研究为中心.GPU拥有数千个并行计算单元,但其逻辑控制单元较少,相对于CPU具有更强的并行计算能力,但逻辑控制和复杂内存管理能力较弱,因此并不适合需要复杂数据结构和复杂内存管理机制的内存数据库查询处理算法直接移植到GPU平台.提出了面向GPU向量计算特性的混合OLAP多维分析模型semi-MOLAP,将MOLAP(multidimensional OLAP)模型的直接数组访问和计算特性与ROLAP模型的存储效率结合在一起,实现了一个基于完全数组结构的GPU semi-MOLAP多维分析模型,简化了GPU数据管理,降低了GPU semi-MOLAP算法复杂度,提高了GPU semiMOLAP算法的代码执行率.同时,基于GPU和CPU计算的特点,将semi-MOLAP操作符拆分为CPU和GPU平台的协同计算,提高了CPU和GPU的利用率以及OLAP的查询整体性能.

The general purpose graphic computing units（GPGPUs） have become the new platform for high performance computing due to their massive parallel computing power, and in recent years more and more high performance database research has placed focus on GPU database development. However, today＇s GPU database researches commonly inherit ROLAP（relational OLAP） model, and mainly address how to realize relational operators in GPU platform and performance tuning, especially on GPU oriented parallel hash join algorithm. GPUs have higher parallel computing power than CPUs but less logical control and management capacity for complex data structure, therefore they are not adaptive for directly migrating the in-memory database query processing algorithms based on complex data structure and memory management. This paper proposes a GPU vectorized processing oriented hybrid OLAP model, semi-MOLAP, which combines direct array access and array computing of MOLAP with storage efficiency of ROLAP. The pure array oriented GPU semi-MOLAP model simplifies GPU data management, reduces complexity of GPU semi-MOLAP algorithms and improves their code efficiency. Meanwhile, the semi-MOLAP operators are divided into co-computing operators on CPU and GPU platforms to improve utilization of both CPUs and GPUs for higher query processing performance.