FineQuery: Fine-Grained Query Processing on CPU-GPU Integrated Architectures

2021 
Using heterogeneous coprocessors, such as GPUs, to accelerate complicated SQL queries has been proved to be effective in the database domain. Previous works show that taking advantage of the high parallelism and computing capacity of heterogeneous coprocessors can bring significant performance improvements. However, in the discrete memory architecture, the advantages of heterogeneous coprocessors will be weakened due to the low PCI-e bandwidth and high latency. Fortunately, hardware vendors have proposed a novel integration architecture design, which integrates CPU and GPU on the same chip. This integrated architecture allows the GPU and CPU to share the same unified memory, taking new opportunities for fine-grained collaboration between the GPU and CPU to optimize SQL queries. In this paper, we propose a query processing engine, called FineQuery, to optimize the execution of SQL queries on the integrated architecture. FineQuery can take advantage of both architectural features and query characteristics by performing fine-grained workload scheduling between the CPU and the GPU. Experimental results show that 1) on the integration architecture, FineQuery can reduce the latency by 25.30% and increase the bandwidth utilization by 39.46% on average. 2) FineQuery on the integrated architecture achieves $13.74\times$ the performance-per-cost ratio and $6.87\times$ energy efficiency over query processing on the discrete GPU platform.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    43
    References
    0
    Citations
    NaN
    KQI
    []