arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15386cs.DCcs.IR
收藏

GPU上大规模近似k-NN图的构造

Large-Scale Approximate k-NN Graph Construction on GPU

Hui Wang, Wan-Lei Zhao, Xiangxiang Zeng

摘要:

k-最近邻图是流形学习、机器学习和信息检索等学科中的关键数据结构,NN-下降算法是解决k-最近邻图构造问题的有效方法。然而,它不能直接移植到GPU由于密集的内存访问所需的方法。在本文中,NN-Descent已被重新设计,以适应GPU架构。特别是,存储器访问的次数已显著减少。重新设计充分利用了GPU硬件的并行性。同时,NN-Descent的通用性和简单性得到了很好的保留。此外,一个简单而有效的k-NN图合并方法。它允许两个图形在GPU上有效地合并。更重要的是,它使得为GPU内存外的数据集构建高质量的k-NN图变得容易。结果表明,我们的方法比单线程NN-Descent快100- 250倍,比现有的基于GPU的方法快2.5- 5倍。

英文摘要:

k-nearest neighbor graph is a key data structure in many disciplines such as manifold learning, machine learning and information retrieval, etc. NN-Descent was proposed as an effective solution for the graph construction problem. However, it cannot be directly transplanted to GPU due to the intensive memory accesses required in the approach. In this paper, NN-Descent has been redesigned to adapt to the GPU architecture. In particular, the number of memory accesses has been reduced significantly. The redesign fully exploits the parallelism of the GPU hardware. In the meantime, the genericness as well as the simplicity of NN-Descent are well-preserved. In addition, a simple but effective k-NN graph merge approach is presented. It allows two graphs to be merged efficiently on GPUs. More importantly, it makes the construction of high-quality k-NN graphs for out-of-GPU-memory datasets tractable. The results show that our approach is 100-250x faster than single-thread NN-Descent and is 2.5-5x faster than existing GPU-based approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑