arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.02543cs.DC
收藏

ETALE:用于GPU上动态图ANN搜索的具有加速无锁执行的演化拓扑

ETALE: Evolving Topology with Accelerated Lock-free Execution for Dynamic Graph ANN Search on GPUs

University of Washington(华盛顿大学)

Dongfang Zhao

AI总结:

研究GPU上基于图的近似最近邻索引相关问题,提出ETALE索引,核心是无锁写时复制平板图,在多数据集上评估,相比其他索引速度更快且内存占用有界。

摘要:

GPU上基于图的近似最近邻(ANN)索引最初是为静态集合构建的,必须重建受影响窗口以吸收更新,而增量更新的动态图索引在CPU上运行且无法利用GPU并行性。本文提出新的ANN索引ETALE,是首个支持流插入和删除且无需全局重建的GPU原生图ANN索引。ETALE的核心是无锁写时复制平板图,其删除状态和邻接共享单个原子发布字,产生可证明的删除单调性不变量以及GPU内存的有界回收,该回收在累积删除中是次线性的。我们在CUDA中实现了ETALE,并在五个不同的多模态数据集上针对四个现有最先进索引进行评估:Tagore(GPU静态,SIGMOD'26)、DIGRA(CPU动态,SIGMOD'26)、CAGRA(GPU静态,ICDE'24)和HNSW(CPU动态,TPAMI'20)。在持续变动情况下,ETALE每轮以数百毫秒的时间将索引维持在召回率高于0.95的水平,比CAGRA的每个窗口重建快4.8 - 8.8倍,比更新的Tagore快1.8 - 2.5倍,比CPU动态索引快3.3 - 147倍。此外,ETALE的内存占用保持有界,而仅墓碑系统的内存占用会无限增长。

英文摘要:

Graph-based approximate nearest neighbor (ANN) indexes on the GPU are originally built for static collections and must reconstruct the affected window to absorb any update, while the dynamic graph indexes that update incrementally run on the CPU and cannot exploit GPU parallelism. This paper presents a new ANN index, namely ETALE (Evolving Topology with Accelerated Lock-free Execution), which is among the first GPU-native graph ANN indexes to support streaming insertion and deletion without a global rebuild. The core of ETALE is a lock-free copy-on-write slab graph whose deletion state and adjacency share a single atomically published word, which yields a provable deletion-monotonicity invariant together with a bounded reclaim of GPU memory that is sublinear in accumulated deletions. We have implemented ETALE in CUDA and evaluate it on five diverse multimodal datasets against four state-of-the-art indexes: Tagore (GPU static, SIGMOD'26), DIGRA (CPU dynamic, SIGMOD'26), CAGRA (GPU static, ICDE'24), and HNSW (CPU dynamic, TPAMI'20). Under continuous churn, ETALE maintains the index in hundreds of milliseconds per round at recall above $0.95$, which is $4.8$--$8.8\times$ faster than CAGRA's per-window rebuild, $1.8$--$2.5\times$ faster than the more recent Tagore, and $3.3$--$147\times$ faster than the CPU dynamic indexes. In addition, the memory footprint of ETALE stays bounded where tombstone-only systems grow indefinitely.

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。

↑