AI 中文总结
GrAND是针对Vamana和CAGRA的GPU原生动态更新算法集合，通过优化图修复、并行邻接表更新和按需反向图构建，在7个数据集的5种流工作负载中，相比SVFusion和FreshDiskANN-GPU大幅提升了ANNS的整体吞吐量。
AI 中文摘要
现代近似最近邻搜索（ANNS）应用针对持续演化的向量集合运行，需要能在维持高吞吐量搜索的同时处理插入和删除操作且保持高召回率的图索引。然而，大多数GPU图索引是静态的，或仅提供有限的更新支持。更新操作需要进行邻居发现、反向边创建、剪枝以及删除引发的图修复；并发执行这些操作会引入冗余距离计算和对共享邻接表的冲突访问。基于后台重建的删除还会产生大量计算开销、额外内存消耗，并干扰前台查询。我们提出GrAND（GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search，用于近似最近邻搜索的基于GPU的动态图索引），这是针对两种流行图索引Vamana和CAGRA的原生GPU动态更新算法集合。GrAND在一个批次中整合图修复，消除冗余剪枝计算，并采用无锁查找替换策略实现并行邻接表更新。为实现可靠的原地删除，GrAND在GPU上按需构建反向图，精准识别入边且无需永久复制索引。我们在7个真实数据集上针对5种流工作负载评估GrAND，将其与SVFusion和FreshDiskANN-GPU（我们对FreshDiskANN的GPU适配版本）对比。GrAND在维持高搜索吞吐量和持续更新下的召回率的同时，分别将整体工作负载吞吐量提升2.2倍至8.7倍、6.5倍至25.4倍。
英文摘要
Modern Approximate Nearest Neighbour Search (ANNS) applications operate over continuously evolving vector collections and require graph indexes that sustain high-throughput searches while incorporating insertions and deletions with high recall. However, most GPU graph indexes are static or provide limited update support. Updates require neighbour discovery, reverse-edge creation, pruning, and deletion-induced graph repair; executing these operations concurrently introduces redundant distance computations and conflicting accesses to shared adjacency lists. Background-rebuild-based deletion further incurs substantial computation, additional memory consumption, and interference with foreground queries. We present GrAND (GPU-based Dynamic Graph Indexes for Approximate Nearest Neighbour Search), a GPU-native collection of dynamic-update algorithms for two popular graph indexes, Vamana and CAGRA. GrAND consolidates graph repair across a batch, eliminating redundant pruning computations, and employs a lock-free find-and-replace strategy for parallel adjacency-list updates. For reliable in-place deletion, GrAND constructs an on-demand reverse graph on the GPU, accurately identifying incoming edges without permanently duplicating the index. We evaluate GrAND on seven real-world datasets across five streaming workloads, comparing it against SVFusion and FreshDiskANN-GPU (our GPU adaptation of FreshDiskANN). GrAND improves overall workload throughput by 2.2x-8.7x and 6.5x-25.4x, respectively, while maintaining high search throughput and recall over sustained updates.
