优化图索引内存布局，能显著提升GPU上近邻搜索速度
PLASMA: A Layout-Aware Benchmark Reveals Memory Layout Matters for Graph-based ANNS on GPU
- 构建统一框架，分离图结构与内存布局影响
- 重排顶点顺序可提升最高80%查询吞吐量
- 适合做向量数据库或AI检索系统性能优化的开发者
我们提出PLASMA：一个用于图结构近似最近邻搜索（ANNS）在GPU上评估的布局感知平台。该框架能提取任意图索引的拓扑结构，并在统一的GPU优化搜索算法下运行，通过指定顶点ID与内存位置的对应关系，实现任意顶点排序。大量实验表明，顶点重排可在保持搜索精度的前提下，使查询每秒处理量（QPS）提升最高80%（通常为10%-30%），凸显内存布局对现代大规模向量检索的重要性。
原文摘要 · Abstract (English)
We propose a $\textbf{P}$latform for $\textbf{L}$ayout-$\textbf{A}$ware $\textbf{S}$earch and $\textbf{M}$emory $\textbf{A}$rrangement ($\textbf{PLASMA}$), a unified evaluation framework for graph-based Approximate Nearest Neighbor Search (ANNS) on GPU that isolates the effects of graph index topology and memory layout. Graph-based ANNS is essential in modern AI applications such as RAG, and GPU utilization is attracting attention for datasets of millions or more vectors. Our framework extracts the topology of arbitrary graph-based indices and enables execution under a unified, GPU-optimized search algorithm, specifying the correspondence between vertex IDs and positions on memory to allow arbitrary vertex orderings. Through comprehensive experiments, we demonstrate that vertex reordering yields up to $80\%$ (typically $10-30\%$) QPS improvement while preserving search accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。