Presentation
GraphAccel: An In-Storage Accelerator for Efficient Graph-Based Vector Similarity Search Using Page Packing and Speculative Search Optimization
DescriptionGraph-based search for approximate vector similarity is essential in AI applications, such as retrieval-augmented generation. To support large-scale searches, vector search graphs are often stored on storage devices like SSDs. In this paper, we introduce GraphAccel, an in-storage accelerator optimized for efficient graph-based vector similarity search. Our architecture incorporates an optimized page packing mechanism to reduce SSD page accesses per query, alongside a speculative search scheme that maximizes utilization of idle SSD chips and channels. Through these optimizations, GraphAccel achieves notable performance improvements over existing SSD-based graph search solutions, including DiskANN and DiskANN++.
Event Type
Research Manuscript
TimeWednesday, June 251:45pm - 2:00pm PDT
Location3002, Level 3
Design
DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems