Presentation
SpecANNS: Accelerating Graph-Based Approximate Nearest Neighbor Search with Speculative In-Storage Computing
DescriptionDisk-based Approximate Nearest Neighbor Search (ANNS) suffers from high I/O latency due to random node access, which dominates over 90% of search time. To address this, we propose SpecANNS, an In-Storage Computing (ISC)-based solution leveraging in-storage FPGAs for fast distance computation. SpecANNS speculatively identifies pages likely to be accessed in subsequent hops and exploits NAND flash parallelism to minimize page read latency. Implemented on real Computational Storage Device (CSD) hardware with a simple interface, SpecANNS significantly reduces query latency and improves energy efficiency compared to state-of-the-art disk-based ANNS methods.
Event Type
Research Manuscript
TimeWednesday, July 293:54pm - 4:06pm PDT
LocationMtg Room 203C
Similar Presentations