Co-design Hardware and Algorithm for Vector Search

Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousands of queries per second on petabyte-scale document datasets by evaluating vector similarities between encoded query text...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International Conference for High Performance Computing, Networking, Storage and Analysis (Online) S. 1 - 16
Hauptverfasser: Jiang, Wenqi, Li, Shigang, Zhu, Yu, de Fine Licht, Johannes, He, Zhenhao, Shi, Runbin, Renggli, Cedric, Zhang, Shuai, Rekatsinas, Theodoros, Hoefler, Torsten, Alonso, Gustavo
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: ACM 11.11.2023
Schlagworte:
Approximate nearest neighbor search
Clustering algorithms
Data centers
FPGA
Hardware
hardware acceleration
Search engines
TCPIP
Training
Vectors
ISSN:2167-4337
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousands of queries per second on petabyte-scale document datasets by evaluating vector similarities between encoded query texts and web documents. As performance demands for vector search systems surge, accelerated hardware offers a promising solution in the post-Moore's Law era. We introduce FANNS, an end-to-end and scalable vector search framework on FPGAs. Given a user-provided recall requirement on a dataset and a hardware resource budget, FANNS automatically co-designs hardware and algorithm, subsequently generating the corresponding accelerator. The framework also supports scale-out by incorporating a hardware TCP/IP stack in the accelerator. FANNS attains up to 23.0× and 37.2× speedup compared to FPGA and CPU baselines, respectively, and demonstrates superior scalability to GPUs, achieving 5.5× and 7.6× speedup in median and 95 th per-centile (P95) latency within an eight-accelerator configuration. The remarkable performance of FANNS lays a robust groundwork for future FPGA integration in data centers and AI supercomputers.
ISSN:2167-4337
DOI:10.1145/3581784.3607045