NSDI '24 - Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered...

NSDI '24 - Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining

Zili Zhang, Fangyue Liu, Gang Huang, Xuanzhe Liu, and Xin Jin, School of Computer Science, Peking University

Vector query processing powers a wide range of AI applications. While GPUs are optimized for massive vector operations, today's practice relies on CPUs to process queries for large vector datasets, due to limited GPU memory.

We present RUMMY, the first GPU-accelerated vector query processing system that achieves …

applications beyond computer computer science datasets fast gang gpu gpus large memory query school science university