Cuckoo-GPU: Accelerating Cuckoo Filters on Modern GPUs

TL;DR

Cuckoo-GPU introduces a high-performance, lock-free GPU-based Cuckoo filter that significantly improves dynamic approximate membership query operations, rivaling static filters and outperforming existing dynamic GPU filters.

Contribution

The paper presents Cuckoo-GPU, a novel GPU-optimized Cuckoo filter with a lock-free design and a new eviction heuristic, achieving unprecedented throughput for dynamic AMQ tasks.

Findings

Achieves up to 378x insertion throughput over GQF and TCF.

Delivers up to 350x speedup over CPU-based Cuckoo filters.

Matches query throughput of GPU-based Blocked Bloom filters.

Abstract

Approximate Membership Query (AMQ) structures are essential for high-throughput systems in databases, networking, and bioinformatics. While Bloom filters offer speed, they lack support for deletions. Existing GPU-based dynamic alternatives, such as the Two-Choice Filter (TCF) and GPU Quotient Filter (GQF), enable deletions but incur severe performance penalties. We present Cuckoo-GPU, an open-source, high-performance Cuckoo filter library for GPUs. Instead of prioritizing cache locality, Cuckoo-GPU embraces the inherently random access pattern of Cuckoo hashing to fully saturate global memory bandwidth. Our design features a lock-free architecture built on atomic compare-and-swap operations, paired with a novel breadth-first search-based eviction heuristic that minimizes thread divergence and bounds sequential memory accesses during high-load insertions. Evaluated on NVIDIA GH200 (HBM3) and RTX PRO 6000 Blackwell (GDDR7) systems, Cuckoo-GPU closes the performance gap between append-only and dynamic AMQ structures. It achieves insertion, query, and deletion throughputs up to 378x (4.1x), 6x (34.7x), and 258x (107x) higher than GQF (TCF) on the same hardware, respectively, and delivers up to a 350x speedup over the fastest available multi-threaded CPU-based Cuckoo filter implementation. Moreover, its query throughput rivals that of the append-only GPU-based Blocked Bloom filter - demonstrating that dynamic AMQ structures can be deployed on modern accelerators without sacrificing performance.