Learned Lock-free Search Data Structures

TL;DR

This paper introduces Kanva, a novel non-blocking search data structure that leverages machine learning-based learned queries to improve scalability and performance on multi-core architectures.

Contribution

Kanva is the first non-blocking search structure to integrate learned queries, combining shallow model hierarchies with dynamic search structures for enhanced efficiency.

Findings

Outperforms state-of-the-art non-blocking search structures in various workloads.

Provably linearizable, ensuring correctness in concurrent environments.

Significantly faster in diverse data distributions.

Abstract

Non-blocking search data structures offer scalability with a progress guarantee on high-performance multi-core architectures. In the recent past, "learned queries" have gained remarkable attention. It refers to predicting the rank of a key computed by machine learning models trained to infer the cumulative distribution function of an ordered dataset. A line of works exhibits the superiority of learned queries over classical query algorithms. Yet, to our knowledge, no existing non-blocking search data structure employs them. In this paper, we introduce \textbf{Kanva}, a framework for learned non-blocking search. Kanva has an intuitive yet non-trivial design: traverse down a shallow hierarchy of lightweight linear models to reach the "non-blocking bins," which are dynamic ordered search structures. The proposed approach significantly outperforms the current state-of-the-art -- non-blocking interpolation search trees and elimination (a,b) trees -- in many workload and data distributions. Kanva is provably linearizable.