GPU LSM: A Dynamic Dictionary Data Structure for the GPU

TL;DR

This paper introduces a GPU-based dynamic dictionary data structure called GPU LSM, which enables fast insertions, deletions, and queries, outperforming traditional methods and being the first of its kind for GPUs.

Contribution

The paper presents the first dynamic general-purpose dictionary data structure for GPUs based on LSM, with high update and query performance.

Findings

Average update rate of 225 million elements/sec

Supports lookup, count, and range queries at 75M, 32M, and 23M queries/sec

Outperforms merging items into sorted arrays by 13.5x

Abstract

We develop a dynamic dictionary data structure for the GPU, supporting fast insertions and deletions, based on the Log Structured Merge tree (LSM). Our implementation on an NVIDIA K40c GPU has an average update (insertion or deletion) rate of 225 M elements/s, 13.5x faster than merging items into a sorted array. The GPU LSM supports the retrieval operations of lookup, count, and range query operations with an average rate of 75 M, 32 M and 23 M queries/s respectively. The trade-off for the dynamic updates is that the sorted array is almost twice as fast on retrievals. We believe that our GPU LSM is the first dynamic general-purpose dictionary data structure for the GPU.