GPU LSM: A Dynamic Dictionary Data Structure for the GPU
Saman Ashkiani, Shengren Li, Martin Farach-Colton, Nina Amenta, John, D. Owens

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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
