# Onesweep: A Faster Least Significant Digit Radix Sort for GPUs

arXiv: https://arxiv.org/abs/2206.01784 · HTML: https://mlsanity.com/paper/2206.01784/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2022.

## Built on by (most cited first, 5 of 5)

- [Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis](https://mlsanity.com/paper/2401.02436/) (2023)
- [Multi-Layer Gaussian Splatting for Immersive Anatomy Visualization](https://mlsanity.com/paper/2410.16978/) (2024)
- [AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs](https://mlsanity.com/paper/2604.18980/) (2026)
- [A Fast Parallel Median Filtering Algorithm Using Hierarchical Tiling](https://mlsanity.com/paper/2507.19926/) (2025)
- [Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks](https://mlsanity.com/paper/2511.20834/) (2025)

## Abstract (arXiv)

We present Onesweep, a least-significant digit (LSD) radix sorting algorithm for large GPU sorting problems residing in global memory. Our parallel algorithm employs a method of single-pass prefix sum that only requires ~2n global read/write operations for each digit-binning iteration. This exhibits a significant reduction in last-level memory traffic versus contemporary GPU radix sorting implementations, where each iteration of digit binning requires two passes through the dataset totaling ~3n global memory operations. On the NVIDIA A100 GPU, our approach achieves 29.4 GKey/s when sorting 256M random 32-bit keys. Compared to CUB, the current state-of-the-art GPU LSD radix sort, our approach provides a speedup of ~1.5x. For 32-bit keys with varied distributions, our approach provides more consistent performance compared to HRS, the current state-of-the-art GPU MSD radix sort, and outperforms it in almost all cases.