19012

NNS: The Case For Neural Network-based Sorting

Xiao-ke Zhu, Tai-ning Chen, Jing He, Wei Zhou
School of Software, Yunnan University, Yunnan, China
arXiv:1907.08817 [cs.DS], (20 Jul 2019)

@misc{zhu2019nns,

   title={NNS: The Case For Neural Network-based Sorting},

   author={Xiao-ke Zhu and Tai-ning Chen and Jing He and Wei Zhou},

   year={2019},

   eprint={1907.08817},

   archivePrefix={arXiv},

   primaryClass={cs.DS}

}

Download Download (PDF)   View View   Source Source   

398

views

CPU-SIMD/GPU/TPUs will be increasingly powerful. The algorithm using neural network and heterogeneous computing framework will bring significant performance improvement. In this paper we prove a novel neural network-based sorting algorithm, NNS which hold lower time complexity than O(nlogn) and easy implement in heterogeneous framework executed by CPU and GPU. Our initial results show that our learned sorting algorithm can increases by 2X than std::sort(). More importantly, this work provides just a glimpse of using neural network to enhance or even replace classical algorithm and also the benefit of designing algorithm specifically for heterogeneous computing frameworks.
Rating: 2.0/5. From 1 vote.
Please wait...

* * *

* * *

HGPU group © 2010-2019 hgpu.org

All rights belong to the respective authors

Contact us: