About Me

I am a Ph.D. student in the Computer Science Department at UC Davis. My advisor is Prof. John Owens. My research interests span across general-purpose computing on graphics processing units (GPGPU,also known as GPU computing), computer graphics, parallel algorithms programming and data compression. Recently, I've been particularly interested in implementing classic algorithms on GPU and large-scale GPU computing.

Before coming to Davis, I received a B.S.E.E. degree in Information Science and Electronic Engineering from Zhejiang University and a CKC Honors Certificate from Chu Kochen Honors College, Zhejiang Univeristy. My research advisor was Prof. Erping Li. In 2012, I was exchanged to National Chiao Tung University for a semester in the Department of Electronics Engineering, during the same time, I worked with Prof. Tzonglin Wu in his EMC research group in National Tainwan University.


CUDPP -- CUDA Data Parallel Primitives Library

CUDPP 2.2 release czar and developer. The library is on github.

Fast Parallel Suffix Array on the GPU: Implemented a linear time suffix array construction algorithm, skew, on the GPU making algorithmic improvements to the previous state-of-the-art work with a speedup of 35%. It has been added as a new primitive in CUDPP 2.2 and has been used in the BWT-based lossless data compression tool.


Peer-reviewed Papers:

Leyuan Wang, Yangzihao Wang, Carl Yang, and John D. Owens. A Comparative Study on Exact Triangle Counting Algorithms on the GPU. In Proceedings of the 1st High Performance Graph Processing Workshop, HPGP'16, May 2016.[bib | DOI | http]

Leyuan Wang, Sean Baxter, and John D. Owens. Fast Parallel Suffix Array on the GPU. In Euro-Par 2015: Proceedings of the 21st International European Conference on Parallel and Distributed Computing, Lecture Notes in Computer Science, pages 573-587. Springer, August 2015. Distinguished Paper. [bib | DOI | http]


Leyuan Wang, Sean Baxter, John D. Owens. Fast Parallel Skew and Prefix-Doubling Suffix Array on the GPU. In GPU Technology Conference, GTC'16, April 2016. [poster]


Fast Parallel Suffix Array on the GPU. GPU Technology Conference, San Jose, April 2016. [slides | recording]
Euro-Par 2015, Vienna, August 2015. [slides | talk]

NVIDIA GPU Computing Spotlight Interview. [blog post]

Course Projects

Communities for A Better Yelp: ECS 289F/ MAE 298 Network Theory and Applications. A project from Yelp Data Challenge where we implement a new method for calculating business ratings that is based on community detection. The project is on github


An Implementation of Connected Component Algorithm on the GPU: EEC 277 Graphics Architecture. A project on optimizing classic connected component algorithm on GPU with a 5x speedup compared with the original CPU implementation.

ECS 289H Flow Visualization: In this project, we explore pathlines and some techniques for dealing with issues that arise in areas of high divergence/convergence in vector fields.

Optimized Eyecatch-based Object Interception: ECS 279 Character Animation. A video is shown here.

Contact Me

  • Address: Department of Computer Science, One Shields Avenue, Davis, CA 95616
  • Email: leywang AT ucdavis DOT edu