Master of Science,
University of California, Davis Sept. 2013 - Present
Research Area: Parallel Computing (GPGPU), Major Advisor: Prof. John D. Owens
Bachelor of Science, Macau University of Science and Technology, Macau June 2013
Graduate Student Researcher (GSR)
Institute of Data Analysis and Visualization (IDAV) at UC Davis, Spring 2014 - Now
Developing algorithms for large-scale graph processing
Characterizing the performance of common high-level graph processing models
Intern, xDATA Summer Workshop 2014
Defense Advanced Research Projects Agency (DARPA) at Arlington, VA, Summer 2014
Built a shared library for GPU graph processing system with a pure C interface
Computed hyperlink graph centrality for visualization companies to solve big-data challenges
Developer of Gunrock, a high-performance CUDA library for graph primitives that re-factors, integrates, and generalizes best-of-class GPU implementations. Currently focus on Performance Modeling/Characterizing and improve framework to better support mutable and more advanced graph primitives.
Collaborated with Yangzihao Wang, together we implemented a novel scene classification method which combines Convolutional Neural Network (CNN) and Spatial Pyramid Pooling to generate high-level context-aware features. We achieved better recognition rate than the state-of-the-art method on the challenging MIT Indoor-67 dataset using only the deep features trained from ImageNet.
Implemented Parallel Boruvka's Minimum Spanning Tree (MST) algorithm using Gunrock's Traverse-Compute programming model. Achieved over 400X speedup against the serial CPU Boost Graph Library (BGL) implementation for both real world road networks, Open Street Maps (OSM) and long-diameter synthetic datasets.
Senior Design Project, IPv6 Research Laboratory, M.U.S.T., Spring 2013
Designed and Implemented Mobile IPv6 Protocol using Filtering Technology. Upgraded a NDIS filter driver to filter bypassing data packets to extend roaming capabilities and merged into standard IPv6 protocol.
Yuduo Wu, Yangzihao Wang, Yuechao Pan, Carl Yang, and John D. Owens. Performance Characterization for High-Level Programming Models for GPU Graph Analytics [Link] (note: this paper is under review and thus not for public dissemination)
Yuechao Pan, Yangzihao Wang, Yuduo Wu, Carl Yang, and John D. Owens. Multi-GPU Graph Analytics. CoRR, abs/1504.04804, Apr. 2015. [arXiv]
Yangzihao Wang, Andrew Davidson, Yuechao Pan, Yuduo Wu, Andy Riffel, and John D. Owens. Gunrock: A high-performance graph processing library on the GPU. In Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2015, pages 265-266, New York, NY, USA, 2015. ACM.[ bib |poster ]