I received my PhD from the University of California, Computer Engineering Department in January, 2015. I am currently working for YouTube/Google in San Bruno. My
advisor was Prof. John Owens. My previous work and interests involved research topics in parallel algorithms, primitives,
numerical methods, automated tuning algorithms, graph algorithms, and graphics.
In addition to being In Professor John Owens research group for six years before joining Google, I've enjoyed a number of internships with various research groups.
Below is a list of the teams I have worked with:
Gabrielle Allen, Mayank Tyagi and Shalini Venkataraman at the Center for Computation and Technology @ Louisiana State University (2005-2007)
Professor John Owens on CUDA Data Parallel Primitives, of which I am still a developer, extending the library and adding functionality (Summer 2007)
Professor Takayuki Aoki at the Tokyo Institute of Technology on auto-tuning parallel primitives on the GPU. (Summer 2009)
Satnam Singh of Microsoft Research, Cambridge (now at Google) on data-parallel languages (such as Accelerator) and work/performance tradeoffs
Michael Garland of NVIDIA Research on the merge primitive, merge sort and string sort on the GPU(Summer 2011). I returned in the spring of 2013 to work on parallel GPU implementations of Single Source Shortest Paths.
Michael Kass of Pixar Research working on hybrid Depth of Field techniques as a post-processing step. (Summer 2012)
Multiple collaborative projects in well-spaced sampling techniques with Mohamed Ebeida and Scott Mitchell from Sandia National Labs.
Divide-And-Conquer Methods for Data Parallel Machines
Ph. D. Dissertation. University of California, Davis. January, 2015
Exercises in High-Dimensional Sampling: Maximal Poisson-disk Sampling and k-d Darts
Mohamed Ebeida, Scott Mitchell, Anjul Patney, Andrew Davidson, Stanley Tzeng, Muhammad Awad, Ahmed Mahmoud, and John D. Owens
Topological and Statistical Methods for Complex Data-Tackling Large-Scale, High-Dimensional, and Multivariate Data Sets, pages 221-238. Springer, November 2014.
Register Packing for Cyclic Reduction: A Case Study
Andrew Davidson, John D. Owens
Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, March 2011
A Hybrid Method for Solving Tridiagonal Systems on the GPU
Yao Zhang, Johathan Cohen, Andrew Davidson, John D. Owens
In GPU Computing Gems, 2011, Jade Edition
Using a Graphics Processor Unit (GPU) for Feature Extraction from Turbulent Flow Datasets.|
Andrew Davidson, Mayank Tyagi, Gabrielle Allen
National Conference for Undergraduate Research(NCUR), April, 2006
"WINDMILLS DO NOT WORK THAT WAY!" - Futurama
Website is derived from Anjul Patney's website.