Neural Networks / N. S. L. P. / GPU / NVIDIA Corporation / Khronos Group / A. Fox Parallel Computing Laboratory / /
Country
United States / / /
Facility
University of California at Berkeley / International Computer Science Institute / library API / library SEJITS / GMM library / University of California / Rochester Institute of Technology / /
University of California / Rochester Institute of Technology / International Computer Science Institute / USENIX Association / Oxford Univ. / IEEE Computer Society / EECS Department / /
Person
J. Xiong / /
Position
speaker / Python interpreter / CUDA programmer / domain programmer / application programmer and the performance tuning specialist / application programmer / Python programmer / programmer / B. Singer / /
Product
Python/SEJITS / /
ProgrammingLanguage
C / Python / Fortran / Ruby / DC / C++ / Scala / /
ProvinceOrState
New York / North Carolina / California / /
PublishedMedium
Journal of Physics /
Technology
Virtual Machine / unsupervised training algorithm / speech recognition / data-parallel algorithm / API / 1 algorithm / machine learning / EM algorithm / computationally-intensive algorithm / particular algorithm / java / training algorithm / http / DSP / using the EM algorithm / /
CUDA-level Performance with Python-level Productivity for Gaussian Mixture Model Applications H. Cook, E. Gonina, S. Kamil, G. Friedland†, D. Patterson, and A. Fox Parallel Computing Laboratory, Computer Science Divis