Modern graphics processing units (GPUs) contain hundreds of arithmetic units and can be harnessed to provide tremendous acceleration for many numerically intensive scientific applications. The key to effective utilization of GPUs for scientific computing
NVIDIA Corporation, the world leader in visual computing technologies and the inventor of the GPU, today announced that the Korea Institute of Science and Technology Information (KISTI) Supercomputing Center has selected NVIDIA Quadro® FX 5600 graphics c
This first post in a series on CUDA C and C++ covers the basic concepts of parallel programming on the CUDA platform with C/C++.
int i = blockDim.x * blockIdx.x + threadIdx.x
Marvin is a deep learning framework designed first and foremost to be hackable. It is naively simple for fast prototyping, uses only basic C/C++, and only calls CUDA and cuDNN as dependencies.
A. Cheik Ahamed, and F. Magoulès. Distributed Computing and Applications to Business, Engineering Science (DCABES), 2013 12th International Symposium on, page 16-20. (September 2013)
N. Vasilache, M. Baskaran, B. Meister, and R. Lethin. Proceedings of the 6th Workshop on General Purpose Processor
Using Graphics Processing Units, page 42--53. New York, NY, USA, ACM, (2013)
A. Panagiotidis, D. Kauker, F. Sadlo, and T. Ertl. International Symposium on Parallel and Distributed Computing, 11, page 87 -94. IEEE Computer Society, (June 2012)
A. Cheik Ahamed, and F. Magoulès. High Performance Computing and Communication 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on, page 836-842. (June 2012)
А. Халитов. Высокопроизводительные вычисления на графических процессорах: тезисы докл. Науч.-практ. конф. с междунар. участием с элементами науч. шк. для молодежи, 21-25 мая 2012 г., page 68-70. (2012)