CArMA » Historique » Révision 3
Révision 2 (Damien Gratadour, 09/11/2013 15:52) → Révision 3/8 (Damien Gratadour, 09/11/2013 16:42)
h1. CArMA
CArMA is the C++ API for Massively parallel Applications. It provides a set of C++ classes for an easy integration of GPU accelerated numerical tools into complex applications.
CArMA is built on top of the CUDA toolkit from NVIDIA. The latter is freely available from NVIDIA's website. CUDA provides a large collection of tools to perform scientific computing (CuFFT, CuBLAS, CuRAND). Moreover, several libraries like MAGMA have been developed using CUDA and provide additional features very useful for scientific computing. You'll find here the list of CUDA-capable video cards : http://www.nvidia.com/object/cuda_gpus.html CArMA has been tested on a variety of platforms, from laptops to servers with various grades of GPU cards from mobile series to high-end scientific-grade cards.
!{width:50%}https://projets-lesia.obspm.fr/attachments/download/696/carma.png!