This can be used as a user-managed cache, enabling higher bandwidth than is possible using texture lookups. Shared memory – CUDA exposes a fast shared memory region that can be shared among threads.Unified virtual memory (CUDA 4.0 and above).
nView – NVIDIA nView Desktop Management Software.NVRTC – NVIDIA Runtime Compilation library for CUDA C++ĬUDA 8.0 comes with these other software components:.nvGRAPH – NVIDIA Graph Analytics library.NPP – NVIDIA Performance Primitives library.cuSOLVER – CUDA based collection of dense and sparse direct solvers.cuRAND – CUDA Random Number Generation library.cuFFT – CUDA Fast Fourier Transform library.cuBLAS – CUDA Basic Linear Algebra Subroutines library.CUDA is compatible with most standard operating systems.ĬUDA 8.0 comes with the following libraries (for compilation & runtime, in alphabetical order): CUDA works with all Nvidia GPUs from the G8x series onwards, including GeForce, Quadro and the Tesla line.
Mac OS X support was later added in version 2.0, which supersedes the beta released February 14, 2008. The initial CUDA SDK was made public on 15 February 2007, for Microsoft Windows and Linux.
ĬUDA provides both a low level API (CUDA Driver API, non single-source) and a higher level API (CUDA Runtime API, single-source). CUDA has also been used to accelerate non-graphical applications in computational biology, cryptography and other fields by an order of magnitude or more. In the computer game industry, GPUs are used for graphics rendering, and for game physics calculations (physical effects such as debris, smoke, fire, fluids) examples include PhysX and Bullet. Third party wrappers are also available for Python, Perl, Fortran, Java, Ruby, Lua, Common Lisp, Haskell, R, MATLAB, IDL, Julia, and native support in Mathematica. In addition to libraries, compiler directives, CUDA C/C++ and CUDA Fortran, the CUDA platform supports other computational interfaces, including the Khronos Group's OpenCL, Microsoft's DirectCompute, OpenGL Compute Shader and C++ AMP. Fortran programmers can use 'CUDA Fortran', compiled with the PGI CUDA Fortran compiler from The Portland Group. C/C++ programmers can use 'CUDA C/C++', compiled to PTX with nvcc, Nvidia's LLVM-based C/C++ compiler, or by clang itself. The CUDA platform is accessible to software developers through CUDA-accelerated libraries, compiler directives such as OpenACC, and extensions to industry-standard programming languages including C, C++ and Fortran.