![]() ![]() *New* Updated versions of the CUDA C Programming Guide (Version 3.1.1) and the Fermi Tuning Guide (Version 1.2) are available via the links to the right.ĬUDA Developer Guide for Optimus Platforms Notebook Developer Drivers for WinVista and Win7 (257.21) Notebook Developer Drivers for WinXP (257.21) More recent production driver packages for developers and end users may be available at For additional tools and solutions for Windows, Linux and MAC OS, such as CUDA Fortran, CULA, CUDA-dgb, please visit our Tools and Ecosystem Pageĭownload Quick Links Windows XP, Windows VISTA, Windows 7 Description of Downloadĭeveloper Drivers for WinVista and Win7 (257.21) Note: The developer driver packages below provide baseline support for the widest number of NVIDIA products in the smallest number of installers. Microsoft Excel GPGPU example showing how to run an Excel function on the GPU.Function pointers in CUDA C/C++ kernels.New and updated SDK code samples demonstrating how to use:.Optimized double-precision implementations of divide and reciprocal routines for the Fermi architecture.Improved performance for GEMV and SYMV subroutines in CUBLAS.CUFFT Real-to-complex (R2C) and complex-to-real (C2R) optimizations for 2^n data sizes.Streaming API now supported in CUBLAS for overlapping copy and compute operations.Significant improvements in double-precision FFT performance on Fermi-architecture GPUs for 2^n transform sizes.Improved performance of selected transcendental functions from the log, pow, erf, and gamma families.Math Libraries Performance Improvements, including:.Unified Visual Profiler now supports both CUDA C/C++ and OpenCL, and now includes support for CUDA Driver API tracing.Support for function pointers and recursion make it easier to port many existing algorithms to Fermi GPUs. ![]() New language features added to CUDA C / C++ include:.Runtime / Driver interoperability enables applications to mix-n-match use of the CUDA Driver API with CUDA C Runtim and math libraries via buffer sharing and context migration.Support for 16-way concurrency allows up to 16 different kernels to run at the same time on Fermi architecture GPUs.GPUDirect(tm) gives 3rd party devices direct access to CUDA Memory.Download Quick Links įor the latest releases see the CUDA Toolkit and GPU Computing SDK home pageįor older releases, see the CUDA Toolkit Release Archive ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |