Download The CUDA Production Release
Download The CUDA Pre-Production Release

Release Highlights

Easier Application Porting

  • Share GPUs across multiple threads
  • Use all GPUs in the system concurrently from a single host thread
  • No-copy pinning of system memory, a faster alternative to cudaMallocHost()
  • C++ new/delete and support for virtual functions
  • Support for inline PTX assembly
  • Thrust library of templated performance primitives such as sort, reduce, etc.
  • NVIDIA Performance Primitives (NPP) library for image/video processing
  • Layered Textures for working with same size/format textures at larger sizes and higher performance

Faster Multi-GPU Programming

  • Unified Virtual Addressing
  • GPUDirect v2.0 support for Peer-to-Peer Communication

New & Improved Developer Tools

  • Automated Performance Analysis in Visual Profiler
  • C++ debugging in CUDA-GDB for Linux and MacOS
  • GPU binary disassembler for Fermi architecture (cuobjdump)
  • Parallel Nsight 2.0 now available for Windows developers with new debugging and profiling features.

Watch the CUDA Toolkit 4.0 Feature and Overview Webinar (or just the slides) for an overview of some of the exciting new features of this release.
Check out the NEW CUDA 4.0 Math Library Performance Review 

Find all the latest versions of other Libraries and Tools on our Tools & EcoSystem Page

Please download the lastest CUDA Toolkit 4.0 Errata Update.

The latest released NVIDIA Drivers are always available at www.nvidia.com/drivers
For previous releases, see the CUDA Toolkit Release Archive
Get yourself fully trained- check out the latest CUDA Webinars
Become a CUDA Registered Developer, report bugs, engage with NVIDIA engineering
Jump to: [Windows][ Linux ] [ MacOS 

Windows 7, VISTA, Windows XP Downloads
Developer Drivers for WinXP (270.81)
Support for XP on notebooks is being phased out and is not available for this release. See Release Notes and Getting Started Guides for more information.
32-bit 64-bit  
Developer Drivers for WinVista and Win7 (270.81) 32-bit 64-bit  
Notebook Developer Drivers for WinVista and Win7 (275.33) 32-bit 64-bit
CUDA Toolkit
  • C/C++ compiler
  • Visual Profiler
  • GPU-accelerated BLAS library
  • GPU-accelerated FFT library
  • GPU-accelerated Sparse Matrix library
  • GPU-accelerated RNG library
  • Additional tools and documentation

32-bit 64-bit

documentation

*NEW* CUDA Toolkit 4.0 Build Customization BUG FIX Update
Fixes  error message "$(CUDABuildTasksPath) property is not valid"
download
GPU Computing SDK - complete package including all code samples 32-bit 64-bit
browse online
Parallel Nsight 2.0  download
Learn about additional tools, libraries, and more… CUDA Ecosystem
CUDA Tools SDK (APIs for 3rd party performance analysis tools and cluster management solutions) 32-bit 64-bit

Linux Downloads
Developer Drivers for Linux (270.41.19) 32-bit 64-bit
CUDA Toolkit
  • C/C++ compiler
  • CUDA-GDB debugger
  • Visual Profiler
  • GPU-accelerated BLAS library
  • GPU-accelerated FFT library
  • GPU-accelerated Sparse Matrix library
  • GPU-accelerated RNG library
  • Additional tools and documentation

documentation

Visual Profiler Errata

CUDA Toolkit for Fedora 13 32-bit, (Visual Profiler_Patch)
64-bit, (Visual Profiler Patch)
 
CUDA Toolkit for RedHat Enterprise Linux 6.0 64-bit(Visual Profiler Patch)
CUDA Toolkit for RedHat Enterprise Linux 5.5 32-bit, (Visual Profiler Patch)
64-bit,  (Visual Profiler Patch)
CUDA Toolkit for RedHat Enterprise Linux 4.8 64-bit,  (Visual Profiler Patch)
CUDA Toolkit for Ubuntu Linux 10.10 32-bit(Visual Profiler Patch)
64-bit(Visual Profiler Patch)
CUDA Toolkit for OpenSUSE 11.2 32-bit(Visual Profiler Patch)
64-bit, (VP Patch -coming soon)
CUDA Toolkit for SUSE Linux Enterprise Server 11 SP1 32-bit, (Visual Profiler Patch)
64-bit, (Visual Profiler Patch)
GPU Computing SDK - complete package including all code samples download 
browse online
Learn about additional tools, libraries, and more… CUDA Ecosystem
CUDA Tools SDK (APIs for 3rd party debuggers, performance analysis tools and cluster management solutions) 32-bit 64-bit

Mac OS X Downloads
Developer Drivers (4.0.50) for MacOS (requires OS ver. 10.6.8 or higher) download
CUDA Toolkit (requires OS version 10.6.7 or higher)
  • C/C++ compiler
  • CUDA-GDB debugger
  • Visual Profiler
  • GPU-accelerated BLAS library
  • GPU-accelerated FFT library
  • GPU-accelerated Sparse Matrix library
  • GPU-accelerated RNG library
  • Additional tools and documentation

download

documentation

GPU Computing SDK - complete package including all code samples download 
Browse Online
Learn about additional tools, libraries, and more… CUDA Ecosystem
CUDA Tools SDK (APIs for 3rd party debuggers and performance analysis tools) download