The NVIDIA GPU Computing SDK provides hundreds of code samples, white papers, to help you get started on the path of writing software with CUDA C/C++, OpenCL or DirectCompute.

The SDK code samples covers a wide range of applications and techniques, including:

	Simple techniques demonstrating Basic approaches to GPU Computing Best practices for the most important features Working efficiently with custom data types Quickly integrating GPU acceleration into C and C++ applications How-To examples covering topics such as: Adding support for GPU-accelerated libraries to an application Using features such as Zero-Copy Memory, Asynchronous Data Transfers, Unified Virtual Addressing, Peer-to-Peer Communication, Concurrent Kernels, and more Sharing data between CUDA and Direct3D/OpenGL graphics APIs (interoperability) Data-parallel algorithms and primitives for linear algebra operations: Matrix transpose Matrix-matrix multiplication Matrix multiplication with multiple right hand sides Parallel prefix sum of large arrays Any many more! Performance measurement and optimization Bandwidth tests Application profiling using timers Advanced application examples Using CUDA with MPI and OpenMP Computational fluid dynamics (CFD) Gravitational n-body simulation Black-Scholes & binomial option pricing 3D Finite-difference time-domain (FDTD) Video encode/decode Image convolution

Availability

The latest versions of the GPU Computing SDK and the CUDA Toolkit (which is required to compile the SDK code samples) are available on the CUDA Downloads Page.

Individual SDK code samples are also available for download, organized into several categories:

All of the code samples in the GPU Computing SDK are available under a permissive license that allows you to freely incorporate them into your applications and create derivative works for commercial, academic, or personal use.

References