SLI Zone
NVIDIA.com Developer Home

NVIDIA CUDA SDK - Data-Parallel Algorithms

The CUDA Developer SDK provides examples with source code, utilities, and white papers to help you get started writing software with CUDA. The SDK includes dozens of code samples covering a wide range of applications including:

  • Simple techniques such as C++ code integration and efficient loading of custom datatypes
  • How-To examples covering CUDA BLAS and FFT libraries, texture fetching in CUDA, and CUDA interoperation with the OpenGL and Direct3D graphics APIS
  • Linear algebra primitives such as matrix transpose and matrix-matrix multiplication
  • Data-parallel algorithms such as parallel prefix sum of large arrays
  • Performance: profiling using timers and bandwidth tests
  • Advanced application examples such as image convolution, Black-Scholes options pricing and binomial options pricing
Refer to the following READMEs for more information ( Linux , Windows )

This code is released free of charge for use in derivative works, whether academic, commercial, or personal. (Full License)

The NVIDIA CUDA Toolkit is required to run and compile code samples. Please obtain the CUDA Toolkit here

Quick Links:
Data-Parallel Algorithms Computational Finance
Performance Strategies Linear Algebra
Physically-Based Simulation CUDA Basic Topics
Graphics Interop Image/Video Processing and Data Compression
CUDA Advanced Topics


256-bin Histogram For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This sample demonstrates efficient implementation of 256-bin histogram.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


64-bin Histogram For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This sample demonstrates efficient implementation of 64-bin histogram.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


Separable Convolution For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This sample implements a separable convolution filter of a 2D signal with a gaussian kernel.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


Texture-based Separable Convolution For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

Texture-based implementation of a separable 2D convolution with a gaussian kernel. Used for performance comparison against convolutionSeparable.
  Minimum Required GPU
Minimum Required GPUor later




Download - Windows
Download - Linux


Bitonic Sort For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

Bitonic sort is a very simple parallel sorting algorithm that is very efficient when sorting a small number of elements: http://citeseer.ist.psu.edu/blelloch98experimental.html This implementation is based on: http://www.tools-of-computing.com/tc/CS/Sorts/bitonic_sort.htm
  Minimum Required GPU
Minimum Required GPUor later




Download - Windows
Download - Linux


N-Body Simulation For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This sample demonstrates efficient all-pairs simulation of a gravitational n-body simulation in CUDA. This sample accompanies the GPU Gems 3 chapter "Fast N-Body Simulation with CUDA".
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


Parallel Reduction For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

A parallel sum reduction that computes the sum of large arrays of values. This sample demonstrates several important optimization stratezies for parallel algorithms like reduction.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


Mandelbrot For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This sample uses CUDA to compute and display the Mandelbrot set.
  Minimum Required GPU
Minimum Required GPUor later




Download - Windows
Download - Linux


Fast Walsh Transform For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

Naturally(Hadamard)-ordered Fast Walsh Tranform for batched vectors of arbitrary eligible(power of two) lengths
  Minimum Required GPU
Minimum Required GPUor later




Download - Windows
Download - Linux


Scan For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This example demonstrates an efficient CUDA implementation of parallel prefix sum, also known as "scan". Given an array of numbers, scan computes a new array in which each element is the sum of all the elements before it in the input array.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux


Scan of Large Arrays For a direct link to this sample, right-click and copy the URL (shortcut) of this link icon.

This example demonstrates an efficient CUDA implementation of parallel prefix sum (also known as "scan") for arbitrary-sized arrays. Given an array of numbers, scan computes a new array in which each element is the sum of all the elements before it in the input array.
  Minimum Required GPU
Minimum Required GPUor later



Whitepaper
Download - Windows
Download - Linux

Last Update: 11/12/2007
NVPerfHUD 4