Displaying 1 to 20 from 24 results

vexcl - VexCL is a C++ vector expression template library for OpenCL/CUDA

VexCL is a vector expression template library for OpenCL/CUDA. It has been created for ease of GPGPU development with C++. VexCL strives to reduce amount of boilerplate code needed to develop GPGPU applications. The library provides convenient and intuitive notation for vector arithmetic, reduction, sparse matrix-vector products, etc. Multi-device and even multi-platform computations are supported. The source code of the library is distributed under very permissive MIT license.

regl-cnn - Digit recognition with Convolutional Neural Networks in WebGL

GPU accelerated handwritten digit recognition with regl. Note that this network will probably be slower than the corresponding network implemented on the CPU. This is because of the overhead associated with transferring data to and from the GPU. But in the future we will attempt implementing more complex networks in the browser, such as Neural Style, and then we think that we will see a significant speedup compared to the CPU.

vulkan_minimal_compute - Minimal Example of Using Vulkan for Compute Operations. Only ~400LOC.

This is a simple demo that demonstrates how to use Vulkan for compute operations only. In other words, this demo does nothing related to graphics, and only uses Vulkan to execute some computation on the GPU. For this demo, Vulkan is used to render the Mandelbrot set on the GPU. The demo is very simple, and is only ~400LOC. The code is heavily commented, so it should be useful for people interested in learning Vulkan. The application launches a compute shader that renders the mandelbrot set, by rendering it into a storage buffer. The storage buffer is then read from the GPU, and saved as .png. Check the source code comments for further info.


A wrapper for NVidia's CuBLAS (Compute Unified Basic Linear Algebra Subprograms) for the CLR.


An implementation of linear algebra numerical structures and methods for the CLR. NPack is unique in that it uses generics for matrix element definitions, and a set of matrix operations via an interface, allowing a CLR-based operations engine as well as the opportunity to use ...

C++ AMP LAPACK Library

Project Description C++ AMP LAPACK Library is a library of linear algebra subroutines that C++ AMP developers can freely use in their own projects. Note that this project builds upon and is dependent upon the C++ AMP BLAS library. Prerequisite Understanding C++ AMP is an ...

C++ AMP: Accelerated Massive Parallelism with Microsoft Visual C++

Samples for the latest Microsoft Press book on programming with C++AMP using Visual Studio 2012.


GPGPUs offer significant horsepower in our computers that are unfortunately not easily available to .NET programs. <project name> is a system capable to map .NET bytecode into GPU IL (e.g. nVidia PTX) so that you can run .NET algorithms on state of the art hardware.


GPCompute is an old CUDA-like but Based on DX81 (or later) for compatibility with almost any current Videocards. It's Developped in C/C++. With Simple Interface for Arrayed-Computations. The Limitation all came from its DX version implemention.


managedCUDA makes the CUDA Driver API available in .net applications written in C#, Visual Basic or any other .net language. It also includes classes for an easy handling and interop with CUDA, i.e. build-in CUDA types like float3.


Optix.NET is a .NET wrapper for the Nvidia Optix GPU ray-tracing library.

C++ AMP RNG Library

C++ AMP RNG Library is a library of Random Number Generators that C++ AMP developers can freely use in their own projects.


The main idea of a this project - create cellular automation (CA) simulation system. We try to reduce ODE/PDE/Integral Equations models to CA-model

NyuziToolchain - Port of LLVM/Clang C compiler to Nyuzi parallel processor architecture

This is a toolchain for a parallel processor architecture called Nyuzi, based on LLVM. It includes a C/C++ compiler (clang), assembler, linker and debugger (lldb). While this project includes a C/C++ compiler, the LLVM backend can support any language. There is a small, experimental SPMD parallel compiler in tools/spmd_compiler.

dw-webgl-sketchbook - Webgl Experiments

Showroom for my Webgl Experiments. The demos require a browser that supports webgl2.

clinfo - Print all known information about all available OpenCL platforms and devices in the system

clinfo is a simple command-line application that enumerates all possible (known) properties of the OpenCL platform and devices available on the system. Inspired by AMD's program of the same name, it is coded in pure C and it tries to output all possible information, including those provided by platform-specific extensions, trying not to crash on unsupported properties (e.g. 1.2 properties on 1.1 platforms).

amgcl - C++ library for solving large sparse linear systems with algebraic multigrid method

AMGCL is a header-only C++ library for solving large sparse linear systems with algebraic multigrid (AMG) method. AMG is one of the most effective iterative methods for solution of equation systems arising, for example, from discretizing PDEs on unstructured grids. The method can be used as a black-box solver for various computational problems, since it does not require any information about the underlying geometry. AMG is often used not as a standalone solver but as a preconditioner within an iterative solver (e.g. Conjugate Gradients, BiCGStab, or GMRES). AMGCL builds the AMG hierarchy on a CPU and then transfers it to one of the provided backends. This allows for transparent acceleration of the solution phase with help of OpenCL, CUDA, or OpenMP technologies. Users may provide their own backends which enables tight integration between AMGCL and the user code.

glsl-read-float - Read floating point values back from WebGL

Workaround for reading floating point values back from the GPU using GLSL. Packs a floating point number into an 8bit RGBA color vector, which can be written to the display using gl_FragColor, for example.