https://github.com/jslee02/awesome-gpgpu
:sunglasses: A curated list of awesome GPGPU (CUDA/OpenCL/Vulkan) resources
https://github.com/jslee02/awesome-gpgpu
List: awesome-gpgpu
awesome-list cuda gpgpu opencl vulkan
Last synced: 10 days ago
JSON representation
:sunglasses: A curated list of awesome GPGPU (CUDA/OpenCL/Vulkan) resources
- Host: GitHub
- URL: https://github.com/jslee02/awesome-gpgpu
- Owner: jslee02
- License: cc0-1.0
- Created: 2018-06-20T15:36:15.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2023-02-27T06:52:42.000Z (about 2 years ago)
- Last Synced: 2025-04-11T02:02:01.916Z (13 days ago)
- Topics: awesome-list, cuda, gpgpu, opencl, vulkan
- Homepage:
- Size: 25.4 KB
- Stars: 89
- Watchers: 4
- Forks: 9
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-robotics-system-design - awesome-gpgpu
- awesome-cuda-and-hpc - jslee02/awesome-gpgpu - gpgpu?style=social"/> : 😎 A curated list of awesome GPGPU (CUDA/OpenCL/Vulkan) resources. (Awesome List)
- awesome-cuda-and-hpc - jslee02/awesome-gpgpu - gpgpu?style=social"/> : 😎 A curated list of awesome GPGPU (CUDA/OpenCL/Vulkan) resources. (Awesome List)
README
# awesome-gpgpu
A curated list of awesome GPGPU (CUDA/OpenCL/Vulkan) resources## CUDA
### Libraries
#### C++
* cuda-api-wrappers - Thin, unified, C++-flavored wrappers for the CUDA APIs [[github](https://github.com/eyalroz/cuda-api-wrappers) ]
* [Thrust](https://thrust.github.io/) - The C++ parallel algorithms library [[github](https://github.com/NVIDIA/thrust) ]### Tutorials
* [CMake setup for CUDA](https://cliutils.gitlab.io/modern-cmake/chapters/packages/CUDA.html)
## OpenCL
### Libraries
#### C++
* [Arrayfire](https://arrayfire.com/) - A General purpose GPU library [[github](https://github.com/arrayfire/arrayfire) ]
* [Boost.Compute](http://boostorg.github.io/compute/) - A C++ GPU Computing Library for OpenCL [[github](https://github.com/boostorg/compute) ]
* [Chlorine](http://polytonic.github.io/Chlorine/) - Dead Simple OpenCL [[github](https://github.com/Polytonic/Chlorine) ].
* clpp - Lightweight and easy to use the OpenCL C++ wrapper in single file [[github](https://github.com/matszpk/clpp) ].
* EasyCL - Easy to run kernels using OpenCL [[github](https://github.com/hughperkins/EasyCL) ]
* EasyOpenCL - The easiest way to get started with OpenCL! [[github](https://github.com/Gladdy/EasyOpenCL) ]
* [VexCL](http://vexcl.readthedocs.org) - VexCL is a C++ vector expression template library for OpenCL/CUDA [[github](https://github.com/ddemidov/vexcl) ]#### Rust
* [Emu](https://calebwin.github.io/emu/) - Emu is a high-level language that compiles to OpenCL and provides a procedural macro for embedding code in Rust [[github](https://github.com/calebwin/emu) ]
### Applications
* [Bullet](http://bulletphysics.org/wordpress/) - Real-Time Physics Simulation (Bullet 3 includes the optional work-in-progress GPU pipeline.) [[github](https://github.com/bulletphysics/bullet3) ]
* [CLBlast](https://cnugteren.github.io/clblast/clblast.html) - Modern, lightweight, performant and tunable OpenCL BLAS library written in C++11 [[github](https://github.com/CNugteren/CLBlast) ]
* DeepCL - OpenCL library to train deep convolutional neural networks [[github](https://github.com/hughperkins/DeepCL) ]
* libclsph - OpenCL based GPU accelerated SPH fluid simulation library [[github](https://github.com/libclsph/libclsph) ]
* MACE - Deep learning inference framework optimized for mobile heterogeneous computing platforms [[github](https://github.com/XiaoMi/mace) ]
* OpenCL-caffe - OpenCL version of caffe developed by AMD research lab [[github](https://github.com/amd/OpenCL-caffe) ]
* Sol-R - CUDA/OpenCL-based realtime ray-tracer [[github](https://github.com/favreau/Sol-R) ]### Tutorials
* [Basic examples of OpenCL with the C++ API](https://github.com/Dakkers/OpenCL-examples)
## Vulkan
### Libraries
#### C++
* [Kompute](https://kompute.cc/) - The general purpose GPU compute framework for cross vendor graphics cards [[github](https://github.com/KomputeProject/kompute) ]