This is a freedom software and it obeys opensource initiative. The main purpose of this project is to bring extra updates to the existing Octave OCL project with more supporting PC devices as well as mobile devices. Due to the fact tremendous time and energy has been spent on its working on many devices, the project name is changing to AnyArray to reflect it is really working on many devices on March 2026. Ever since started providing extra GPU Compute support, it has been for OpenCL-enabled hardware and this promise will not change for OpenSource community. Now, AnyArray supports OpenCL 1.2 API.
My profile is here: https://www.researchgate.net/profile/Jinchuan-Tang-4. To add clBlast to this project to speed up matrix multiplication by 5 times or more, please join my summon to tuning your GPU to make clBlast better: https://github.com/CNugteren/CLBlast/issues/1#issuecomment-1570253
Features
- Support AMD/Intel/Nvidia CPUs/GPUs
- OpenCL Kernel Enhancement
- Support Apple Silicon GPUs
- Support Microsoft OpenCL and OpenGL Compatibility Pack
- Support Qualcomm Adreno and ARM Mali GPUs via Android Termux
- Support POCL runtime on CPU
- No Strange Memory Problem on AMD CPUs
- Support Mesa RustiCL
- Support OpenCL 1.2 API