The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Development repository for the Triton language and compiler

C++ examples for the Vulkan graphics API

A collection of tools, libraries, and tests for Vulkan shader compilation.

Fork of the Triton language and compiler for Windows support and easy installation

Making data lake work for time series

Benchmarking Deep Learning operations on different hardware

Assembler for NVIDIA Maxwell architecture

Optimize floating-point expressions for accuracy

A small C11 compiler

Java GameStream client for PC (Discontinued in favor of Moonlight Qt)

Exocompilation for productive programming of hardware accelerators

Winograd minimal convolution algorithm generator for convolutional neural networks.

Implementation of a Tensor Processing Unit for embedded systems and the IoT.

Open single and half precision gemm implementations

JavaScript to Lua compiler with runtime library.

Single cell perturbation prediction

Developer repository for ViennaCL. Visit http://viennacl.sourceforge.net/ for the latest releases.

What features does your CPU and OS support?

segmentation, instance segmentation and single image depth

Block-sparse primitives for PyTorch

A Re-implementation of Fixed-update Initialization

Vulkan Compute for C++ (experimentation project)

extensible collectives library in triton

Header-only C library for Binary Neural Network Feedforward Inference (targeting small devices)

ROCm - AMDGPU Compute Application Binary Interface

rtl88x2bu driver updated for modern kernels.

Superhuman Accuracy on the SNEMI3D Connectomics Challenge