Toy Tensor Language and MLIR-based Compiler

CUDA Templates for Linear Algebra Subroutines

This is the canonical git mirror of the LLVM subversion repository. Please see http://llvm.org/ for instructions on contributing to LLVM.

STREAM, for lots of devices written in many programming models

oneAPI Technical Advisory Board (TAB) Meeting Notes

Examples for using SYCL on CUDA

cuDNN sample codes provided by Nvidia

Port of Facebook's LLaMA model in C/C++

A new high-level IR for clang.

Collection of samples, documentation and utilities for using ComputeCpp, Codeplay's beta SYCL implementation

Public development project of the LAMMPS MD software package

Kokkos C++ Performance Portability Programming EcoSystem: The Programming Model - Parallel Execution and Memory Abstraction

an educational compiler intermediate representation

A performant and modular runtime for TensorFlow

Open Source Parallel STL implementation

Cross compiling toolchains in Docker images

The OpenCL ICD Loader project.

Repo to create docker images containing Intel(R) Graphics Compute Runtime for OpenCL(TM)

Introduction to Parallel Programming class code

Intercept Layer for Debugging and Analyzing OpenCL Applications

Tutorial for the Vulkan graphics and compute API

Rodinia benchmark

Guidelines Support Library