Heterogeneous Computing

Colossal-AI - An Integrated Large-scale Model Training System with Efficient Parallelization TechniquesPython

A unified deep learning system for efficient large-scale model training and inference with advanced parallelism strategies.

Paddle - PArallel Distributed Deep LEarning by BaiduC++

An industrial deep learning framework supporting unified dynamic/static graphs, automatic parallelism, and integrated training/inference for large models.

PaddlePaddleC++

An industrial deep learning framework from China supporting unified dynamic/static graphs, automatic parallelism, and integrated training/inference for large models.

TaskflowC++

A fast, expressive, and header-only C++ library for building task-parallel programs with static, dynamic, and conditional task graphs.

Boost.ComputeC++

A C++ GPU computing library providing an STL-like interface for OpenCL-based parallel programming.

CodeXLC++

A comprehensive GPU tool suite for debugging, profiling, and analyzing OpenCL, OpenGL, Vulkan, and DirectX kernels and shaders.

Intel Parallel STLC++

A high-productivity C++ library for parallel programming across devices using Data Parallel C++ (DPC++) APIs.

BoltC++

A C++ template library optimized for GPUs providing high-performance implementations of common algorithms like scan, reduce, transform, and sort.

ClojureCL - parallel computations with OpenCLClojure

A Clojure library for parallel computations using OpenCL 2.0 with fast JNI bindings.