16 best C++ GPU libraries in 2023
by Open Weaver kits ✔ Updated: Jan 15, 2023
C++ is a powerful programming language, which is widely used in many fields, especially in the embedded system. C++ is a statically typed, compiled programming language for general-purpose programming. It is also considered to be an intermediate-level language, as it comprises both high-level and low-level language features. These features make C++ a popular choice in the software industry and allow developers to create efficient applications that can be used in various domains. GPU libraries are widely used to accelerate the performance of matrix calculations, image processing and machine learning. GPUs are used not only in gaming and entertainment, but also in modern science. The number of computations that can be done on a GPU is significant. A few of the most popular open source libraries for C++ GPU are: Tensor RT - Tensor RT is a C library for high performance inference on NVIDIA GPUs and deep learning accelerators; array fire - Array Fire: a general purpose GPU library; compute - A C GPU Computing Library for OpenCL.
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
C++ 7240 Version:v8.6.1 License: Permissive (Apache-2.0)
ArrayFire: a general purpose GPU library.
C++ 4137 Version:v3.8.3 License: Permissive (BSD-3-Clause)
GPU Accelerated C++ User Interface, with WYSIWYG developing tools, XML supports, built-in data binding and MVVM features.
C++ 2159 Version:Current License: Others (Non-SPDX)
Win2D is an easy-to-use Windows Runtime API for immediate mode 2D graphics rendering with GPU acceleration. It is available to C#, C++ and VB developers writing apps for the Windows Universal Platform (UWP). It utilizes the power of Direct2D, and integrates seamlessly with XAML and CoreWindow.
C++ 1627 Version:Current License: Others (Non-SPDX)
Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning
C++ 1083 Version:v1.1 License: Others (Non-SPDX)
Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions
C++ 1063 Version:v2.0.0 License: Permissive (Apache-2.0)
Minerva: a fast and flexible tool for deep learning on multi-GPU. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy.
C++ 678 Version:Current License: Others (Non-SPDX)
An efficient C++17 GPU numerical computing library with Python-like syntax
C++ 727 Version:v0.4.0 License: Permissive (BSD-3-Clause)
HCC is an Open Source, Optimizing C++ Compiler for Heterogeneous Compute currently for the ROCm GPU Computing Platform
C++ 402 Version:roc-hcc-3.0.0 License: Others (Non-SPDX)
GPU Raytracer from scratch in C++/CUDA
C++ 636 Version:v1.3.0 License: Permissive (MIT)
Blazing-fast Expression Templates Library (ETL) with GPU support, in C++
C++ 189 Version:1.2.1 License: Permissive (MIT)
.NET bindings for PyTorch. Machine Learning with C# / F# with Multi-GPU/CPU support
C# 246 Version:Current License: Others (Non-SPDX)
Sample projects for TensorFlow Lite in C++ with delegates such as GPU, EdgeTPU, XNNPACK, NNAPI
C++ 294 Version:20210814 License: Permissive (Apache-2.0)
Burstcoin C++ CPU and GPU Miner
C++ 171 Version:1.9.0 License: Strong Copyleft (GPL-3.0)
:sparkler: A modern particle engine running on GPU, using c++14 and OpenGL 4.4.
C++ 165 Version:Current License: Permissive (MIT)