Ginkgo is a high-performance linear algebra library for manycore systems, with a focus on sparse solution of linear systems. It is implemented using modern C++ (you will need at least a C++14 compliant compiler to build it), with GPU kernels implemented in CUDA (for NVIDIA devices) and HIP (for AMD devices).

Get Ginkgo

High Performance

Competitive performance on state-of-the-art hardware architectures.

Performance Explorer

Cross Platform

Ginkgo supports execution on CUDA and HIP accelerators, and OpenMP-enabled devices.

Cross Platform

Collaborative Effort

Collaborative open-source effort with a permissive license.

Show License


Check out some tutorials.



Easily integrate new solvers, matrix formats, loggers, stopping criteria for your application.

Show Tutorial

Get Involved

Discuss library features, issues, and extensions.

Get Involved