A standard algorithms library for ILGPU
Clone or download
m4rs-mt Redesigned huge parts of the Lightning library to enable cross-platfo…
…rm support.

Removed native CUB dependency (no Cuda compiler required any more, no native libs required any more).
Ported existing functionality to new ILGPU version.
Adapted namespaces.
Latest commit 94af1a5 Dec 1, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
.gitattributes Initial github commit. Jun 11, 2017
LICENSE-3RD-PARTY.txt Redesigned huge parts of the Lightning library to enable cross-platfo… Dec 1, 2018



Real-world applications typically require a standard library and a set of standard algorithms that "simply work". The ILGPU Lightning library meets these requirements by offering a set of auxiliary functions and high-level algorithms (e.g. sorting or prefix sum). All algorithms can be run on all supported accelerator types. The CPU accelerator support is especially useful for kernel debugging.

Build instructions

ILGPU.Lightning requires Visual Studio 2017.

Build ILGPU.Lightning

Use the provided Visual Studio solution to build the ILGPU.Lightning libs in the desired configurations (Debug/Release).

Note: ILGPU.Lightning uses the build configuration "Any CPU" (which simplifies an integration into other projects).

License information

ILGPU.Lightning is licensed under the University of Illinois/NCSA Open Source License. Detailed license information can be found in LICENSE.txt.

Copyright (c) 2016-2018 ILGPU Lightning Project. All rights reserved.

License information of required dependencies

Different parts of ILGPU.Lightning require different third-party libraries.

Detailed copyright and license information of these dependencies can be found in LICENSE-3RD-PARTY.txt.