clMath: An Open Source BLAS and FFT Library for OpenCL

ScottAnnouncements, OpenCL Leave a Comment

If you’re reading our blog, BLAS and FFT libraries likely form an important basis for your work. For instance, BLAS and FFT libraries are used in some of ArrayFire’s higher-level functions for linear algebra, signal processing, and image processing.

Today, OpenCL is getting a significant boost in BLAS and FFT library availability. AMD has announced a bold and generous move to contribute to the OpenCL community by open-sourcing its APPML BLAS and FFT OpenCL libraries.

At AccelerEyes, we have previously used AMD’s OpenCL libraries within our higher-level ArrayFire library. These libraries are the best BLAS and FFT OpenCL libraries available anywhere. We are thrilled to join AMD and the open-source community in maintaining and improving these libraries for the benefit of all.

The source is now available as “clMath” on GitHub. The clMath libraries include clBLAS and clFFT. The libraries will run on any OpenCL-conformant device. They will benefit all OpenCL developers, spanning from mobile apps to supercomputing codes.

We have collaborated closely with AMD in the lead-up to making clMath available. AccelerEyes engineers are dedicating significant resources to the continued development of the clMath library. These libraries will also be used in our upcoming ArrayFire v2.0 release.

This marks a great step in the right direction for the OpenCL ecosystem. We continue to observe increased demand for OpenCL from our customers in various application domains, and we look forward to ongoing development efforts contributing to the growing OpenCL community.

Along with AMD, we welcome your adoption and contributions to the source, and we look forward to contributing to this project for years to come!

Additional info:

Leave a Reply

Your email address will not be published. Required fields are marked *