Welcome to ACL, AMD Compute Libraries. We have transitioned our math libraries from a proprietary, closed source codebase to open source solutions, providing developers with a set of open source libraries targeted to those who want to accelerate computations on GPUs, APUs and CPUs. ACL is composed of a number of libraries designed to enhance the open source ecosystem and help software developers code faster for faster code. All of the source code, readme files and other documentation can now be found at the corresponding github links noted below. Let us know what you think by posting in one of the specific GitHub repositories.
AMD’s commitment to Open Source is growing. The AMD Compute Libraries are now located at the GPUOpen website. GPUOpen is an AMD initiative designed to enable developers to create ground-breaking PC games, computer generated imagery and GPU computing applications for great performance and lifelike experiences using no cost and open development tools and software.
Our CPU-based math libraries have moved from a proprietary, closed source ACML codebase to an open source solution, leveraging, in part, the BSD-licensed Science of High-Performance Computing (SHPC) software stack, developed and maintained by the SHPC group based at the University of Texas, Austin. This software includes BLIS, an implementation of the BLAS, and libflame, an implementation of LAPACK. Both provide high performance as well as superior maintainability and portability.