AMD OpenCL™ Zone - OpenCL is a powerful, non-proprietary solution for accelerating your applications on CPUs, GPUs and APUs.

OpenCL™ is the first truly open and royalty-free programming standard for general-purpose computations on heterogeneous systems. Open Computing Language allows programmers to preserve their expensive source code investment and easily target multi-core CPUs, GPUs, and the new APUs. Developed in an open standards committee with representatives from major industry vendors, OpenCL™ gives users what they have been demanding: a cross-vendor, non-proprietary solution for accelerating their applications on CPU, GPUs and APUs. AMD, an early supporter of OpenCL™ and leading innovator and provider of high-performance CPUs and GPUs, is uniquely positioned in this industry to offer a complete acceleration platform for OpenCL™. Developer and technology partners have created several applications, libraries and technology demonstrations taking advantage of AMD Accelerated Parallel Processing acceleration, also abbreviated as “APP.”  Use the resources below to get started with OpenCL™ today.

Tools & SDKs

AMD OpenCL™ APP SDK – execute heterogeneously to accelerate many applications beyond just graphics

CodeXL – A comprehensive tool suite that includes powerful debugging, profiling, and static OpenCL™ kernel analysis capabilities

Legacy AMD OpenCL™ Tools — These tools have lived a long and fruitful life. Now discontinued but provided here without warranty as a convenience


ACML — ACML includes optimized and threaded linear algebra math libraries for use in for high performance computing, scientific, engineering, and related compute-intensive applications for use on AMD processors. Includes BLAS, LAPACK, FFT, and RNG routines.

clMagma —  OpenCL™ port of the MAGMA project, a linear algebra library similar to LAPACK but for Multicore+GPU systems

clMath — OpenCL™ software libraries containing FFT and BLAS functionalities

Bolt — An STL compatible library for creating accelerated data parallel applications

GPUPerfAPI — AMD’s library for accessing GPU performance counters on ATI Radeon graphics cards

ArrayFire — ArrayFire is a high performance software library for parallel computing with an easy-to-use API.

PARALUTION — is a sparse linear algebra library with OpenCL™ support that has a rich collection of iterative solvers and preconditioners. The code can be compiled under Linux/Unix, Mac OS and Windows


Getting Started with OpenCL™

Programming in OpenCL

Porting CUDA Applications to OpenCL™

Training — Check out these AMD partners who offer a variety of OpenCL™ training options customized to fit your needs

OpenCL™ Articles and Papers

OpenCL™ Technical Overview Video Series

OpenCL™ On-Demand Webinar Series


AMD OpenCL™ Developer Forums

AMD Developer Forums Home Page

OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.