OpenCL™ (Open Computing Language) is an open, royalty-free standard for cross-platform, parallel programming of diverse accelerators found in supercomputers, cloud servers, personal computers, mobile devices and embedded platforms. OpenCL greatly improves the speed and responsiveness of a wide spectrum of applications in numerous market categories including professional creative tools, scientific and medical software, vision processing, and neural network training and inferencing.
Raising the Bar for Cross-Platform Heterogeneous Compute
OpenCL 3.1 brings widely deployed, field-proven capabilities into the core specification to expand functionality, including SPIR-V ingestion, that developers can rely on across implementations.
Read the OpenCL 3.1 Launch Blog
OpenCL Image: FluidX3D CFD © Dr. Moritz Lehmann.
The Essential Resources for OpenCL Development
Thanks to the support of the Khronos membership and our passionate developer community, there is a full set of well-supported developer information and educational resources available to help you get you up and running with your OpenCL application development.
Blogs, Releases and More ...
OpenCL 3.1 brings widely deployed, field-proven capabilities into the core specification to expand functionality, including SPIR-V ingestion, that developers will be able to rely on across conformant implementations.
The OpenCL working group has been working on a follow-on to OpenCL 2.0 SVM and we would love your feedback.
This maintenance update adds numerous bug fixes and clarifications and adds two new extensions: cl_khr_spirv_queries and cl_khr_external_memory_android_hardware
_buffer
Low-Level Parallel Programming
OpenCL speeds applications by offloading their most computationally intensive code onto accelerator processors - or devices. OpenCL developers use C or C++-based kernel languages to code programs that are passed through a device compiler for parallel execution on accelerator devices.
OpenCL provides the industry with the lowest 'close-to-metal' processor-agile execution layer for accelerating applications, libraries and engines, and also providing a code generation target for compilers. Unlike 'GPU-only' APIs, such as Vulkan, OpenCL enables use of a diverse range of accelerators including multi-core CPUs, GPUs, DSPs, FPGAs and dedicated hardware such as inferencing engines.
As the industry landscape of platforms and devices grows more complex, tools are evolving the enable OpenCL applications to be deployed onto platforms that do not have available native OpenCL drivers. For example, the open source clspv compiler and clvk API translator enable OpenCL applications to be run over a Vulkan run-time. This gives OpenCL developers significant flexibility on where and how they can deploy their OpenCL applications.
An OpenCL application is split into host and device parts with host code written using a general programming language such as C or C++ and compiled by a conventional compiler for execution on a host CPU.
The device compilation phase can be done online, i.e. during execution of an application using special API calls. It can alternatively be compiled before executing the application into the machine binary or special portable intermediate representation defined by Khronos called SPIR-V. There are also domain specific languages and frameworks that can compile to OpenCL either using source-to-source translations or generating binary/SPIR-V, for example Halide.
The OpenCL working group has transitioned from the original OpenCL C++ kernel language first defined in OpenCL 2.0 to C++ for OpenCL developed by the open source community to provide improved features and compatibility with OpenCL C. C++ for OpenCL is supported by Clang along with documentation. It enables developers to use most C++17 features in OpenCL kernels. It is largely backwards compatible with OpenCL C 2.0 enabling it to be used to program accelerators with OpenCL 2.0 or above with conformant drivers that support SPIR-V. Its implementation in Clang can be tracked via the OpenCL in Clang Support Page.
A Consistent Platform for Developers
OpenCL is widely adopted with the majority of vendors now offering conformant implementations of OpenCL 3.0 and 2.0. Most of these offer public access to drivers and development platforms, including:
Development Implementations (non Conformant)
The OpenCL Conformance Test Suite (CTS) is available on GitHub and helps to create a reliable platform for developers by ensuring that OpenCL is implemented consistently across all platforms. If your company is developing a product that implements OpenCL, and passes CTS, then you should consider becoming an official adopter to enjoy the following benefits -- and you don't need to be a Khronos member to become an Adopter.
Widely Adopted & Deployed
Community
There are several ways to follow the latest OpenCL developments, provide feedback on the specification, and get your questions answered. It's a great way to get involved and will help forge the future of OpenCL and the wider ecosystem.
If you are working with OpenCL and wish to get involved in helping shape its future, please consider Joining Khronos and our Working Group. Any organization is welcome to join, and multiple levels of membership are available to enable any organization, large or small, to get involved.
Join Khronos