The Khronos Group, an open consortium of leading technologies companies and the group responsible for such open industry standards such as OpenGL computer graphics technology, has released OpenCL 3.0
OpenCL technology was invented by Apple for parallel computing based tasks and data-based parallelism. The technology was then offered up as an open, industry-standard technology and has been managed by The Khronos Group since.
OpenCL 3.0
The latest version of OpenCL responds to developer-requested functionality and broadly deployed hardware platforms. It will help developers with OpenCL implementations address precise functionalities pertinent to their target markets.
OpenCL 3.0 is announced and excites the developer community with its newest features.
OpenCL 3.0 also integrates subgroup functionalities into the core specification, it ships with a new OpenCL 3.0 language specification, uses a new unified specification format, and introduces extensions for asynchronous data copies to enable a new class of embedded processors.
The provisional OpenCL 3.0 specifications enable the developer community to provide feedback on GitHub before the specifications and conformance tests are finalized.
Compatibility
All OpenCL 1.2 applications will continue to run unchanged on any OpenCL 3.0 device. All OpenCL 2.X features are coherently defined in the new unified specification, and current OpenCL 2.X implementations that upgrade to OpenCL 3.0 can continue to ship with their existing functionality with full backward compatibility.
OpenCL has wide industry support including from Intel, Apple, ARM, Imagination, NVIDIA and dozens of other key computer software and hardware companies.
“OpenCL is the most pervasive, cross-vendor, open standard for low-level heterogeneous parallel programming—widely used by applications, libraries, engines, and compilers that need to reach the widest range of diverse processors,” said Neil Trevett, vice president at NVIDIA, president of the Khronos Group and OpenCL Working Group Chair.
Big Industry Support
“OpenCL 3.0 has opened up a new chapter for the OpenCL API which has served as the standard GPGPU API during the past 10 years,” said Weijin Dai, executive vice president and GM of Intellectual Property Division at VeriSilicon. “With the streamlined OpenCL 3.0 core feature set, OpenCL 3.0 will enable a whole new class of embedded devices to adopt OpenCL API for GPU Compute and ML/AI processing, and it will also pave the way forward for OpenCL to interop or layer with the Vulkan API.
NVIDIA Support
“NVIDIA welcomes OpenCL 3.0’s focus on defining a baseline to enable developer-critical functionality to be widely adopted in future versions of the specification,” said Anshuman Bhat, compute product manager at NVIDIA. “NVIDIA will ship a conformant OpenCL 3.0 when the specification is finalized and we are working to define the Vulkan® interop extension that, together with layered OpenCL implementations, will significantly increase deployment flexibility for OpenCL developers.”
Intel Support
“Intel strongly supports cross-architecture standards being driven across the compute ecosystem such as in OpenCL 3.0 and SYCL,” said Jeff McVeigh, vice president, Intel Architecture, Graphics and Software. “Standards-based, unified programming models will enable efficiency and unleash creativity for our developers with the upcoming release of our new Xe GPU architecture.”
OpenCL and COVID-19
OpenCL is widely used by applications, libraries and software engines and compilers that reach a diverse and wide range of industries including medtech, vision processing, machine learning, and professional creative tools.
OpenCL is being used for COVID-19 research and recently powered the world’s fastest supercomputer with the non-profit org, Folding@Home who brought together volunteer scientists to fold proteins, a task that could prove instrumental in the fight against the coronavirus pandemic.
SFolding@Home users OpenCL for parallel programming to offload computations onto the GPUs contained in the networked home PCs that are often use for gaming—significantly boosting available compute power. The combined power of this network broke a record of 2.4 exaflops, making it faster than the top 500 traditional supercomputers in the world combined.
About Folding@Home
Folding@Home is a distributed computing project for simulating protein dynamics, including the process of protein folding and the movements of proteins implicated in a variety of diseases. It brings together citizen scientists who volunteer to run simulations of protein dynamics on their personal computers. Insights from this data are helping scientists to better understand biology, and providing new opportunities for developing therapeutics.