Khronos Releases OpenCL 1.2 Specification

[btarunr]

The Khronos Group today announced the ratification and public release of the OpenCL 1.2 specification, the latest update to the open, royalty-free standard for cross-platform, parallel programming of modern processors. Released eighteen months after OpenCL 1.1, this new version provides enhanced performance and functionality for parallel programming in a backwards compatible specification that is the result of cooperation by over thirty industry-leading companies. Khronos has updated and expanded its comprehensive OpenCL conformance test suite to ensure that implementations of the new specification provide a complete and reliable platform for cross-platform application development. The OpenCL 1.2 specifications, online reference pages and reference cards are available here.

"The OpenCL working group is listening carefully to feedback from the developer and middleware community to provide significant and timely functionality for heterogeneous computing in this cross vendor open standard," said Neil Trevett, chair of the OpenCL working group, president of the Khronos Group and vice president of mobile content at NVIDIA. "The OpenCL working group is also broadening its membership and has growing representation from the mobile and embedded industries and is enabling innovative devices such as FPGAs to be driven through OpenCL."

OpenCL 1.2 enables significantly enhanced parallel programming flexibility, functionality and performance through many updates and additions including:

• Device partitioning - enabling applications to partition a device into sub-devices to directly control work assignment to particular compute units, reserve a part of the device for use for high priority/latency-sensitive tasks, or effectively use shared hardware resources such as a cache;
• Separate compilation and linking of objects - providing the capabilities and flexibility of traditional compilers enabling the creation of libraries of OpenCL programs for other programs to link to;
• Enhanced image support - including added support for 1D images and 1D & 2D image arrays. Also, the OpenGL sharing extension now enables an OpenCL image to be created from OpenGL 1D textures and 1D & 2D texture arrays;
• Built-in kernels represent the capabilities of specialized or non-programmable hardware and associated firmware, such as video encoder/decoders and digital signal processors, enabling these custom devices to be driven from and integrated closely with the OpenCL framework;
• DX9 Media Surface Sharing - enables efficient sharing between OpenCL and DirectX 9 or DXVA media surfaces;
• DX11 Surface Sharing - for seamless sharing between OpenCL and DirectX 11 surfaces.

Working Group Member Support
"AMD promotes industry standards like OpenCL 1.2 that encourage developer freedom and creativity," said Manju Hegde, corporate vice president, AMD Fusion Experience Program. "In addition to being one of the leading contributors to the OpenCL working group and specifications, AMD Accelerated Processing Units (APUs) and GPUs are the perfect platforms to take advantage of the potential of OpenCL - for developers and end-users."

"Having worked with our Khronos partners in the evolution of OpenCL we are pleased to support the announcement of the latest version of the standard," said James McNiven, vice president, compute sub-systems, processor division, ARM. "We believe the vision of energy efficient heterogeneous compute subsystems can only be realized through industry collaboration and standards. ARM remains committed to supporting OpenCL across both CPU and GPU technology and helping our partners deliver high-performance compute systems that leverage ARM Mali GPU and Cortex processor technology."

"Intel is encouraged by the progress of the OpenCL specification and proud to be an OpenCL adopter and contributor to the OpenCL 1.2 release", said Bill Savage, vice president and general manager of the Developer Products Division of Intel's Software and Services Group. "OpenCL 1.2 promises better performance and more flexibility in software design for developers targeting current and future Intel Platforms."

"The existence of an unified programming interface for multi-core platforms is becoming a crucial element for boosting the productivity of software engineers." said Satoshi Miki, Founder and CEO, Fixstars Corporation. "With the release of the OpenCL 1.2 specification, I am very excited for the increased flexibility that it brings to multi-core programming. My hope is for many hardware vendors to support this new specification to allow for further innovations that can only come about from taking full advantage of the multi-core architecture."

OpenCL Session at SC11, Seattle November 14-18th 2011
There is an OpenCL BOF "Birds of a Feather" Meeting on Wednesday 16th, 5:30- 7PM in Room TCC 101 at SC11, where attendees are invited to meet OpenCL implementers and developers and learn more about the new OpenCL 1.2 specification.

View at TechPowerUp Main Site

 

[Mussels]

any word on hardware support? do all DX11 cards support this with driver updates, same for DX10?

 

[BorgOvermind]

The specs were made considering current hardware, so there should be no HW support problems.

 

[Sihastru]

It's like SSE. Depending on your hardware, you'll be able to access subsets or supersets of instructions thay may or may not be backwards or forwards compatible.