The Mora research group at UML released SparkCL an open source unified programming framework for heterogeneous clusters based on Java, OpenCL, Aparapi and the Apache Spark framework. The motivation behind this work is to bring unconventional compute cores such as FPGAs/GPUs/APUs/DSPs and future core types into mainstream programming use. The framework allows equal treatment of different computing devices under the Spark framework and introduces the ability to offload computations to acceleration devices. There is a white paper describing this work and documentation and source repository on Gitlab.
AJ Guillon, who is a Khronos member and contributed to OpenCL 2.1 and the OpenCL C++ kernel language, has written an introduction to OpenCL C++. Previous versions of OpenCL have featured OpenCL C, based upon the C programming language. The provisional OpenCL 2.1 specification is the first OpenCL version to feature a kernel language based upon C++. The relative advantages and disadvantages of C and C++ are already well known, and OpenCL C++ inherits many of them. The OpenCL working group has responded to developers’ requests to be able to write high-level abstractions enabled by C++, while maintaining some compatibility with OpenCL C, by providing the OpenCL C++ kernel language.
Codeplay Software today announced ComputeCpp, an easy-to-use standards-based product for lowering the power consumption and increasing the performance of C++ software. The first commercial release of ComputeCpp will support SYCL for OpenCL, the open-standard C++ programming model from The Khronos Group. SYCL allows C++ application developers to write high-performance modern C++ and deploy it to multiple processor cores without hardware-specific rewrites or optimizations. The Khronos Group just released SYCL 1.2 Final Specification.
Intel Integrated Native Developer Experience (Intel® INDE) Update 2 introduced the OpenCV beta feature. Intel INDE OpenCV beta is compatible with the open source OpenCV 3.0. Provides pre-complied libraries for computer vision applications development for usages like enhanced photography, augmented reality, video summarization, and more. This release Includes IDE integration features. Provides easy to build and create environment for computer vision applications directly from preferred IDEs like Microsoft Visual Studio, Eclipse, or Android Studio. Also available open source at OpenCV.org, the standard optimizations with OpenCL and Intel Integrated Performance Primitives (Intel IPP) and Intel Threading Building Blocks (Intel TBB) ensures Intel INDE OpenCV applications are optimized to Intel’s heterogeneous platforms, accelerated with Intel HD and Intel Iris™ graphics family.
The Khronos Group announced the ratification and public release of the finalized SYCL 1.2 specification. SYCL for OpenCL enables code for heterogeneous processors to be written in a "single-source" style using completely standard C++. The multi-vendor SYCL 1.2 standard is available royalty-free for industry use, and the full specification together with details about the SYCL conformance test suite and Adopters Program can be found on the Khronos Group SYCL page.
AMD unveiled their new AMD 7000 Series Accelerated Processing Units (APUs), AMD Radeon 300 and M300 Series Graphics, and AMD A-Series desktop APU updates. The AMD A-Series Desktop APUs offer Windows 10 readiness including DirectX 12 Multiengine and Multiadapter features. Combined with existing support for AMD FreeSync, AMD Mantle, HSA features heterogeneous queuing (hQ) and heterogeneous uniform memory access (hUMA) as enabled by OpenCL 2.0 applications, and OpenGL 4.4.
The new OpenCL Code Anlayzer, a feature of Intel INDE OpenCL Code Builder, adds performance analysis capabilities integrated in Microsoft Visual Studio OpenCL development environment. With this new feature the OpenCL Code Builder now supports each state of the OpenCL code development, enables developer to carry on performance optimizations in each step of the development from build, to debug, and to tuning and get the best out of Intel Graphics Compute capabilities. OpenCL Code Builder in conjunction with Intel INDE Platfrom Analyzer now enables tuning features for OpenCL applications like:
- Application level profiling
- Platform level timeline view
- Platform performance counters
- Correlate CPU & GPU activities
- Kernel hot-spots analysis
For full description of the OpenCL Code Builder and Analyzer features watch this 2 min video.
The Embedded Vision Alliance has published an in-depth overview of OpenCL, jointly published by some Khronos Group members. Please note that a free registration is required to view the entire article.
This >a href="http://www.iwocl.org/conf-2015/the-future-of-heterogeneous-compute-apis-a-developer-feedback-session-on-khronos-opencl-sycl-and-spir-v/">special FREE to attend IWOCL 2015 session will kick-off with a technical presentation of the new features of OpenCL 2.1 followed by a developer feedback session covering OpenCL 2.1, SYCL and SPIR-V. This session provides developers with an opportunity help drive future development of the OpenCL related APIs. During the session you will have the opportunity to provide your feedback to key members of the Khronos specification working groups, fellow developers and a select group of OpenCL vendors.
AJ Guillon will be presenting the upcoming Fields Institute Working Lunch Seminar on OpenCL this April 28th 2015. This talk will motivate the OpenCL standard and present its opportunities and challenges. A survey of performance gains and energy savings will be provided so that the potential of the parallel heterogeneous compute era can be understood. The recent announcements from Khronos at GDC 2015, including Vulkan and OpenCL 2.1, will be echoed. AJ Guillon is a Khronos member and actively contributed to the new OpenCL C++ kernel language, provisionally released as part of OpenCL 2.1. In order to attend, you must register by April 26th.