Using OpenCL, programmers can utilize FPGAs with C, or other familiar high- level programming languages, instead of hardware-specific language. At SC16, one of the major issues for discussion is optimizing OpenCL kernels for high-performance computing.
Today sees the emergence of ROCm (Radeon Open Compute Platform) 1.3, which brings the official release of the LLVM native compiler and support for AMD’s current Polaris family of 14nm GPUs (Radeon RX 480, RX 470, RX 460). Also hopping aboard is support for OpenCL 1.2+. More specifically, ROCm 1.3 support the OpenCL 1.2 runtime along with the OpenCL 2.0 kernel language.
Intel SDK for OpenCL Applications 2016 R3 is now available for download. This update adds support for new OSes and platforms, more performance analysis features and various SDK improvements including: OpenCL 2.1 development environment with the experimental CPU-only runtime for OpenCL 2.1; SPIR-V generation support with Intel® Code Builder for OpenCL offline compiler and Kernel Development Framework including textual representation of SPIR-V binaries.
Join the Khronos Group in Booth 304 @ SC16. There will be people in the booth from the Khronos working groups who can answer your technical questions about OpenCL, SYCL, and SPIR. Visit the Khronos Booth for your free HPC t-shirt, OpenCL sticker, and reference guides for OpenCL and SYCL. Khronos members Xilinx and Codeplay will be in the booth to answer questions, give talks, and show demos. This year at SC Khronos will show where OpenCL fits in with the larger pantheon of open standards for HPC in a panel held on Wednesday 10:30am in room 255-BC.
Nimbix announced the availability of the Xilinx SDAccel development environment for on-demand development, testing, and deployment of FPGA-accelerated workflows in the Nimbix Cloud, powered by JARVICE. The SDAccel development environment combines the industry’s first architecturally optimizing compiler supporting any combination of OpenCL, C, and C++ kernels, along with libraries, development boards and industry standard development and run‐time experience for FPGAs.
After informing us last week about the availability of the Release Candidate (RC) version of the first point release of Mesa 13.0.0, as well as about Mesa 13.0.1’s upcoming launch on November 13, 2016, Collabora’s Emil Velikov released the final version today.
NVIDIA introduces the VK_NVX_device_generated_commands (DGC) Vulkan extension, which allows the GPU to generate the most frequent rendering commands on its own. Read about Vulkan Device-Generated Commands on the NVIDIA Blog.
The Khronos Group is proud to announce that Igalia S.L. has joined as a Contributor Member. Igalia is a Free Software consultancy with headquarters in Spain and developers all around the world. They are passionate about their work, active in their communities, eager to learn and happy to contribute their knowledge. In short, they are inspired to make the world a better place through Free Software, and driven by the knowledge that they can.
ReFLEX CES, a leading European-based provider of custom embedded and complex systems, will showcase its expertise in the design and manufacture of complex FPGA network accelerator cards at the Super Computing 2016 tradeshow. Highlights of the booth include Networking & Processing FPGA boards, Instant-DevKits and OpenCL demos. ReFLEX CES will demonstrate High Performance Computing OpenCL BSP (Board Support Package) based on various Altera Arria 10 base boards. Visit Khronos in Booth #304 at SC16.
The Khronos Group will participate in the Embedded Technology 2016 at Booth number B-31 in Japan from November 16-18. In addition to introducing the latest information of each API specification by Japanese member companies, Khronos is scheduled to conduct demonstrations of their products and technologies. There will also be an open stage presentation and workshop held in the exhibition hall with Neil Trevett, President of The Khronos Group.
If you missed the Khronos DevU in Seoul, you can now catch up with the online presentations. Khronos Group gave a full-day workshop on Vulkan in the latest DevU series in Seoul, Korea. This session providing attendees with an important overview, then quickly diving deep beyond the basics into Vulkan’s use and structure, and then some case studies with code walkthroughs. If you are interested in hearing about Khronos Groups next DevU, signup for the Khronos mailing list.
Amazon has started shipping the 1st Edition of “Vulkan Programming Guide: The Official Guide to Learning Vulkan.” The guide is written by Graham Sellers, API lead on the Vulkan specification and John Kessenich, language lead on the Vulkan specification and Senior Compiler Architect at LunarG. The next generation of the OpenGL specification, Vulkan, has been redesigned from the ground up, giving applications direct control over GPU acceleration for unprecedented performance and predictability. Vulkan™ Programming Guide is the essential, authoritative reference to this new standard for experienced graphics programmers in all Vulkan environments.