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.
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.
MAXON announced they have reached a licensing agreement for the use of AMD’s Radeon ProRender technology in MAXON’s Cinema 4D application. Radeon ProRender’s physically-based GPU rendering engine is built on platform-agnostic OpenCL architecture and will provide outstanding performance on both macOS and Windows. Written using OpenCL, Radeon ProRender can run on virtually any hardware. Radeon ProRender also provides a CPU backend which means Radeon ProRender can run on GPU, CPU, or a combination of multiple disparate GPUs.