Intel's open-source Beignet project for OpenCL support on Intel graphics hardware has landed a bunch of OpenCL 2.0 enablement work.
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.
A new version of the Lightweight Java Games Library has been released. This provides java bindings for OpenGL, OpenGL ES, Vulkan, OpenCL, OpenAL, EGL, BGFX, etc.
The Vulkan-enabled ARM Mali-G51 graphics processor extends new Bifrost architecture to mainstream devices to enable more compelling user experiences. The ARM Mali-G51 also supports OpenGL ES 3.2 and OpenCL.
Fresh OpenCL compute benchmarks of 11 different GPUs when using the latest NVIDIA (370.28) and AMDGPU-PRO (16.30.3) Linux drivers on Ubuntu 16.04 LTS. The open-source (Clover-based stack) wasn't used for any open-source AMD OpenCL testing due to its less than stellar state.
Magic Bullet Suite delivers for the first time ever, real-time color correction thanks to OpenCL support in Adobe Premiere Pro CC, extending the toolset for users of the industry’s leading NLE.
Phoronix benchmarking offers an initial look at the OpenGL / OpenCL / Vulkan Linux performance plus some thermal numbers for the GTX 1050 Mini. A follow-up article will include power consumption / performance-per-Watt metrics of the GTX 1050 / GTX 950 / GTX 750 / GTX 650 for a fun comparison of Pascal, Maxwell, and Kepler of these low/mid-range cards.
Blender 2.78 comes with lots of improvements to the Cycles render engine, including support for CPU groups, support for Nvidia GTX 10×0, along with better support for Nvidia GTX 980 Ti and Nvidia Titan X GPUs, OpenCL and CUDA memory improvements.
The recent announcement covers the new XM6 DSP, CEVA's new set of imaging and vision software libraries, a set of new hardware accelerators and integration into the CDNN2 ecosystem. XM6 will support OpenCL and C++ development tools, and the software elements include CEVA's computer vision, neural network and vision processing libraries with third-party tools as well.
ArrayFire released v3.4 of their open source library of parallel computing functions supporting CUDA, OpenCL, and CPU devices. This new version of ArrayFire improves features and performance for applications in machine learning, computer vision, signal processing, statistics, finance, and more. Performance Improvements to JIT have resulted in up to 5x speed gains in OpenCL.