Furian is designed to address the increasing compute requirements across multiple applications and market segments with efficient use of compute APIs including OpenCL 2.0, Vulkan 1.0 and OpenVX 1.1*. Furian adds a bi-directional GPU/CPU coherent interface for efficient sharing of data; and a transition to user mode queues from kernel mode queues which reduces latency and CPU utilization for compute operations. Based on a published Khronos specification, GPUs based on the PowerVR Furian architecture are expected to pass the Khronos Conformance Testing Process. Current conformance status can be found at www.khronos.org/conformance.
Igalia has contributed several features and bugfixes that helped achieve this important milestone. During the last several months, Igalia has been working hard on improving the Intel driver to enable 64-bit floating point support. We developed OpenGL extensions such as ARB_gpu_shader_fp64 and ARB_vertex_attrib_64bit, which were a major contributor to increasing the supported OpenGL version. As members of the Khronos Group, Igalia also had the opportunity to contribute tests and bugfixes to the conformance suite itself.
NVIDIA graphics driver for Windows version 378.66 is now offering some OpenCL 2.0 support. From the release notes: "New features in OpenCL 2.0 are available in the driver for evaluation purposes only." Some known issues include: The current implementation is limited to 64-bit platforms only; OpenCL 2.0 allows kernels to be enqueued with global_work_size larger than the compute capability of the NVIDIA GPU. The current implementation supports only combinations of global_work_size and local_work_size that are within the compute capability of the NVIDIA GPU; For executing kernels (whether from the host or the device), OpenCL 2.0 supports non-uniform ND-ranges where global_work_size does not need to be divisible by the local_work_size. This capability is not yet supported in the NVIDIA driver, and therefore not supported for device side kernel enqueues.
Intel now has drivers certified for the most advanced versions of all three open industry-defined 3D graphics APIs on Linux: OpenGL 4.5, OpenGL ES 3.2 and Vulkan 1.0. OpenGL 4.5 certification was announced 3 February 2017 on the Khronos Group's Conformant Product page.
Paulo Miguel Dias updated his Padoka PPA (Personal Package Archive) for Ubuntu 16.04 LTS and Ubuntu 16.10 operating systems to the latest Mesa 17.0.0-git, bringing us OpenGL 4.5 support for Intel Haswell GPUs.
Inspur and Khronos Member Intel announced partnership on an R&D project -- the Field Programmable Gate Array (FPGA) accelerator card F10A, at the SC16. This is a high density and high performance FPGA card based on OpenCL.
Huawei Consumer Business Group event saw the unveiling of the HUAWEI Mate 9 using the Kirin 960 chipset. The Kirin 960 features an ARM Cortex-A73/A53 Octa-core CPU and Mali G71 Octa-core GPU. The GPU boasts a 180 percent performance uplift and a 40 percent improvement in energy efficiency compared to its predecessor. The Kirin 960 also takes full advantage of the pioneering Vulkan graphics standard on Android 7.0, increasing graphics performance by up to 400 percent.
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.
Vulkan API supports multithreading, which is particularly important for mobile platforms. Multithreading enables the system to balance the workload across multiple CPUs, allowing for lower voltage and frequency. The results give considerable energy savings compared to OpenGL ES API. In this video from ARM, you can see just how big a difference there is between OpenGL ES and Vulkan.