In another significant announcement today, OpenCL 2.1 and Vulkan™, the new open standard API for high-efficiency access to graphics and compute on modern GPUs, are now sharing core intermediate language technologies resulting in SPIR-V; a revolution in the Khronos Standard Portable Intermediate Representation initially used by OpenCL™, now fully defined by Khronos with native support for shader and kernel features. SPIR-V splits the compiler chain, enabling high-level language front-ends to emit programs in a standardized intermediate form to be ingested by Vulkan or OpenCL drivers. Eliminating the need for a built-in high-level language source compiler significantly reduces driver complexity and will enable a diversity of language front-ends. Additionally, a standardized IR provides a measure of kernel IP protection, accelerated kernel load times and enables developers to use a common language front-end, improving kernel reliability and portability across multiple implementations. You can read more on the SPIR homepage, registry and whitepaper, and give us valuable community feedback in our SPIR forum.
Imagination Technologies announces a new area-optimized PowerVR GPU designed to drive high-quality graphics with full OpenGL ES 3.0 functionality into low-cost and space-constrained devices. The new PowerVR G6020 GPU has been specially designed for graphics efficiency in ultra-compact silicon area, obtaining better real device performance and compatibility without unnecessary overhead. It is the smallest member of the PowerVR Series6XE family, with four arithmetic logic unit (ALU) cores and a silicon footprint of 2.2mm2 (28nm process technology at 400MHz).
OmniVision Technologies announced the availability of an OpenCL optimized imaging algorithm library ideally suited for ARM Mali GPUs. The library includes advanced imaging features such as 3D noise suppression, chroma noise reduction, de-fringe and de-haze and is targeted at smartphones, tablets and notebooks.
Offering OpenCL 2.0 support, and engineered to unlock new capabilities in AMD APUs and AMD Radeon GPUs based on GCN architecture, AMD Catalyst Omega special edition driver delivers enhanced capabilities, additional performance, and greater reliability. AMD has also made available a beta version of their APP SDK 3.0 which contains a complete set of sample code illustrating how to utilize each of the major new features of OpenCL 2.0.
AMD FirePro S9150 GPUs are delivering more than 3 petaFLOPS of AMD FirePro S9150 server GPU performance for the GSI Helmholtzzentrum für Schwerionenforschung GmbH in support of physics research related to heavy ion studies. Each of the 160 ASUS ESC4000 G2S nodes of the new L-CSC cluster include four AMD FirePro S9150 server GPUs, for a total GPU peak of 3.25 petaFLOPS single precision and 1.62 petaFLOPS double precision performance. The cluster is enabling Lattice Quantum Chromo Dynamics (Lattice QCD) computational research using one of the fastest OpenCL implementations for research applications in the world.
GizmoSphere, a not-for-profit embedded specialist, has announced the launch of a next-generation development board featuring a 1GHz dual-core AMD system-on-chip with Radeon HD8210E graphics on-board. The GPU supports OpenGL 4.2, OpenCL 1.2 and DirectX 11.1.
GROMACS is a molecular simulation kit, which can do all kinds of “soft matter” simulations such as nanotubes, polymer chemistry, zeolites, adsorption studies, proteins, and more. It is being used by researches worldwide and is one of the bigger bio-informatics softwares around. Until now only CUDA was being used. To make it possible to use other accelerators, Stream Computing ported GROMACS to OpenCL. The folks at Stream Computing are looking for help on this project.
Sony Creative Software announced its new line of production applications, Catalyst Browse and Catalyst Prepare. Both applications are built on a set of technology components which provide a powerful, consistent experience, including OpenCL GPU accelerated video engine for smooth playback and fast rendering; Precise color engine featuring ultra wide color gamut and large dynamic range capabilities for previewing and adjusting S-Log, S-Log2, S-Log-3, RAW, and Rec.709 source footage and Precise and comprehensive format support for all the Sony Professional cameras including the new PXW-FS7.
Neil Trevett on initiatives that are unlocking the power of the GPU for web applications including WebGL and WebCL. Talk was at The Graphical Web 2014 conference at The University of Winchester as organised by The Office for National Statistics.
ARM announced OpenCL for ARM NEON technology. This enables the use of the OpenCL framework on ARM Cortex-A processors. Alongside the already supported ARM Mali GPUs, OpenCL for NEON now enables heterogeneous multiprocessing on any Cortex-A based device. Heterogeneous multiprocessing enables compute-intensive workloads to be tasked to the most appropriate CPU or GPU resource improving both end-user experience and battery life.
Luxoft announced the creation of its Professional VP9 Codec Software Development Kit (SDK). Luxoft’s codec is designed to help video content providers, cloud servers, and live-streaming companies produce effective, real-time 4K/UltraHD encoding and video streaming. As a result of utilizing the OpenCL standard, the SDK also offers a significant time-to-market advantage for todays hardware architectures such including CPUs, GPUs, and heterogeneous computing systems. VP9 4K SDK is ready for beta evaluation.
Altera is demonstrating several advanced reconfigurable logic technologies at the Intel Developers Forum (IDF) 2014 that showcase how its FPGA-based solutions are advancing the capabilities of software-defined data centers and high-performance computing applications. The Financial Model Acceleration with FPGAs demonstration uses OpenCL to efficiently implement multiple kernels on an FPGA performing a Monte Carlo simulation to price options. Utilizing the OpenCL standard on a massively parallel FPGA architecture provides an effective solution for system acceleration, offering significantly higher performance at much lower power versus GPUs.
Boost.Compute is a header-only C++ library for GPGPU and parallel-computing based on OpenCL. This proposed library for Boost is available on GitHub and instructions for getting started can be found in the documentation. Are you interested in Parallel Computing? The Boost.Compute project is currently looking for additional developers. Boost.Compute is not yet an official Boost library.
There is a certain category of wearables and IoT devices that require advanced graphics and video processing alongside the sensors, connectivity and general-purpose processors; these devices feature displays and need to run multimedia-rich apps that require smooth OpenGL ES graphics. PowerVR GX5300 is designed to address the ultra-low power requirements of wearables. Whereas previous generation smartwatches could render graphics using a software-only approach or a simple 2D engine, newer wearable devices require fully featured GPUs to drive higher resolution user interfaces. PowerVR GX5300 can comfortably drive 480p and 720p resolutions representative of modern smartwatches, while offloading the main CPU and reducing software complexity.
FinalWire has announced AIDA64 v4.50. The new AIDA64 release introduces a multi-threaded OpenCL GPGPU AES-256 benchmark to measure cryptographic processing performance of modern graphics processors and APUs.