Khronos Group News Archives

Khronos member Axell to start selling OpenVG 1.1 compliant AG903

Axell will start production of the AG903, the latest product in the "AG9" series graphics LSI for embedded systems. As with existing products, it has strengths not only in functionality and performance, but also in the supply and support. It is the LSI for industrial devices used in the factory automation, measurement, and medical equipments, among others. The AG903 is in conformance with OpenVG 1.1 and uses the ARM Cortex-A5 for it's built in CPU. Read More

Leveraging asynchronous queues for concurrent execution

GPUOpen has posted a new entry "Leveraging asynchronous queues for concurrent execution." Understanding concurrency (and what breaks it) is extremely important when optimizing for modern GPUs. Modern APIs like Vulkan provide the ability to schedule tasks asynchronously, which can enable higher GPU utilization with relatively little effort. Read More

Khronos Group welcomes Razer as newest Contributing Member

Khronos Group welcomes Razer as newest Contributing Member

The Khronos Group is proud to announce that Razer has joined as a Contributor Member. Razer is a world leader in connected devices and software for gamers. Its award-winning design and technology span systems, peripherals, audio and wearable technologies. Razer co-founded OSVR, an open-source platform that integrates VR, AR and mixed reality hardware and software APIs that support a universal VR ecosystem. Read More

Amazon EC2 Elastic GPUs support OpenGL

Amazon EC2 users will soon have the ability to add OpenGL acceleration to existing EC2 instance types. Amazon-optimized OpenGL library will automatically detect and make use of Elastic GPUs. Amazon will start out with Windows support for OpenGL, and plan to add support for the Amazon Linux AMI and other versions of OpenGL after that. The GPU added to the instance can have 1, 2, 4, or 8 gigabytes of video memory. It’s becoming much easier to use OpenGL from GPUs in the cloud. Read More

NVIDIA GTX 680 To GTX 1080 Blender OpenCL Benchmarks

Phoronix has published benchmarks of 13 Kepler/Maxwell/Pascal NVIDIA GeForce graphics cards when testing Blender 2.78's OpenCL renderer. Unfortunately, no AMD OpenCL benchmarks for Blender yet -- the current open-source stack doesn't work until ROCm OpenCL support comes into play and the AMDGPU-PRO stack wasn't working for Blender OpenCL but was falling back to CPU rendering. Read the complete article. Read More

Vulkan Renderer In The Works For A PlayStation Emulator

The LibRetro crew is now working on a Vulkan renderer for a PlayStation One emulator. They have a Vulkan renderer working for the Beetle PSX, but the code hasn't been published yet. In the past few days the LibRetro crew uploaded some YouTube videos showing the Vulkan-renderered PlayStation One emulator in action. Read More

Vulkan, OpenGL ES, EGL, and OpenCL API Trace and Debug Tool

The Mali Graphics Debugger allows developers to trace Vulkan (1.0), OpenGL ES (1.x, 2.x, and 3.x), EGL (1.4), and OpenCL (1.x) API calls in their application and understand frame-by-frame the effect on the application to help identify possible issues. Read More

Codeplay helping bridge the gap on RISC-V with OpenCL and SYCL

Codeplay helping ensure software developers are correctly equipped to host their software applications on RISC-V. Codeplay is working extensively with machine learning solutions such as Google with TensorFlow to bridge the gap on RISC-V with OpenCL and SYCL open standards. Read More

S2C announces development of new Arria 10 Prodigy FPGA Prototyping Logic Modules supporting OpenCL

S2C Inc. has announced the development of a new family of Arria 10 Prodigy FPGA Prototyping Logic Modules based on Altera's Arria 10 1150GX FPGA. The Arria 10 Prodigy Logic Module includes compatibility with Altera's Software Development Kit (SDK) for OpenCL allowing easy implementation for HPC applications. Read More

OpenCL training from Acceleware

Acceleware has updated their courses for GPU and Altera FPGAs. You may find a complete listing of all upcoming training on their website. Read More

Sketchfab announces support for glTF

Quietly in the Sketchfab forums, support for glTF was announced. sketchfab support staff James replied to a request asking for glTF support with "Hi guys, We just shipped support for glTF. We're still improving, but let us know how it goes!" Read More

Vulkan barriers explained

AMD post from October explaining Vulkan's Barrier system. Vulkan’s barrier system is unique as it not only requires you to provide what resources are transitioning, but also specify a source and destination pipeline stage. This allows for more fine-grained control of when a transition is executed. However, you can also leave quite some performance on the table if you just use the simple way, so today we’re going to look at vkCmdPipelineBarrier in detail. Read More

OpenVX-Based Python Framework for Real-time Cross-Platform Acceleration

Neuro-Biomorphic Engineering Lab, Faculty of Engineering, Jerusalem College of Technology, Jerusalem, Israel has posted on Github their OpenVX based PyOpenVX library - PythonOpenVX. Included is a complete article and discussion outlining how to use this framework. Read More

Intel Skylake OpenGL vs. Vulkan Numbers With The Latest ANV Mesa Changes

Fresh OpenGL vs Vulkan graphics API performance numbers on the Intel side with their Mesa "ANV" driver. Read More

OpenCL GPU Training – Amsterdam, 16 Jan 2017

Stream Computing is offering OpenCL training in Amsterdam in January 2017. For those wanting to learn solid GPU programming. This is a public training with trainees from various companies – get in contact if you want to learn more about our in-company trainings. For pre-requisites and pricing, please see the Stream Computing website. Read More

Page 1 of 175 pages  1 2 3 >  Last ›

safety