News Archives

AImotive’s aiWare3 Hardware IP Helps Drive Autonomous Vehicles To Production with Khronos’ NNEF

AImotive, the global provider of full stack, vision-first self-driving technology, today announced the release of aiWare3, the company's 3rd generation, scalable, low-power, hardware Neural Network (NN) acceleration core. The scalable aiWare3 architecture facilitates low-power continuous operation for autonomous vehicles (AVs) with up to 12 or more high-resolution cameras, LiDARs and/or radar. aiWare3 delivers up to 50 TMAC/s (> 100 TOPS) per chip at more than 2 TMAC/s (4 TOPS) per W1. aiWare3's IP core is supported by a comprehensive software development kit (SDK) that uses The Khronos Group's NNEF standard. It will ship to lead customers in Q1 2019.

AImotive's aiWare3 Hardware IP Helps Drive Autonomous Vehicles Towards Production.

Percepio Tracealyzer for OpenVX allows you to visualize the execution of OpenVX applications and identify bottlenecks where optimization can make a big difference. Tracealyzer for OpenVX is initially available for Synopsys EV6x embedded vision processors, leveraging the built-in trace support in Synopsys ARC MetaWare EV Development Toolkit. Percepio Application Note PA-025 describes how to get started with Tracealyzer for OpenVX, using Synopsys EV6x processors and Synopsys MetaWare EV Development Toolkit.

Qualcomm has introduced the new Qualcomm Snapdragon 675 Mobile Platform. The Snapdragon 675 offers outstanding gaming, a leap in artificial intelligence (AI) capability and a cutting-edge camera. Premium features in the Snapdragon 675 are enabled by the Qualcomm AI Engine, Qualcomm Spectra ISP, Qualcomm Kryo CPU and Qualcomm Adreno GPU. A number of specific games and game engines have been optimized including Unity, Unreal, Messiah, and NeoX. Qualcomm Technologies also supports popular tools and APIs, including Vulkan, OpenGL 3.2, OpenCL, and Snapdragon profiler.

Magnum 2018.10 released with animation, web glTF player and Vulkan interoperabilityThe MIT-licensed C++11/C++14 engine Magnum released a new version with six months worth of changes. It has a new animation framework and provides initial Vulkan interoperability enabling users to take advantage of Magnum asset management pipeline for developing Vulkan applications. It also ships with both a native and a drag&drop web app that can play back complex glTF scene animations.

Neil Trevett, President of the Khronos Group, delivers the presentation "Update on Khronos Standards for Vision and Machine Learning" at the Embedded Vision Alliance's September 2018 Vision Industry and Technology Forum. Neil Trevett shares updates on recent, current and planned Khronos standardization activities aimed at streamlining the deployment of embedded vision and AI. For the full version of this video, along with hundreds of others on various embedded vision topics, please visit the Embedded Vision website.

The next WebGL/WebVR Meetup to be held at the SVVR HQ in Mountain View on November 1st. Lots of great talks and speakers including: Browser Implementor Update - representatives from Google Chrome, Mozilla and Safari will be on-hand and giving us an update on recent browser improvements; Brandel Zachernuk, Gregor Lakner (Axum Graphics); Romain Guy and Philip Rideout (Filament); Xiaohan Zhang, interactive works and Yağız Mungan.

Au-Zone NNEF converter appears in NNEF Tools on GitHubKhronos Group contractor Au-Zone has added their NNEF converter to the Khronos Group NNEF Tools repository. There are now two sets of converters in this repository. The converters provided by the Khronos Group convert between Caffe and TensorFlow. The Caffe converter reads/writes models in protobuf format, while the TensorFlow converter reads/writes the Python script that builds the TensorFlow graph. The converters provided by Au-Zone convert between Caffe2 and TensorFlow, both reading/writing models in protobuf format.

Mozilla is committed to the next wave of creativity in the open Web, in which people can access, create and share immersive VR and AR experiences across platforms and devices. Together with the Khronos Group and developers of existing open source Blender tools, we are providing a complete GL Transmission Format (glTF) import and export add-on for Blender, offering a powerful and free round-trip workflow for WebXR creators. This effort builds on the work of existing open source tools, and adds support for the newest Blender and glTF features. The tool itself along with further technical details will be available in the coming weeks. The blueprint for the collaboration model that allowed us to get there already exists. This article will explain how we got there, how this model works, and why it can accelerate the ecosystem.

LunarG now delivers native Ubuntu Linux packages for all the elements in the Vulkan SDK in addition to the Linux SDK tarball. Follow the Ubuntu Packages link on the LunarXchange SDK web page to gain access to the native Ubuntu Linux packages. These packages will install pre-built SDK binaries on a system running Ubuntu Linux and contain all the LunarG Vulkan SDK components at the latest available version. For Ubuntu Linux users, this is the most convenient way to get the Linux SDK content since you will not need to build any binaries yourself. Headers, libraries, and tools are included and prebuilt. Read the LunarG blog for more details.

The Adobe Animate team just announced the latest version of Adobe Animate CC. Animate CC 2019 enables 2D animators to use their existing skills for creating VR experiences (beta), introduces a new WebGL-based runtime (beta), export to GL transmission format (glTF), significant performance enhancements to the HTML Canvas output and more.

NXP delivers a wide range of processing solutions on which machine-learning (ML) applications can run. Developers will need the associated software and tools to make them work and this is where eIQ framework and development tools come into play. The eIQ framework is designed to work with hardware abstraction layers like OpenCL, OpenVX, and the Arm Compute Library, as well as inference engines like the Arm NN (neural net), Android NN, GLOW, and OpenCV.

The AMD Developer Tools team has been busy working on many new tools, some of which replicate functionality found in older versions of CodeXL. To limit confusion for our users, several major components have been removed from CodeXL. Graphics Frame Analysis for DirectX 12 and Vulkan applications have been removed and can now be found in the following AMD and third-party tools: Radeon GPU Profiler, RenderDoc, Microsoft PIX.