Jetson TX1 is the first embedded computer designed to process deep neural networks. With 1 teraflops of performance, Jetson delivers exceptional performance for machine learning, computer vision, GPU computing and graphics, while drawing very little power. Jetson TX1 includes a comprehensive SDK for embedded visual computing, including VisionWorks, an implementation of the OpenVX 1.0.1 specification with additional NVIDIA extensions as well as support for the latest graphics drivers and APIs, including OpenGL 4.5, OpenGL ES 3.1 and Vulkan.
The slides from Khronos Group President Neil Trevett at SIGASIA 2015 are now online. The WebGL course slides from SIGASIA are also online, including: Building 3D Web Applications Using WebGL; Building Google Maps on WebGL; Intro to WebGL with Three.js and WebGL 2.0.
Khronos will be on the west side of the SC15 hall in booth #285. Technical experts will be available to answer your questions and there will be OpenCL 2.1 and SYCL reference guides to give away. The Khronos BOF "Flocking Together: Experience the Diverse OpenCL Ecosystem" starts off with an overview of the OpenCL 2.1 C++ kernel language, the SYCL 2.1 abstraction layer, and SPIR. Following the presentation, attendees are invited to bring their code and their toughest questions. Attendees will have the opportunity to experiment with implementations and tools from multiple vendors across several platforms. The BoF session is geared for those experienced with OpenCL, it will also provide an opportunity for newcomers to ask questions both basic and technical of our experts from the OpenCL working group as well as those from various participating vendors. Be sure to visit the Khronos DevU tutorial "Portable programs for heterogeneous computing: a hands-on introduction" on Monday November 16th. Details on all of these events and much more are available on the official Khronos event page.
Basemark announced a new product called Basemark GPU Vulkan. This benchmarking software enables the industry to objectively and reliably quantify and compare graphics and computing performance of next generation mobile and desktop processors compatible with the new generation Vulkan API from the Khronos Group. Basemark GPU Vulkan is developed in close cooperation with key player semiconductor companies, such as AMD, Imagination Technologies, Intel, NVIDIA, Qualcomm and Renesas within Basemark’s benchmark development program.
Imagination Technologies webinar series part II on Vulkan is now online. Vulkan is designed from the ground up with the idea of not being bottlenecked by the CPU, and provides huge efficiency gains over previous generation graphics APIs in this area. This webinar provides an overview of what mechanisms in Vulkan enable this, what this means in practice, and why it is so important for embedded and mobile devices. The episode was presented by Tobias Hector, Software Design Engineer for Vulkan and OpenGL ES, Imagination Technologies. Be sure to add November 19th to your calendar as the webinar series continues with 'Scaling to multiple threads'.
Cesium announce the release of Cesium 1.15. Highlights include: Support for glTF 1.0 and the KHR_binary_glTF and KHR_materials_common extensions. Also, updated the online model converter to output glTF 1.0; Decreased GPU memory usage in BillboardCollection and LabelCollection by using WebGL instancing; New CZML examples thanks to Tiff Lu and Adam Cole from the University of Pennsylvania.
Altera is demonstrating how its field programmable gate arrays (FPGAs) can enable system acceleration in trading and regulatory environments at the FIA Futures & Options Expo taking place November 3-5, 2015, at the Chicago Hilton (Green Hall, Booth #107). This industry event focuses on the technology requirements and critical issues associated with the financial derivatives market. Demonstrations at the Altera booth include include an OpenCL flow on an Arria 10 FPGA using the Altera SDK for OpenCL design tool running a Mandelbrot algorithm, video downscaling, and other applications.
The DesignWare® EV Family of vision processors consists of fully programmable and configurable IP cores that have been optimized for embedded vision applications, combining the flexibility of software solutions with the low cost and low power consumption of dedicated hardware. To speed application software development, the EV Processor Family is supported by a comprehensive software programming environment based on existing and emerging embedded vision standards including OpenCV and OpenVX, as well as Synopsys’ ARC MetaWare Development Toolkit.
The Brenwill Workshop Ltd. announced that they have added support for OS X to their MetalGL product, which seamlessly brings the performance of Metal to OpenGL ES games and applications on iOS, and now OS X. MetalGL is an implementation of the OpenGL ES 2.0 API that runs on Apple's Metal graphics framework on compatible iOS and OS X devices. MetalGL unleashes the power of Metal's low-latency rendering to let OpenGL ES games and applications perform up to 3x the number of draw calls, and benefit from the advanced tools available for the Metal development ecosystem, all without changing the way the game or app use OpenGL ES.
CSS-Tricks has a guest post by Matt DesLauriers on rendering SVG paths in WebGL. Matt discusses some of the tools and ideas involved in making it happen, as well as other approaches and other related concepts.