This podcast episode of “The Interview” with The Next Platform focuses on an effort to standardize key neural network features to make development and innovation easier and more productive. To explore this topic, The Next Platform was joined by Neil Trevett. Listen to the podcast and read the write up.
NNEF and ONNX are two similar open formats to represent and interchange neural networks among deep learning frameworks and inference engines. At the core, both formats are based on a collection of often used operations from which networks can be built. Because of the similar goals of ONNX and NNEF, we often get asked for insights into what the differences are between the two. Read the Khronos blog to learn more about the similarities and differences between NNEF and ONNX.
Khronos member Renesas Electronics has outlined their plans for ADAS and self-driving cars. Renesas is working with Codeplay Software Ltd., experts in high-performance compilers and software optimization for multi-core processing. The collaboration allows programs already written in CUDA for Nvidia’s SoC to be brought to R-Car SoCs, using Codeplay’s OpenCL open standard-based software framework. The framework, first made available on R-Car H3 as a proof of concept, is now coming to the R-Car V3M and other R-Car SoCs of Renesas’ autonomous platform for both ADAS and automated driving.
Khronos announced the conformance program for OpenGL 4.6 and Intel has successfully passed conformance tests for its GPU models for the Mesa Linux driver. For specifics on the conformant hardware you can check the list of conformant OpenGL products at the Khronos website. Learn more about these drivers and the OpenGL conformance tests and why they are important to you.
The Khronos™ Group, an open consortium of leading hardware and software companies creating advanced acceleration standards, announces the launch of the OpenGL® 4.6 Adopters Program to enable implementations to become officially conformant to the latest generation OpenGL specification. The significantly enhanced OpenGL 4.6 Conformance Test Suite used in the Adopters Program has been released in open source on GitHub to enable industry participation in testing and ongoing conformance test suite improvements. General information on Khronos Adopters Programs can be found here.
Unreal Engine 4.19 preview has a experimental importer for glTF. This is an open format, that, once final, should work better than FBX, and actually work great with Blender. The Unreal Engine forums mentions that "Right now its much superior to FBX for some simple cases. The cool point about glTF is that the same file holds a full scene, with multiple 3d objects, each of them with animation, and each of them with materials, and each material actually imports as a material graph, and with textures." Take a look and tell us what you think.
The Khronos Group will be at GDC & VRDC 2018. Be sure to mark us in your calendar for the Khronos Dev Day on March 19th in Moscone, West Hall, Room 3022. This years sessions are now posted and include WebGL, glTF, OpenXR and Vulkan. Be sure to book mark the Khronos GDC event page and checkout some of our other upcoming events and meet ups.
Codeplay has written up a detailed run through of how they how they ensure C++ fundamental types are translated correctly from SYCL code through to OpenCL, retaining their correct size and signedness.
If you're an application developer, this will help you learn a little about how SYCL works under the hood. If you're looking to implement SYCL, this will help you find a way to get the compiler to do your lifting for you.
While current generation Linux games with current Linux GPU drivers using the Vulkan API rather than OpenGL may not be significantly faster with higher-end hardware right, the impact of this newer Khronos graphics API tends to be more profound on lower-end hardware, especially when it comes to lightening the load on the CPU. Following recent Pentium vs. Ryzen 3 Linux gaming tests, Phoronix carried out some fresh benchmarks looking at OpenGL vs. Vulkan on the Ryzen 3 1200 quad-core CPU with NVIDIA and Radeon graphics.
Imagination Technologies announces the PowerVR CLDNN SDK for developing neural network applications on PowerVR GPUs. The neural network SDK makes it easy for developers to create Convolutional Neural Networks (CNNs) using PowerVR hardware. CLDNN sits on top of OpenCL making use of OpenCL constructs so it can be used alongside other custom OpenCL code. It uses standard OpenCL memory, so it can be used alongside standard OpenGL ES contexts. Learn more about CLDNN and download the SDK today.
The Khronos recently announced SYCL 1.2.1. The SYCL 1.2.1 specification has improved on the existing 1.2 standard by introducing new features which allow for better integration with existing machine learning and OpenCL-based frameworks such as TensorFlow as well as various improvements based on user feedback. This is an exciting piece of news for Codeplay is it enables them to work towards full compliance of SYCL 1.2.1 for ComputeCpp, and their v0.5 release which is now available to download. Read more about how Codeplay is using SYCL 1.2.1 with ComputeCpp v.0.5.0.
This three-day training provides a comprehensive introduction to modern OpenGL development. The course begins with basic concepts and includes all the fundamental topics needed to develop flexible, high performance OpenGL code that can run on the desktop and embedded / mobile devices. Key techniques including lighting, texturing, framebuffer objects and transformations are introduced, in a format suitable for any developer working in C or C++. For more information including how to register, or to discuss other OpenGL and related trainings offered by KDAB, please get in touch via the web page.
Startup Sketchfab is taking one of its biggest steps yet today and launching features so that users can buy and sell 3D objects. The company is supporting the industry standard glTF as its download format, which should make it easy for creators to take the objects purchased from the site and import them into creativity software.