The Khronos Group is about to release a new standard method of moving trained neural networks among frameworks, and between frameworks and inference engines. The new standard is the Neural Network Exchange Format (NNEF™); it has been in design for over a year and will be available to the public by the end of 2017. Learn more about NNEF and the upcoming released in the Khronos blog post.
The Khronos Group has reached a cooperative agreement with the China Academy of Information and Communications Technology (CAICT), part of the Chinese National Research and Development Program. Under this agreement, CAICT and Khronos will work together to encourage and enable local Chinese companies to adopt Khronos international standards and benefit from becoming officially conformant.
Intel has announced the availability of a new Graphics driver, namely version 188.8.131.5249, which adds support for Microsoft Windows 10 Fall Creators update features. This update also resolves the intermittent crashes/hangs encountered in DOTA 2 (Vulkan version), enhances memory usage in OpenCL applications.
The Khronos Group has released Vulkan 1.0.65. As well LunarG has released their SDK to match. The following new extensions were added: VK_AMD_shader_image_load_store_lod; VK_AMD_shader_info; VK_EXT_global_priority as well as Updates to loader, layers, and documents.
The Khronos Milano Chapter is thrilled to renew the collaboration with Microsoft Italia, organizing the Fall Edition of Milan's most popular event showing the new frontiers for Virtual, Augmented and Mixed Reality technologies. On November 14, VR enthusiasts, advocates, creators, users and consumers will have the chance to experience a unique blend of networking, demonstrations of cutting edge technology and presentations by leading VR experts. Be sure to checkout the complete lineup of upcoming Chapter events.
Be sure to join AJ Guillon, Yetiware and Yassine Hariri, PhD, CMC Microsystems tomorrow November 8th for the webinar 'Introducing HCMP'. As heterogeneity increases, the gap between the application layer and the hardware layer increased as well. To reduce this gap, we introduce a heterogeneous computing middleware platform (HCMP), which provides middleware that significantly reduces the complexity of developing industrial-strength heterogeneous computing software. Complex tasks such as multi-device memory management, device I/O, kernel scheduling, and dependency management are handled by the platform so that users can focus on writing their applications instead of adhering to complicated specifications.
OpenCOLLADA for Maya 2018 on Windows 64 has been released. Version 1.6.59 was released on August 30th for Max 2018. Binaries are now provided for Max and Maya in versions: 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018. If you find any issues, please contribute on the OpenCOLLADA Github repository.
Join CMC Microsystems and AJ Guillon, chair of the Khronos OpenCL Safety Critical (SC) TSG and founder of YetiWare, on November 8th. This webinar will discuss how to reduce the gap between the application layer and the hardware layer by introducing a heterogeneous computing middleware platform (HCMP), which provides middleware that significantly reduces the complexity of developing industrial-strength heterogeneous computing software using an OpenCL programming model.
The Khronos Group will be holding a two hour tutorial at the Embedded Systems Conference '17 in December. Attendees will gain an understanding of the architecture of Khronos standards for computer vision and neural networks; getting fluent in actually using OpenVX and NNEF for real-time computer vision and neural network inference tasks.