Khronos News

The Khronos Group recently announced a request for industry feedback to gauge interest in developing a new low-level, heterogeneous communications open standard that could transform the way applications are developed for High Performance Embedded Computing (HPEC) systems. If there is industry support, then Khronos would create a working group and invite any interested company to participate for a voice and a vote in creating and evolving a multi-vendor standard under Khronos’ proven multi-company governance process. Khronos encourages you to fill out the online survey to provide us your feedback, or email hetcommsfeedback@khronos.org if you would like to discuss getting involved.

Online Feedback Survey

Khronos has released OpenCL 2.2-10Khronos has released OpenCL 2.2-10. This maintenance release fixes multiple community reported issues, brings all KHR OpenCL extensions neatly into the Extensions spec, and adds support for the SPV_KHR_no_integer_wrap_extension. You will find the OpenCL 2.2-10 version of the specification in the Khronos Group OpenCL Registry.

Khronos announces newest Associate Member NSITEXEThe Khronos Group would like to welcome its newest Associate Member NSITEXE. In NSITEXE’s semiconductor IP, we realize a balance between performance and power that realizes compatibilities, and also support the quality aspects that meet automotive standard. We will supply a processor and development environment that you can use generically, from various industrial applications to smart home appliances.

Be sure to check out the first Boston meetup of the year hosted by Jim Susinno. One of my favorite applications for accelerated graphics is video games. I've been working on some simple games lately using OpenGL directly without any engines or frameworks - and it's fun! Let's discuss our game-making techniques and how to keep things as fast as possible - minimizing state changes and per-frame uploads, packing bits into channels, re-using data... playing to the strengths of the silicon as enabled by OpenGL. Pizza will be provided.

Adding Machine Learning based Image Processing to your Embedded Product with NNEFKhronos member Au-Zone Technologies has written a guest post on the CNX Embedded Software blog showing how to add Machine Learning (ML) processing to an embedded product with the help from the Khronos Groups Neural Network Exchange Format (NNEF). The post illustrates, with an example implementation, how to detect and classify different pasta types on a moving conveyor belt.

Members

Khronos members are individuals, companies and academic institutes from around the world shaping the standards that are driving the world.

  • Khronos on Github
  • Khronos Blog
  • Khronos Reference Cards
  • Khronos Bookstore
  • Khronos Merchandise Store