News Archives

The Khronos Group announces the release of the Vulkan 1.1 and SPIR-V 1.3 specifications. Version 1.1 expands Vulkan’s core functionality with developer-requested features, such as subgroup operations, while integrating a wide range of proven extensions from Vulkan 1.0. Khronos will also release full Vulkan 1.1 conformance tests into open source and AMD, Arm, Imagination, Intel Corporation, NVIDIA and Qualcomm have implemented conformant Vulkan 1.1 drivers.

Vulkan now ships natively on almost all GPU-enabled platforms, including Windows 7, 8.X, 10, Android 7.0+ and Linux, plus Khronos recently announced open source tools to enable Vulkan 1.0 applications to be ported to macOS and iOS. Vulkan has widespread support in leading games engines including Unreal, Unity, Source 2 from Valve, id Tech, CroTeam’s Serious Engine, CryEngine, and Xenko. Vulkan is being used in over 30 cutting-edge games on diverse desktop and mobile platforms, including Doom, Quake, Roblox, The Talos Principle, Dota 2, and is the exclusive API used in AAA titles such as Wolfenstein II and Doom VFR.

Read the press release and learn more about the Vulkan 1.1 specification and associated tests and tools on the Vulkan home page.

New functionality in Vulkan 1.1 includes Subgroup Operations that enable highly-efficient sharing and manipulation of data between multiple tasks running in parallel on a GPU. Khronos member and guest author Neil Henning (@sheredom), Principal Software Engineer, for Vulkan & SPIR-V at Codeplay Software has written an in-depth tutorial on how to use this new feature. Head on over to the Khronos blog and check out the tutorial. Feedback is welcome.

GSN Composer: Online GLSL shader editorThe GSN Composer is an online node-based visual programming environment that allows generating custom nodes using GLSL/WebGL. For every uniform variable that is created within the GLSL shader code editor, an input slot is automatically added to the corresponding shader node, which can be connected to other nodes of the dataflow graph. This makes online shader prototyping very fast and intuitive and frees the developer of writing many lines of support code to fill the GLSL uniform variables with values. The GSN Composer requires no login and is free-of-charge. All that is needed to get started is a web-browser and your creativity. Several simple GLSL examples are provided such that this tool is also suited as starting point for GLSL/WebGL beginners.

This blog will give a quick run through of the SYCL profiling features that have been developed in the latest version of LPGPU2 CodeXL. LPGPU2 CodeXL is not yet available to the public but it was made available to the LPGPU2 consortium during February 2018. It is the aim to make a version of CodeXL with SYCL profiling features available when the project is completed.

LunarG releases a new Linux/Windows SDK that supports Vulkan API revision 1.1.70, and is backward-compatible with Vulkan 1.0.70. The prior LunarG Linux/Windows SDK release supported Vulkan API revision 1.0.68. Read on for an overview of new features in the release and links to the release notes and the SDK. Refer to the release notes for driver and CMake requirements.

Registration now open for the Khronos Standards for Neural Networks and Embedded Vision workshop at the Embedded Vision Summit in Santa Clara. Early bird pricing is now $99. This seminar is intended for engineers, researchers, and software developers who develop vision and neural network applications and want to benefit from transparent HW acceleration. Also, managers that want to get a general understanding of the structure and uses of Khronos standards.

Buy your tickets today

Khronos Group announces two NNEF Request for Quotes (RFQ)The Khronos Group has posted two new RFQs, both for NNEF:

  • Caffe2 to NNEF Converter: The project will deliver Caffe2 to NNEF converter that receives a set of Caffe2 protobuf files and generates semantically and functionally equivalent NNEF container.
  • TensorFlow to NNEF Converter: The project will deliver a converter between Tensorflow and NNEF that receives a TensorFlow protobuf file and generates semantically and functionally equivalent NNEF container, and is able to convert the NNEF container back to a TensorFlow protobuf file which when executed in TensorFlow produces equivalent results with the original source of conversion (although the backward conversion may not result in a one equivalent to the original protobuf).
The deadline for submissions is March 29th.