NXP delivers a wide range of processing solutions on which machine-learning (ML) applications can run. Developers will need the associated software and tools to make them work and this is where eIQ framework and development tools come into play. The eIQ framework is designed to work with hardware abstraction layers like OpenCL, OpenVX, and the Arm Compute Library, as well as inference engines like the Arm NN (neural net), Android NN, GLOW, and OpenCV.
The 2018 X.Org Developer's Conference (XDC2018) videos have now been posted online. XCD 2018 saw many Khronos members sponsor this conference, including Igalia, AMD, Arm, COLLABORA, Google, NVIDIA, Intel and Valve. The talks covered Vulkan, OpenGL, OpenGL ES, OpenCL, SPIR-V, GLSL and OpenXR. We've compiled a list of all the videos discussing these Khronos standards here, or you can watch all the videos from the conference on the X.Org Foundation YouTube channel.
Khronos has formed a liaison agreement with the Open Geospatial Consortium (OGC) in the interest of jointly advancing open geospatial standards related to AR and VR, distributed simulation, and 3D content services. The liaison will let Khronos and OGC assess standards in these fields as well as identify future potential standards that will facilitate interoperability and hardware capabilities of relevant data sharing and analysis. The collaboration will occur through working groups, forums, workshops, committee activities, etc., and OGC will adopt Khronos standards where appropriate.
During the two weeks of October 17-26, Neil Trevett, president of the Khronos Group, will visit a few cities in China to speak at local conventions, universities and member companies. Khronos is looking forward to meeting with local Khronos members, academias and the developer community, to share the latest updates about Khronos APIs. A complete list of public talks at conferences and free public sessions & registration is now online.
A libre-licensed software implementation of Vulkan has started up again. Originally started in c++ in 2017, for a reimplementation Rust has been chosen for its concurrency and memory-safety features, and Rust's LLVM support makes it highly portable. With OpenGL having both llvmpipe and MesaGL for fallback and testing purposes, it seems strange that there does not exist a corresponding Reference Implementation for Vulkan: the only implementations available are in hardware, making it extremely challenging for anyone considering entering the market. Kazan helps fill that gap. Sponsorship of this entirely libre-licensed project welcomed.
NVIDIA has released the new VRWorks Graphics SDK V3.0 for application and headset developers along with the NVIDIA display driver 411.63, both updated for NVIDIA's new Turing GPU generation. The drivers are available for download and the SDK has been posted. The SDK includes an OpenGL sample to demonstrate Turing's “Variable Rate Shading” (VRS) feature showing how to vary fragment load across the screen, e.g. for foveated rendering. Another sample demonstrates Turing's “Multi-View Rendering” (MVR) feature by showing how to render the same scene from different viewpoints. There are Vulkan versions of the samples too.
Khronos has released a provisional Vulkan Memory Model Specification that includes extensions for Vulkan, SPIR-V, and GLSL and gives Vulkan developers additional control over how their shaders synchronize access to should cooperate safely over memory operations in a parallel execution environment. In tandem with the extension specification, Khronos has released memory model extension conformance tests to enable implementers to do early tests on their shader compilers to ensure that the specified memory synchronization is implemented correctly. The memory model will have an Alloy description of the extension functionality to enable formal modeling and experimentation.
European Union-funded researchers have today released a tool suite which enables developers to deliver longer battery life in mobile devices, while ensuring high quality and performance. The LPGPU2 tool-suite helps programmers develop power-efficient code for GPUs by identifying bottlenecks relating to performance (for example in terms of frames-per-second) and power (for example in terms of energy per instruction). The LPGPU2 tool suite has benefited from the expertise of a range of academic and industrial partners including Khronos members Samsung, who designed and implemented the data collection frameworks and feedback engine; Think Silicon validated it on their four-core NEMA GPU system and Codeplay extended AMD’s CodeXL tool, allowing programmers to profile their SYCL applications. Download the tool suite from the GitHub repository.
Vulkan multi-GPU support was announced by Khronos in March 2017 but it wasn’t until Vulkan 1.1 was released in March this year that explicit multi-GPU support was added to the API. Now the first AAA game to support multi-GPU in Vulkan has been released - the action-packed Strange Brigade for PC.