News Archives

Khronos Vulkan Working Group Releases Shading Rate Extension to Increase Rendering Performance and Quality

The Vulkan Working Group has just released the VK_KHR_fragment_shading_rate extension, which provides a new, flexible technique to control the fragment shading rate, enabling developers to perform shading at a lower resolution than the render targets. This fine level of control allows developers to focus shading resources where they are needed, which ultimately increases rendering performance and quality.

NVIDIA’s NRD Real-time Denoiser Supports Vulkan Ray Tracing

NRD is an open sourced, spatio-temporal ray tracing de-noising library that’s designed to provide high-quality real time imagery with as few as 0.5 or 1 rays per pixel. NRD uses input signals together with environmental conditions to deliver results comparable to ground truth images. NRD supports diffuse lighting, specular lighting or reflections, and infinite light source shadows. The NRD library is fast, robust, and easy to integrate with Vulkan applications using ray tracing.

Microsoft Tech Community: Moving forward to OpenXR

What an amazing ride! Earlier this year, Microsoft and Oculus started shipping conformant OpenXR runtimes to all customers, with SteamVR previewing OpenXR support soon after. Since then, we’ve seen wide adoption of OpenXR across the industry: from the new RenderDragon engine in Minecraft to the WebXR implementation in Edge and Chrome – from Babylon Native to Blender 2.83. With OpenXR, you can build engines and apps that target HoloLens 2 with the same API that you use to target PC VR headsets, including Windows Mixed Reality headsets, Oculus Rift headsets and (currently in developer preview) SteamVR headsets. OpenXR lets engines write code once that’s then portable across hardware platforms from a wide range of VR and AR vendors. Learn more about Microsoft and OpenXR.

Unity ‘Accelerating efforts’ on OpenXR Support, Preview Expected by End of Year

Khronos member Unity has long been a public supporter of OpenXR, but the company has yet to deploy support for the standard. As a key figure in OpenXR (owed to it being one of the leading VR game engines), it’s good news today to hear the company affirm its commitment to the standard and say that it’s accelerating work to bring OpenXR to Unity. Learn more about these efforts by Unity.

Intel OpenGL/Vulkan Linux Drivers Strike Another Optimization For Tiger Lake

Intel merged a change to benefit Intel’s Iris Gallium3D (OpenGL) and ANV Vulkan drivers for making use of the HDC data cache for uniform buffer object (UBO) pulls on Gen12+ hardware, namely Tiger Lake at this point. By making use of the data cache for UBO pulls, there is generally up to another few percent improvements for various OpenGL and Vulkan games running on Linux—either natively or through the likes of the DXVK layer. Some improvements cited in the merge include:

  • GTA V DXVK 104.0%
  • Talos Principle GL 102.8%
  • Rise of Tomb Raider VK 102.8%
  • Dark Souls 3 DXVK 101.4%
  • Witcher3 DXVK 101.3%
  • Bioshock Infinite GL 100.5%
  • Doom 2016 VK 97.7%

RapidCompact aligned with Khronos 3D Commerce Real-Time Asset Creation Guidelines

DGG CEO Dr. Max Limper is co-chair of the Asset Creation TSG. DGG is happy to have had the opportunity to contribute to this effort and believes that these kinds of joined-up activities and achievements will support rapid growth in the industry. DGG has aligned the development of their RapidCompact platform with the Asset Creation Guidelines, so that RapidCompact users can optimize the 3D assets to match with the official publishing targets fully-automatically, without requiring 3D domain expertise. Learn more about DGG, RapidCompant, and how they are working with the Khronos Group 3D Commerce working group.

In December of 2019, LunarG conducted a Vulkan ecosystem survey. Many Vulkan developers shared their requests for improvements. LunarG took those suggestions to heart and created projects to address many of the developer suggestions from the survey. To learn more about the results of these projects, check out the LunarG report that itemizes key requests from the survey and reports on the status of those requests.

Blog: 3D Commerce Working Group Releases Real-time Asset Creation Guidelines to Assist Artists Create Efficient, Reliable Models for Retail and E-Commerce

The Khronos 3D Commerce™ Working Group was established with the goal of spearheading industry alignment on the creation, management and display of 3D content for e-commerce—and since its formation, the use cases for 3D assets in e-commerce have rapidly expanded. In response, the 3D Commerce Working Group has today released V1.0 of its Realtime Asset Creation Guidelines for use by 3D artists who are familiar with 3D workflows, but new to creating e-commerce 3D assets for cross-platform delivery. Learn more about the Real-time Asset Creation Guidelines.

One challenge to deploying 3D at scale lies in its interoperability, or rather, in its lack thereof. Whilst the dream is to create a fully end-to-end digital workflow made up of previously siloed platforms that now seamlessly integrate and communicate, the reality is that 3D tools today don’t play particularly well with others. This Spotlight offers a roadmap to achieving simple integration and subsequent seamless data flow to underpin a future digital supply chain. You can view all of the panel discussions here:

NVIDIA Blog: Preferring Compile-time Errors over Runtime Errors with Vulkan-hpp

Andreas Süßenbach, a senior software developer at NVIDIA, has posted a new developer tutorial on compile-time errors vs runtime errors with Vulkan-hpp. If you are using Vulkan, there are a few ways to create runtime errors. Even with the great validation layers available with Vulkan, you must run that part of the code to detect such errors. When you use Vulkan-hpp, a header-only C++ binding for the Vulkan API, some of those runtime errors are turned into compile-time errors. Read this tutorial to learn more.

Tutorial: Making the most of Arm NN for GPU inference: OpenCL Tuner

Arm NN is an open-source inference engine for CPUs, GPUs and NPUs. It bridges the gap between existing NN frameworks and the underlying IP. Arm NN is built on top of the Arm Compute Library (ACL). This contains a collection of highly optimized low-level functions to accelerate inference on the Arm Cortex-A family of CPU processors and the Arm Mali family of GPUs. For GPUs, ACL uses OpenCL as its compute API. The OpenCL memory model closely maps to the GPU architecture making it possible to implement optimizations that significantly reduce the accessing of global memory. Read on to learn how.


End of content

No more pages to load