Three new Vulkan samples have been released in the past month: HPP Instancing Sample - NVIDIA provides a transcoded Instancing Sample that illustrates the usage of the C++ bindings. Portability Sample - Holochip presents a tutorial demonstrating the use of the VK_KHR_portability_subset extension. Graphics Pipeline Libraries - Sascha Williams brings us this tutorial on the VK_EXT_graphics_pipeline_library extensions that allows separate compilation of different parts of the graphics pipeline. With this it’s now possible to split up the monolithic pipeline creation into different steps and re-use common parts shared across different pipelines.
At the recent GTC 2022 Conference NVIDIA released multiple initiatives to boost the productivity of Vulkan developers. The new NVIDIA Nsight Systems 2022.2 system-wide performance analysis tool supports the new Vulkan graphics pipeline library extension and Vulkan memory operations. NVIDIA’s new Streamline open-source, cross-IHV framework can be used to integrate multiple super-resolution technologies into Vulkan games and applications. And lastly, NVIDIA’s new Cloud Playtest virtual development environment that builds on GeForce NOW infrastructure enables the coordination and observation of playtests for Vulkan games without physical hardware or presence.
GPU Performance API (GPUPerfAPI) is a powerful library providing access to GPU Performance Counters to help analyze the performance and characteristics of applications using a Radeon GPU. GPUPerfAPI v3.11 adds support for raytracing counters in Vulkan on RDNA2 (Radeon RX 6000 Series) hardware: RayTriTests, and RayBoxTests: These counters collect the number of ray intersections for triangles and boxes, respectively. TotalRayTests: This counter collects the aggregated number of ray-box and ray-triangle intersection tests. RayTestsPerWave: This counter collects ray intersection test count at a more granular level – per wave.
Join us to help drive the evolution of Machine Learning acceleration standards. ML developers lament the growing fragmentation in the ML ecosystem. Khronos knows that open and royalty-free standards can play an essential role in reducing fragmentation, reducing costs, and providing the industry participants the opportunity to grow. Based on feedback from previous summit and discussions, Khronos is creating a coalition of interested parties to meet the needs of the ML community for hardware acceleration.
Vulkan Portability aims to counter platform fragmentation by encouraging layered implementations of Vulkan functionality over Metal, DX12, and other APIs. Vulkan Portability enables Vulkan applications to be reliably deployed across diverse platforms. Khronos released a provisional version of Vulkan Portability Extension 1.0 in September 2020. The VK_KHR_portability_subset extension allows a non-conformant Vulkan implementation to be built on top of another non-Vulkan graphics API and identifies the difference between that implementation and a fully-conformant native Vulkan implementation. The extension is detailed in the Vulkan Specification. For already released applications that are expecting to see only fully Vulkan conformant devices, a backward-compatibility issue exists. To solve the backward-compatibility issue, Khronos has released the new Vulkan Loader extension, VK_KHR_portability_enumeration. The purpose of this extension is to enable or disable enumeration of portability (non-conformant) implementations.
Khronos has introduced a new extension named VK_EXT_graphics_pipeline_library that allows for shaders to be compiled much earlier than at full Pipeline State Object (PSO) creation time. By leveraging this extension, I was able to avoid many causes of frame hitches due to PSOs being late-created at draw time in the Source 2 Vulkan renderer. The extension spec was released today and SDK support will follow soon, you can track the release status at https://github.com/KhronosGroup/Vulkan-Docs/issues/1808.
A new blog from Collabora shows the latest utilities and helpers to make writing Vulkan drivers easier and demonstrates the latest Mesa best practices.
With the release of Mesa 22.1, Lavapipe exposes Vulkan 1.3 for running atop CPUs.
The Advanced Media Framework SDK provides developers with optimal access to AMD GPUs for multimedia processing. In the latest release, v1.4.24.0, AMD has enabled Vulkan support for HEVC Encoder (Navi+) and have improved H264 encoding on Vulkan for both Windows & Linux Navi+.
Basemark launched GPUScore, an all-new GPU performance benchmarking suite to produce the most professional measurements in the industry. GPUScore will consist of three different testing suites. The first one is GPUScore: Relic of LIfe compares Vulkan and DirectX accelerated ray tracing performance.