The latest update of the AMDVLK Open Source Vulkan driver sees several notable additions. The driver now officially supports VK_EXT_host_query_reset, VK_EXT_separate_stencil_usage, and VK_KHR_uniform_buffer_standard_layout extensions and updates the Vulkan API headers against version 1.1.108. Read more about this update at Phoronix or download the driver on GitHub.
Intel has released their 184.108.40.20661 graphics drivers. OpenGL has been bumped to 4.6, which adds an extension to use Vulkan’s SPIR-V shaders in OpenGL. Vulkan has been given four new extensions: VK_EXT_depth_clip_enable, VK_EXT_host_query_reset, VK_EXT_scalar_block_layout, and VK_KHR_shader_float16_int8. The OpenCL kernel compile times have been reduced.
NVIDIA Tech Blog: Learn more about machine learning acceleration in Vulkan with cooperative matrices by NVIDIA experts. If the Cooperative Matrix Vulkan extension is interesting to you, you can try it out right now! It is shipping for Turing-based GPUs in NVIDIA driver versions 419.09 (Windows) and 418.31.03 (Linux). Links to all the relevant specifications are here.
Yesterday AMD developers did their first AMDVLK open-source push of 2019. That first update in nearly a month updated against the Vulkan 1.1.96 headers, added GPU memory references to software compositing images, clean-ups for the barrier handling, various PAL and LLPC fixes, and other changes. Based upon that source code state from yesterday, an Ubuntu Debian package is now available of just the Vulkan driver and validated for at least 16.04/18.04 installations but should end up working too for e.g. 18.10. Read the entire story on Phoronix.
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.
Intel’s driver team has published a new graphics driver for all recent GPUs (Intel 6th, 7th and 8th Gen processors) on Windows 10. This driver version exposes Vulkan 1.1.82, and continues to support OpenGL 4.5, exposing the same OpenGL support as v4944 (245 OpenGL extensions). Direct download from Intel is here.
Intel announces the Windows Graphics Driver Version 220.127.116.1125. Included in this update is support for Vulkan 1.1. Platforms include 6th, 7th and 8th Generation Intel Core processor family as well as Apollo Lake and Gemini Lake.
Khronos announced the conformance program for OpenGL 4.6 and Intel has successfully passed conformance tests for its GPU models for the Mesa Linux driver. For specifics on the conformant hardware you can check the list of conformant OpenGL products at the Khronos website. Learn more about these drivers and the OpenGL conformance tests and why they are important to you.
To coincide with the release of OpenGL 4.6, NVIDIA is pleased to announce the immediate availability of our OpenGL 4.6 beta drivers for Windows and Linux. These drivers provide full OpenGL 4.6 and GLSL 4.60 functionality and also add support for the GL_KHR_parallel_shader_compile extension released today. This beta release is based on the published OpenGL 4.6 Khronos Specification, and is expected to pass the OpenGL 4.6 Khronos Conformance Testing Process when available. Current conformance status can be found online. Further details and driver downloads are available at the NVIDIA OpenGL driver website.
The Vulkan working group has released a major Vulkan 1.0 specification update that adds eighteen new KHR extensions. They include KHR replacements for the experimental KHX_external_memory_* and KHX_external_semaphore_* extensions released earlier this year, incorporating changes based on developer and implementer feedback. The release also adds a set of KHR_external_fence_* extensions. Together, these extensions allow applications to share memory and synchronization primitives across process and API boundaries. Two new extensions, KHR_dedicated_allocation and KHR_get_memory_requirements2, provide more expressive and extensible ways for applications to optimize their GPU memory allocation policies. KHR_16bit_storage, KHR_storage_buffer_storage_class, and KHR_variable_pointer allow Vulkan implementations to accept shader programs containing new programming constructs recently added to the SPIR-V intermediate shading language.
NVIDIA graphics driver for Windows version 378.66 is now offering some OpenCL 2.0 support. From the release notes: “New features in OpenCL 2.0 are available in the driver for evaluation purposes only.” Some known issues include: The current implementation is limited to 64-bit platforms only; OpenCL 2.0 allows kernels to be enqueued with global_work_size larger than the compute capability of the NVIDIA GPU. The current implementation supports only combinations of global_work_size and local_work_size that are within the compute capability of the NVIDIA GPU; For executing kernels (whether from the host or the device), OpenCL 2.0 supports non-uniform ND-ranges where global_work_size does not need to be divisible by the local_work_size. This capability is not yet supported in the NVIDIA driver, and therefore not supported for device side kernel enqueues.
Intel now has drivers certified for the most advanced versions of all three open industry-defined 3D graphics APIs on Linux: OpenGL 4.5, OpenGL ES 3.2 and Vulkan 1.0. OpenGL 4.5 certification was announced 3 February 2017 on the Khronos Group’s Conformant Product page.
NVIDIA 378.09 beta driver has aded support for the Vulkan extensions VK_KHR_display and VK_KHR_display_swapchain. OpenGL threaded optimizations is enabled by default in the driver, as well the driver has added support for the ARB_parallel_shader_compile extension to allow multi-threaded compilation of GLSL shaders.