AMD released three updates this week with Vulkan improvements: The 18.12.2 Radeon driver, Vulkan Memory allocator and the AMDVLK open-source Vulkan driver. The AMDVLK 2018.Q4.4 update enables some additional features to allow up to 5% performance gains for tessellation workloads, enables the atomic optimizer, updates the Vulkan headers against v1.1.94, enables primitive under estimation for VK_EXT_conservative_rasterization, and has a number of fixes. The Vulkan Memory allocator sees many major changes including the addition of structure member VmaVulkanFunctions::vkCmdCopyBuffer. And finally the Radeon Software Adrenalin 2019 Edition 18.12.2 sees improved Vulkan support with 3 new extensions: VK_EXT_inline_uniform_block, VK_KHR_swapchain_mutable_format, VK_EXT_scalar_block_layout. Additionally Sparse Support is enabled.
The Khronos Group OpenCL API is a SIMD programming model which maps well to the GPU but mostly bypass the fixed graphics-specific logic. The latest Radeon GPU Profiler 1.4 (RGP) now has the ability to profile OpenCL workloads in RGP. Most of the major RGP features that you’re used to using for profiling graphics workloads generated by Vulkan and DirectX 12 are there when profiling OpenCL applications, including the workload and barrier overviews.
This Rust crate by @gwihlidal, a Senior Rendering Engineer II at Electronic Arts (EA), provides an FFI layer and idiomatic rust wrappers for the AMD Vulkan Memory Allocator (VMA) C/C++ library. Designed to help game developers to manage memory allocations and resource creation by offering some higher-level functions. vk-mem is Cross-platform: Windows, Linux and macOS (MoltenVK).
New post on Gamasutra, "Explicit resource state management and synchronization is one of the main advantages and main challenges that modern graphics APIs such as Direct3D12 and Vulkan offer application developers. It makes parallel command recording very efficient, but getting state management right is a challenging problem. This article explains why explicit state management is important and introduces a solution implemented in Diligent Engine, a modern cross-platform low-level graphics library."
In a recent update, Diligent Engine now gives applications direct control of state transitions in Vulkan API and DirectX12. Diligent Engine includes support for Vulkan and OpenGL 4.2 on Win32 and Linux, as well as OpenGL ES 3.0 on iOS and OpenGL 4.1 on macOS.
Students of Patrick Cozzi, glTF Working Group Chair, in the GPU course at University of Pennsylvania will be live streamed Monday, December 10, at 6pm EST. The students have built final projects with everything from WebGL to Vulkan to CUDA to DXR - ranging from photon mappers to water sims to feature detection algorithms. Many of the projects use glTF for models.
The Khronos Group was in Japan this week for SIGGRAPH Asia 2018. There were five BOF sessions covering Vulkan, OpenXR, WebGL, glTF, NNEF, OpenVX and OpenCL. Most of the presentations from these sessions is now online and we have lots of photos as well. Unfortunately not video this year.
Ventuz has released a white paper detailing why they are support glTF 2.0. With Ventuz release 6.1, they have implemented a glTF importer, and with 6.2 we have added full support of glTF animations. Why are we embracing the new file format? Download the whitepaper to find out! Free registration is required.
AImotive has released its aiSim2 simulator to significantly upgrade the speed and quality of testing and validating self-driving solutions. aiSim2 is the next generation of the award-winning aiSim1, powered by a purpose-built engine that ensures a high level of physical realism, deterministic running alongside optimized hardware utilization and flexibility. aiSim2 is built on AImotive’s experience developing aiDrive, a full stack self-driving software solution. The new simulator offers flexibility and scalability by being hardware agnostic, utilizing The Khronos Group’s Vulkan API to maximize portability and flexibility to enable efficient execution on a wide range of single and multi-GPU system configurations.
To further its goal of passing trained frameworks to embedded inference engines, the Khronos Group adds to its existing converters with two new bidirectional converters. Now available on the NNEF GitHub, these new tools enable easy conversion of trained models, including quantized models, between TensorFlow or Caffe2 formats and NNEF format.
Alibaba's datacenter uses Xilinx FPGAs to accelerate billions of transactions for shoppers and Microsoft, in a recent announcement, said it would deploy Xilinx in its datacenter as well. This is good news for OpenCL, as Xilinx FPGA acceleration includes support for high-level programming languages and tools, including C, C++, and OpenCL.
Artifact is now available with launch-day support for Linux, macOS, and Windows. Artifact is a competitive digital card game. The game is targeting Dota 2 players as well as card gaming enthusiasts. Vulkan support on macOS is done through MoltenVK.
Intel’s open-source programming function computer vision library OpenCV has released the first stable version in its 4.0 line. Release highlights list the dnn module now includes experimental Vulkan backend, and the popular Kinect Fusion algorithm has been implemented and optimized for CPU and GPU using OpenCL.
Basemark has releases version 1.1 of the its multi-platform graphics hardware evaluation tool Basemark GPU for enthusiasts and professionals alike. Basemark GPU 1.1 Benchmark offers unparalleled, objective comparisons between Vulkan, OpenGL, OpenGL ES and now DirectX 12 for graphics performance analysis across both mobile and desktop platforms.