Skip to main content

News Archives

Blender 2.78 comes with lots of improvements to the Cycles render engine, including support for CPU groups, support for Nvidia GTX 10×0, along with better support for Nvidia GTX 980 Ti and Nvidia Titan X GPUs, OpenCL and CUDA memory improvements.

Khronos is pleased to present a full-day workshop on Vulkan in the upcoming DevU in Seoul, Korea. This session will go in depth into Vulkan, providing you with an important overview, then quickly diving deep beyond the basics into its use and structure, followed by a few case studies with code walkthroughs. There will be ample opportunity to speak with the instructors both during, and after the event in a social get together. This DevU session will be taught by Khronos working group members who specialize in Vulkan and who participated in its creation. Beginners are welcome, but the session is intended for experienced developers with knowledge of 3D graphics and rendering. In addition to a full day of Vulkan training, the session will include all course materials, a Vulkan Quick Reference Guide, a Vulkan t-shirt, and a buffet lunch. For more information and to register your spot, please visit the DevU session page.

The recent announcement covers the new XM6 DSP, CEVA’s new set of imaging and vision software libraries, a set of new hardware accelerators and integration into the CDNN2 ecosystem. XM6 will support OpenCL and C++ development tools, and the software elements include CEVA’s computer vision, neural network and vision processing libraries with third-party tools as well.

The Khronos Group today issued a request for quotes to create a series of Vulkan tutorials that will demonstrate efficient use of the core Vulkan API across a range of GPU architectures. The tutorials must consist of example code and associated documentation. It should be possible to guide an audience of experienced 3D graphics developers through a given tutorial in a classroom environment within an hour. Details online here.

Don’t miss the Vulkan deep-dive webinar on Tuesday September 27th at 10am PDT. This one-hour webinar provides a detailed review of the Vulkan Validation Layers, how they are architected, how you use them, and why they are so important. The main presentation is followed by a Q&A session.

ArrayFire released v3.4 of their open source library of parallel computing functions supporting CUDA, OpenCL, and CPU devices. This new version of ArrayFire improves features and performance for applications in machine learning, computer vision, signal processing, statistics, finance, and more. Performance Improvements to JIT have resulted in up to 5x speed gains in OpenCL.

LunarG has launched a Vulkan Samples Tutorial on LunarXChange. The tutorial is organized into sections that walk you through the steps to create a simple Vulkan program. Each tutorial section corresponds directly to a sample program in the LunarG samples progression and is designed to be read as you look at and experiment with real code from the progression.

Codeplay is giving developers free, early access to ComputeCpp with a pre-conformance beta implementation of the SYCL open standard, along with an open-source preview of the latest Parallel Technical Specification to be adopted into C++17. Other open-source projects being made available are VisionCpp, a machine vision library demonstrating C++ techniques for performance-portability, and an early version of the Eigen C++ library that uses SYCL for acceleration on OpenCL devices.

Chakra GNU/Linux maintainer Neofytos Kolokotronis announced the availability of the latest software versions in the main repositories. Support for the latest Vulkan API is the largest addition along with updates to LibreOffice 5.2.1, Wine 1.9.18, Rust 1.11.0, FontConfig 2.11.94, systemd 231 init system, and Mesa 12.0.1 3D Graphics Library.

Loading...

End of content

No more pages to load