AMD has announce it will start rolling out in January an open source set of tools called GPUOpen. The "All Open" stack will contain open source modules for two parallel stacks, each containing modules for OpenGL graphics, motion video codecs, and OpenCL GPU computation. The "Professional/Gamer" stack will include the open source motion-video module and a closed source OpenGL module. Its final OpenCL module will support both OpenCL and Vulkan. Linux will gain access to a full open source, high-performance driver stack, with the only constraint being that developers must use Vulkan instead of the older OpenGL.
Neil Trevett, President of the Khronos Group recently spoke at the 2015 Q4 Q4 2015 Embedded Vision Alliance Member Meeting on December 9, 2015 in San Jose. This is the slide presentation from that talk.
Most flows use EGL to facilitate the sharing of objects between multiple client APIs, requiring the Khronos extension CL_KHR_EGL_IMAGE. The examples in this PowerVR Imaging Framework installment from Imagination Technologies show the different zero-copy flows supported.
The International Workshop on OpenCL (IWOCL) has posted their December 7th 2015 news roundup. Be sure to take a look at this extensive list, and update IWOCL if anything is missing.
It's been a very busy few weeks for the Khronos Group chapters. We've added three new chapters: Paris France, Washington DC and Wroclaw Poland. There is a good selection of upcoming meetups as well:
- Computer Graphics on the Web: Dec 8, 2015 - Melbourne, Australia
- First Khronos Wroclaw meetup + VR: Dec 9, 2015 - Wroclaw, Poland
- Image Processing with WebGL: Dec 10, 2015 - London, Britain
- WebGL Developers Meetup: Dec 17, 2015 - Milano, Italy
- OpenGL for beginners part 1: Jan 06th, 2016 - Naritaweg, Amsterdam
Errata: We originally said Seattle Washington... our mistake, our latest chapter is in Washington DC.
We are glad to announce the availability of Intel SDK for OpenCL Applications 2015 R3 with awesome new features! We made significant progress in the quality and ease of use. You can proceed straight to downloading the Intel SDK for OpenCL Applications 2015 R3.
Avtech Scientific announces cooperation with IBM and NVIDIA to ensure optimal productivity and smooth user experience of its OpenCL-based open source multiphysics simulation software - Advanced Simulation Library on vendors' hardware platforms.
The Wireless Innovation Forum announced the release and public availability of three new reports and the best paper from the recent WInnComm-Europe 2015. The International Coordinating Committee on International SCA Standard’s (CC SCA) “Business Models for New Entrants in the SDR Tactical Radio Market,” and the Spectrum Sharing Committee’s (SSC) “SSC WG4 Certification Process” and “Interim SAS to CBSD Protocol Technical Report-A” were approved for public release by Forum members recently. The paper “Using OPENCL to increase SCA application portability,” by Steve Bernier, François Levesque and Martin Phisel (NordiaSoft, Canada) and David Hagood (Aeroflex, USA) was presented at the recent WInnComm-Europe 2015 and awarded best paper on 8 October.
Inspur Group and the FPGA chipmaker Altera today launched a speech recognition acceleration solution based on Altera's Arria® 10 FPGAs and DNN algorithm from iFLYTEK, an intelligent speech technology provider in China, at SC15 conference in Austin, Texas. The deep learning speech recognition acceleration solution leverages an Altera Arria 10 FPGA, iFLYTEK's deep neural network (DNN) recognition algorithms and Inspur's FPGA-based DNN parallel design, migration and optimization with OpenCL.
Jon Masters, a chief ARM architect at Red Hat has talked to FPGA makers about starting an initiative to define a programming interface for FPGA accelerators, probably based on OpenCL. Such an interface should include standard drivers that support PCI Express virtualization and be available for download on system boot up. IBM and Xilinx announced a multi-year strategic collaboration to jointly develop FPGA accelerators for OpenPower systems that target data centers and network function virtualization for carriers. They are collaborating on a cloud-based service for FPGA acceleration and will work on enabling programming FPGAs in C, C++ and OpenCL