Tech Source, Inc. has announced a conduction cooled and rugged version of its Condor 3000x XMC processor targeted at general purpose graphics processing unit (GPGPU) applications. The Condor 3000x-cc XMC card is based on the AMD RadeonTM E6760 AIB. With 576 GFLOPs of peak single precision floating point performance and 480 individual processing units (shaders), the Condor 3000 graphics processor is particularly well suited for highly parallel computations and other GPGPU applications such as image analysis, radar, sonar, and video surveillance.
At GDC, SemiAccurate sat down with Andrew Richards of Codeplay to talk about OpenCL’s past, present, and future. The results went in directions we had not been anticipating, especially surrounding the future directions of the language. The video of the interview is available on the SemiAccurate website. The Khronos Group YouTube channel also has a good select of video interviews, including one with Andrew Richards.
Marketing Manager for Intel HD Graphics demos several examples of how the Intel SDK for OpenCL Applications 2012 supports 3rd generation Intel Core processors on both Intel Processors and HD graphics 4000/2500 for accelerated video processing.
The Khronos Group has posted video presentations from Barcelona. Speaking in Barcelona were Neil Trevett, Khronos Group President, Erik Noreke, Kristof Beets from Imagination Technology, Enrica Filippi from ST-Ericsson and Sri Kannan Iyer from ARM. A complete presentation list, photos and video list is also available from the Khronos event page.
Adobe announced that they will be using their newly enhanced Adobe Mercury Playback Engine that incorporates OpenCL heterogeneous compute for the very first time on a number of Apple MacBook Pro laptops with AMD Radeon graphics.
AMD announced it has invested in Nuvixa, Inc, a developer of gesture-based video communication and presentation solutions. Using depth-sensing camera technologies, the Nuvixa StagePresence immersive video presentation tool extracts a presenter from virtually any background environment, and embeds their live video persona within any compatible digital desktop or slide content. Image processing enhancements are only available with OpenCL and AMD accelerated processing units (APUs). This technology creates immersive performance and quality improvements and experience to online audiences.
HT4U staff have benchmarked 55 GPUs using three tests with three applications compatible with OpenCL. Especially interesting are the results with the 3D rendering application LuxRender. The article is written in Portuguese, but the results are easy to understand for all.
In this talk form the 2011 LLVM Developers Meeting, Intel presents their OpenCL SDK 1.5 and its core technology the vectorizer compiler.
The video presents an overview of the implicit vectorization module and discusses experience with the LLVM compiler toolkit. The presenter also presents some of the design decisions and and plans for future features (future instruction sets, vector select, predicated instructions, etc).
In a quiet post on the LLVMdev mailing list, it was announced that AMD is going Open Source with the AMD IL Code Generator which is compatible with LLVM 2.9. Also, video and slides from the recent 2011 LLVM Developers’ Meeting are starting to appear online. Including SKIR: Just-in-Time Compilation for Parallelism with LLVM, Univeristy of Colorado; Intel OpenCL SDK Vectorizer, Intel; Polly - First successful optimizations - How to proceed?, ENS/INRIA and finally Symbolic Testing of OpenCL Code from Imperial College London.
OpenScales announce that they have created the first version of OpenScalesGL, which uses HTML5 and WebGL. Like OpenScales, OpenScalesGL will be distributed with a LGPL license. More information and a proof of concept video is available on the OpenScales website.