Altera will demo live video streaming using OpenCL, and real-time video processing such as Sobel edge-detection and image manipulation, all coded in OpenCL software and running on Altera FPGAs. In addition, this demo uses an Altera’s Nios II soft processor, and enables the power of OpenCL in embedded applications by removing the need for external processor or host server machine.
AMD and Adobe have teamed up to bring support for OpenCL to Windows with the upcoming release of Adobe Premier Pro. This marks the first time Microsoft's OS has been had hardware-accelerated video editing using OpenCL, and exporting video from source to final format can now be achieved up to 4.3 times faster.
The Technical Papers Program at SC is the leading venue for presenting the highest-quality original research, from the foundations of HPC to its emerging frontiers. Papers presented at SC have to pass a high bar – only 21% of submissions were accepted for SC12. Abstract submissions are due April 5th and full submissions are due no later than April 12th 2013. The SC13 call for papers is available in PDF format as well.
As part of its ongoing enablement of embedded vision, CogniVue Corporation announces joining the Khronos Group as a Contributing Member. CogniVue is strategically focused on aligning its Image Cognition Processor (ICP) core IP products with OpenCL. CogniVue’s ICP technology is based on APEX, CogniVue’s innovative massively parallel SIMD-MIMD processing architecture, specifically geared to drive new levels of vision performance per area per power.
New drivers for Intel's Ivy Bridge-based third-generation Core processors brings support for OpenCL 1.2 general-purpose GPU (GPGPU) language and a 10 percent performance boost. The HD4000 is the GPU found in Intel's Ivy Bridge-based third-generation Core processors.
Version 4.2 of the open-source, cross-platform volume visualization tool Voreen is now available for download. This version brings significant performance optimizations, stereoscopic rendering, a OpenCL-based 3D random walker implementation for interactive volume segmentation, and extended visual debugging features of the network editor.
Intel has submitted several resources to the OpenCL resource page. The Khronos Group Resource pages are open to the community to submit their own resources. Each of Khronos technologies has it's own resource page.
Neil Trevett will be the Keynote speaker at the Low Energy Application Parallelism (LEAP) Conference in the UK. LEAP 2013 will be the place to learn about and share the latest advances in the use of high-performance parallel computing technology on low-power mobile CPU, GPU, FPGA and embedded processors. Keynotes from ARM and Khronos will set the stage for world-class knowledge transfer around parallel computing on low-energy platforms happening May 21st-2nd 2013 in London.
After the success of the GPGPU-day 2012, a new GPGPU event will be organised in the Netherlands. Details will be available online later, however you can signup to the newsletter today to stay on top of upcoming event information.