Shaderific version 3.0 now available. Shaderific is an educational app for iPad, iPhone and iPod touch that makes it possible to write, compile and test OpenGL ES 2.0 shader programs directly on any iOS device. Version 3.0 adds camera support, face detection, movie textures and video capture. Video frames provided by the built-in camera as well as movie files can be used as dynamic textures. Automatic face detection provides shader programs with access to a new uniform array containing the bounding rectangles of up to five faces. Furthermore, it is now possible to record a video of the ongoing rendering session and the video is automatically exported to the photo library.
The GPGPU Continuum from mWatts to peta flops workshop addresses the current and future challenges of the GPGPU community. This workshop aims to address two important directions of future GPGPU based systems: at the high-end, it will focus on using GPUs as part of clusters, clouds, compute farms, etc., that aim to achieve peta flops of computations. At the low-end, it will focus on using GPUs as part of mobile devices, which limits the power consumption of the GPU to mWatts. We conclude the workshop with a panel discussion on the differences and similarities and on the challenges each domain faces.
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.