It's been an incredible week hasn't it? The latest news about OpenGL rendering Zombies faster than Direct3D really got the twittersphere going! SimLab Composer 2013 adds WebGL export capability and ARM has submitted the Mali-T604 GPU for full profile OpenCL conformance. Back on the Khronos front, COLLADA still has room for you to come on over and show off your COLLADA demo at Siggraph, and we've also updated the official Khronos Siggraph event page with updated BOF schedules, and lots more sponsors for the OpenGL Party! Thank you everyone that has sponsored the party so far. Big news this year, it's OpenGL's 20th Anniversary and we'll be celebrating this momentus occasion in style.There will be lots of OpenGL legends, lots of food, drink and of course, lots and lots of prizes!
Going to SIGGRAPH? Be sure to check out some amazing demo's, presentations, prizes and more. Khronos has a news conference, five BOFs (COLLADA, OpenCL, WebGL, OpenGL ES & OpenGL) and a huge OpenGL party, all happening on Tuesday next week. Full details can be found here, and the party details can be found here.
ARM has submitted their Mali-T604 graphics processing unit (GPU) for OpenCL 1.1 Full Profile conformance with The Khronos Group. This product is based on a published Khronos Specification, and is expected to pass the Khronos Conformance Testing Process.
Todd Roberts of AMD, discusses the key concepts and workflows behind the OpenCL execution model that incorporates both task and data parallelism. He also discusses the standard pattern for building an OpenCL program as well as offering sample code.
Watch Alina Alt explain compute API interoperability with OpenGL (using CUDA and OpenCL APIs) and delve into interoperability at a system level (or review the slides). Alina explains challenges and benefits of dedicating one GPU for compute and another for graphics, how different system configurations affect data transfer between two GPUs, and how it translates into application design decisions helping to enable an efficient, cross-GPU interoperability between compute and graphics contexts.
You can find updated schedules for all Khronos Group BOFs online.
Acceleware's customized 4-day OpenCL training consists of classroom lectures and several practical hands-on exercises. It is specifically tailored for learning parallel programming in OpenCL on AMD GPUs and APUs. Attendees should have a background C/C++ (2 or more years).
The Intel® SDK for OpenCL Applications 2012 provides a comprehensive development environment and tools for the build, debug, and tune stages of an OpenCL application. Join this webinar on Wednesday July 25th at 9am pacific time.
If used correctly, OpenCL images / textures can give you large speedups on GPUs. In this post, author Erik Smistad shows you a very short example of how to use OpenCL to blur/smooth an image. The goal is to show how images/textures are used in OpenCL and the benefits of using them.
Jon Peddie Research will be hosting an informational luncheon for press and analysts at SIGGRAPH 2012. The topic will be "Doing More with Multicore," and we'll have a distinguished panel to debate the different aspects of putting multiple CPU and GPU cores to work. What technology is best suited for what jobs? Or maybe a core is just a core, is just a core. The event will be held August 8, 2012 at 11:45 to 14:00 in the JW Marriott, L.A. Live - 900 W Olympic Blvd, in room PLAZA 1