CAPS is pleased to announce the availability of an OpenCL code generator within the just released 2.3 version of its HMPP directive-based hybrid compiler. The HMPP compiler integrates powerful data-parallel backends for NVIDIA CUDA and OpenCL that can drastically reduce development time. The OpenCL version of HMPP fully supports AMD and NVIDIA GPU compute processors, bringing to users a wider set of hybrid platforms they can execute their applications on. “The addition of this OpenCL back-end to our existing NVIDIA CUDA back-end is a major milestone in HMPP development that gives users another powerful standard programming option,” comments Stéphane Bihan, Sales manager at CAPS
A short tutorial to help you get started with coding OpenCL in Java. The tutorial is OS X based.
Learn and share ideas at the Brisbane GPU Users group. Founded to bring together GPU users from all fields and experience levels from southeast Queensland. Topics of discussion include general GPU computing, GPGPU, CUDA, OpenCL, OpenGL, DirectCompute, DirectX and related technologies. The next meetup is tentatively scheduled for June 23rd at GP Library (V Block) Room V714 Queensland University of Technology, from 6pm - 9pm.
AMD is offering an introductory tutorial to OpenCL™ that will be held alongside the 2010 Symposium on Application Accelerators in High Performance Computing (SAAHPC’10). This will be a “programmer’s introduction” where we cover the ideas behind OpenCL™ but also show how these ideas are translated into source code. We will do this through a series of progressively more challenging examples--thereby providing examples that experienced programmers will need to become productive OpenCL™ programmers.
Inotube.com has posted an interesting demo of WebGL that displays non-streaming sparse octal voxels. The demo runs fairly quickly and gives one some good insight into the future of using octal voxels for computer graphics. A short article behind the building of this demo is here, and the demo is here.
The goal of the COLLADA Web Viewer is to allow the drawing of COLLADA content using the O3D API without the need for an offline converter. COLLADA Web Viewer provides a fast open source tool that uses cross domain xhttp requests to directly download and draw a COLLADA scene directly into any web browser without the need for an offline converter. We make use of standard browser techniques to ensure it works on any O3D compatible platform.
JogAmp will be at SIGGRAPH 2010 with their own BOF Session "3D & Multimedia Across Platforms and Devices Using JOGL." This BOF session, on Tuesday, 27 July from 4:00pm to 6:00pm, will discuss the features, contributions, and future of OpenGL, OpenCL, and OpenMax across devices and OS exposed on top of Java using the JogAmp open-source libraries.
Using OpenCL to manipulate OpenGL objects has important advantages: the GPU is usually faster and data transfer from Host memory to Device memory is kept to a minimum. CMSoft OpenCL/GL interop tutorial shows detailed implementation of circular wave interference simulation using CL/GL interop, including commented source code available for download.
Tony Parisi, one of the co-creators of VRML--Virtual Reality Modeling Language--along side Mark Pescue, recently discussed the future of Virtual Worlds. When asked "What conditions should be present that are not today for a serious widespread of virtual worlds in the future?" Tony response was "two things. First, a ubiquitous client. Either Unity, or a Unity competitor; or WebGL (maybe not version 1.0 because it might not have all the features)." The second item is game play within the virtual worlds.
Scientific American interviewed several institutes to discover how they plan on using OpenCL. Read how researchers at Virginia Polytechnic Institute and State University (Virginia Tech) and The National Institutes of Health plan on using OpenCL to further their studies within the small budgets at their disposal.