Realizing the success of Nvidia’s CUDA university initiatives, AMD recently announced a new OpenCL University Kit, a collection of materials that can be used in any university environment to teach OpenCL programming.
“Teaching students to effectively leverage the OpenCL standard involves all the intricacies of parallel programming plus support for a new class of heterogeneous computing devices built on a variety of hardware technologies,” said David Kaeli, professor and associate dean of undergraduate programs, Northeastern University College of Engineering. “The OpenCL University Kit introduced by AMD is an easy tool to enable educators to quickly introduce OpenCL learning into their curriculum, helping them strike a balance between teaching syntax and higher level architectural issues.”
The kit includes 13 lectures, with instructor and speaker notes, as well as code examples. Combined with the recently announced ‘Accelerated Parallel Processing SDK‘, (the new name for the old Stream SDK) it’s a great way to get into OpenCL development.
via AMD Helps Advance Parallel Computing with OpenCL™ University Kit.
ATI has released the newest version of their Streak GPGPU library, this time containing their first production release with OpenCL support. They’ve also added an integrated Visual Studio tool and several multi-library interoperability features. The full list of new whiz-bang features looks like this:
- First production release of ATI Stream SDK with OpenCL™ 1.0 support.
- New: Support for OpenCL™ ICD (Installable Client Driver). Please see this knowledge base article for important information concerning changes that must be made to code developed with previous beta releases of the ATI Stream SDK v2.0.
- New: Support for atomic functions for 32-bit integers.
- New: Microsoft® Visual Studio® 2008-integrated ATI Stream Profiler performance analysis tool.
- Preview: Support for OpenCL™ / OpenGL® interoperability. Please see this knowledge base article for more information about this preview feature.
- Preview: Support for OpenCL™ / Microsoft® DirectX® 10 interoperability. Please see this knowledge base article for more information about this preview feature.
- Preview: Support for double-precision floating point basic arithmetic in OpenCL™ C kernels. Please see this knowledge base article for more information about this preview feature.
- Updated OpenCL™ runtime to conditionally load ATI CAL runtime libraries to allow execution on compatible CPUs without ATI Catalyst™ installed.
- Updated OpenCL™ runtime to allow simultaneous use of OpenCL™ and ATI CAL APIs in a single user application.
- Updated cl.hpp from the Khronos OpenCL working group release.
- Various OpenCL™ compiler and runtime fixes and enhancements (see developer release notes for more details).
Hit their site to download.
via AMD Developer Central – ATI Stream SDK v2.0 with OpenCL™ 1.0 Support.
If you couldn’t make it to Portland for SC09 this year but you want to see what’s going on in the “3D Internet” track, you can hit Intel’s website to view a live stream of Intel CTO Justin Rattner’s Opening Address kicking off the topic.
Intel Software Network at SuperComputing SC09 – Intel® Software Network.
AMD/ATI (I never know what to call them anymore) has updated their Stream GPGPU library, and released the new “2.0 Beta” for registered developers. The big feature in this version is OpenCL support, but that’s not all.
What’s New in v2.0-beta3
- ATI Stream SDK v2.0 OpenCL™ for x86 CPUs is now certified conformant by Khronos on September 3, 2009.
- 64-bit atomic built-ins are now recognized.
- Fixed some compiler assertion issues.
- Fixed some incorrect compiler warnings.
- Fixed some incorrect compiler assertion failures.
- Fixed some code generation issues.
via AMD Developer Central – ATI Stream SDK v2.0 Beta Program with OpenCL 1.0 Support.
AMD has been hard at work trying to boost their “Stream” technology to somethign competitive with NVidia’s CUDA, and a new press release does a great job at cataloging the recent successes they’ve had.
- AMD was the first company to deliver a public beta release of an OpenCL software development platform for x86-based CPUs on August 5, 2009. The OpenCL for CPU implementation was certified conformant by Khronos on September 3, 2009.
- The complete ATI Stream SDK v2.0 for CPU and GPU software development using OpenCL is planned for full release later this year.
- To further meet the ATI Stream developer community’s needs, AMD has successfully completed the migration of its Brook+ project to SourceForge. SourceForge is a centralized online location for software developers to control and manage open source software, where the developer community can continue to work with and evolve the Brook+ code.
- AMD’s upcoming next generation ATI Radeon™ family of DirectX™ 11 enabled graphics processors are expected to be the first to support accelerated processing on the GPU through DirectCompute.
The real focus of the release is that they’ve submitted their OpenCL implementation to the Khronos Working Group for certification, which (if/once approved) will make AMD the only company to have a working CPU & GPU implementation of OpenCL.
via AMD Advances its Commitment to OpenCL™ for GPU With Review by Standards Body.
When you start talking about GPGPU, you have two major players in the marketplace: NVidia CUDA and ATI’s Stream technologies. PC Perspective takes the two to task and pits them against each other in a battle of the bits:
Since our initial review of five of NVidia’s CUDA-enabled applications back in June, we’ve been chomping at the bit to get our first real look at ATI’s entry into the GPU computing ring called ATI Stream. Both of these platforms use parallel computing architectures to utilize the GPU’s stream processors, in tandem with the CPU, to significantly increase any system’s video transcoding speeds.
Today, we are going to discuss both of these technologies as well as benchmark a couple video transcoding applications from Cyberlink that support both CUDA and ATI Stream platforms. We will also take a brief look at ATI’s Avivo video converter to see what ATI’s own free software has to offer.
via PC Perspective – ATI Stream vs. NVIDIA CUDA – GPGPU computing battle royale.
A press release from Meru announces a new “Video over Wireless” technology specifically designed for streaming High-definition video over 802.11N. While 802.11N definitely has the bandwidth for high-definition video, it lacks the reliability necessary in many situations.
“But high-definition video delivery over wireless is especially challenging because it combines the high bandwidth requirements of heavy data traffic with the delay sensitivity and loss characteristics of voice traffic. And while 802.11n dramatically increases available bandwidth it also increases per-transmission error rates. “
The offering is based around their new “Video Services Module” which combines various prioritization and management strategies into a single tool for easier configuration. It should be available in June as an addon to their existing System Director software for $8000 for 100 nodes.
via Meru Unveils First Video-Over-Wireless Infrastructure Solution Optimized for 802.11n Networks.