Researchers from the University of Warwick’s Performance Computing and Visualization Department and Oxford University’s eResearch Centre have put together a study: should we install a GPGPU-based system or a more traditional IMB Blue Gene-like supercomputer? The team’s research will present their work at the 1st International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems at the SC10 conference in New Orleans. The Khronos Group will be at Booth # 1132 at SC10.
Currently there are several ways to feed data to the GPU no matter of what API we use and what type of application we develop. In case of OpenGL we have uniform buffers, texture buffers, texture images, etc. The same is true for OpenCL and other compute APIs that even provide more fine-grained memory management taking advantage of the local data store (LDS) available on today’s hardware. In this article I’ll present the memory access performance characteristics of AMD’s Evergreen-class GPUs focusing on what this all means from OpenGL point of view. While most of the data is about the HD5870, the general principles and relative performance characteristics are valid for other GPUs, including ones from other vendors.
Rob Farber has an in-depth two part tutorial on OpenCL. The first part of the tutorial will get you going using the ATI Stream software development kit (SDK). Part two of the OpenCL tutorial covers memory spaces and the OpenCL memory hierarchy, as well, how to start thinking in terms of work items and work groups. Both parts contain lots of code examples to help the novice OpenCL programmer get started.
ZDNet sat down with Huang at the recent GPU Technology Conference in San Jose, California to discuss CUDA, OpenCL and all things parallel computing.
ArcSoft is collaborating with AMD using their Radeon™ HD 6800 series GPUs on OpenCL™ technology with the pre-release of its best-selling multimedia player application, TotalMedia Theatre 5. ArcSoft's products are optimized with OpenCL, include the upscaling technology SimHD® on TotalMedia Theatre 5 and H.264 encoders across many applications such as TotalMedia ShowBiz, TotalMedia Studio, and MediaConverter 7.
Vincent Hindriksen, owner of StreamComputing will be speaking at the Thalesian seminar on the Usability of OpenCL for Financial Computations. The meetup will be held in Canary Wharf, London, at 7:30 p.m. on Wednesday, 27th October, 2010. Founded in 2008. the Thalesians are a think tank of dedicated professionals with an interest in quantitative finance, economics, mathematics, physics, computer science, and synergetics.
In the Catalyst Driver 10.10 for Windows release AMD introduces the Accelerated Parallel Processing (APP) technology edition. The APP technology edition includes everything from the standard driver and adds the OpenCL driver component. You can still download the Catalyst components individually. The version also includes Blu-Ray 3D support, Stereo 3D gaming support and video acceleration for HD WMV video content (Windows 7).
StreamComputing.nl has posted a third instalment of their OpenCL–The Battle series. Part I covered the hardware companies and operating systems, Part II the software companies. The latest entry focuses on Games. Covering many aspects of games and gaming with a focus on the physics of material. Well written and lots video examples, the article is informative and a fast read.
MacResearch is an open and independent community for scientists using Mac OS X and related hardware in their research. MacResearch has a good collection of OpenCL tutorials as well as tutorials covering many other topics.
MVTec is a developer of software products for machine vision, used in, for example, the semiconductor industry for board, wafer and die Inspection. Halcon 10 will take advantage of GPUs based on the OpenCL standard to make optimum use of available compute power.