Imagination Technologies announces further details of the first POWERVR SGX graphics IP core with multi-processor (MP) core support. The technology, henceforth POWERVR SGX543MP, is being delivered to customers in SGXMP2 (two-core) to SGXMP16 (16-core) variants. The cores support Khronos APIs including OpenGL™ ES 2.x, OpenVG™ 1.x and OpenCL™. With the POWERVR SGX543MP family Imagination continues to extend its leadership of the embedded graphics acceleration market with blistering POWERVR solutions which address the rapidly growing demands for high performance graphics in a wide range of consumer electronics segments. Imagination’s graphics IP cores now range from SGX520, the world’s smallest OpenGL™ ES 2.0 mobile core, to SGX543MP16 for high-performance console and computing devices. Some of the innovative technology behind POWERVR SGX543MP is being revealed in a keynote presentation at the 4th annual Multicore Expo.
Khronos Group has announced the availability of an OpenCL Quick Reference card in PDF format. This comprehensive 6 page quick reference covers all important aspects of the OpenCL API. You can download your copy of the OpenCL Quick Reference Card today. If you are attending the Game Developers conference this year, Khronos will be handing out a nicely printed version of this reference guide.
NVIDIA wants to give you between $0.5M to $5M, plus partner with you on marketing, development, distribution, and more. If you're developing an application that leverages a GPU's parallelism, and your application is built using OpenCL 1.0, CUDA, or ATI's Stream SDK, NVIDIA wants to hear from you. NVIDIA announced its new GPU Ventures Program and GPU Venture Zone website to support its new market-building effort.You can find details of how to submit your proposal on their GPU Ventures Program website.
Khronos has posted their speaking schedule for the Multicore EXPO on March 16th. Speakers from NVIDIA, Codeplay, Nokia, ARM and Imagination Technologies will be present, with a question and answer period and demo's. Khronos will cover two areas of our standards development: OpenCL and the Khronos "Handheld API Ecosystem".
The first public demonstration of OpenCL running on a GPU was done by NVIDIA on December 12, 2008 at Siggraph Asia. This demo of OpenCL on NVIDIA GPU was based on early non-released OpenCL API/driver interface. The nbody simulation shown was a simulation of massive particles under the influence of physical forces. Nbody simulation is known to be computationally intensive. The demo shows how OpenCL can deliver high performance computing using the parallel cores of the CUDA architecture on NVIDIA GPUs. This demo also illustrates the idea that core computational code can be written in OpenCL and will scale to whatever number of cores are available. The demo shown in Siggraph used the 32 parallel cores available on the NVIDIA Quadro FX 570M GPU that it ran on.
The Khronos Group has announced that it will hold a DevU tutorial at this years Game Developers Conference in San Francisco. The Khronos DevU will cover four major topics: OpenCL, OpenGL, COLLADA, and the Khronos “Mobile API Ecosystem. This will be an all day event held on Tuesday March 24 2009 in partnership with the GDC 2009. Admittance to the session is available to all registered Mobile GDC and regular GDC conference attendees.
Khronos Group will be offering a Developers University session at Multicore Expo on March 16th in Santa Clara. The Khronos Group DevU will be focused on OpenCL and the handheld API ecosystem for accelerating 2D and 3D graphics. For complete details please visit the Khronos Group DevU event page.
AMD announces its latest FireStream 9270. According to TechPowerUp, this latest FireStream 9270 supports OpenCL on Windows and Linux systems. This board features 800 stream cores with a top compute rate of 1.2 TFLOPs (single precision), 240 GFLOPs (double precision), 2GB of GDDR5 SDRAM at 850MHz and a peak memory bandwidth of 108.8 GB/s.
AMD gave the first public demonstration of OpenCL functionality at Siggraph Asia 2008 using a particle & fluid simulation app. We've posted a screen capture of the demo. It shows how OpenCL extracts high performance parallel computing out of multi-core CPUs (as well as GPUs and DSPs). As you can see in the video, as the additional CPU cores are enabled the simulation compute time is cut in half!