| NVIDIA nTeresting: 6 November 2009 |
| Written by NVIDIA - Brian Burke | |||
| Sunday, 08 November 2009 | |||
NVIDIA nTeresting: 6 November 2009In this Issue:
WSJ's Mossberg: Get a GPUWall Street Journal has released Walt Mossberg's highly anticipated Fall PC Buying Guide. In it he specifically recommends buying a system with a discrete GPU: "The new operating systems allow software makers to speed up some tasks by offloading them from the main processor onto the graphics chip. So, if possible, get a "discrete" graphics processor, which has its own memory. Otherwise, find a potent "integrated" graphics chip, which shares your main memory." That is a nice way of saying stay away from crummy Intel integrated graphics for Windows 7 and Snow Leopard...or get an optimized PC for GPU computing. A modern PC uses the GPU and the CPU in a co-processing design. ION, No More WorriesWhile ION has almost single-handedly redefined the netbook, a few people still expressed some reservations about the product: "Our big worry about ION has been battery life. Nothing that's gone before has suggested that adding a graphics chip capable of running HD movies and even some games - you can play Call of Duty 4 relatively happily - will do anything other than decimate a netbook's battery. In our tests, though, the N510 ran for over seven hours, with Bluetooth and Wi-Fi active. That's not just good for a netbook, that's incredible. There's no way it should last that long. But it does." It is nice to over deliver: "As a flagbearer for ION it confounds our - admittedly low - expectations. It doesn't just set a new benchmark for netbook performance, it actually delivers on all the pre-release hype. And for that, it gets heartily recommended." By combining a an NVIDIA ION GPU with an Atom processor, NVIDIA is able to deliver premium PC performance and features in low-cost, small form factor PCs. Another Intel Anti-trust CaseA new anti-trust case against Intel surfaced this week, this time in New York. Following the lead of foreign regulators, New York's attorney general, Andrew M. Cuomo, filed a federal antitrust lawsuit Wednesday against Intel. The lawsuit charges that Intel violated state and federal laws by abusing its dominant position in the chip market to keep AMD at bay. But an Intel spokesperson shrugs it off: "It is the AMD case filed 4.5 years ago. It's the same case the EU brought. There's nothing significant or new here that hasn't been discovered," Mulloy said. If memory serves, the EU case cost them $1.45 billion. Real-Time Ray Tracer: NVIDIA OptiXAs the world's first interactive ray tracing engine, the NVIDIA OptiX ray tracing engine leverages the massively parallel power of NVIDIA GPUs for maximum performance and scalability. In providing a programmable ray tracing pipeline, the OptiX engine gives developers great flexibility to accelerate their ray tracing applications, bringing previously unseen levels of interactivity to a wide range of uses. These include auto styling, design visualization and visual effects. It's also ideal for non-rendering disciplines, such as optical design, acoustical design and collision analysis. "This(OptiX) opens the door to a new level of interactive realism. Ray tracing's inherent parallelism makes it a perfect fit for GPU computing. The OptiX engine makes it easy for developers to exploit that power to create an exciting new class of applications. It enables critical design tasks - such as examining reflections, refractions and shadow - to be performed now in real-time," - Jeff Brown, NVIDIA's GM for Professional Solutions The NVIDIA OptiX ray tracing engine is now available downloading Most Respected Semiconductor Company, MaybeThe Global Semiconductor Alliance (GSA) announces the nominees for awards to be presented at the GSA Awards Dinner Celebration on Thursday, Dec. 10, 2009, at the Santa Clara Convention Center in Santa Clara, Calif. NVIDIA was nominated along with Broadcom and Xilinx for Most Respected Public Semiconductor Company achieving $500 million to $10 billion in annual sales. Three New CUDA Centers of ExcellenceThe CUDA Center of Excellence (CCOE) program by NVIDIA recognizes, rewards, and fosters collaboration with universities at the forefront of massively parallel many core computing research. NVIDIA recognizes institutions having demonstrated their commitment to revolutionizing science and engineering research with GPU Computing across a host of science and engineering research projects as CUDA Centers of Excellence. We have expanded the list to include Chinese Academy of Sciences, Tsinghua University and University of Tennessee. They join an elite list of five other universities as CUDA Centers of Excellence, including: Harvard University, University of Illinois at Urbana-Champaign and University of Utah, in the U.S.; Cambridge University, in the UK; and National Taiwan University, in Taiwan. Additionally, more than 250 other universities around the world teach the CUDA C programming model.
|
|||