NVIDIA called in the big guns to help promote its Tesla graphics processing units (GPUs), announcing new efforts this week with Microsoft to explore applications for high performance parallel computing using Windows HPC Server 2008. In that vein, NVIDIA Research developed several GPU-enabled applications on the Windows HPC Server 2008 platform, including a ray tracing application that can be tapped to do advanced photo-realistic modeling of automobiles. NVIDIA also collaborated with Microsoft’s research arm to install a large Tesla GPU computing cluster with the intention of studying new applications optimized for the GPU. NVIDIA’s Tesla GPUs support Windows XP and Windows Vista on the workstation, and Windows Server 2003 and Windows Server 2008 in the data center. A number of large workstation OEMs, including Cray, Dell, Hewlett-Packard and Lenovo offer personal workstation platforms built on the Tesla C1060 and S1070 GPUs. Andy Keane, general manager of NVIDIA’s Tesla business, maintains that scientific and engineering communities leveraging the GPU platform are achieving performance boosts of between 20 to 200 times, depending on their application.
Surveillance, reconnaissance, and search and rescue in military and first responder situations are popular applications for aerial robots. Yet not all the robots are considered unmanned aerial vehicles.
For industrial control applications, or even a simple assembly line, that machine can go almost 24/7 without a break. But what happens when the task is a little more complex? That’s where the “smart” machine would come in. The smart machine is one that has some simple (or complex in some cases) processing capability to be able to adapt to changing conditions. Such machines are suited for a host of applications, including automotive, aerospace, defense, medical, computers and electronics, telecommunications, consumer goods, and so on. This radio show will show what’s possible with smart machines, and what tradeoffs need to be made to implement such a solution.