Nvidia wants to help create some of the world's fastest computers with its latest Tesla K40 graphics chip, which is its fastest supercomputing co-processor to date.
The Tesla K40 graphics processor delivers 1.43 teraflops of performance, which is roughly 20 percent faster than its predecessor Tesla K20X, which was announced a year ago. Nvidia's Tesla processors are widely used in supercomputers alongside CPUs to process complex scientific and math applications.
The K40 is "faster in every way" than the K20X, said Sumit Gupta, general manager of Tesla Accelerated Computing products at Nvidia.
The graphics processor is based on a modified version of Nvidia's Kepler architecture, which was also used in the K20X. The K20X chip was used in the U.S. Department of Energy's Titan supercomputer, which delivered 17.59 petaflops of performance and was the world's fastest supercomputer until June this year, when it was eclipsed by China's Tianhe-2, which has Intel's Xeon E5 chips and Xeon Phi accelerators, and delivers 33.86 petaflops of performance.
Tesla chips are also used in some workstations, but are not targeted at PCs. Cray, Hewlett-Packard, Dell, IBM, Silicon Graphics, Asustek and others will make products based on the K40, though Nvidia did not comment on the price of K40 or when it would be in supercomputers.
The K40 has 2880 processing cores, and 12GB of memory, which is double the memory of K20X. The base clock speed of all graphics cores is 745Mhz, which can be boosted to 810MHz or 875MHz, depending on computing needs. There is no ability to shut down idle cores as a power-saving measure, so the entire GPU is either lit up or not, Gupta said.
Nevertheless, the K40 is more power efficient than its predecessor, Gupta said.
There is an effort to boost supercomputing speeds as countries and companies race to reach the milestone of creating an exaflop computer by 2020. Chip companies are trying to reduce the power consumption of current chips and components, while boosting performance.
Via: PCWorld
The Nvidia Shield, released earlier this year, is essentially a small Android tablet welded to a gamepad controller, creating effectively a portable Android-powered gaming console that can go toe-to-toe with the likes of Nintendo and Sony’s dedicated mobile gaming hardware. A recent software update for the Shield also improves its ability to output games content to big screens, including TVs, making it also a suitable microconsole for living room systems.
Huang’s statement is perhaps the clearest articulation of Shield’s intended purpose yet; the console is designed to provide a focal point for free-floating Android game developer ambitions, offering up a target to build for. This helps the overall gaming ecosystem, but also helps Nvidia, by prompting more developers to build experiences tailored for Tegra, its mobile system-on-a-chip, thus encouraging more Android device OEMs to look its way when building out specifications for their latest hardware.
Android’s potential goes beyond gaming into virtually every corner of connected living, however, says Huang. Tegra’s presence in automotive systems and set-top boxes, data centers, all-in-one PCs and more make it the perfect platform for the future, Huang noted, calling Google’s mobile OS “the most disruptive operating system that we’ve seen in a few decades.”
Source : TechCrunch
Driver support for graphics cards can be a major stumbling block for would-be Linux gamers. Since fewer people use Linux (and most games are created with Windows in mind), driver support for the operating system can be a bit, well, hit-or-miss.
AMD
AMD has actually been pretty active in the Linux community in recent memory, though its open-source Linux drivers still lag behind its Windows drivers. Just a few months back, the company released a massive set of 165 kernel patches that enabled some key features in Linux Radeon drivers, such as dynamic power management and initial support for the "Sea Islands" family of GPUs.
AMD's holding a GPU showcase in Hawaii on Wednesday. A new series of graphics cards are almost certainly going to be the stars of the show, but corporate VP Raja Koduri said there will also be news concerning Linux driver support, according to AnandTech. The AMD GPU showcase is expected to start around the same time that Valve unveils its second Steam-related announcement for the week.
Nvidia
Nvidia's relationship with Linux has been a bit more, shall we say, tense.
In July 2012, after a woman at a group chat session described her frustrations trying to use Nvidia's power-saving Optimus technology, Linux creator Linus Torvalds launched into an expletive-riddled tirade.
"Nvidia has been the single worst company we've dealt with," he said, before turning towards the video camera and extending his middle finger. "Nvidia... F*** you!" he hissed, uttering the words slowly and sharply.
To be fair, Nvidia does a decent job of supplying basic (or better!) Linux drivers for its latest graphics cards, and the company took issue with the remarks. Nvidia's drivers, however, are closed source, and unlike AMD, it hasn't traditionally offered open source drivers or documentation, which doesn't sit well with fanatical Linux lovers.
That changed on Monday--the same day SteamOS was announced.
That day, Nvidia's Andy Ritger messaged members of Noveau--the group that reverse-engineers Nvidia's closed-source Linux drivers to create an open-source alternative--and said Nvidia developers working on the closed-sourced Linux GPU drivers will start paying attention to the Noveau mailing group, offering assistance when possible. Additionally, Ritger said Nvidia will provide more official help.
Source : Computerworld
Subscribe to:
Posts (Atom)
Recent Comments