Engadget

NVIDIA outs a pair of Tesla GPUs to electrify your supercomputer

Daniel Cooper — Wed, 16 May 2012 09:51:00 EST

NVIDIA's announced a pair of Tesla GPUs that'll give some extra pep to your supercomputing tasks. The K10 and K20 units harness the power of Kepler to add more muscle to the company's scientific and technical computing arm that supplies gear to the Barcelona Supercomputing Center and Tokyo's Tsubame 2.0. Internal tests reveal that the hardware is around three times faster than the company's Fermi GPUs -- with the latter card expected to arrive at the end of the year. The company didn't announce pricing, since its aiming them squarely at the big academic institutions, defense contractors and oil explorers -- but if your surname is Buffet or Abramovitch, then they might sell you one at trade.

Continue reading NVIDIA outs a pair of Tesla GPUs to electrify your supercomputer

NVIDIA outs a pair of Tesla GPUs to electrify your supercomputer originally appeared on Engadget on Wed, 16 May 2012 09:51:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA's Tesla GPU powers Tsubame 2.0 to green supercomputer supremacy

Terrence O'Brien — Wed, 23 Nov 2011 17:20:00 EST

The Green500 might not be quite as well known as the Top500, but it's no less of an honor to be counted among the world's most energy efficient supercomputers. NVIDIA is tooting its own horn for making it on to the list for the second year in a row as part of the "greenest" petaflop machine. The Tsubame 2.0 at the Tokyo Institute of Technology's Global Scientific Information Center is powered by Intel's Xeon CPUs, but NVIDIA's Tesla general purpose GPUs do a vast majority of the number crunching, allowing it to deliver 1.19 petaflops of performance while consuming only 1.2 megawatts. That's roughly 958 megaflops per watt, a huge increase over the most efficient CPU-only super computer, the Cielo Cray, which gets only 278 megaflops per watt. The Tsubame 2.0 isn't the greenest machine on the planet though, that honor belongs to IBM's BlueGene which takes the top five spots on the Green500. Still, number ten ain't bad... right? Check out the PR after the break.

Continue reading NVIDIA's Tesla GPU powers Tsubame 2.0 to green supercomputer supremacy

NVIDIA's Tesla GPU powers Tsubame 2.0 to green supercomputer supremacy originally appeared on Engadget on Wed, 23 Nov 2011 17:20:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA's Maximus combines Quadro and Tesla for serious warrior power

James Trew — Mon, 14 Nov 2011 19:57:00 EST

Back in August, NVIDIA sneaked us a few deets about its curious Maximus project, and now the ~~joint CPU / GPU~~ card is officially ready to rev up your workflow. The idea is simple: dramatically improve productivity by using one system to handle the graphics along with the processing to deliver it. You might say it's got the looks and the brains. By melding the graphics ham of its Quadro GPUs with the cheesy smarts from the Tesla C2075, NVIDIA has made one epic processing sandwich that 'transparently' delegates tasks to the right processor; also expect to see Maximus-optimized applications from the likes of Adobe and Bunkspeed in the not-too-distant future. Workstations can supe up their core immediately, but whether the Maximus will ever be accompanied by a companion Biggus Diskus is unclear.

Update: As many of you pointed out in the comments, Tesla is technically still a GPU. Though, in this case, the cores are being used exclusively for general computing purposes to offload work from the CPU while the Quadro half of the equation handles graphical tasks.

Continue reading NVIDIA's Maximus combines Quadro and Tesla for serious warrior power

NVIDIA's Maximus combines Quadro and Tesla for serious warrior power originally appeared on Engadget on Mon, 14 Nov 2011 19:57:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA opens Windows 8 developer program with support for Kal-El tablets

Dana Wollman — Tue, 13 Sep 2011 15:00:00 EST

Unless you've been living under a rock, you know Microsoft's Build developer conference is going on right now in Anaheim, California, and Windows 8 is the belle of the ball. Earlier today, Windows chief Steven Sinofsky spilled more details about the OS, touting the minimum requirements and NFC support, while we fessed up to having had some quality hands-on time ourselves. So it shouldn't come as a surprise that the company's hardware partners are also ready to start talking. NVIDIA just opened its Windows 8 developer program, and says it'll embrace not just x86-based PCs, but Tegra-powered tablets as well. Specifically, that means support for its forthcoming quad-core Tegra platform, codenamed Kal-El, along with PCs packing GeForce, Quadro and Tesla cards. Any developers who happen to be hanging around the Anaheim Convention Center can sign up at NVIDIA's booth, though there's also an online registration page for everyone else. Find that at the source link, along with the full PR after the break.

Continue reading NVIDIA opens Windows 8 developer program with support for Kal-El tablets

NVIDIA opens Windows 8 developer program with support for Kal-El tablets originally appeared on Engadget on Tue, 13 Sep 2011 15:00:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA's Project Maximus takes multi-GPU mainstream, 'Virtual Graphics' takes it to the cloud

Darren Murph — Mon, 08 Aug 2011 23:15:00 EST

NVIDIA just wrapped up an intimate press briefing here at SIGGRAPH 2011, where -- amongst other things -- it officially took the wraps off of two major initiatives. Project Maximus and Virtual Graphics are the two main topics of conversation here, and while both are obviously targeting working professionals at the moment, there's no question that a trickle-down effect is already on the company's mind. With Maximus, the outfit plans to stop recommending bigger GPUs to pros, and start recommending "a light Quadro GPU and as large a Tesla as you can get in the system." The overriding goal here is to make multi-GPU technology entirely more accessible; to date, it hasn't exactly been easy to get a finely tuned multi-GPU setup to the masses, but it sounds like a good deal of future flexibility (it'll be "nearly infinitely scalable") aims to change that. Just imagine: dynamic coupling and decoupling of GPUs depending on user load, at a far more detailed level within the application...

Update: Regarding that Tesla bit, NVIDIA clarified with this: "What we're saying is for applications that are light on graphics / don't place a heavy demand on graphics, but more so a heavy demand on computational tasks, users will have an option to choose an entry- or mid-level Quadro card for graphics functions, such as the Quadro 600 or Quadro 2000. For certain applications, better performance is achieved by adding a Tesla companion processor, as opposed to scaling up the primary Quadro graphics. Users still require as much graphics as possible."

Gallery: NVIDIA's Project Maximus and Project Monterey revealing at SIGGRAPH 2011

Continue reading NVIDIA's Project Maximus takes multi-GPU mainstream, 'Virtual Graphics' takes it to the cloud

NVIDIA's Project Maximus takes multi-GPU mainstream, 'Virtual Graphics' takes it to the cloud originally appeared on Engadget on Mon, 08 Aug 2011 23:15:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Tesla Model S is bundled up at CES, we unwrap it (video)

Tim Stevens — Thu, 06 Jan 2011 09:32:00 EST

We'll get this out of the way up front: no, we didn't get to drive it. In fact we didn't even get to sit in its creamy white seats, a tragedy that we're still a little sensitive about. But we did get to open the door of the Tesla Model S, testing out the trick powered door handles that motor themselves out after a touch and then, when the door is closed, zip back flush to the sheet metal. It's a nice detail, one that we think would probably lose its ability to inspire wonder after about a week. But, for now, it's cool. Check out a video of that and other details below.

Gallery: Tesla Model S at CES 2011, eyes-on

Continue reading Tesla Model S is bundled up at CES, we unwrap it (video)

Tesla Model S is bundled up at CES, we unwrap it (video) originally appeared on Engadget on Thu, 06 Jan 2011 09:32:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Tesla Model S to have 17-inch infotainment console powered by Tegra; BMW using NVIDIA tech too

Vlad Savov — Tue, 04 Jan 2011 10:37:00 EST

Tesla is touting the world's biggest center console for its upcoming Model S today: a titanic 17-inch touchscreen display powered by NVIDIA's Tegra chip. Infotainment, climate control and navigation will all be managed using the vast dashboard dominator, while NVIDIA's hardware will also take responsibility for keeping the 12.3-inch instrument cluster LCD updated. Considering the Model S, like the Roadster before it, is an all-electric vehicle, you'd expect energy efficiency to be a pretty important consideration in the choice of infotainment system and Tesla points that out as a key advantage of Tegra, describing it as "power-stingy." Another motor company hooking up with NVIDIA is BMW, who promises that all of its upcoming models for 2011 will benefit from Green Team GPUs powering their iDrive navigation and information systems. We don't know what exact GPUs will be used, but a "visually rich" next-gen UI is being promised, stretching out to a 1280 x 600 resolution. You'll find both press releases after the break.

Continue reading Tesla Model S to have 17-inch infotainment console powered by Tegra; BMW using NVIDIA tech too

Tesla Model S to have 17-inch infotainment console powered by Tegra; BMW using NVIDIA tech too originally appeared on Engadget on Tue, 04 Jan 2011 10:37:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

China's Tianhe-1A is world's fastest supercomputer, plans to usurp the West now complete

Thomas Ricker — Thu, 28 Oct 2010 01:21:00 EST

It happened. China just passed the US and the world with the reveal of the world's fastest supercomputer. The fully operational Tianhe-1A, located at the National Supercomputer Center in Tianjin, scored 2.507 petaflops as measured by the LINPACK benchmark. That moves it past Cray's 2.3 petaflops Jaguar located at Oak Ridge National Lab in Tennessee. Tianhe-1A achieved the record using 7,168 NVIDIA Tesla M2050 GPUs and 14,336 Intel Xeon CPUs consuming 4.04 megawatts. Knowing that 10 petaflops is within reach by 2012, we'll see if Tianhe-1A can maintain its title when the new Top500 supercomputers list is released next week.

China's Tianhe-1A is world's fastest supercomputer, plans to usurp the West now complete originally appeared on Engadget on Thu, 28 Oct 2010 01:21:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Rambus victorious in patent fight with NVIDIA, can expect neat wad of cash for its troubles

Vlad Savov — Tue, 27 Jul 2010 03:02:00 EST

So what if Rambus doesn't really produce anything tangible these days? We're hearing the "innovation" business is going really well for the company that recently celebrated its 1,000th patent, and now there's a nice big windfall in its near future as well. The US International Trade Commission has handed down a ruling agreeing with a previous judgment that NVIDIA infringed on three Rambus patents in the design of its memory controllers, with the ultimate outcome being a ban on importing such infringing goods into the country. Of course, that's the one thing we're sure won't be happening, but NVIDIA will now have to sign up for a license to Rambus' precious IP portfolio, which might be a tad bit costly given that GeForce, Quadro, nForce, Tesla and Tegra chips are named as being in violation -- aside from Ion, that's pretty much NVIDIA's whole hardware business.

[Thanks, Marc]

Update: NVIDIA, unsurprisingly, has said it will appeal the ruling. [Thanks, Xero2]

Rambus victorious in patent fight with NVIDIA, can expect neat wad of cash for its troubles originally appeared on Engadget on Tue, 27 Jul 2010 03:02:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Tokyo Institute of Technology announces SSD-packing, 2.39 petaflop supercomputer

Joseph L. Flatley — Wed, 23 Jun 2010 14:06:00 EST

IBM has announced plans to start using SandForce SSDs in its enterprise machines, and now it looks like the Tokyo Institute of Technology is doing one better, working with NEC and HP to produce Tsubame 2.0. This next-gen supercomputer will reportedly operate at 2.39 petaflops (that's a lot of flops!) and uses a new multilevel storage architecture consisting of DRAM as well as SSDs. Not only will this bad boy have thirty times the computing capacity of Tsubame 1.0 (due in part to its some 2,816 Intel Westmere microprocessors and 4,224 NVIDIA Tesla M2050 GPUs), its power draw should be some 1/25th of its predecessor's. If all goes according to plan, it should be in operation this fall, at a cost of ¥3.2 billion (approx $35.5 million).

[Thanks, Dylan]

Tokyo Institute of Technology announces SSD-packing, 2.39 petaflop supercomputer originally appeared on Engadget on Wed, 23 Jun 2010 14:06:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Core Values: What's next for NVIDIA?

Anand Shimpi — Fri, 04 Dec 2009 15:00:00 EST

Core Values is our new monthly column from Anand Shimpi, Editor-in-chief of AnandTech. With over a decade of experience poring over the latest in chip developments, he's here to explain how things work and why our tech is the way it is.

I remember the day AMD announced it was going to acquire ATI. NVIDIA told me that its only competitor just threw in the towel. What a difference a few years can make.

The last time NVIDIA was this late to a major DirectX transition was seven years ago, and the company just quietly confirmed we won't see its next-generation GPU, Fermi, until Q1 2010. If AMD's manufacturing partner TSMC weren't having such a terrible time making 40nm chips I'd say that AMD would be gobbling up marketshare like a fat kid. By the time NVIDIA gets its entire stack of DX11 hardware out the gate, AMD will be a quarter away from putting out newly refreshed GPUs.

Things aren't much better on the chipset side either -- for all intents and purposes, the future of NVIDIA's chipset business in the PC space is dead. Not only has NVIDIA recently announced that it won't be pursuing any chipsets for Intel's Core i3, i5. or i7 processors until its various legal disputes with Intel are resolved, It doesn't really make sense to be a third-party chipset vendor anymore. Both AMD and Intel are more than capable of doing chipsets in-house, and the only form of differentiation comes from the integrated graphics core -- so why not just sell cheap discrete GPUs for OEMs to use alongside Intel chipsets instead?

Even Ion is going to be short lived. NVIDIA's planning to mold an updated graphics chip into an updated chipset for the next-gen Atom processor, but Pine Trail brings the memory controller and graphics onto the CPU and leaves NVIDIA out in the cold once again.

Let's see, no competitive GPUs, no future chipset business. This isn't looking good so far -- but the one thing I've learned from writing about these companies for the past 12 years is that the future's never as it seems. Chances are, NVIDIA's going to look a lot different in the future because of two things: Tesla and Tegra.

Continue reading Core Values: What's next for NVIDIA?

Core Values: What's next for NVIDIA? originally appeared on Engadget on Fri, 04 Dec 2009 15:00:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA Tesla 20-series GPUs promise to dramatically cut supercomputing costs

Donald Melanson — Mon, 16 Nov 2009 22:29:00 EST

Sure, you've been hearing NVIDIA toss around names like CUDA, Fermi and Tesla for what seems like ages now, but we're guessing this is the sort of thing that'll get most folks to really take notice: a promise to cut supercomputing costs by a factor of ten. That rather impressive feat comes courtesy of the company's new Tesla 20-series GPUs, which come in the form of both single GPU PCI-Express Gen-2 cards and full-fledged GPU computing systems, and promise a whole host of cost-saving benefits for everything from ray tracing to 3D cloud computing to data analytics. Of course we are still talking about "cheap" in supercomputing terms -- look for these to run between $2,499 and $18,995 when they roll out sometime in the second quarter of 2010.

Filed under: Desktops

NVIDIA Tesla 20-series GPUs promise to dramatically cut supercomputing costs originally appeared on Engadget on Mon, 16 Nov 2009 22:29:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

Asustek announces a 1.1 Teraflop, Tesla GPU powered supercomputer

Joseph L. Flatley — Wed, 28 Oct 2009 01:18:00 EST

Some of us love nothing more than a portable and convenient netbook -- something that Asustek knows all too well -- but how about those of us who need real computing power? To that end, Taipei's choice for all things ultraportable has just announced its very own 1.1 Teraflop supercomputer. Dubbed the ESC 1000, this (albeit large) desktop-sized machine sports a 3.33GHz Intel LGA1366 Xeon W3580 microprocessor and three CUDA-based Tesla C1060 GPUs, the likes of which we last saw in Dell's Precision "personal supercomputer" line. Shipping with 24GB of DDR3 DRAM (1333MHz) and a 500GB SATA II hard drive, the machine is said to have a cost structure of $14,519 over five years. We're guessing that you'll be able to both surf the net and watch HD quality video on the thing, although you probably won't be taking it along with you to Crazy Mocha any time soon. According to a company spokesperson, this thing is ready to ship now, although a launch date and street price have yet to be determined. One more pic after the break.

Continue reading Asustek announces a 1.1 Teraflop, Tesla GPU powered supercomputer

Filed under: Desktops

Asustek announces a 1.1 Teraflop, Tesla GPU powered supercomputer originally appeared on Engadget on Wed, 28 Oct 2009 01:18:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments

NVIDIA Tesla GPUs now shipping with Dell 'personal supercomputers'

Joseph L. Flatley — Wed, 06 May 2009 15:18:00 EST

Been itching to get your hands on a personal supercomputer, as NVIDIA's ad wizards put it? The company has just announced that its CUDA-based Tesla C1060 GPU is now available in Dell's Precision R5400, T5500 and T7500 workstations. And just to put things into perspective, NVIDIA points out that a Dell workstation rockin' a single Tesla C1060 has enough going on under the hood to power the control system for the European Extremely Large Telescope project ("the world's largest," apparently). According to one of the developers, Jeff Meisel at National Instruments, a workstation "equipped with a single Tesla C1060 can achieve near real-time control of the mirror simulation and controller, which before wouldn't be possible in a single machine without the computational density offered by GPUs." Wild, huh? If you're curious about the workout that Tesla GPUs are getting on a wide range of projects, from Bio-Informatics to Computational Chemistry to Molecular Dynamics and more -- or if you're merely a glutton for long-winded PR -- check out the good stuff after the break.

Continue reading NVIDIA Tesla GPUs now shipping with Dell 'personal supercomputers'

Filed under: Desktops

NVIDIA Tesla GPUs now shipping with Dell 'personal supercomputers' originally appeared on Engadget on Wed, 06 May 2009 15:18:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments

NVIDIA's GT300 specs outed -- is this the cGPU we've been waiting for?

Darren Murph — Sun, 26 Apr 2009 13:22:00 EST

NVIDIA's been dabbling in the CPU space behind closed doors for years now, but with Intel finally making a serious push into the GPU realm, it's about time the firm got serious with bringing the goods. BSN has it that the company's next-generation GT300 will be fundamentally different than the GT200 -- in fact, it's being hailed as the "first truly new architecture since SIMD (Single-Instruction Multiple Data) units first appeared in graphical processors." Beyond this, the technobabble runs deep, but the long and short of it is this: NVIDIA could be right on the cusp of delivering a single chip that can handle tasks that were typically separated for the CPU and GPU, and we needn't tell you just how much your life could change should it become a reality. Now, if only NVIDIA would come clean and lift away some of this fog surrounding it (and the rumored GTX 380), that'd be just swell.

[Thanks, Musouka]

Filed under: Misc. Gadgets

NVIDIA's GT300 specs outed -- is this the cGPU we've been waiting for? originally appeared on Engadget on Sun, 26 Apr 2009 13:22:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments

Lenovo ThinkStation S20 / D20 sport new Xeon CPUs, Tesla C1060 GPU

Darren Murph — Tue, 24 Mar 2009 00:01:00 EST

We have to say, we didn't exactly expect Lenovo to have any hard-hitting news emanating from the floor at Game Developer's Conference, but this is pretty swank. The company has just unveiled two new ThinkStation desktops, the S20 and D20, both of which are designed exclusively for specialized professionals in fields such as computer-aided design and digital content creation. Within, you'll find your choice of Intel's latest Nehalem-based Xeon chips (yep, the same 5500 and 3500 series as in Apple's newest Mac Pro), NVIDIA's Tesla C1060 GPU platform (or an ATI FirePro, if you prefer) and Windows Vista or RedHat Enterprise Linux 5.2 running the show. Hit up the gallery below for the specifications breakdown, and as for pricing, you'll find 'em in Q1 for $1,070 and $1,550, respectively. Full release is after the break.

Gallery: Lenovo ThinkStation S20 / D20 sport new Xeon CPUs, Tesla C1060 GPU

Gallery: Lenovo ThinkStation S20 / D20 specs

Continue reading Lenovo ThinkStation S20 / D20 sport new Xeon CPUs, Tesla C1060 GPU

Filed under: Desktops

Lenovo ThinkStation S20 / D20 sport new Xeon CPUs, Tesla C1060 GPU originally appeared on Engadget on Tue, 24 Mar 2009 00:01:00 EST. Please see our terms for use of feeds.

Permalink | Email this | Comments

NVIDIA announces cost, energy-saving Tesla Personal Supercomputer

Donald Melanson — Tue, 18 Nov 2008 12:27:00 EST

AMD has already outlined its plans to harness the power of its GPUs for some added computing muscle, and it looks like NVIDIA is now taking things one step further by announcing its new GPU-based Tesla Personal Supercomputer, which promises to deliver the power of a traditional supercomputer cluster at 1/100th of the price. That "personal supercomputer" is actually a platform based on NVIDIA's new Tesla C1060 GPU Computing Processor, which itself is based on NVIDIA's CUDA parallel computing architecture. The supercomputers themselves will come from a whole host of manufacturers that have already partnered with NVIDIA, including ASUS, Dell, Lenovo, and a number of more specialized computer makers. While complete details on those systems are still a bit light at the moment, they'll apparently be "priced like a conventional PC workstation," and the first few out of the gate should be available starting today.

Filed under: Desktops

NVIDIA announces cost, energy-saving Tesla Personal Supercomputer originally appeared on Engadget on Tue, 18 Nov 2008 12:27:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments

NVIDIA unveils second-gen Tesla GPU-based workstation cards

Nilay Patel — Mon, 16 Jun 2008 15:20:00 EST

NVIDIA's Tesla GPU-based high-performance computing workstations and add-in cards have been on the market for a whole year now, and to celebrate, they're getting birthday cake, balloons, and an upgrade to GT200-based chipsets. Like AMD's recently-announced FireStream 9250, the new T10P processing units are capable of breaking the teraflop barrier, up from the first gen's paltry 518 GFlops, and they're up to 240 cores from the first gen's 128. You'll have to shell out to get all that horsepower, though: the entry-level, 900GFlops C1060 PCI card will sell for $1699, while the four-GPU 1U S1070 blade will sell for $7995 for two PCIe-interface version or $8295 for the single PCIe connect model. The standalone Tesla workstation has been discontinued, as customers were increasingly buying the cards, so it looks like those are really fast collectors' items for now. So, who's going to be the first to add one of these bad boys to the Engadget Folding@Home team?

[Via Tom's Hardware, thanks Matan]

Filed under: Misc. Gadgets

NVIDIA unveils second-gen Tesla GPU-based workstation cards originally appeared on Engadget on Mon, 16 Jun 2008 15:20:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments

NVIDIA launches Tesla: GPUs are the new CPUs

Nilay Patel — Wed, 20 Jun 2007 18:10:00 EST

We've seen a couple cautious attempts at leveraging the raw floating-point capabilities of modern high-powered graphics cards, but NVIDIA is taking the gloves off with the launch of Tesla, its new general-purpose computing platform built on the 8-series graphics cards we all know and love. According to NVIDIA, the only way to skirt the inevitable collapse of Moore's Law is to join the GPU and CPU together, so two of the three Tesla configs are in the form of workstation upgrades -- a $1,499 single GPU PCI Express card and a $7,500 dual-GPU "deskside supercomputer" that plugs into a custom PCI controller. The truly crazy can pony up a full $12,000 for NVIDIA's first rack units, the four-GPU Tesla S870, which has a peak performance of 2 Teraflops. We're hearing the card and deskside unit will be available in August and that the servers will start shipping in November or December -- perfect for the Engadget Folding@Home holiday rush.

Filed under: Desktops

NVIDIA launches Tesla: GPUs are the new CPUs originally appeared on Engadget on Wed, 20 Jun 2007 18:10:00 EST. Please see our terms for use of feeds.

Read | Permalink | Email this | Comments