Virginia Tech’s HokieSpeed supercomputer to rely on CPU and GPU synergies

Virginia Tech’s no stranger to housing supercomputers — those folks strung together 324 Mac Pros back in 2008 just for kicks, giggles and “research” — but their latest computing monolith is quite the shift from the ordinary. A cool $2 million is floating over to Blacksburg in order to create HokieSpeed, a “versatile new supercomputing instrument” that’ll soon be primed and ready to handle not just one or two tasks, but a variety of disciplines. Wu Feng, associate professor of computer science at the university, calls this magnificent monster a “new heterogeneous supercomputing instrument based on a combination of central processing units (CPUs) and graphical processing units (GPUs),” with expected performance to be orders of magnitude higher than their previous claim to fame, System X. One of its first assignments? To give end users the ability “to perform in-situ visualization for rapid visual information synthesis and analysis,” and during the late hours, hosts a campus-wide Quake deathmatch. Just kidding on that last bit… maybe.

Virginia Tech’s HokieSpeed supercomputer to rely on CPU and GPU synergies originally appeared on Engadget on Sat, 07 Aug 2010 08:10:00 EDT. Please see our terms for use of feeds.

Permalink Physorg  |  sourceVirginia Tech  | Email this | Comments

ATI overtakes NVIDIA in discrete GPU shipments

You’d think with ATI having the performance, value and power efficiency lead for so long — at least since the Radeon HD 4000 series — NVIDIA would be in all kinds of trouble, but it’s only now that AMD’s graphics division has finally taken the lead in quarterly shipments. This is according to Mercury Research, whose analysts place the split at 51 to 49 percent in favor of ATI — still a tightly contested thing, but it compares very favorably to the Red Team’s 41% share in the same quarter last year. This data is concerned with discrete GPU shipments only (laptops included), whereas on the integrated front Intel continues to reign supreme with 54 percent of the market shipping its cheap and cheerful IGP units. ATI has made forward strides there as well, however, with 24.5% ranking ahead of NVIDIA’s 19.8%. If Apple shifting its iMac and Mac Pro lines away from the Green livery wasn’t enough, perhaps these numbers will finally start ringing some alarm bells over at NV HQ.

[Thanks, Zubayer]

ATI overtakes NVIDIA in discrete GPU shipments originally appeared on Engadget on Fri, 30 Jul 2010 05:31:00 EDT. Please see our terms for use of feeds.

Permalink Fudzilla  |  sourceCNET  | Email this | Comments

NVIDIA’s refreshed Optimus interface sheds more light on what your GPU is doing

There’s no question that NVIDIA’s Optimus system — which enables a discrete GPU to operate when a machine is taxed and a power-sipping IGP to function when you’re involved in less strenuous tasks — has changed the way the world looks at laptop graphics, but it hasn’t been able to avoid a fair amount of criticism about the controlling interface. With the July release of the monthly Verde drivers, the company has just rolled out a revised UI that provides “even more visibility into how Optimus is working and allows you even more control over how Optimus operates.” The newest Optimus control panel, as well as a brief demonstration of what’s been tweaked, is available for viewing just after the break, but it’s on you to hunt down drivers for whatever rig you call your own.

Continue reading NVIDIA’s refreshed Optimus interface sheds more light on what your GPU is doing

NVIDIA’s refreshed Optimus interface sheds more light on what your GPU is doing originally appeared on Engadget on Wed, 28 Jul 2010 15:38:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceNVIDIA  | Email this | Comments

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

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 EDT. Please see our terms for use of feeds.

Permalink Bloomberg  |  sourceInternational Trade Commission  | Email this | Comments

ASUS Mars 2 teases superpowered dual GeForce GTX 480 goodness

We’ll be honest with you, we thought the GTX 480 was finally a graphics core too damn large and power-hungry to get the dual-GPU treatment. ASUS, however, is making us think again. Imagery has emerged of a Mars 2 (or II, if you’re into outdated numbering schemes) reference board that fits two 480s on its densely populated surface, and is fed by not one, not two, but three 8-pin auxiliary power connectors. Back when Galaxy showed off a dual-GTX 470 prototype at Computex a month ago, we deemed it an unreasonable proposition — in terms of power draw, heat dissipation, and cost — but apparently those Taiwanese focus groups are really into their extravagantly overpowered video cards. We suspect if and when this Mars 2 hits retail it’ll do so in a highly exclusive fashion, like its predecessor, and anticipate the unveiling of its cooler — which is likely to be either the biggest or best engineered one we’ve seen yet.

ASUS Mars 2 teases superpowered dual GeForce GTX 480 goodness originally appeared on Engadget on Sun, 18 Jul 2010 22:21:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceLegit Reviews  | Email this | Comments

Twelve flavors of GeForce GTX 460 now shipping from Newegg (update: official)

NVIDIA’s GeForce GTX 460 hasn’t even been officially announced, much less reviewed, but that won’t keep you from buying the company’s latest Fermi-based graphics card anyhow. Over at Newegg, usual suspects ASUS, EVGA, Gigabyte, MSI and Palit have fielded twelve models in all, most with slightly different features, thought it seems the base configuration has 336 CUDA cores (down from 352) and a mere 768MB of GDDR5 memory. Interestingly enough, this silicon’s actually rated faster than its older brother the $280 GTX 465 with 675MHz graphics and 1,350MHz processor speeds, and a 3.6GHz effective memory clock. All your frames are pushed through a decidedly narrower 192-bit memory interface, though, so we’d guess that for around $200, you won’t be getting (much) more than you pay for. Let’s just hope they run cool.

Update: The card’s official, and it seems there’s a 1GB, 256-bit version of the GTX 460, too. Hit the break for the full press release, filled with all the puffery a video game marketing team could want.

[Thanks, Polytonic]

Continue reading Twelve flavors of GeForce GTX 460 now shipping from Newegg (update: official)

Twelve flavors of GeForce GTX 460 now shipping from Newegg (update: official) originally appeared on Engadget on Sun, 11 Jul 2010 16:34:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceNewegg  | Email this | Comments

ASUS ARES cries havoc, lets slip the GPUs of war: a review roundup of the world’s fastest graphics card

When you name your graphics card after the God of War, you’d better hope it brings some heat, but judging by early reviews, that’s just what ASUS has done. The three slot monstrosity above is the ARES, a $1200 limited edition, fully custom board, sporting twin Radeon HD 5870 GPUs, four gigabytes of GDDR5 memory and practically enough raw copper to smelt a sword. We’re not joking: the thing weighs nearly five pounds and requires a 750 watt power supply with three power connectors (two 8-pin, one 6-pin) to even run. Of course, you’re getting a graphical behemoth for that kind of price, steamrolling every other GPU on the planet — paired with even a 3.8GHz Core i7-930 CPU in 3DMark Vantage (on Extreme settings), Overclock 3D racked up a fairly ludicrous 15,000 score, and the card ripped past 25,000 with a Core i7-980X and a second ARES in CrossFire. The card was less impressive in actual gameplay, merely spanking the (much cheaper) Radeon 5970 and GeForce GTX 480 by a modest amount, and several reviewers complained it was fairly loud… but as the old adage goes, nobody needs a Ferrari to drive the speed limit, but we’ll all drool over them anyhow. Bring on the liquid nitrogen, folks.

Read – Legit Reviews
Read – Overclock3D
Read – Guru3D
Read – PC Perspective
Read – TechPowerUp

ASUS ARES cries havoc, lets slip the GPUs of war: a review roundup of the world’s fastest graphics card originally appeared on Engadget on Thu, 08 Jul 2010 03:09:00 EDT. Please see our terms for use of feeds.

Permalink   |   | Email this | Comments

NVIDIA thanks Intel for saying GPUs are ‘only’ 14 times faster than CPUs

Well, we’ve gone a full month since the last episode of NVIDIA’s and Intel’s ongoing public feud, but it looks like Intel has now stoked the flames once again (albeit inadvertently) in a paper presented at the recent International Symposium on Computer Architecture. That attempted to debunk the “100X GPU vs. CPU myth,” but it also contained the tidbit that GPUs are “only” up to 14 times faster than CPUs in running application kernels, which NVIDIA has more than a happily latched onto. In a blog post, NVIDIA’s Andy Keane says that it’s a “rare day” when a competitor states that their technology is only 14x faster, and that he can’t recall another time when he’s “seen a company promote competitive benchmarks that are an order of magnitude slower.” Of course, he then further goes on to note that Intel’s tests were done with NVIDIA’s previous generation GeForce GTX 280, and that the codes were simply run out-of-the-box without any optimization — but, still, he seems more than happy to accept this bit of “recognition.” In Intel’s defense, however, the overall finding of the paper (linked below) is that the performance gap between a GTX 280 GPU and Core i7 960 processor is actually just 2.5X “on average,” which NVIDIA hasn’t highlighted for some reason.

NVIDIA thanks Intel for saying GPUs are ‘only’ 14 times faster than CPUs originally appeared on Engadget on Thu, 24 Jun 2010 13:52:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceThe NVIDIA Blog, Intel’s Insides, Intel paper  | Email this | Comments

EVO 4G loses 30fps limit thanks to devoted community (video)

Whatever the reason HTC instituted that 30fps cap on the EVO’s graphical output, the issue has just been remedied by — surprise, surprise — coders over at xda-developers. We’ve come across video evidence of the EVO 4G rolling along at a swift 54fps average clip, and another motion picture reel shows the positive effect this has had on the touch-tracking of the handset. Check them both out after the break and hit the source to get educated on how to make this happen on your own EVO. You should be warned that there are still some issues to resolve before the whole thing’s buttery smooth, but hey, it’s still a lot better than waiting for HTC to do it.

[Thanks to everyone who sent this in]

Continue reading EVO 4G loses 30fps limit thanks to devoted community (video)

EVO 4G loses 30fps limit thanks to devoted community (video) originally appeared on Engadget on Wed, 23 Jun 2010 05:24:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourcexda-developers  | Email this | Comments

NVIDIA GeForce GTX 480M reviewed: fastest mobile GPU to date

It’s one thing to have a product called the world’s fastest on paper, but it’s another thing entirely to have the benchmarks confirm it. NVIDIA‘s GeForce GTX 480M has been swooned over for months now, but it just recently hit the hardcore review sites in a big way. Frankly, there’s not a whole lot to say about the thing at this point: it’s simply the fastest mobile GPU to date, with Hot Hardware finding it to be “significantly faster in nearly all gaming benchmarks,” with just one title showing the Mobility Radeon HD 5870 as the champ by only a few frames. If you’ve been searching for the fastest mobile GPU in town, you’re wasting your time looking any harder; ‘course, all of that power consumes an insane level of energy, so true road warriors will certainly want to look elsewhere. Critics pointed out that energy consumption and excess heat were real issues, though both of those are easily overlooked when you’re able to take a beastly laptop to a LAN party rather than your desktop. Give those links below a visit if you still need proof.

NVIDIA GeForce GTX 480M reviewed: fastest mobile GPU to date originally appeared on Engadget on Thu, 17 Jun 2010 13:03:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceHot Hardware, Notebook Check  | Email this | Comments