Nvidia Maxwell Gtx 780 Delayed till 2014

Originally, Kepler GPU architecture was scheduled to debut in 2011, with the successor codenamed Maxwell coming in 2013. We were not surprised to hear that Maxwell, tied to a 20nm process node - is getting delayed as well.

"The battle with manufacturing nodes continues." - This would be a summary of what our sources told us over the past couple of weeks. No manufacturer is having an easy time, and even Intel - known for its manufacturing excellence - pulled its 22nm Low Power node deeply into 2013, debuting about half a year later.

When it comes to Nvidia, the company is heavily engaged on increasing the yields for its products. With Kepler, Nvidia shifted to a new die strategy, and even though we've heard more rumors about the GK106 chips, the fact of the matter is that Kepler will remain a three GPU line-up: GK104 for performance, GK107 for mobile and entry-level desktop and the GK110 for high-end computational and visualization parts.

Ultimately, GK104 served as the GTX 660/670/680/690, Quadro K5000 and Tesla K10, GK107 serves in numerous low-power mobile and desktop designs. GK110 will make a public appearance only in December as the Tesla K20, with a yet unannounced amount of video memory (according to our sources, NV is trying to secure different packaging to enable 12GB of GDDR5 memory, but realistically - prototype boards we saw utilized "just" 6GB).

Naturally, all of these movements don't hold much promise for the next generation GeForce cards. Given that the Maxwell, GM1xx parts won't be available until the first half of 2014, the GeForce and Quadro parts should continue to rely on refreshed/renamed GK104/107/110 parts. The GK110 is planned to expand and become available as the Quadro K6000 6GB, for those that require ultimate performance on a single piece of silicon.

In case you've doubted it, Maxwell is a 20nm part, capable of being manufactured in GlobalFoundries, IBM, Samsung and TSMC - 20nm Gate-Last HKMG will equalize between TSMC and Common Platform alliance - a move Nvidia and Qualcomm cannot wait to see come to frutition.

Availability of that part however, will not come sooner than the first half of next year. As far as the GeForce GTX 700 Series is concerned, the parts should repeat the same cadence as this year's lineup. However, the newer revised parts should offer further clock improvements, to the level where they can offer between 25-30% higher performance and power efficiency, while the company is working on parts based on the Maxwell GPU architecture, which should drive 2014 as one of key years in Nvidia's history.

Maxwell will be the first top-to-bottom GPU architecture, powering everything from Tegra to Tesla. Furthermore, Maxwell should be the first GPU part to integrate the 64-bit ARM core which carries the codename "Project Denver". Putting the typically-bandwidth starved ARM cores onto an internal bus which in GPUs goes beyond 1.5TB/s should significantly change the playing game - a GPU capable of booting an operating system, regardless of what lies currently in public documents.

All in all, 2013 will see AMD's Sea Islands fight first versus Nvidia's Kepler refresh, and only then against the Maxwell. Real battle will come only in 2014.

Source: http://vr-zone.com

Read More

Most Powerful Graphics Technology NVIDIA Keplar Just Got Much More Affordable

When NVIDIA debuted video cards featuring its powerful Kepler architecture earlier this year, PC gamers around the world stood up and cheered. Then they got quiet when they realised their only options were the $US500+ GTX 680 card or the GTX 690, packing dual-Kepler graphics processing units for around $US1000.

PC players drooled over these pricey pieces of hardware. Many bit the bullet and bought one or two or three of each. Still others patiently waited for a more affordable option. Well, their wait is over now. The GeForce GTX 660 Ti is now available for an incredibly reasonable $US299.

That relatively modest amount of cash will secure gamers a card featuring all the bells and whistles that make the Kepler tech so damn impressive. It’s power efficient, its lightning fast. and it’s fully capable of doing amazing things to a game like The Secret World, which utilises the card’s TXAA anti-aliasing process to smooth jagged edges to CGI-film quality.

The GeForce GTX 660 Ti is NVIDIA’s new flagship graphics card, the one the company expects will become the standard for years to come, offering nearly twice the power of 2010′s GTX 470 and 3.3 times that of 2008′s GTX 260, both of which are still in heavy rotation in PC gaming circles.

To illustrate this point, NVIDIA taps on of the most eagerly-anticipated PC games of the year, Borderlands 2.

If a simple FPS comparison chart featuring Borderlands 2 is enough to send you shopping, get this — purchasing the GTX 660 Ti from NVIDIA’s online retail partners will score buyers a free copy of the game, giving them something shiny to show off their brand new video card with.

The specs aren’t as impressive as its more expensive big brothers, of course, but it’s more than enough to generate a chart that compares it favourably to the AMD Radeon HD7870.
As well as the Radeon HD7950, a card slightly above its pay grade.
But these are just slides from a PowerPoint presentation. If you want a true measure of the GTX 660 Ti, slap one in your machine. They should be available all over the damn place today.

Source: kotaku.com

Read More

Maximus workstation platform launch by NVIDIA

The technology deployed in the Maximus will automatically assign visualisation and simulation or rendering work to the accurate processor

NVIDIA has launched a new Kepler GPU architecture featured Maximus workstation platform, which is offered with Quadro K5000 or with Tesla K20 GPUs.

The new Kepler architecture supported GPU platform is expected to enhance performance and efficiency of the workstation used by manufacturing, visual effects and oil exploration professionals.

The company has earlier launched a Maximus platform, which allows the workstation users to simultaneously perform complex analysis and visualisation on a single machine.

Initially, Maximus was a single system which would manage interactive graphics and the compute-intensive number crunching required to simulate or render them, further resulting in accelerated workflows.

In the new Maximus, compute work is allocated for running the new NVIDIA Tesla K20 GPU computing accelerator, which will free up the new NVIDIA Quadro K5000 GPU to handle graphics functions, the company said.

The technology deployed in the Maximus will automatically assign visualisation and simulation or rendering work to the accurate processor.
Features of NVIDIA's new Quadro K5000 GPU include bindless textures, which allow the users to access over 1 million textures directly in memory while reducing CPU overhead.

The FXAA/TXAA film-style anti-aliasing feature will enhance image quality, while its frame buffer capacity is increased to 4GB and a new PCIe-3 bus interconnect has been added which speeds up data movement by 2 times over PCIe-2.

A new display engine which can drive up to four displays at the same time with a single K5000 and a display port 1.2 supports resolutions of up to 3840x2160 @60Hz.

The another variant NVIDIA Tesla K20 GPU features SMX streaming multiprocessor technology which offers for up to a 3 times performance per watt advantage, while the dynamic parallelism and hyper-Q GPU technologies ease parallel programming and improve performance.

Read More

AMD and Nvidia Gonna launch new pro-grade GPUs & APUs

Pro-graphics fans have received some good news this week, as both Nvidia and AMD have outed their latest-generation high-end products for the workstation market - including the first workstation-class accelerated processing units (APUs.)

First, Nvidia's announcement: the Quadro K5000. Based on the latest Kepler GPU, the Quadro K5000 includes 1,536 CUDA cores and 4GB of GDDR5 on a 256-bit memory bus. The result, Nvidia claims, is a card capable of pushing 2,150 gigaflops in single-precision mode or 90 gigaflops in double-precision mode. Coupled with support for DVI-I, DVI-D and DisplayPort monitors - with the option to drive up to four independent displays from a single board - the company is clearly hoping to win over pro-graphics types with the two-slot 122W TDP design.

As befits a Kepler board, the Quadro K5000 also includes bindless texture support for referencing over a million in-memory textures with reduced CPU overhead and TXAA anti-aliasing - both features missing from prior Quadro products.

If you were thinking about adding a Quadro board to your next build, however, the price may be something of a stumbling block: while UK pricing has yet to be confirmed, Nvidia has given the Quadro K5000 a US recommended retail price of $2,249 (around £1,440 excluding taxes) ahead of its planned release in October. For those who prefer pre-builds, Nvidia has announced that Maximums systems - combining a Tesla K20 processor with the Quadro K5000 - will be available from the likes of Dell, Fujitsu, HP, Lenovo and Supermicro by the end of the year.

AMD's offerings start with a quartet of FirePro boards based on the Graphics Core Next (GCN) architecture. The entry point for the new boards is the FirePro W500, a Pitcairn-based system which packs 2GB of GDDR5 on a 256-bit memory bus with a claimed performance of 1,270 gigaflops single-precision or 80 gigaflops double-precision. A single-slit design, the board includes two DisplayPort outputs and a single dual-link DVI port, and boasts a fairly sedate TDP of just 75W.

For those who demand more, the FirePro W7000 doubles the memory to 4GB of GDDR5, boosts performance to 2,430 gigaflops single-precision and 150 gigaflops double-precision, includes four DisplayPort outputs and has a 150W TDP in - again - a single-slot design.

Moving from the Pitcairn boards to the Tahiti boards, things get bulkier: the FirePro W8000 has a 189W TDP and a hefty dual-slot design, but manages 3,230 gigaflops single-precision and 810 gigaflops double-precision. If that's not enough, the top-end FirePro W9000 includes 6GB of GDDR5 memory on a 384-bit memory bus, packs six mini-DisplayPorts and boasts 3,990 gigaflops single-precision and 1,000 gigaflops double-precision performance - but has a massive 274W TDP.

Pricing for AMD's standalone FirePro range starts fairly low, but rapidly ramps up: US RRPs for the range have been given as $599 for the FirePro W5000, $899 for the FirePro W7000, $1,599 for the FirePro W8000 and a whopping $3,999 for the FirePro W9000.

Alongside the standalone FirePro boards came AMD's announcement of two FirePro APU chips. The first, the AMD FirePro A300, boasts a 3.4GHz base clock speed peaking at 4GHz in single-core turbo mode and a 65W TDP, while the AMD FirePro A320 speeds things up with a 3.8GHz base clock and 4.2GHz peak turbo clock in a 100W TDP. Both models include 384 stream processors, running at 760MHz on the A300 and 800MHz on the A320.

AMD is hoping that its FirePro-certified APUs will help end the stigma of on-board graphics for professional purposes, promising full compatibility with even high-end software packages. Better still, the company claims that a FirePro A300 will outperform Nvidia's Quadro 600 entry-level dedicated graphics board.

What AMD isn't currently sharing is the price, stating only that off-the-shelf systems based on the two new FirePro APUs will be appearing some time later this month.

Source: bittech.net

Read More

Nvidia GTX 660 Ti available For Pre-Order

Videocardz.com managed to notice that some of the retail/e-tail shops in Sweden decided to jump the gun and start listing the GTX 660 Ti graphics card a few days ahead of its expected launch.

The card is currently listed at anywhere between 3,350 and 3,551 Swedish Kronor which roughly converts to around US $490 and US $520, including taxes, which is way higher than expected, but Swedes have the misfortune of traditionally paying more for their gear than the rest of the continent. We still did not manage to put our finger on the final price as according to our sources, Nvidia still did not wire the final price to its partners and can easily change it just a day before the official launch.

The expected price is somewhere between US $200 and US $300, although US $300 sounds a tad more realistic. However, according to these early listings we would not be surprised to see a US $349 price tag on the new GTX 660 Ti. Of course, this just might be the case of pumped up pre-order price, while the launch price could end up to be lower.

Nvidia's GTX 670 currently sells at around US $399 and judging by the recent performance of the GTX 660 Ti, Nvidia could easily market the GTX 660 Ti for US $349, leaving the rest of the US $200 to US $300 market for the rest of its lineup.

In case you missed it the GTX 660 Ti is based on Nvidia's quite well known 28nm GK104 GPU and features 1344 CUDA cores, 2GB of GDDR5 memory paired up with 192-bit memory interface and clocks set at 915/980MHz for base/boost GPU clock and 6008MHz for memory.

The new GTX 660 Ti graphics card is expected to launch on 16th of August, according to earlier reports, but the Sweden stores claim that the listed graphics card will be available on August 14th.

Source: Videocardz.com

Read More

The Nvidia GTX 660 Ti 2GB Specs

Priced around $300 and with very similar specs to a GTX 670. Frakking hell...

The much-awaited GTX 660 has allegedly hovered in a "we made it, but need to sell our old stuff first" limbo for over a month. With the GTX 560 and 550 soon to be discontinued, the time is definitely right for the first truly midrange Kepler part to emerge into the daylight. Emerge it has... and dear Gods, the specs!

Packing 1334 'CUDA' cores (the same as a GTX 670), a 915 MHz base clock, 980MHz 'boost clock' (also the same as a GTX 670) and 2GB of memory (same) the GTX 660 is closer, specifications wise, to its bigger cousin than any graphics card has been. The card does however lose a quarter of its ROPs (parts designed to handle Anti-Aliasing and other 'post rendering' effects). Similarly restricted is a quarter of the memory bandwidth via a move to a 192-bit, rather than 256-bit bus.

This is not quite the configuration we were expecting, given a relatively low proportion of manufactured GK-104 silicon (the same part used in the GTX 680 and 670) come without flaws. As such fewer of the 1536 cores were expected to be enabled and a 1.5GB compliment of RAM was mooted as being most likely. However it's seems Kepler yields may have improved, while Nvidia have already perfected using non-homogenous memory chips (a la the GTX 460 1GB) allowing 2GB of RAM to be powered by a 192 bit bus.


Tweaktown.com managed to get their hands on one of the upcoming GTX 660 Ti 2GB graphics cards they allege they're in a running fight with Nvidia, but not its cardmakers. From their review, performance at resolutions of 1920x1200 and below performance is simply stellar. The ~90% of a '670 power is what we would expect from card that is memory restricted - on the upper end of a scale between the AMD HD 7950 and GTX 670.

Launch is likely to occur over the coming two to three weeks and should Nvidia keep the supply stable, we could potentially be seeing this card below the $AU 300 mark by month end – given that performance is not that far off the GTX 680, this looks to be the most important release of the efficient Kepler architecture yet. Should the '660 hit its mark without issue AMD will have to go on the defensive in the mid and upper-mid range, leaving the consumer even better off. It's also quite likely we'll see a non 'Ti' GTX 660 further down the track.

Source: atomicmpc.com

Read More

NVIDIA Releases Kepler Graphics based GPUs Demo: A New Dawn

Ten years ago Nvidia released Dawn, a GeForce FX tech demo featuring a fairy gymnast as seen through the tunnel vision of someone who’s been eating unidentified fungi. It was impressive, but in the past ten years extreme use of bloom and depth of field has become less novel. Today, Nvidia released “A New Dawn,” an updated demo (announced last month) which shows off the power of Kepler-based GPUs.

Dawn has new hair (40,000 hairs, to be precise, as opposed to the original demo’s 1,700 strands), a new skin shader, a fully modeled environment to live in, screen space ambient occlusion, and all of the other stuff we expect from Nvidia’s fastest and most efficient GPU yet. Her hair is especially striking, in that it looks very impressive, but not quite like hair.

To deal with the challenge of anti-aliasing 40,000 strands, A New Dawn uses “a special hair smoothing shader that inspects each strand and blurs them in the combing direction.” According to last month’s post, “the final result looks soft and silky, as if she just jumped out of the shower after an extensive conditioner routine.” That is seriously extensive conditioning.

The demonstration will run on a 2.5GHz dual-core processor with a GTX 670 or higher. The download link, a complete list of upgrades, and the full system specs can be found in Nvidia’s post.

Source: Pcmag.com

Read More

Nvidia GTS 650 with GDDR5 memory

According to rumours over at It168.com, it appears that Nvidia might use the 650 name for GDDR5 version of the GT 640. Based on the same 28nm GK107 Kepler GPU, it will feature 384 CUDA cores but have higher clocks when compared to the GT 640.

As we already wrote here, Nvidia still did not talk about model names but according to rumours from the It168.com crew, the lineup will include the aforementioned GTS 650 GD5 as well as the GTX 660 and the GTX 660 Ti graphics cards, in addition to the GT 640 GD3 of course.

The rumoured clocks of the GTS 650 are set at around 1000MHz for the GPU and 4800MHz and performance is around 44 percent higher than what you get on the GT 640, which means that the GK107 surely benefits from faster GDDR5 memory. The GTS 650 could end up without any PCI-Express power connectors as it would draw around 70W.

In any case, August will certainly be interesting for Nvidia as it will finally put some pressure in the mid-range part of the market.


Source: Fudzilla.com

Read More

NVIDIA GeForce GTX 660 Ti To Release In 3rd Week Of August

According to Nvidia's programming, the Geforce GTX 660 Ti is introduced in the middle of next month, that is, sometime between 13 and 19 August. It is time for the important start of school, when students upgrade for the upcoming fall semester.

It seems that NVIDIA is finally going to release the GeForce GTX 660 Ti sometime in August. It is expect at some point between August 13th and 19th, but it could very well be Thursday August 16th or the 14th as previous Kepler GPUs have up till now launched on Tuesdays or Thursdays.

The GTX 660 Ti, as we previously reported, is expected to be a GK104 powered mid-range GPU, with 1334 CUDA cores, 1.5GB of GDDR5 memory on a 192-bit bus. The card is expected to use just one 6-pin PCIe power connector, as well as a short PCB. The fact this GPU should be releasing finally has been given further credence as the newest version of GPU-Z has now added support for GTX 660 among others.

All things considered, if this rumor is more fact than fiction we will see a true mid-range GPU from NVIDIA's Kepler architecture that should arrive in August and come priced around $300. A further scaled down GTX 660 with 1152 CUDA cores may also be in the works and could release in August as well, but as with all rumors take this information with a grain of salt until we get samples for review.

Source: Legitreviews.com

Read More

NVIDIA Readies GeForce GTS 650 Ti for August

NVIDIA is almost ready to launch their whole mid-range lineup. We all know that there’s GeForce GTX 660 coming in about a month, but it seems that there are at least two other cards being prepared as well.

GeForce GTX 660 / GTX 660 Ti and..
As far as the rumors go, there are three cards planned for release in August. From the mid-range segment we expect the GK106 based GeForce GTX 660 along with GTX 660 Ti, which is supposedly based on GK104 GPU. But according to the latest leaks, we might also see yet another card – GeForce GTS 650 Ti (it’s still not clear whether the card receives GTX or GTS naming).

GeForce GTS 650 Ti

Card will purportedly feature five streaming multiprocessors, which gives 960 CUDA cores in total. This model will likely not be equipped with the memory higher than 1.5 GB, not to mention 192-bit interface. This model should be available for around $150, but this is only the estimation.

NVIDIA refreshing GeForce GT 640

NVIDIA is also preparing a new version of GT 640, which is reported to feature GDDR5 memory. There is currently a GDDR3 version available, but it’s obviously not very fast. Card might cost a little more, since it will deliver higher memory bandwidth with some additional frames per second in few games. But still, this is not a gaming card.

NVIDIA’s Mid-range to High-end Lineup

There’s still a lot of discussion on multiple forums, people are speculating about specs of those cards, but the truth is nobody knows anything, and as long as there is no leak in some photographs we should always call those predictions. However, this gives you a quick look of how many cards are still missing from the mid-range segment of NVIDIA’s 600 series.

GeForce 600 Series	GPU	CUDA Cores	Memory	Memory Interface	Launch Price	Release
GeForce GT 640 D3	GK107	384	1GB / 2GB GDDR3	128-bit	$99	April
GeForce GT 640 D5*	GK107	384	1GB / 2GB GDDR5	128-bit	$120	August
GeForce GT 650 Ti*	GK106	960	1GB / 2GB GDDR5	192-bit	$120 – $160	August
GeForce GTX 660*	GK106	1152	1.5 GB GDDR5	192-bit	$200 – $250	August
GeForce GTX 660 Ti*	GK104	1344	1.5GB / 3GB GDDR5	192-bit	$300 – $320	August
GeForce GTX 670	GK104	1344	2GB / 4GB GDDR5	256-bit	$399	May
GeForce GTX 680	GK104	1535	2GB / 4GB GDDR5	256-bit	$499	March
GeForce GTX 690	2xGK104	3072	4GB GDDR5	512-bit	$999	May

Source: Videocardz.com

Read More

AMD Radeon HD 7970 GHz Edition

Radeon series GPU holds a slight edge in multi-monitor gaming

The latest round of the graphics war is over. Advanced Micro Devices, Inc. (AMD) came storming out first [1][2][3], but in the end it was NVIDIA Corp (NVDA) who seized the peformance crown with its GeForce GTX 680 Kepler GPU. And that's where the story might have ended, had AMD not said "not so fast."

AMD countered with a specially binned Radeon HD 7970 "Gigahertz Edition" (GE). The new card is essentially the exact same as the original Radeon HD 7970, which shipped at the end of January. But it does bump the core clock from 925 MHz up to 1000 MHz (hence the GHZ part) and the memory clock from 5.5 GHz to 6 GHz.

But the majority of the gains come from a new set of drivers that in some ways mirror NVIDIA's Kepler drivers, by providing a "Boost" mode. Unlike the Kepler drivers, AMD locks the cards into a solid maximum clock -- 1050 GHz -- which is sort of nice, given that you know what you're getting. This contrasts with NVIDIA which guarantees a minimum boost clock, but whose maximum boost clock is somewhat random depending on chip quality -- essentially luck of the draw.

That's all fine and good, but the compelling question is whether the Gigahertz Edition was worth alerting the press and claiming to steal NVIDIA's thunder. Well it turns out it does provide a significant boost over the base model, enough to put it in contention once more for the graphics crown.

The card trades blows with the Geforce GTX 680 in AnandTech's testing, with neither card managing a convincing victory. The only area where one card clearly wins is in the multi-monitor tests, where AMD's card is the clear winner.

The most important issue thus becomes price. Both the GTX 680 and new HD 7970 GE are $500 USD. Thus the graphics races is essentially a dead heat.

Moving down the ladder AMD offers the base HD 7970 for $430 USD. For $30 USD less NVIDIA offers the $400 USD GTX 670 -- which predictably has a bit less performance than HD 7970. Then there's AMD's HD 7950 at $360, which is in turn a bit lower performance than the GTX 670.

In other words, smart pricing from both companies means that the best card for you in this round of the graphics war depends on which price point you're looking at. At the points occupied by AMD, AMD wins, at the points occupied by NVIDIA, NVIDIA wins. But at the top there's now no longer a clear winner.Click To See AMD Radeon HD 7970 GHz Edition Review

Source: Dailytech.com

Tags: AMD, Graphic Cards, AMD Radeon HD 7970

Read More

Indian Space Research Organization to Use Nvidia GPU for its supercomputer

Nvidia announced that supercomputer SAGA system, which holds eighty sixth position on the Top 500 list, is leveraging 640 Nvidia Tesla GPUs providing up to 394 teraflops of peak performance.

Developed by the Indian Space Research Organization (ISRO), one of the six largest space research agencies in the world, the SAGA supercomputer is used to tackle aeronautical problems.

“GPUs enabled us to reduce the time to create, simulate and verify a new launch vehicle design from weeks to days, while improving the overall quality and durability of the design dramatically,” said sources at ISRO. “This level of supercomputing power has made a huge difference in our space program, by enabling us to continually refine and improve our prediction capabilities.”

ISRO leverages the SAGA system and PARAS-3D application to run compute-intensive, detailed computational fluid dynamics (CFD) simulations that optimize the launch vehicle design for improved performance under a range of flow conditions.

With GPUs, ISRO is able to run simulations seven-eight times faster than with a CPU-based system, reducing the time to create, test and finalize new designs by the same factor.

In addition, the higher compute density in a GPU based system enables better application scalability while requiring a much lower investment in communication infrastructure.

“The Indian government has jumped into global supercomputing race in a big way, with its recent $1 billion pledge to build a network of next-generation, peta scale-class supercomputers throughout the country,” said submit Gupta, senior director, Nvidia’s Tesla business. “India joins the US, China, Germany, Japan, Russia, and other leading nations who are applying supercomputing resources to solve some of the worlds’ most pressing computational, scientific and engineering problems.”

Source: Ciol.com

Tags: Nvidia, Nvidia Tesla, Graphic Cards, Tech News, Latest Tech

Read More

Nvidia Tesla systems will be out before November

Nvidia has said that it will have Kepler based K20 Tesla boards in supercomputers in time for November's Top 500 list.

Nvidia recently launched its Kepler K10 Tesla boards that focus on single-precision floating point performance, with the firm claiming its Tesla K20 boards will appear in the fourth quarter. Now the firm has said it expects supercomputer clusters featuring its Tesla K20 boards will appear in the November 2012 Top 500 list.

When The INQUIRER asked Nvidia if its Kepler-based accelerators will make a big splash in the June Top 500 list Sumit Gupta, GM of Nvidia's HPC business unit said that was "highly unlikely". Gupta continued, "A lot of the supercomputing centres running.

Linpack need double-precision [floating point] and our double-precision product is going to be available in the Q4 time frame, so its not going to impact Top 500 in the June announcement. But we expect to make a huge impact in the November announcement."

Although Gupta said K20 boards are penciled in for the fourth quarter, given that the Top 500 list will be released in November, K20 boards should be available a few months before then, which could push Intel to move forward its Xeon Phi launch plans.

Nvidia claims its K20 Tesla boards will provide three times the double-precision floating point performance of its previous generation Fermi M2090 boards, which in theory would put the board in the 1.5TFLOP region, significantly higher than AMD and Intel are currently claiming with their respective Firepro and Xeon Phi products expected around the same time.

While Nvidia might not improve on its already impressive Top 500 positions, the fact that it expects to make a big dent in November's list should give cause for concern at Intel for its Xeon Phi board.

Source: The Inquirer

Tags: Nvidia, Nvidia Keplar, Nvidia Tesla, Processor, Graphic Cards

Read More

NVIDIA Kepler Cards in Alienware to Continue Delivering Maximum Performance for Gamers

A little over a month ago, we announced the first wave of major hardware upgrades for our Alienware line of laptops based on the newest Intel Ivy Bridge processors and also NVIDIA GeForce 6-series cards. Since then, NVIDIA has certainly kept busy as they continue to introduce more members of the next-generation Kepler family such as the GTX 690, GTX 670, and most recently, the GTX 680M.

Alienware M17x/M18x getting GTX680M options

By the time you read this, NVIDIA will have finally revealed the details of their GTX 680M from Computex 2012 in Taipei, Taiwan. The GTX 680M is based on the GK104 Kepler architecture and features similar silicon to its beefy desktop version, the GTX 680. NVIDIA calls this card the ‘fastest, most advanced gaming notebook GPU ever built’ and we have little reason to argue otherwise.

On the flip side of that power-packed coin, customers who order a system with the GTX 680M will also see greater improvements to power efficiency utilizing NVIDIA’s Optimus technology which enables long battery life by automatically switching on the dedicated GPU only when necessary. All in all, the GTX 680M paves the way for superior next-gen mobile gaming performance and makes the most of the additional technologies below that can only be found on GeForce GPUs:

• Adaptive V-sync – newly developed technology for a smoother gameplay experience
• Advanced AA modes – for crisper images, including NVIDIA FXAA and new TXAA
• PhysX support – for accelerated in-game physics
• NVIDIA 3D Vision 2 technology – for bigger, brighter, more comfortable 3D gaming
• 3DTV Play software – for connecting notebooks to 3DTVs for the most immersive gaming experience to be had in a living room
• NVIDIA SLI technology – for up to double the gaming performance. Two GeForce GTX 680M GPUs in SLI mode represent the fastest notebook graphics solution available anywhere
• CUDA technology support – for high-performance GPU computing applications
  

We are particularly proud to be a launch partner with NVIDIA for the GTX 680M. The Alienware M17x will be available with the GeForce GTX 680M 2GB DDR5 GPU along with the option for the NVIDIA 3D Vision technology. The Alienware M18x will also be available with the GeForce GTX 680M GPU in single or dual-card SLI configurations before the end of the month.

Alienware Aurora preparing for GTX 690 option

The Alienware M17x and M18x aren’t the only two products getting the Kepler kick, and they certainly won’t be the last. Before the end of the month, we will have configuration options to allow users to equip their custom built Aurora with the newly released GeForce GTX 690.

Based on many of the initial reviews of the GTX 690 as can be seen Anandtech and Hot Hardware, most people have drawn one consistent conclusion; the GTX 690 is easily the most powerful single-card GPU they have ever tested. With that level of graphical power and performance, we have been working with NVIDIA to offer the GTX 690 in our Alienware Aurora R4 desktops in order to equip our ultimate gaming machines with even more processing power.

The GeForce GTX690 is certainly a fantastic and ridiculously powerful pairing for the Alienware Aurora. The GTX 690 brings all the performance of a dual GTX 680 SLI setup while drawing less power and outputting less noise – all while staying within the same thermal levels. Considering that the Aurora uses a mini-ITX board, the GTX 690 allows for users to enjoy the pinnacle of dual-card performance without having to deal with PCI-e slot spacing, drastic thermal levels, or slim dual card watercooled GPU blocks.

Again, expect the GTX 680M on the M17x/M18x and GTX 690 to be available for the Alienware Aurora R4 worldwide before the end of the month on Alienware.com or also Dell.com. Be sure to stay tuned to our Direct2Dell blog to be alerted of the exact date that both card upgrades become available.

Source: Dell.com

Tags: Dell, Alienware, Nvdia Keplar, Graphic Cards, Gaming Laptop, Desktop PC

Read More

Four pillars of Kepler GPU Power Describes By NVIDIA

This week NVIDIA demonstrated the power of their Kepler GPU in its future iterations in an investor call covering both desktop and mobile computing. The three different elements that focus the power of NVIDIA’s Kepler GPU were listed as SMX, Hyper-Q, and Dynamic Parallelism, each of these explained in brief, and two relatively new products were reintroduced: Tesla K10 and Tesla K20, the first available now, the second available in the forth quarter of 2012.

In the slide you see above, the four pillars of Kepler are shown and we shown by NVIDIA as such. SMX is Kepler delivered at three times the performance of the current computing market. Hyper-Q improves the utilization of the GPU, multiple threads at once. Dynamic Parallelism allows developers to use the GPU much easier than ever before and broadens the capabilities that can be utilized on the GPU. All of these technologies are used on Kepler which is part of NVIDIA’s intensely quickly growing market which, shown here, is gaining new giant customers all the time:


NVIDIA is presenting this week to investors on what their business is doing in both the mobile and the desktop world.

Source: Slashgear

Tags: Nvdia, Nvdia Keplar, Graphic Cards

Read More

Nvidia Introduces World's First Virtualized GPU Technology

Five years in the making, Nvidia's virtualized the GPU to bring you graphical power on your VDI. 


Cloud was a big topic at Nvidia's GPU Technology Conference, which wasn't unexpected given the focus of GPUs in servers and enterprise applications.


At a keynote speech, Nvidia CEO Jen-Hsun Huang announced the fruit of the company's five-year-long effort in creating the world's first virtualized GPU, dubbed the VGX platform, which enables IT departments to deliver a virtualized desktop with the graphics and GPU computing performance of a PC or workstation to employees using any connected device.


While virtualized CPU computing is commonplace today, Nvidia VGX enables workers for the first time to access a GPU-accelerated desktop similar to a traditional local PC, which is hugely advantageous for 3D design and simulation tools – applications which had previously been too intensive for a virtualized desktop.


Nvidia also pitched the VGX platform as a solution for enterprise IT departments to address the complex challenges of "BYOD" – or bring your own device to work. It delivers a remote desktop to these devices, providing users the same access they have on their desktop terminal. 


At the same time, it helps reduce overall IT spend, improve data security and minimize data center complexity. The Nvidia VGX hardware is designed for hosting large numbers of users in an energy-efficient way. 


The first of such VGX board packs four GPUs, 16 GB of memory, 4 GB of frame buffer, and fits into the industry-standard PCI Express interface in servers. Perhaps even better is that the VGX boards are designed to be passively cooled.


On the software side is the GPU Hypervisor, a software layer that integrates into commercial hypervisors, such as the Citrix XenServer, enabling virtualization of the GPU. The VGX package also features Nvidia User Selectable Machines (USMs). 


This manageability option allows enterprises to configure the graphics capabilities delivered to individual users in the network based on their demands. Up to 100 users can be served from a single server powered by one VGX board, which Nvidia says will improve user density on a single server compared with traditional virtual desktop infrastructure (VDI) solutions.


Source: Tomsitpro

Read More

Asus unveils new ROG desktops with Ivy Bridge, GTX 680

With Ivy Bridge, Southern Islands and Kepler on the loose, it's a great time to upgrade. Recognizing that fact, Asus has unveiled new enthusiast-grade desktops, the CM6870, CG8270 and CG8580. The first machine is lower specced than the latter two, though it should still hold its own in lightweight games.

The CM6870 is offered with a third-generation Core i3, i5 or i7 processor, various Nvidia and AMD graphics cards (top options are the GT 640 and HD 7470), up to 16GB of DDR3 1600MHz RAM, up to 4TB of storage (there are SATA 6Gb/s ports in case you want an SSD), a Blu-ray drive and a 350W PSU.

In the mid-range, Asus' CG8270 comes with your choice of an Ivy Bridge-based Core i5 or i7, an Nvidia GPU ranging from the GT 620 to the GTX 560 Ti, as well as the same memory and storage mentioned above. It also has a beefier 500W PSU and a larger, sleeker chassis with a brushed aluminum façade.

The CG8580 only offers Core i7 processors and has three graphics configurations: one GTX 560 Ti, two GTX 560 Tis or one GTX 680. It also has Xonar DX audio, dual 128GB SSDs, three PCIe x16 slots (no word on bandwidth), four SATA 6Gb/s ports, a 700W PSU and a "stealth submarine"-inspired case.

Connectivity is largely equal across the systems. The CM6870 has a 16-in-1 card reader, six USB 2.0 and four USB 3.0 ports between the front and back, VGA, DVI-D and HDMI ports, as well as 7.1-channel audio. The CG8270 adds legacy PS/2, while the CG8580 gets two more USB 3.0 ports and S/PDIF-out.

There are various other differences between the packages, too. The CM6870 doesn't seem to ship with peripherals, the CG8580 looks to have a basic keyboard and mouse combo, while the CG8580 touts an ROG-branded mechanical keyboard (Cherry MX Black switches) and a 4000DPI gaming mouse.

The machines also ship with various Asus features, such as Smart Cooling System, which supposedly reduces temps by up to 11.4%, Instant On, AI-Charger, WebStorage, Music Maker, AI Suite II and so on. Availability and pricing are unknown, but we imagine the higher-end units won't be cheap.

Source: Techspot

Tags: Asus, Desktop PC, Ivy Bridge, Graphic Cards

Read More

MSI Launches its Most Powerful Graphics Card, the GeForce GTX 690

Graphics card and mainboard manufacturer, Micro-Star International (MSI), has launched its most powerful graphics card, the GeForce GTX 690, adopting dual GeForce GTX 600 GPUs with 3072 CUDA Cores and 4 GB/512bits GDDR5 memory.

Dual GPUs Provide Double Performance

MSI GeForce GTX 690 graphics card is equipped with dual 28 nm GeForce GTX 680 GPUs with 3072 CUDA Cores (1536units x2) and 4 GB/512bits (256bits x2) GDDR5 memory, supports the latest PCI Express Gen 3 standard and DirectX 11 technology delivering the most powerful performance on earth. Through Quad SLI technology, the ultimate performance of dual graphics cards can definitely satisfy the demands of any enthusiast gamer.

Power Limit Control by Afterburner

The MSI GeForce GTX 680 graphics card supports Nvidia's GPU Boost technology that allows the core clock to be adjusted on the fly for optimal gaming performance. When used with MSI's Afterburner overclocking utility, gamers can control the power limit and clock offset for better overclocking capability. The card is also equipped with advanced fans speed control based on GPU temperature.

Afterburner supports the free video/audio capturing function Predator and can even use smart phones to control the graphics card in desktop machines. When combined with the Kombustor burn-in testing function, it is an indispensable tool for enthusiasts looking to get the most out of their graphics card.

Run 3DVision Surround with a Single Card

MSI GeForce GTX 690 graphics card features three dual-link DVI and one mini DisplayPort connector. With just one GeForce GTX 690 graphics card, users can experience vivid 3D games with 3D glasses and use three 120 Hz monitors through advanced 3DVision Surround technology from Nvidia.

Additionally, support for up to four displays driven by one graphics card allows gamers to make the most of multiple-monitor gaming configurations.

Tags: MSI, Graphic Cards, Nvdia, GeForce GTX 690

Read More

NVIDIA Prepares Two More GK104-based cards - GeForce GTX 660 Ti and 670

The word on the street was that NVIDIA worked on GTX 680 and GTX 690 since third quarter of 2012, and once the work was done on the GTX 680 - the company pulled no stops to make GTX 690 the highest performing single slot dual-GPU card. However, even with high yield of fully enabled GK104 chips enabling the launch of GTX 680 (which are in constant shortage sans one AIB that allegedly has an exclusive deal for some markets), there is a lot of 3.5 billion transistor chips which aren't performing up to par.

In order to address those chips, NVIDIA will launch not one, but two cut-down versions of the GK104 chip: the Geforce GTX 660 (or 660 Ti) and GTX 670 (or 670 Ti). According to WCCFTech, the GK104-335-A2 will power the GTX 670, while GTX 660 may be powered by another revision. Given the way NVIDIA labels the GPUs, we would not be surprised if some of NV partners are in a lot of hot water, since NVIDIA typically uses three-number customer codes (GX1XX-XXX-AX).

GeForce GTX 670 should feature 1344 CUDA cores, same uncut 256-bit memory controller and paltry 2GB GDDR5 memory. The clocks should be set at around 915-950MHz for the GPU, and 1.25GHz QDR for video memory, resulting in 156GB/s of video memory bandwidth. Estimated price for the part should be around $399-429, going head to head against the Radeon HD 7950.

GeForce GTX 660 would be a different bird, with no less than whole GPC (Graphics Processing Cluster) disabled , resulting with 1152 CUDA codes. Memory bus would be cut to 192-bit, meaning again - the odd combination of either 768MB or 1.5GB. Given that it's 2012, we don't see anyone launching a product with 768MB of video memory. This part should go for $199-249, targeting AMD Radeon HD 7800 Series (Pitcairn GPUs).

The pricing structure would leave a pretty large hole between $249 and $399, but so is the performance difference between the two. That room is left to the partners to come up with overclocked cards, liquid cooled products, multiple memory configurations etc. According to our sources, don't expect GK107 to come to desktop anytime soon - all the allocated volume goes into laptops and Ultrabooks.

NVIDIA pricing structure (for now), should look as follows:

• $999 - GTX 690 4GB
• $579 - GTX 680 4GB OC (Preferred AIB Pricing)
• $499 - GTX 680 2GB
• $479 - GTX 670 4GB (Preferred AIB Pricing)
• $399 - GTX 670 2GB
• $249 - GTX 660 (Ti?) 1.5GB

Products are expected to be formally announced next week, with mass availability and custom designs by Computex Taipei 2012, which is scheduled to take place between June 5-9 at World Trade Center and Nangang Exhibition Hall in Taipei, Taiwan.

Source: Vrzone

Tags: Nvdia, Graphic Cards

Read More

Nvidia Announces GeForce GTX 690 Dual-GPU Video Card For $1000 bucks

Delivering the keynote address at the GeForce LAN/Nvidia Game Festival in Shanghai, Nvidia CEO Jen-Hsun Huang announced the company's news video card, the GeForce GTX 690.

The latest card from the company to use dual GPUs (following the GTX 590, which was released last year), the GTX 690 utilizes the new 28nm Kepler architecture Nvidia introduced on the GTX 680 last month.

Huang claimed that the GTX 690 had been "designed from the ground up to deliver the highest performance of any graphics card in history. This particular graphics card we paid special attention to every single detail so that we could deliver the highest thermals, the highest acoustics, and the highest electrical performance with this particular design."

Foremost among the GTX 690's specs are 3,072 CUDA parallel processing cores, which means the card offers essentially the performance of two GTX 680s, although according to Nvidia the GTX 690 will actually run quieter and with better power efficiency than two GTX 680 cards connected in an SLI configuration. The card would contain 4GB of 6GHz GDDR5 RAM, and support all the other features found on the GTX 680 (such as GPU Boost, which is a style of automatic overclocking similar to the Turbo Boost and Turbo Core on Intel and AMD's CPUs respectively).

Nvidia touted the revamped design of the GTX 690, which includes an exterior frame of trivalent chromium-plated aluminum, which Nvidia says provides excellent strength and durability; a new fan housing constructed from a thixomolded magnesium alloy, for improved heat dissipation and vibration dampening; high-efficiency power delivery thanks to the use of a ten-phase power supply and a ten-layer, two-ounce copper printed circuit board (PCB); dual vapor chambers, nickel-plated fins, and an optimized center-mounted axial fan (which Huang bragged spins at 3,000rpm) for cooling; and low-profile components and ducted baseplate channels that reduce airflow obstruction to improve the card's acoustics.
The GTX 690 will be available "in limited quantities" starting May 3, and move to a wider distribution from Nvidia's usual add-in card partners (Asus, EVGA, Gigabyte, MSI, and others) on May 7. Pricing for the GTX 690 is $999 list.

Source: PCmag

Tags: Nvdia, Graphic Cards, GeForce GTX 690

Read More