July 9-10, 2013
San Francisco, CA

Early Bird Tickets on Sale

ARM made its name designing an architecture for low-power microprocessors that are the heart of devices that need long battery lives. But the company’s designs for graphics processors are stepping out of that shadow.

The Cambridge, England-based chip intellectual property design firm said that its partners shipped more than 150 million processors with the Mali graphics units in them, up from 50 million in 2011. The number is projected to hit 240 million in 2013.

The number of licensees has grown by 30 percent to 75 companies, which use the Mali designs in smartphones, tablets, and digital TVs.  The licensing company made the announcement at the Mobile World Congress event in Barcelona, Spain. At the show, ARM will demonstrate GPU Compute, or the use of ARM Mali graphics to handle nongraphics tasks. Key areas that benefit from GPU Compute are photography and games.

“ARM’s Mali has slowly snuck up on the embedded graphics markets, particularly in DTVs and Android tablets where they have established somewhat of a beachhead,” said Patrick Moorhead, an analyst at Moor Insights & Strategy. “Imagination, Qualcomm and Nvidia really need to keep an eye on what they doing in smartphones as ARM is making many strong moves.”

ARM’s Mali GPUs blend performance and power efficiency for smart devices where power consumption is a must. The GPUs are in more than 70 percent of graphics-enabled digital TVs. The GPUs are used in 50 percent of Android tablets and 20 percent of all Android smartphones. ARM’s Mali competes with homegrown graphics cores from Nvidia, Intel, and Imagination Technologies.

Smartphone shipments could hit 1.1 billion units in 2013, according to Strategy Analytics. As the market grows, so does the breadth of devices. With Mali GPUs, gadget makers can diversify their offerings based on the level of graphics fidelity needed. Mali delivers computational photography, face detection, and real-time gaming. The products using Mali graphics range in price from $50 to $650, said Kevin Smith, the vice president of strategic marketing for ARM’s multimedia processing division in an interview with VentureBeat.

“We’ve got wide adoption in diverse markets,” he said.

ARM’s Mali GPUs are designed for integration into a system-on-chip, or a chip that has a bunch of different functions. The GPU is married with a CPU (central processing unit) such as ARM’s Cortex-A series processor. About 95 percent of the Mali graphics processors shipped alongside an ARM Cortex-A processor last year. The number of combinations and choices for phone makers and consumers will keep multiplying this year.

“We are incredibly pleased to see the success enjoyed by ARM partners that have chosen Mali GPUs,” said Pete Hutton, the general manager of the media processing division of ARM. “This impressive market growth has been achieved by only a quarter of the current Mali licensees. In 2013 we look forward to even more of our licensees, who have transitioned to Mali GPUs for improved performance and short development cycles, bringing new solutions to market and enjoying success.”

Mali graphics are being used in Samsung’s Smart TV F8000, LG’s GA7900 and GA6400 smart TVs, Leadcore’s LC1810 smartphone, ST-Ericsson’s NovaThor U8500 ModAp, a variety of phones frm MediaTek, and more than 300 different devices made by Spreadtrum. The ST-Ericsson chips shipped in tens of millions of smartphones in 2012.

“Mediatek addresses a wide range of markets through scalable adaptable solutions,” said Johan Lodenius, the chief marketing officer and corporate vice president of Mediatek. “ARM Mali GPUs enable us to target markets quickly and introduce first class products with a short time to market.”

ARM said that the number of mass market smartphones using ARM Mali-400 and ARM Mali-450 GPUs will grow significantly this year. High-end phones will use the Mali-T600 family of graphics processors. MediaTek

In tablets, the ARM Mali appeared in the Google Nexus 10. It also shipped in Android tablets based on products from AllWinner and Rockchip.

Yesterday, I reported that the new iPod Touch would ship with the A5x processor. That was a mistake in reporting. Greg Joswiak, the vice president of iOS and iPod product marketing, said that the new iPod Touch will ship with the A5 chip, the very same inside the iPhone 4S — not the A5X, which is used in the iPad (2012 model). This error in reporting made sense considering the announcement of new iPods: The A5x, scaled down, could provide the extra horsepower that games need. Or so it seemed.

After confirming with an Apple spokesperson earlier today, the upcoming iPod Touch does in fact have last year’s A5 chip. That information can further be confirmed on Apple’s features webpage for the iPod Touch. But in light of this error, a larger question arises: How is an A5 chip, the same as in the iPhone 4S, going to keep the iPod Touch relevant? The iPod Nano and Shuffle both have very specific functions; the Touch has always been an iPhone minus the phone — all of the capabilities without the girth, the two-year contract, or cellular service. That’s the price. Buy a phone and get an all-in-one device, or get the Touch, pay less, but split the cost between the iPod Touch and something else.

For most people, that’s a no-brainer — buy the iPhone. And with the ridiculous sales figures the iPhone has, Apple knows this. So who buys the iPod Touch? Simple: people who don’t need or want a new phone but still want the benefits of the latest iDevice. We all know parents who buy them for their kids — the responsible sort that doesn’t need a constant connection with their children through another line on that expensive family plan. Or it’s a gift to friends, family, and neighbors. The iPod Touch has always been relatively inexpensive yet remarkably useful, so year after year, it made for one of the best holiday buys.

That changed last year when Apple announced the iPhone 4S but no new iPod — not the Shuffle, not the Nano, and not the Touch. These devices were barely even discussed. Only the iPod Nano was mentioned, and only because Apple wanted owners to upgrade the firmware so they would have access to new watch faces.

Not updating the iPod Touch made sense. The only real difference between the A4 and A5 as far as most people were concerned was that the A5 was a dual-core CPU while the A4 had only one core. But there’s more: The A5 is an ARM Cortex-A9 with a PowerVR SGX543MP2 on a 45nm chip, clocked at 1GHz but scaled back to 800MHz for the iPhone 4S. The A4 is an ARM Cortex-A8 with a PowerVR 535 GPU on a 45nm chip, also scaled back to 800MHz. That’s a whole generation difference in ARM-processing technology.

The reason the iPod Touch never needed to be upgraded is simple enough. Business Insider reported that for the iPad 2, the cost of making the new A5 processor was 75% more expensive than the A4. Apple built the chip to fit in the iPad but didn’t manage to scale it down to the smaller, easier-to-fit-in-a-smartphone 32nm frame. With only a year for each new product and only seven months from the iPad to iPhone 4S, Apple didn’t manage to do that, and the same A5 chip went into the iPhone. This can account for a number of possible reasons why the 4S was such an iterative update. There simply wasn’t enough space to add in features like an LTE antenna or a larger battery.

And the iPod Touch? As a hugely profitable company, one that’s struggled to fit this processor into a larger device while simultaneously knowing that every phone has at least a two-year lifespan, there was only one smart business decision to make: don’t release a new iPod Touch. The old A4 was in tens of millions of iPhone 4s sold worldwide, and they were all capable of running the same applications as the newer iPhone 4S. Meanwhile, the manufacturing of the iPod Touch, with no changes, gets cheaper and cheaper, and the product itself makes money either way. And most customers don’t know the difference because unlike the iPhone, the iPod Touch isn’t numbered. We media label them by generation number … but even in conversation, it’s still the same iPod Touch.

So the new iPod Touch? There’s very little new or noteworthy about it. Just like the iPhone, the iPod Touch lives on a two-year cycle because it has all of the same hardware. Only this time, for this new model, that hardware is already a year old.

Don’t get me wrong. You can read Meghan’s impressions on the iPod Touch for judgment on the actual device. And the upgrades since the last model are pretty major: It has the same 5MP camera that was in the iPhone 4, Siri, a widescreen display … and it even comes in six colors. It may well make for an excellent buy or a great gift.

But don’t be fooled — the iPod Touch doesn’t have new hardware. It has a bigger screen, but that’s it. Everything else is from either the iPhone 4S or from the iPhone 4 (like the camera). In one year’s time, the current iPod Touch will be two generations behind the next iPhone, which is historically when devices stop getting regular software updates and when applications require more power than the older devices can afford. In effect, Apple has limited the lifespan of the iPod Touch by a whole year by using an older processor and older parts while still charging a $300 premium for the device.

---

GamesBeat 2013 is our fifth annual conference on disruption in the video game market. You'll get 360-degree perspectives from top gaming executives, developers, and analysts on what’s to come in the industry. Our theme this year is “The Battle Royal.” Check out full event details here, and grab your early-bird tickets here!

---

In gamer talk, Nvidia says it is unveiling a new weapon of choice for gamers today. In English, that means a new graphics chip. Starting at $299, the Nvidia GeForce GTX 660 Ti GPU (graphics processing unit) is a new midlevel graphics chip that can keep up with the latest high-end PC games.

The new chip, pictured within the add-on graphics card above, is based on the powerful Nvidia Kepler architecture that the Santa Clara, Calif.-based company introduced in March with its high-end chip, the GeForce GTX 680.This new chip is the kind of gadget that will help the PC take back the throne of top gaming machine from the video game consoles.

When Nvidia launched that chip, it reclaimed the throne as the world’s fastest graphics chip, something only gamers or scientists at NASA could appreciate. The new chip will make its way to more of the mass-market, price-conscious gaming enthusiasts. As such, Nvidia says it will bring blazing-fast game graphics to a much wider market.

The chip is a sequel to the GTX 560 Ti (based on the previous-generation Fermi architecture) from 2011. The 660 Ti is 41 percent faster than the 560 Ti, and it is 58 percent faster than the GTX 470 chip from 2010. The 660 Ti falls below the GTX 670, GTX 680, and dual-GPU GTX 690 in the graphics hierarchy. As such, it is Nvidia’s most affordable high-end chip.

The GTX 660 Ti has support for DirectX 11 tessellation, TXAA, and PhysX technologies. That means it will play games faster, with smoother imagery and more realism. Using tessellation means that a character such as Max Payne from Max Payne 3 will have ears that look real, rather than blocky or jagged (as pictured). It can drive three displays from a single graphics card. James Wang, product manager, said in an interview with GamesBeat that the 660 Ti can keep up with rival cards that cost $50 more while consuming 25 percent less power.

Nvidia said that the 660 Ti will run Max Payne 3 at 44 frames per second, compared to a barely acceptable 29 frames per second on the GTX 470. The new Secret World game will run at 61 frames per second on the 660 Ti, compared to 31 frames per second on the GTX 470. The TXAA anti-aliasing technology means that buildings won’t shimmer when you move down a street in a realistic shooter game.

When you put two GTX 660 Ti cards paired together in a single machine, the performance beats rival Advanced Micro Devices’ chip by 21 percent. Those who buy a new GPU from a participating retailer or web site will get a voucher for a free copy of Gearbox Software’s Borderlands 2, which launches next month. Borderlands 2 runs at 78 frames per second on a 660 Ti, compared to 45 frames per second on a GTX 470. Nvidia says the 660 Ti is 20 percent to 30 percent faster at running games than the AMD Radeon HD 7870.

The 660 Ti is based on a 28-nanometer Kepler architecture (a nanometer is a billionth of a meter). It has 1,344 CUDA cores and consumes 150 watts of power.

Suppliers shipping cards with the new 660 Ti include ASL, ASUS, Colorful, ECS, EVGA, Gainward, Galaxy, Gigabyte, Innovision 3D, Jetway, Leadtek, MSI, Palit, Point of View, PNY, Sparkle, and Zotac.

---

GamesBeat 2013 is our fifth annual conference on disruption in the video game market. You'll get 360-degree perspectives from top gaming executives, developers, and analysts on what’s to come in the industry. Our theme this year is “The Battle Royal.” Check out full event details here, and grab your early-bird tickets here!

---

ARM, the British multinational semiconductor and software design firm, is announcing a graphics technology that could power a new generation of portable devices like tablets and smartphones with visuals that could rival game consoles such as Sony’s PlayStation 3 and Microsoft’s Xbox 360.

The technology is ARM’s new series of Arm Mali T600 designs, with anywhere from one to eight graphics computing cores, or brains. ARM develops the underlying architecture and the “cores,” or the basic blueprints of a chip, which its licensees fashion into chips for mobile devices. The new T600 designs will provide ammunition for scores of manufacturers to build ground-breaking portable machines.

The company’s hallmark is creating power-efficient chips that are used in billions of devices each year, making them ideal in smartphones or tablets where battery life is a premium.

The ARM Mali family is a graphics processing unit (GPU) that displays the visuals of devices such as smart TVs, smartphones, and tablets. The GPU can be used in a machine with an ARM central processing unit (CPU) and Khronos Group graphics processing software such as Open GL ES 3.0, which is also debuting today.

“You’ll see this result in faster devices with more fluid user interfaces,” said Steve Steele, senior product manager at ARM, in an interview with GamesBeat. “It can handle graphics with increasing complexity and resolution.”

Long a leader in CPU cores, ARM began creating its Mali graphics cores in 2007. ARM Mali T200 products are shipping now in about 70 percent of digital TVs, 20 percent of Android smartphones, and 50 percent of Android tablets. About 160 manufacturer devices are shipping. About 12 partners shipped 48 million units in 2011, and 25 are expected to ship more than 100 million in 2012.

The previous Mali T400 series was unveiled in November 2010, and products based on it will be coming out in the second half of 2012. Devices based on the T600 series (T624, T628, and T678) are likely to be out next year.

ARM has to keep a steady cadence of designs coming for its licensees to keep up with the rapid pace of mobile innovation. The Mali T600 designs will be able to handle graphics with resolution of 4K by 2K, or far more pixel density than today’s high-definition TVs. They will also have adaptive, scalable texture compression and a 50 percent increase in performance in the same given area as the prior chips.

ARM has a total of 63 Mali licensees and 51 company partners. It has 34 licensees for the Mali T400 and eight for the Mali T600.

The ARM technology competes against rivals designed by Nvidia, which makes the Tegra series of chips, and Imagination Technologies.

---

GamesBeat 2013 is our fifth annual conference on disruption in the video game market. You'll get 360-degree perspectives from top gaming executives, developers, and analysts on what’s to come in the industry. Our theme this year is “The Battle Royal.” Check out full event details here, and grab your early-bird tickets here!

---

Supercomputers are often used, so we hear, to model nuclear explosions. Life-and-death stuff like weather and storm patterns — like maybe global warming simulations. Or maybe the way aircraft wing metals age and weaken over time. So that’s what you might expect would occupy the time of an ultra-sophisticated Cray XK6, theoretically capable of scaling to 500,000 processors and 50 petaflops of peak performance.

But scientists at the University of Edinburgh have turned to supercomputers to understand … ice cream.

“If you zoom in on these substances — if you were able to view them microscopically — you would see that they’re actually made up from quite complicated structures of different materials,” says Dr. Alan Gray, a professor at Edinburgh.

Who knew?

Working with Cray supercomputers, the scientists are trying to understand how ice cream’s constituent parts — like the cookie dough in my favorite flavor — interact and change over time. Part of that is to make it better: more yum per lick, perhaps. And part of that is to make it last longer at peak flavor.

The supercomputer they’re using?

It’s built from graphical processing units originally designed to run games like Quake, or Doom, or (get to the modern stuff, granpaw) BioShock Infinite on your PC. In fact, this particular top-of-the-line ice cream simulator is running 936 NVidia Tesla 20-series processors, each of which comes with six gigabytes of memory and can run at speeds of up to 515 gigaflops.

Source: Nvidia

Nvidia Tesla 20-series GPU

In English, 515 gigaflops translates into 515,000,000,000 calculations per second. That’s 515 billion … each and every second.

It sounds big and it sounds fast, and it is. But … that’s just a single processor. And the machine that Edinburgh used to simulate ice cream, with all of 963 processors, is just a baby machine compared to what is actually possible.

A 500,000 processor Cray XK6 at 50 petaflops could theoretically run 50,000,000,000,000,000 operations each and every second. That’s — if my math language skills have not completely deserted me — 50 quadrillion calculations per second.

That would be the fastest supercomputer on earth, faster than the current champ at Lawrence Livermore National Laboratory, which runs 16.32 petaflops.

And that makes my head hurt. Even more than an ice cream brain freeze.

Here’s the video:

Image credit: iFong/ShutterStock

With the debut of  its code-named Kepler project, Nvidia is retaking the crown today as the creator of the world’s fastest graphics chip. Most people may not care about that, but hardcore gamers who play the latest games will be happy.

The new chips will take PC technology a leap forward as the chips make their way into new gamer desktops and other high-end machines. Nvidia paid a lot of attention to balancing the system’s power efficiency, so new computers based on the machine will not only be fast, they’ll be more power efficient, will fit in a smaller space, and will operate more quietly.

The next-generation chip is called the GeForce GTX 680 and is the result of 1.8 million man-hours of work over five years. With this chip, Nvidia reclaims the fastest-graphics-chip title from Advanced Micro Devices’ code-named Tahiti chip, formally known as the AMD Radeon HD 7970, analysts say. The 680 is just one of several new models of chips based on the Kepler architecture. Already, new laptops are being introduced with Kepler-based notebook graphics chips, dubbed GeForce GT 640M.

As an example, a single graphics card with the new chip can run Epic Games’ high-end game demo, Samaritan, without any visible flaws, Nvidia’s Justin Walker, senior GeForce product manager, told VentureBeat that. And it can do so using a power supply that consumes 195 watts. Last year, it took three Fermi-based GeForce GTX 580 graphics cards running on a power supply with 730 watts to run the same demo.

“This is the fastest and most efficient GPU (graphics processing unit) ever built,” Walker said. “It’s a game changer for us.”

The combination of performance and power efficiency means that Nvidia will likely score a lot of wins in Ultrabooks, the Intel-based laptops that are thin like the MacBook Air but affordable and fast. Nvidia’s new GeForce 600M series of Kepler-based graphics chips will be used in the notebook computers. Both the desktop chips and the laptop chips are available now. And the days of loud fans or exotic power supplies may be numbered. The 600M series will likely be used in Ultrabooks with Intel’s upcoming Ivy Bridge processor.

Rene Haas, general manager of Nvidia’s notebook graphics division, said that, contrary to popular belief, laptops with standalone graphics chips are not disappearing despite the introduction of combo microprocessor-graphics chips from Intel and AMD. In 2011, computer makers shipped 75 million laptops with standalone graphics, Haas said. Nvidia has four mobile chips in the 600M family: the GeForce 640M, the 620M, the 660M, and the 675M. Laptops with those chips will be able to play all of the top 30 PC games, Haas said.

Patrick Moorhead, analyst at Moor Insights and Strategy, said that up until this point it was tough to get discrete graphics chips into Ultrabooks because of the power constraints. ”Kepler decreased power by half at the same performance point and also enables sophisticated power sharing between CPU (central processing unit) and GPU,” he said.

The previous GeForce GTX 580 had a total of 512 cores, with 32 streaming multiprocessors in each core. The 680 has 192 streaming multiprocessors in each core and eight cores altogether, for a total of 1,536 cores. Full told, the 680 has more than 3.5 billion transistors, the basic components of electronics, compared to 3 billion in Fermi.

Kepler can run three high-definition monitors in stereoscopic 3D, whereas it took two Fermi boards to do the same thing. AMD’s graphics chip can run six screens at the same time, but Nvidia’s Walker said the only time six screens is useful is at a trade show. Gamers don’t want to play with six screens because the bezels between the screens are too disruptive, he said.

Kepler chips are based on the 28-nanometer process at Taiwan Semiconductor Manufacturing Co. That compares to 40-nanometer technology used in the previous generation Fermi chips, which debuted in March 2010. Nvidia said that the 680 is 300 percent faster in DirectX 11 tessellation performance and 43 percent faster than AMD’s Radeon HD 7970 in cutting-edge games such as Elder Scrolls V: Skyrim. Many games run about 20 percent faster.

Walker said the 680 has twice the performance per watt of the GeForce GTX 580. The 680 also has some new technologies, including a “streaming multiprocessor block,” known as SMX, that is more power efficient. The new FXAA and TXAA antialiasing technologies help get rid of the jaggies, or jagged diagonal lines in games. And they do so without slowing the overall speed of the graphics chip as much as in the past. The 680 can also now run 3D Vision, Nvidia’s stereoscopic 3D solution, in a single graphics card.

Kelt Reeves, president of Falcon Northwest, a maker of high-end gaming systems, said,“The GTX 680 lays down what should be whiplash-inducing speed at the sound of a whisper. Even at full throttle, it doesn’t heat up. In the immortal words of Obi-Wan describing a lightsaber, it’s ‘an elegant weapon for a more civilized age.’”

Mark Rein, vice president of Epic Games, said he used a GTX 680 to demo a preview of the Unreal Engine 4 for select developers at the recent Game Developers Conference in San Francisco. Manufacturers making graphics cards with the 680 include ASL, Asus, Coloful, ECS, EVGA, Gainward, Galaxy, Gigabyte, Innovision 3D, Jetway, Leadtek, MSI, Palit, Point of View, PNY, Sparkle, and Zotac. The cards will sell for $499. Computer makers shipping laptops with the new chips include Acer, Asus, Dell, HP, Lenovo, LG, Samsung, Sony, and Toshiba.

An Acer Timeline Ultra M3 laptop uses the GTX 640M graphics chip, and it weighs 5 pounds, is 20 millimeters thick, and has an eight-hour battery life. By comparison, in March 2010, you could buy an Alienware laptop with a GeForce GTX 285 that weighed nine pounds, was 50 millimeters thick, and had three hours of battery life.

Nathan Brookwood, analyst at Insight 64, said, “No doubt about it, Nvidia has reclaimed the single-chip performance crown. The high-end is a small niche with big bragging rights. The challenge will be to move the new technology to mainstream price points.”

Jon Peddie, analyst at Jon Peddie Research, said the bragging rights for having the fastest graphics chip are always fleeting. But he is impressed with how much faster Kepler is than the older Fermi chips.

Sept. 9 - 10, 2013
San Francisco, CA

Early Bird Tickets on Sale

Nvidia is forging ahead with its plans to revolutionize supercomputers and workstations with a number of announcements today. Among them, the Barcelona Supercomputing Center will be the first in the world to adopt a solution that combines Nvidia’s low-power ARM-based Tegra central processing units (CPUs) with Nvidia’s graphics processing units (GPUs).

That combination could be a powerful way to improve computing power without consuming a lot of electricity. Power consumption and the electricity costs that go with it are now the No. 1 cost for maintaining supercomputers these days. Until now, Nvidia’s Tegra CPUs were used as mobile device processors, and most supercomputers used Intel microprocessors.

The supercomputers will use the hybrid architecture that combines the speedy serial (one thing after another) processing nature of CPUs with the parallel (many small tasks at once) nature of GPUs. The Barcelona Supercomputing Center plans to improve its energy efficiency by two to five times, according to the announcement today at the SC11 supercomputing conference in Seattle.

Of course, Nvidia is a long way from knocking Intel out of supercomputers in the big picture. Intel has 64-bit processors while Nvidia doesn’t and that’s an important feature for high-end computers. Intel is also using its manufacturing advantages to race ahead with low-power server chips, and it is starting initiatives to use low-power Atom chips in microservers.

The GPUs take advantage of Nvidia’s Cuda programming environment to perform non-graphics computing tasks on a GPU. The Barcelona center ultimately plans to deliver exascale-level performance while using 15 to 30 times less power than current supercomputers. Nvidia is the world’s largest independent graphics chip maker, but it has recently made headway in the processor market with its ARM-based Tegra CPUs.

An exascale supercomputer will, at some point in the future, be able to execute an exaflop. That is a billion billion floating point operations per second. A flop is the equivalent of taking two 15-digit numbers and multiplying them together. Right now, supercomputers such as the upcoming Titan machine at the Oak Ridge National Laboratory are targeting computation levels at 20 petaflops. A thousand petaflops is equal to one exaflop. So supercomputers have a long way to go to get to exascale.

Alex Ramirez, leader of Barcelona’s Mont-Blanc Project, said that CPUs alone often consume the lion’s share of the energy — 40 percent or more — in a supercoputer. By comparison, he said the Mont-Blanc machine will use the Tegra mobile processors to achieve a four to 10-fold improvement in energy efficiency by 2014.

Nvidia will create a new hardware and software development kit to enable more ARM-based supercomputing initiatives. The Barcelona version will feature a quad-core Nvidia Tegra 3 ARM-based CPU along with an Nvidia GPU. The center is starting with 256 Tegra CPUs and 256 GPUs. The kit will be available in the first half of 2012. Nvidia is naming the Barcelona center a Cuda “center of excellence,” the 14th such institute.

Nvidia is also introducing its Maximus circuit cards (pictured right) for advanced workstations. The Maximus technology can be used to design fancy cars and other high-computation tasks that normal PCs can’t handle. The Maximus cards will combine graphics and computation in the same system. The Maximus technology combines Nvidia’s Quadro professional workstation GPUs with Nvidia Tesla C2075 companion processors (which are separate computing cards).

Previous workstations forced designers and engineers to do compute-based and graphics-based work separately or offline. Now, with Maximus, they can do both of those kinds of tasks at the same time on the same machine, said Jeff Brown, general manager of Nvidia’s professional solutions group. The workstations will speed up science, engineering and design applications from Adobe, Ansys, Autodesk, Bunkspeed, Dassault Systèmes and MathWorks.

Meanwhile, Nvidia has joined with Cray, the Portland Group, and Caps to create a new standard for parallel programming known as OpenACC. That will make it easier to accelerate applications that use both CPUs and GPUs. The OpenACC should benefit programmers working in chemistry, biology, physics, data analytics, weather and climate, intelligence, and other fields. Initial support for OpenACC is expected to be available in the first quarter of 2012.

CloudBeat 2011 takes place Nov 30 – Dec 1 at the Hotel Sofitel in Redwood City, CA. Unlike any other cloud events, we’ll be focusing on 12 case studies where we’ll dissect the most disruptive instances of enterprise adoption of the cloud. Speakers include: Aaron Levie, Co-Founder & CEO of Box.net; Amit Singh VP of Enterprise at Google; Adrian Cockcroft, Director of Cloud Architecture at Netflix; Byron Sebastian, Senior VP of Platforms at Salesforce; Lew Tucker, VP & CTO of Cloud Computing at Cisco, and many more. Join 500 executives for two days packed with actionable lessons and networking opportunities as we define the key processes and architectures that companies must put in place in order to survive and prosper. Register here. Spaces are very limited!

The supercomputer will pave the way for “exascale computing” and will be known as Titan. It will use Tesla graphics processing units (GPUs) from Nvidia to deliver GPU computing, or parallel processing that uses the graphics chips for non-graphics processing tasks. The system will deliver over 20 petaflops of peak performance. That’s more than two times faster and more than three times more energy efficient than today’s fastest supercomputer, the K computer in Japan. The Titan system will probably be the world’s most powerful supercomputer upon its installation, according to the semiannual Top500, which ranks computers based on their peak performance.

Titan will let scientists use massive parallel computing power for research and discovery in a variety of fields, including material science, energy technology, medical research, geoscience, and others. It’s worth noting that microprocessor makers IBM and Intel lost out on the deal.

“All areas of science can benefit from this substantial increase in computing power, opening the doors for new discoveries that so far have been out of reach,” said Jeff Nichols, associate laboratory director for Computing and Computational Sciences at the lab in Oak Ridge, Tenn.

Titan will be used to research things such as more viable biofuels, cleaner burning engines, safer nuclear energy, and more efficient solar power. Steve Scott, chief technology officer of Tesla products at Nvidia, said that the Tesla GPUs will provide over 85 percent of the peak performance of Titan, showing that a supercomputer that runs on microprocessors alone is less efficient than one that runs on GPUs too.

The combination of microprocessor and GPUs together will help break through barriers of performance that Intel-based supercomputers have hit in recent times, due to concerns about cooling and overheating, according to Addison Snell, chief executive of Intersect360 Research.

In the first phase of the Titan deployment, Oak Ridge will upgrade its existing Jaguar supercomputer with 960 Tesla M2090 GPUs using Nvidia’s code-named Fermi designs. These GPUs will serve as companion processors to multi-core microprocessors in that Cray XK6 supercomputer. In the second phase, expected to begin in 2012, Oak Ridge plans to use up to 18,000 Tesla GPUs based on the next-generation architecture code-named Kepler.

July 9-10, 2013
San Francisco, CA

Early Bird Tickets on Sale

Graphics chip maker Nvidia has high hopes for its Tegra mobile processor.

Nvidia’s forecast for its upcoming third-quarter revenue was even more optimistic than Wall Street analyst expectations, thanks to the company’s confidence in its Tegra smartphone processor. The company forecast 4 percent to 6 percent revenue growth for the third quarter this year, putting its forecast revenue somewhere north of $1.06 billion.

Looking at the quarter just completed, Nvidia’s revenue rose 26 percent to $1.02 billion in the second quarter this year, up from $811 million in the second quarter last year. The company flipped from a $175 million loss in the second quarter last year to a $174 million profit in the second quarter this year after reducing its cost of revenue by nearly 28 percent.

This was only the second quarter of sales for its Tegra chip, a graphics processor designed for high-end smartphones like those running Google’s Android mobile operating system. The chip appears in the Samsung Galaxy Tab 10.1, a thin tablet computer that runs Android’s latest tablet-optimized operating system called Honeycomb.

Nvidia chief executive Jen-Hsun Huang said he expects Tegra to continue to perform well for the next two quarters. The company’s Tegra chip appears in the Motorola Photon, a 4G smartphone, and the Droid X2. The Tegra accounts for 10 percent of all Android devices shipped today.

There is a quad-core Tegra mobile processor in the pipeline called the Kal-El that the company plans to ship with high-end smartphones. The Kal-El is more powerful and actually consumes less power than the Tegra 2, Huang said. The company is also working on a unified chipset that includes both a modem and an application processor that will go into lower-end smartphones.

“That part of the marketplace is really not well served by anyone, we are going to build an integrated application processor and modem to address that,” Huang said in today’s earnings call. “That allows us to address the lower end of the smartphone, that part of the marketplace will become quite large over the next few years.”

The company’s mainstream graphics processing wasn’t going anywhere, though. Huang said he expects the company to sell discrete graphics chips for high-end notebooks and workstations for the foreseeable future thanks to high GPU “attach rates” internationally — basically the number of machines that carry a discrete GPU. It’s around 80 percent in China and 70 percent in Europe, but only 20 percent in the U.S.

“I don’t know exactly why, maybe it’s because people have a greater sense of value outside the U.S.,” he said. “I wouldn’t be surprised for our workstation business to continue to grow for many years to come as the world becomes a more design economy.”

The Santa Clara, Calif.-based company produces the Nvidia Tegra — a system on a chip much like Apple’s A4 processor in its iPhone and iPod Touch devices — for use in mobile devices like phones. The Tegra is a combination of Nvidia’s graphics processing technology and other ARM-based chips. It’s competing for marketshare in a somewhat crowded space, as Advanced Micro Devices and Intel also produce low-power system-on-a-chip products for use in mobile devices.

The Tegra will be included in a number of smartphones run on Google’s Android operating system, according to a report by Reuters. That should give Nvidia a nice boost to its primary market, which is mainly video processors for gamers. Nvidia recently announced a new lineup of video processors, the GTX 580 GPU, that once again broke the record for the fastest graphics processor.

Its most recent quarterly performance wasn’t quite as stellar as its outlook. Nvidia reported a 21 percent drop in profit, from $108 million in the third quarter a year ago to $85 million in the third quarter this year. Nvidia’s revenue also fell 6.5 percent to $844 million in the third quarter this year, down from $903 in the same quarter a year earlier. Nvidia said it expects 3 to 5 percent growth in revenue for the upcoming quarter.

That’s likely a result of the recent slowing growth in chip sales. Chip sales grew 26.2 percent in September compared to the same month a year earlier but were only up 2.9 percent from the month before. Chip sales are usually an indicator of demand for the devices they power, such as computers, phones and other mobile devices. The chip sales likely indicate weakening demand for gadgets and computers heading into the holiday shopping season — which makes Nvidia’s outlook all the more surprising.

Its earnings reports today were in line with the expectations of a number of Wall Street analysts, so there wasn’t much of a downside for investors. They were instead satisfied with the upbeat outlook from the GPU manufacturer. Shares of Nvidia were up 4.5 percent to $13.18 in extended trading today.

Adobe

Speaking at Nvidia‘s GPU Technology conference, Adobe researchers David Salesin and Todor Georgiev showed how they can fix bad photos using a technology that is not yet commercially available. They showed that they could take an out of focus photo and use computing techniques to put the photo into focus.

Once this technology is available in the future, it could make us all into better photographers. The technology makes use of CUDA, the programming technology that allows a graphics chip to do non-graphics computing tasks.

You can see an example of the technology in action with the pictures here. In the picture at the right, the girl is out of focus and the cans behind her are in focus. In the picture at the top, Adobe has processed the photo so that the girl is in focus and the cans are not. Now, you can’t do this with just any kind of camera photo. The photos have to be taken with a camera that has a “plenoptic lens.” That technology was first developed by a team at Stanford University. This kind of lens can also be used to stitch together a single large image from lots of small images, as shown in the pictures at the very bottom. 

---

GamesBeat 2013 is our fifth annual conference on disruption in the video game market. You'll get 360-degree perspectives from top gaming executives, developers, and analysts on what’s to come in the industry. Our theme this year is “The Battle Royal.” Check out full event details here, and grab your early-bird tickets here!

---

In short, Nvidia has worked with software company PGI to create a new compiler to take code for its graphics chips and run them on machines without its graphics chips. Before you dismiss this announcement as a narrow one, you have to realize that its programming technology, CUDA (Compute Unified Device Architecture), is part of Nvidia’s plan to steal more of the computing inside the computer for itself. It’s a platform technology that has been a big draw for those programming compute-intensive tasks, from sophisticated math computations to video encoding. The company has built an entire conference, the GPU Tech event in the San Jose Convention Center in San Jose, Calif., around CUDA. That’s where it announced CUDA-x86, as the new compiler software is called.

Nvidia created CUDA to take advantage of the parallel computing capabilities of its graphics chips. The graphics chips are able to process lots of things in parallel, or at the same time, compared to a microprocessor, which mostly works in a serial fashion. But CUDA allows the graphics chips to do non-graphics computing tasks that were formerly done by Intel’s chips. The more CUDA spreads, the more demand is created for Nvidia’s graphics chips. And, consequently, there is less demand for Intel’s chips. Looked at this way, CUDA is an attempt by Nvidia to defeat Intel, or at least rein in its ambition of dominating computing within the PC, without doing an Nvidia-made microprocessor.

There are some 250 million CUDA-enabled computers in the market, thanks to the inclusion of CUDA-processing hardware inside Nvidia’s GeForce graphics chips. Now, with CUDA-x86, CUDA will also run on Intel-compatible computers that don’t have Nvidia’s graphics chips.

“We can now run CUDA on any PC or server in the world,” said Jen-Hsun Huang, chief executive of Nvidia, in a keynote speech at the conference today.

CUDA-x86 attracts those software developers who want to reach a wider audience than CUDA can currently hit. Left unspoken is that CUDA is Nvidia’s thrust to beat back Intel, which has tried to take over Nvidia’s turf by putting graphics into a microprocessor with its latest chips, code-named Sandy Bridge. The tug-of-war between Nvidia, Intel and Advanced Micro Devices, is kind of like a thinly veiled Cold War between partners in the PC.

CUDA, viewed through this lens, is Nvidia’s bid to remain relevant by winning over the hearts of computer programmers through software that they can’t live without.

---

GamesBeat 2013 is our fifth annual conference on disruption in the video game market. You'll get 360-degree perspectives from top gaming executives, developers, and analysts on what’s to come in the industry. Our theme this year is “The Battle Royal.” Check out full event details here, and grab your early-bird tickets here!

---

Code-named Sandy Bridge, the hybrid chip is a threat to the maker of stand-alone graphics chips such as Nvidia and Advanced Micro Devices. AMD is creating its own rival hybrid chips, but not Nvidia. Paul Otellini, chief executive of Intel, said the company would begin shipping the Sandy Bridge chips in “very high volume” in the first half of 2011.

“Sandy Bridge will revolutionize the PC,” Otellini said. “This is a very important chip to Intel.”

Otellini showed a working version of the chip in a laptop on stage during his keynote at the Intel Developer Forum, a conference for Intel developers that began today in San Francisco. In the demo, Otellini showed that the chip could run Starcraft II: Wings of Liberty, the most popular PC game on the market, without flaws. The demo ran side by side with a version of the game running on a stand-alone graphics chip.

Nvidia says it isn’t threatened by Sandy Bridge, which it says is akin to a “turboprop in an age of jet engines.” The company says that its graphics chips can run DirectX 11 graphics, which meets the highest standards for graphics on computers today. It’s also worth noting that StarCraft II is not the most demanding game when it comes to 3D graphics. The majority of readers polled in our story last Friday on Sandy Bridge believe that Intel won’t kill off the stand-alone graphics chip.

The Sandy Bridge chip is the latest attempt to put an end to the ongoing debate about whether graphics processing should be done with a much more powerful 3D graphics processing unit, or GPU, or if it can be handled better as part of a computer’s central processing unit, CPU, also known as the microprocessor.

Intel launched a combo chip last year that glued together two chips in a single package. But Nvidia laughed that chip off as brain-dead when it came to running the top 30 computer games. But this second-generation effort, Sandy Bridge, combines the two chips into one and poses a greater threat to Nvidia. Anand Lal Shimpi, a noted hardware reviewer at Anandtech, said he thinks entry-level GPUs will be unnecessary in the wake of Sandy Bridge’s introduction.

Sandy Bridge does have some features that aficionados will appreciate, such as the ability to display stereoscopic 3D Blu-ray videos and high-definition TV. It can support the Intel Wireless Display, which can display the image on your laptop on the big screen TV in your home. And it will have high-performance transcoding, or the ability to translate video from one format to another so that it can run on just about any device. Intel said its goal was to improve its graphics performance by 10-fold from 2006 to 2010. With Sandy Bridge, it has hit a 25-fold improvement.

Intel recognizes that it isn’t going to kill off the market for $600 graphics cards that hardcore gamers want. But the market trends favor its direction, Intel said. By 2014, about 80 percent of the PCs shipped are expected to have hybrid chips (which Intel calls Processor Graphics), according to market researcher iSuppli.

After Otellini’s speech, Intel executive Dadi Perlmutter showed that Sandy Bridge, with four processing cores (or brains), can dynamically shift from high-power to low-power modes as needed to preserve a laptop’s battery life. Otellini said the hybrid chips can be used in both laptops and all-in-one desktop PCs, which combine a monitor and computer in the same chassis.

In a post-keynote session, Intel fellow Tom Piazza said that Intel’s Sandy Bridge chip will not run DirectX 11 graphics, but he noted there are very few DirectX 11-only games now and most will default to earlier technology. He also said Intel’s chip will run most mainstream games, but not the high-end games. The typical use-case will be that someone will use productivity applications on a laptop during the day that do not require much graphics performance and do not strain the battery. Then they can go home at night and play high-end games that consume more power.

Otellini said Intel’s goal with Sandy Bridge is to target the mainstream computing market. He noted in his talk that 1 million PCs are being sold a day now. Here is some video of Otellini and Perlmutter at the press Q&A after the speech.

Code-named Sandy Bridge, the chip will figure prominently in the keynote speech of Intel chief executive Paul Otellini, who kicks off the Intel Developer Forum event in San Francisco on Monday.

The processor-graphics combo chip is available in prototypes now and will ship to customers in early 2011. It will target low-end desktop computers and laptops, and could cause a big headache for Nvidia, the maker of stand-alone graphics chips.

The Sandy Bridge chip is the latest attempt to put an end to the ongoing debate about whether graphics processing should be done with a much more powerful 3D graphics processing unit, or GPU, or if it can be handled better as part of a computer’s central processing unit, CPU, also known as the microprocessor.

Intel launched a combo chip last year that glued together two chips in a single package. But Nvidia laughed that chip off as brain-dead when it came to running the top 30 computer games. But this second-generation effort, Sandy Bridge, combines the two chips into one and poses a greater threat to Nvidia. Anand Lal Shimpi, a noted hardware reviewer at Anandtech, said he thinks entry-level GPUs will be unnecessary in the wake of Sandy Bridge’s introduction. (See Anandtech chart at right, which compares the performance of existing Intel-compatible integrated graphics chips, where a graphics chip is combined with a chip set).

“Is it enough to kill all discrete graphics? No,” Anandtech wrote. “But it’s good enough to really threaten the entry-level discrete market.”

One of the reasons Intel can do this is Moore’s Law, the notion formulated by former Intel chairman Gordon Moore that says chip performance doubles every couple of years. As it makes circuitry smaller, it can fit more electronics onto a chip, improving performance. By moving to a new generation of manufacturing technology, Intel can combine a capable microprocessor (with four cores, or processing brains) with a decent graphics component.

Intel’s Otellini said during the company’s recent earnings call that Intel was accelerating its investment in new 32-nanometer manufacturing technology because of strong demand from PC makers. Meanwhile, Advanced Micro Devices is preparing to launch its own hybrid chips, under the Fusion brand name, early next year.

Nvidia, meanwhile, continues to be a naysayer on the capabilities of hybrid chips and is skeptical of Intel’s (as yet unreleased) performance claims.

“They are launching a faster turbo-prop in a world that has moved on to jets,” said Ken Brown, an Nvidia spokesman.

You would expect that, since Nvidia doesn’t have its own microprocessor. But the company points out that Intel’s Sandy Bridge won’t be able to run DirectX 11, which is the graphics standard from Microsoft that governs whether developers can take advantage of certain cool graphics features. Nick Knupffer, spokesman for Intel, says that Intel is working on boosting its investment in driver technologies so that it will be able to run more games with better graphics.

“Integrated graphics and standalone graphics each have their place in the market in terms of performance and power consumption,” said Dean McCarron, analyst at Mercury Research. “Both graphics segments have coexisted for more than a decade, during which the capabilities of both segments have improved tremendously. It is highly unlikely either segment will displace the other, and increasingly we have seen active coexistence, particularly in the mobile market where computer makers are configuring notebooks to make use of both types of GPUs in the same platform.”

Sandy Bridge does have some features that aficionados will appreciate, such as the ability to display stereoscopic 3D Blu-ray videos and high-definition TV. It can support the Intel Wireless Display, which can display the image on your laptop on the big screen TV in your home. And it will have high-performance transcoding, or the ability to translate video from one format to another so that it can run on just about any device.

Intel recognizes that it isn’t going to kill off the market for $600 graphics cards that hardcore gamers want. But the market trends favor its direction, Knupffer said. By 2014, about 80 percent of the PCs shipped are expected to have hybrid chips, which Intel calls Processor Graphics, according to market researcher iSuppli.

What do you think? Please take our poll.

Will Intel succeed with hybrid graphics-processor chips, or will Nvidia rule with stand-alone graphics chips?survey software