NVIDIA’s GeForce team put on a show at the Maker Faire for the tens of thousands of do-it-yourselfers crowding through the grounds of the San Mateo County Event Center for the weekend event.

The Faire is at the center of a movement of do-it-yourselfers who take pride in mastering the technologies in the world around them, whether that means turning scooters and sheet metal into cupcake cars — complete with sprinkle-adorned hats — or learning how to mix Diet Coke and Mentos into magnificent, and messy, displays of do-it-yourself science.

Hands on: NVIDIANs walked fairgoers through the process of building a PC.

NVIDIA’s GeForce team fit right in, leading attendees through hands-on workshops showing them how to build their own PC, overclock a GPU and turn a PC case into a work of art.

“The reason we’re here is we want to celebrate the spirit of do-it-yourself,” NVIDIA’s Peter Kingsley said as he toted his 20-month-old daughter around the show.  “Building your own GeForce gaming PC is easy, cost efficient, rewarding and a lot of fun.”

In between sessions led by NVIDIANs clad in black and green t-shirts, the GeForce hardware on display at NVIDIA’s booth drew lustful glances.

“What I would give for that PC,” said Chris, as he eyed a machine equipped with three NVIDIA GTX Titan graphics cards.

“I’m a total NVIDIA fanboy,” said David, a freshman at Harvey Mudd College, before diving into a session led by NVIDIA’s Tom Petersen explaining how to tune up your GPU. “All this hardware is first rate.”

Also drawing gawkers: Brian Carter — who runs Bods Mods, a custom PC case shop — hand assembled a robot-shaped PC case out of acrylic over the course of the weekend as fair-goers asked him about his work.

The clear plastic case, and its motorized robot arms, drew plenty of comments as Carter pieced the machine together.

“Amazing, that’s just amazing,” said Andy, who was showing his son, Rob, around the Maker Faire.

Andy, who hand-built his own gaming PC for sessions of “Call of Duty: Black Ops II,” was inspired.

“We need to build him one at some point,” he said, gesturing towards Rob, who grinned. “In fact, I think it’s time to get started.”

Mission accomplished.

NVIDIA will be at the Maker Faire all weekend at booth #328. Check our list of workshops and plan your day here: http://ow.ly/l8ODO

GeForce 320.14 drivers and optimal game settings for Metro: Last Light are available starting today through GeForce Experience.

NVIDIA worked closely with 4A Games to deliver a truly next-gen gaming experience in Metro: Last Light, complete with explosive PhysX effects, immersive 3D Vision Surround technology, and DirectX 11 tessellation.

For more details, refer to the release highlights on the driver download pages and read the GeForce driver article on GeForce.com.

Enjoy the mutant-ridden Metro catacombs with our new GeForce Game Ready drivers and let us know what you think.

Driving this ambition is an upstart — located over a Home Depot in the scruffy Bay Area town of San Leandro — that’s committed to showing how technology can turn Hollywood on its head.

PhaseSpace CEO Tracy McSheery is using his company’s patented system — which substitutes light-emitting diodes (LEDs) for the reflectors used with most motion capture setups — to capture performances that can be woven into elaborate virtual worlds, thanks to GPUs.

Virtual Movies

McSheery has already built a business helping would-be movie makers pitch their stories. At our recent GPU Technology Conference, he told attendees that the speed and power offered by GPUs helps filmmakers create “pre-visualizations” of entire movies for $50,000 or less. No need to sit down and read a script. “We can prototype every line of dialog,” McSheery says.

An early sketch for a scene from an artist …

… is fleshed out into something more detailed …

… before being turned into a 3D model animated characters whose movements are generated by PhaseSpace’s motion-capture technology can inhabit.

But the UC Berkeley-trained engineer isn’t content to just give filmmakers the tools for putting together rough drafts of the real thing. He’s using technology to bring a long-time dream — “Tower of the Dragon” — to fruition.

‘Top Gun’ Meets ‘Game of Thrones’

If all goes well, the film will tell an intriguing tale. It features a young heroine on a medieval planet battling fire-breathing dragons with the help of a dragon companion and a team of fighter jets. McSheery wants to put the film on screens late next year.

A $50 million box office take for the work could open the door for many aspiring, low-budget filmmakers and really shake things up in Hollywood, McSheery says.

Revolutionizing Moviemaking

And it’s not the film itself that promises to be groundbreaking so much as how it’s being made. Using GPU-equipped PCs and PhaseSpace’s cutting-edge motion capture tools, his crew is employing the “pre-viz” approach McSheery believes will revolutionize how movies are made.

The system revolves around the LED lights PhaseSpace places on its actors. Instead of motion-capture cameras marking movement by locating reflectors, McSheery’s cameras are getting constant signals from the LEDs, giving them more information, and thus more detailed movement.

Using McSheery’s patented system, PhaseSpace’s 15 employees can record the motions of actors as they fight, leap, and emote their way through scenes. A director, meanwhile, carries a tablet computer that gives a peek at the virtual scenery.

“The attitude that we can fix it later is why Hollywood films are costing $100 million to $200 million,” he says.

In addition to PhaseSpace’s patented motion-capture systems, the crew is relying heavily on PCs equipped with NVIDIA’s Kepler-based Quadro K5000 video card and powerful Autodesk software.

Without the GPU component, says McSheery, the project would take much longer — and exceed his budget long before completion. Specifically, his graphic artists are getting more responsiveness from the software, with designs morphing in near real-time as they’re viewed from a multitude of angles.

“We’re proving that a PC and GPU graphics card can do the job of an army of artists,” says McSheery. “Artist months become artist days.”

Cheaper, Better, Faster

Behind all of his technological goals is a passion for movies, and a sense that the magic of moviemaking has been compromised. McSheery believes that Hollywood’s excessive spending is hurting the quality of big-budget films, with studios insisting that expensive scenes survive final cuts regardless of their flaws.

GPUs and other modern tools, he says, “allow us to try things over and over again, visualize them, and then decide whether we’ll use them.”

In other words, technology might be the key to improving the storytelling aspect of movies.

And it’s not just animated films that can benefit. McSheery says, the technology can be used just as effectively to assemble pre-visualizations of live-action films — a fact he intends to demonstrate with his next film project, a sequel to “When Harry Met Sally” currently dubbed “When Sally Left Harry.”

Now a pair of researchers in Japan has used GPUs and the CUDA parallel programming model to create a 100,000 neuron simulation of the human cerebellum, one of the largest simulations of its kind in the world. And they’ve put their model to the test by applying this knowledge to teach a robot to learn to hit a ball.

Tadashi Yamazaki at the University of Electro-Communications in Tokyo, and Jun Igarashi at Okinawa Institute of Science and Technology Graduate University in Okinawa, recently issued a paper detailing how they used NVIDIA GPUs to build a large-scale network model of the human cerebellum. They began this work while at the RIKEN Brain Science Institute near Tokyo, a top international center for advanced brain research.

The two believe that modeling the cerebellum could help robots move around more easily and learn to respond autonomously to their environments, a problem that has proven to be a daunting problem for conventional approaches. And in turn, they hope to shed more light on how cerebellum motor control works.

Their work is part of a subfield of robotics called “biomimetic” robotics that aims to help robots deal with ever-changing environments by mimicking some of the ways that humans solve these problems.

The robot’s task is to learn the timing needed to hit a flying ball, mimicking the sort of visual thinking humans use to quickly learn how to navigate through the real world.

According to Igarashi, their work involved modeling realistic neural brain function to enable the robot to interact with its environment, which is no easy task.

“Our physical actions change the environment, which changes the sensory input to human brain our sensation. The brain then processes this changed sensory information and determines what action to take. It is called the ‘sensorimotor loop,’” Igarashi explains. “The brain must continue to choose appropriate actions on the basis of gradually-changing sensory information.”

One of the biggest challenges in modeling neural brain function: simulation speed. Using a CPU alone it took 98 seconds of compute time to figure out how to respond to a stimulus lasting just one second. Using GPUs resulted in a 100x speedup, giving the GPU-based system the speed needed to handle real world tasks.

To show their system in action, the researchers demonstrated their robotic system learning – in real time – how to hit a small plastic ball thrown by a toy pitching machine with a round plastic racket.

The robot’s task is to learn the timing needed to hit a flying ball, mimicking the sort of visual thinking humans use to quickly learn how to navigate through the real world. “When the ball speed is changed the robot forgets the learned timing and relearns the new timing, rather than just repeating what it learned before.” Yamazaki says.

Using GPUs resulted in a 100x speedup, giving the GPU-based system the speed needed to handle real world tasks.

To be sure, none of this will result in a robot that can walk into a batting cage and start hitting dongs anytime soon. It could be years before scientists agree on a standard model of how the cerebellum works, and putting the results into a working robot would require this work to be integrated into a larger system – no easy task.

Yet, GPUs gave Yamazaki and his colleagues a big leap in this direction, by making it possible for them to run their model on a PC equipped with a single off-the-shelf NVIDIA GPU. None of this required any exotic or expensive hardware.

Up next for Yamazaki and Igarashi will be advancing their brain research even further, with the ultimate goal of expanding their cerebellum model until they have a complete understanding of how this area of the brain works.

Armed with this data, researchers can better understand human motor function, the interaction between the cerebellum and other parts of the brain, and potentially uncover the causes of motor neuron diseases.

And what’s next in the area of biomimetic robotics?

Yamazaki believes his work could result in robots within 5 years that rely on a silicon cerebellum that will allow them to “think” – that is, they would be able to assess their environment and organize movements autonomously.

“GPUs would play an essential role… because in my opinion, GPUs are the supercomputer for the rest of us,” says Yamazaki.

Not bat.

Employees are ditching company-issued black-and-grey boxes for their own devices. They’re swapping heavy laptops and deskbound workstations for tablets and smartphones and tapping into computing resources that live in the cloud rather than underneath their desk.

The solution: break the link between data and devices with tools that give employees the resources they need, whatever device they’re using, with NVIDIA GRID.

Close to Heaven

Jen-Hsun – known for his love of cars – seemed right at home at a conference packed with industrial designers, many from the world’s biggest carmakers.

“It’s great to be at Excite, surrounded by visual computing, surrounded by beautiful cars, surrounded by GPUs,” Jen-Hsun quipped. “It feels pretty close to heaven.”

The RTT Excite exhibit hall was a window into a future where visual computing is everywhere.  By one estimate, there were nearly 130,000 GPU cores at RTT Excite, powering a sea of high-definition displays showcasing the rising importance of visual computing across the design, development, marketing and sales of new products, from an upcoming BMW electric car to a tailored Brioni suit.

A Graphics Card That Lives in the Cloud

To deliver the graphics power needed to design and market all of these products on any device, NVIDIA has introduced a new product we call GRID.

Think of GRID as a graphics card that contains a whole bunch of other graphics cards that live on the network, rather than being attached to any device. The result: cutting edge graphics can be poured into a MacBook Air, a netbook, an iPad. The device no longer matters.

And employees – who already use cloud-based consumer services – will get it, immediately. It’s like Netflix, except it’s interactive thanks to technology that lets GRID respond to data at the speed of a keystroke.

Jen-Hsun shared a trio of demos with his audience. He showed how a single GRID Visual Computing Appliance (VCA) can deliver multiple sessions of powerful workstation-class software — Adobe Premiere, 3DSMax, and DeltaGen –to a single MacBook.

On the flip side, he showed how VCA can give a single worker instant access to multiple GPUs to tackle the most demanding jobs. In this demo, DeltaGen tapped into the power of 6 GPUs to perform real-time, interactive ray-tracing.

Last, he demonstrated how GRID can be used to transform the retail experience, showing how rich, immersive car buying applications can be accessed from the showroom floor from an iPad.

ARM’ed and Dangerous

While GRID puts visual computing muscle in the cloud, Tegra puts that power as close to as many of the world’s display as possible.

We all know the PC industry is struggling, but the latest news was still shocking. PC shipments fell 14% during the first quarter, amid a spate of bleak headlines about the fortunes of the industry’s giants, according to IDC. But in this shift – like any big shift – there’s opportunity.

That’s why NVIDIA turned itself inside out several years ago to create an SOC business with Tegra, a mobile processor designed to bring visual computing everywhere.

While the PC, which has dominated the industry for decades, is stumbling, visual computing is becoming more ubiquitous than ever. By 2015, there will be nearly 5 billion HD displays on the planet.

Energy-efficient, mobile processors are powering more and more of those displays: each year more ARM processors are shipped than all of the x86 processors shipped since the beginning of mankind.

The architecture will extend far beyond just handsets. And specifically into one platform ripe for more computing power: our cars.

More than handsets: Tegra will transform a wide array of devices, including cars.

Cars Keeping Up With Phones

Just imagine if the interfaces in our cars could keep pace with the innovations in our smartphones. We built the Visual Computing Module to make that happen, giving automakers access to our visual computing capabilities and the rich ARM ecosystem.

We’re taking this further with Jetson, a new development kit we’ve put into the hands of automakers that includes a discrete GPU, modular I/O breakout boards and a touchscreen display.

Jetson lets automakers easily create and test automotive and computer-vision applications, from in-vehicle infotainment to advanced driver assist systems that rival the stuff of science fiction.

Photos: Susanna Tatar

Now tablets are about to get the same technologies that make PC and console games so immersive.

Our CEO, Jen-Hsun Huang, showed footage of “Battlefield 3” running on a mobile version of our Kepler GPU at our annual Investor Day last week.

The result is a huge leap forward, from what Jen-Hsun described as the “vintage 1999” graphics found on the latest Apple iPad.

“Our crown jewels, our GPU, the highest performance GPUs in the world, can make a real contribution in mobile, can make a real contribution in Android, can make a real contribution in these mobile devices,” Huang said.

That comes thanks to the Kepler-class GPUs NVIDIA is building into its next-generation mobile processors, dubbed “Logan.”

Disclosed last month, Logan will pair ARM-based mobile processor cores with our powerful Kepler GPUs, putting technologies now found in high-performance PCs and workstations – such as PhysX, CUDA 5, DirectX 11, and Open GL 4.3 – into mobile devices.

Last week, Jen-Hsun gave the crowd at NVIDIA’s annual Investor Day a taste of what DirectX 11 in a mobile will look like. And it’s amazing, with Kepler delivering graphics that convey all the details that make games such as “Battlefield 3” so immersive.

Take a look for yourself.

Note: an earlier version of this post inaccurately characterized the system powering the “Battlefield 3” demo. 

The NVIDIA Graduate Fellowship Program awards $25,000 to Ph.D. students involved in computer research. The aim is to help students continue researching ways to use GPUs to tackle complex computing challenges in industries such as medical imaging, space exploration, automotive design and film production. The program provides a financial incentive and technical support to graduate students conducting outstanding GPU-based research.

In September, we kicked off the 12th Annual NVIDIA Graduate Fellowship Program and invited students to submit their research projects for consideration.

Our Graduate Fellowship award winners were selected from hundreds of applicants in 39 countries. Their projects involve a variety of technical challenges, including computer architecture, programming models, character animation, computer graphics and computational methods for simulating chemical events.

“NVIDIA is committed to supporting outstanding academic research because it fuels innovation,” said Bill Dally, chief scientist and senior vice president of research. “We’ve invested millions of dollars to support ground-breaking research in science, engineering and medicine. We’re delighted to support the work of these exceptional graduate students, whose efforts will help define the future of computing.” 

Recipients of the 2013 NVIDIA Graduate Fellowship Program are:

Brian Zimmer, from Berkeley, Calif.

Studying at the University of California, Berkeley

Brian’s research focuses on architecture and circuit-level techniques for improving energy efficiency.  He is developing circuits and systems that cope with the increasing variability of static random-access memory cells in deeply scaled technologies.

Haicheng Wu, from China
Studying at Georgia Institute of Technology
Haicheng is developing a compiler, Red Fox, for accelerating large-scale data warehousing applications on cloud architectures augmented with GPU accelerators. Red Fox is now capable of running all TPC-H queries in one GPU device with small-scale inputs.  The longer term goal of Red Fox is to be integrated with large relational database systems consisting of multiple nodes and multiple GPU devices to explore the opportunities for GPU computing in the “Big Data” era.

James Hegarty, from St. Louis, Mo.
Studying at Stanford University
James’s research involves studying new programming models for CPUs and GPUs. He is examining image processing languages, with the goal of creating a programming model that is able to automatically exploit localities that are difficult for a general-purpose language to discover.

Juliet Fiss, from Rochester, Minn.
Studying at the University of Washington

Juliet is studying computational photography, focused on light field video. She is working on the design of light field video cameras, light field image and video processing algorithms and light field video editing software that will allow filmmakers to control focus effects in post-production.

Nathan Luehr, from Alsip, Ill.
Studying at Stanford University

Nathan is a graduate student in the chemistry department at Stanford University. Working under Todd Martinez, Nathan develops computational methods for simulating chemical events. His particular research interests include efficient electronic structure algorithms for massively parallel architectures, and the application of molecular dynamics to large chemical systems such as proteins. 

Sergey Levine, from Redmond, Wash.
Studying at Stanford University

Sergey is  developing learning algorithms that can allow virtual characters to emulate human behaviors. Such characters could be “programmed” simply by acting out the desired behaviors and recording the demonstration with a motion capture system. By allowing anyone to specify behaviors for virtual characters from demonstration, this technology could open up character animation to a much broader range of users, allowing more people to realize their creative ambitions and create engaging virtual characters. The same techniques could be extended for specifying behaviors for robots, or even studying motor control in humans and animals.

Stephen Tyree, from Tulsa, Okla.
Studying at Washington University in St. Louis

Stephen’s research specializes in machine learning on parallel computing hardware, rethinking and reengineering existing methods in light of current hardware trends.  He is porting support vector machine training to the GPU, and aims to contribute an open-source machine learning toolbox optimized for highly parallel platforms. 

Tianyi David Han, from Ontario, Canada
Studying at the University of Toronto

David’s primary research goal is to develop compiler and run-time support to make parallel and heterogeneous architectures easier to program. His current research focuses on optimization auto-tuning for GPU programs using machine learning techniques. This research builds upon his earlier work on GPU optimizations for reducing thread divergence and on hiCUDA, a directive-based interface that simplifies the process of porting a sequential program to CUDA.

Timothy Rogers, from Halifax, Canada
Studying at the University of British Columbia

Tim’s research is focused on architectural changes to GPUs to improve their performance and power efficiency on highly parallel irregular applications, traditionally thought to be unsuitable for GPU acceleration. Such applications can be found in economically important areas like server and cloud computing.  Tim is focused on improving the way GPUs capture data locality when accelerating these workloads.

Wei-Fan Chiang, from Taiwan
Studying at the University of Utah

Wei-Fan is a Ph.D. student in the School of Computing at the University of Utah and co-advised by Prof. Ganesh Gopalakrishnan and Prof. Zvonimir Rakamaric. He received his Master’s degree from the University of Utah in 2010. His research interest is software verification in GPU or HPC context.

Yunsup Lee, from South Korea
Studying at the University of California, Berkeley

Yunsup’s research explores ways to provide better performance and energy efficiency while retaining programmability and flexibility in data-parallel processors. He is developing new techniques to support irregular control flow more efficiently.

The NVIDIA Graduate Fellowship Program is open to applicants worldwide. Eligibility criteria include completion of the first year of Ph.D.-level studies in the areas of computer science, computer engineering, system architecture, electrical engineering or a related area. In addition, the student must hold a current membership on an active research team.

For more information on the NVIDIA Graduate Fellowship Program please visit our website.

Two years ago, a 9.0-magitude earthquake off the east coast of Japan killed more than 15,000 people and caused over $200 billion worth of damage.  A year earlier, 200,000-plus died from a quake in Haiti. In 2004, a massive temblor in Indonesia killed an estimated 230,000.

These hit close to home for those of us who live in California, where the San Andreas Fault runs for 800 miles.

To help Californians better prepare for earthquakes, a team of researchers at the San Diego Supercomputing Center (SDSC), led by Yifeng Cui, has developed a GPU-based seismic wave propagation code, which simulates how earthquakes make the ground move.

Cui’s work is part of an effort coordinated by Southern California Earthquake Center (SCEC) – dubbed Cybershake 3.0 — to create a new state-wide seismic hazard map using 3D waveform modeling that will improve earthquake forecasts and help engineers design safer buildings and retrofit existing high-risk buildings.

The team plans to reach their goal by running large scale simulations on GPU-accelerated supercomputers such as Oak Ridge National Laboratory’s Titan and Georgia Tech’s Keeneland.

The image shows a snapshot of ground motion of the 2008 magnitude 5.4 Chino Hills earthquake in an east-to-west direction; the red-yellow and green-blue colors depict the amplitude of shaking. The simulation indicates that small-scale heterogeneities (causing the highly irregular pattern of shaking in the image) may significantly affect ground motion in geologic basins. Simulation by Efecan Poyraz/UC San Diego and Kim Olsen/SDSU. Visualization by Efecan Poyraz; map image courtesy of Google.

Petascale Performance on Titan Supercomputer

To meet the needs of the CyberShake 3.0 project, Cui realized they would need 750 million CPU hours on a traditional CPU-based supercomputer, costing over $800,000 just in power cost to support his simulations.  That’s when they turned to GPUs for help.

AWP-ODC, the research team’s primary seismic application, is more than 5x faster when run with GPUs, allowing researchers to discover insights they would not have been able to before.  At the same time, they would save over $600,000 in power costs for their simulations.

Less than a month ago, Cui’s team achieved over one petaflop of performance running on over 8,000 GPUs on the Titan supercomputer, shattering their previous record of 220 teraflops of sustained performance on Oak Ridge’s Jaguar supercomputer.  The video below shows the results of their previous work on Jaguar.

Faster Results Lead to Safer Buildings, Saving Lives

In the past, researchers were limited to simulations that required less computation at lower wave frequencies, which feel like a “roller-coaster” motion.   While lower frequency simulations are useful for predicting how high-rise buildings will respond in a quake, more common, low-rise structures suffer more damage from higher-frequency shaking, which feel like a series of sudden jolts.

But high-frequency simulations demand significantly more computation. So much more that they’re possible now with GPUs.   New scenarios can run on supercomputers to understand how a broader range of buildings will respond- particularly for the low-rise structures that most building engineers care about.

The goal is to help engineers design safer buildings in California by producing U.S. Geological Survey regulated seismic forecast data products.  The hazard map will ultimately offer details on the impact of earthquakes in specific building sites, helping engineers design new buildings or retrofit existing structures in high risk areas.

While we may not be able to prevent earthquakes, thanks to Cui and his SCEC collaborators, and GPUs, we can now have more computing power than ever to provide better seismic hazard assessments, inform safer California building codes, and prepare for the ‘big one.’

If you are using GPUs to do science, we’d love to hear from you in the comment box below.

Today’s launch of our GeForce GT 700M GPUs brings new slang — and three pieces of technological goodness! — to the forefront: “automagic.”

Automagic first came into heavy use here a few years ago when we introduced our Optimus technology, which garnered a lot of critical praise and earned numerous ‘best of the year’ awards.”

The reason was that Optimus was simple, but revolutionary: give notebooks extra-long battery life by automatically switching on and off the GPU so that it runs only when you need it. Through years of hard work, we created a solution that worked so elegantly, so seamlessly and so effectively, you can’t help but think that it works like magic.

In addition to Optimus, GeForce 700M GPUs have a new automatic technology: GPU Boost 2.0, which intelligently adjusts the graphics processor’s clock speed to maximize the graphics performance of your notebook. If you have unused power in your notebook, the GPU revs up its engine to provide additional performance.

GPU Boost is dynamic and requires no end-user input or settings. You just use your notebook as you normally would and it silently works to give you performance bumps of up to 15%. It does it safely, on the fly and behind the scenes.

The final piece of technology is a game changer. The GeForce Experience automatically changes game settings so you get the best performance and visual quality that your notebook can deliver. It will also automatically download the latest drivers, keeping your system tuned and ready for whatever application you run over the life of your GeForce notebook.

With the GeForce 700M series, we’re delivering more than just powerful graphics performance. We’re bringing you a notebook that is intelligent enough to unlock all the potential a GeForce GPU can provide to you, and to do it painlessly.

Step up to a GeForce 700M GPU in your next notebook and let NVIDIA Optimus, GeForce Experience and the new GPU Boost 2.0 get the maximum performance, maximum battery life and maximum fun out of your system, automagically.

We’ve been working for years to analyze and improve the gaming experience for our customers. What we found is what many customers have long noticed: the most common software tool for measuring a game’s performance – FRAPs – doesn’t always capture what users are seeing.

Particularly when using multiple graphics cards, users are noticing that the action can often pause and stutter even when their software tools are telling them they should be seeing silky-smooth action.

The problem: FRAPs accurately measures frames when they are transferred from a game engine. But a lot happens between that point and when a game gets to the screen. In fact, we found that gamers weren’t imagining things: there can be a big difference between what users see on FRAPs and what they experience.

Two of the problems: what we call ‘drops’ and ‘runts.’ Drops occur when frames that are counted by FRAPs are never displayed. Runt frames, by contrast, are displayed, but only for a few lines of the full 1080p that should be displayed.

Sometimes these drops and runts can cause visible ‘tears’ in the scene being put on the screen. Other times they’re too small to see, but like drops they break the smooth flow of the onscreen action, resulting in a stuttery experience.

So, to better understand what was going on behind the scenes and to help make the overall gaming experience as good as possible, we devised a solution that we call Frame Capture Analysis Tools or FCAT for short.

Capturing the data and properly analyzing it isn’t a trivial task. It includes the use of a special capture card, special overlay software that shows a ‘color bar,’ or fixed color sequence on the display, and scripts that help analyze and graph the data.

By using the capture card with the on-screen color bar we are able to compare the content that’s actually shown on the screen with what we know should be there and correlate that to what the real gaming experience is. Simple.

We’re proud of the work that we’ve put into this – and we think it can help gamers get the experience they’re paying for. So we’re opening up our FCAT solution, making the scripts and software associated with FCAT freely-modifiable and redistributable. The technical press has already dug in, and the results have been dramatic.

Our hope: that third-party apps can replicate and replace our tools, giving gamers what they need to be sure they’re getting all of the graphics quality they’re paying for.