Processing Pixels: Revving up GPUs

Subtitle: DigitalGlobe and NVIDIA on the Quiet Revolution
By LBx Staff | Published May 23, 2012

Summary: This interview discusses the operational and customer experience enhancements to satellite imagery products resulting from investments in GPU computing architecture.

Background

Geospatial technologies, and therefore geospatial solutions (especially those dealing with large imagery files) have always been burdened by high computing challenges. These challenges have translated into latency issues. Over the last several years, DigitalGlobe has invested in GPU technology to accelerate speed to market in delivering imagery products and services. We spoke with Jason Bucholtz about how DigitalGlobe is using GPU technology to improve operations and create a technology infrastructure to support next-gen imagery-based applications. We also spoke with Kevin Berce of NVIDIA, a leader in GPU technology, on the future of advanced computer processing power.

LBx: What is your focus at DigitalGlobe?

Jason: Iím an architect who deals with data. Iím interested in and responsible for determining how quickly raw data can be turned into information. Imagery that hits the ground from the satellite is ìBig Data;î it needs to be processed, and the faster it is processed, the faster organizations have access to the data to answer all sorts of questions about our changing world, and to respond to emergency situations and save lives.

LBx: How do you achieve faster processing?

Jason: DigitalGlobe invested quite a bit over the last several years in GPU (Graphic Processing Unit) technology. GPUs are high-performance computing processors that accelerate image processing applications to enable more, higher quality and faster work. GPUís enhance traditional high performance computing architectures, by breaking down complex instructions into simpler steps and enabling more simple steps to be executed at the same time. This simplification dramatically increases computational speed. Our goal is to achieve faster processing of pixels. GPU technology has primarily been used in the video gaming sector, and is incredibly well suited to geospatial imagery files.

LBx: Kevin, how would you describe GPUs in a nutshell?

Kevin: GPUs are being used to power everything from supercomputers to smartphones. Technically speaking, GPUs excel at parallel processing, and that makes them ideal to accelerate image processing and other computationally intensive applications. The goal of employing GPU technology is to reduce the processing time on algorithms (improved customer experience) and reduce the amount of computer rack space, which reduces the sheer number of systems required (reduced operational costs).

Bio

Jason Bucholtz has been designing and implementing large scale high-performance compute systems and large data infrastructures for 15 years. At DigitalGlobe, Jason designs the next generation compute and storage systems that power the companyís leadership in automated image processing.

Kevin Berce has more than 15 years of experience in High Performance computing as Director of sales, business development and other customer-facing roles in the United States. Kevin is currently Manager of Business Development for NVIDIA. In his current role, he has responsibility for NVIDIAís Defense and Intelligence business inside the United States.

LBx: What is driving GPU adoption?

Kevin: There are lots of drivers, including the need to increase raw performance of computationally intensive applications, the need to do more processing with less hardware and power, and enabling greater mobility. Big Data and graphically complex video games are driving the need for more horsepower to run analytics and simulations faster. Relative to geospatial applications and the federal government, GPUs are being used to accelerate the processing of Big Data and analytics in the cloud. The issue with Big Data is that the massive volumes of source data canít be processed quickly enough with typical CPU-only computing solutions.

LBx: What does the faster processing get you?

Jason: It lowers our operating costs for one, and most importantly, it delivers faster analysis to our customers. With GPU computing we can deliver a meaningful geographic image from the tasking of the satellite to delivery to the customer within as little as 120 minutes. That may still seem like a long time in a real-time tweeting world, but that is amazing speed given the complexity of satellite imagery processing workflows. Feature extraction takes more time, but with advanced algorithms we can identify objects on the ground faster ñ for example, cars in parking lots.

GPUs enable us to speed up common preprocessing steps such as orthorectification and pan sharpening. See Figure 1. Orthorectification is the process of tying a pixel to a known location on the earth to render an accurate geographic reference from an image. Pan sharpening merges high-resolution black and white images with lower-precision color bands and fills in the color for a precise high-resolution color image. Intermediate imagery products that include feature extraction and the type of analysis I mentioned earlier all depend on this base-level processing. And thatís the heavy lifting that is performed extremely well by GPUs.

Kevin: Speed gains depend on the application, but can be as much as 20x or more. Cost savings on the reduced hardware footprint can be as much ...

Full article available in LBx Journal Winter 2012 digital edition.

SEE MORE IN THIS CATEGORY:

Product Review: Find Spot

Spotlite 2.O Pet GPS Locator

SecurusGPS released their advanced pet locator Spotlite 2.0 in early March 2013. I had the privilege of trying out this nifty gadget. It is designed to be worn by a 10 pound or greater sized dog. I don’t have a dog, so I did the next best thing. I used it to track my car and to track my partner’s suitcase (with his permission of course) as he traveled from Colorado to the East Coast. Let’s call them both Spot.

By Natasha Léger | April 22, 2013 April 22, 2013

Scaling Map Wizardry

To 100 million Microsoft Office 2013 Users

Marketing, operations, and business managers have been asking their IT departments for several years now for ways to see data on a map. IT and GIS (or IT and geo applications) have not mixed well as departments or as integrated priorities. This difficulty left many managers and departments to seek other solutions or to engage in skunk works projects with a variety of available technologies, including free and open source applications. These work-arounds to productivity have had both their successes and challenges. Microsoft has come to the rescue...

By Natasha Léger | April 18, 2013 April 18, 2013

Underground Assets

Streamlining the Call-Before-You-Dig Process

Designers of large projects, such as a highway expansion, a new shopping mall, a sewer or water lineupgrade project, or a gas line replacement, are often presented with unique challenges – including those that lie beneath the earth’s surface. Although not seen from a casual, above-ground glance, there is a world of assets and critical infrastructure that exist underground. When new projects are in the early phases of development, it is vital...

By Bill Kiger | April 17, 2013 April 17, 2013

COLUMNS

Executive Interview

Bringing More Attention to the Location Profession

Past, Present, and Future

MINDY BROWN, President of Bruun Consulting shares the past, present and future of location and GIS. She was one of the early pioneers of the geospatial industry and watched it ebb and flow over the last thirty years. As such she has a unique perspective on how the location professional has evolved over the years.

By Natasha Léger | March 8, 2013 March 8, 2013

Scaling Enterprise GIS

A Retail Perspective

Jillian Elder is not your average GIS Manager. Jillian sees GIS as another tool in a broader information toolbox that helps to solve a problem. As her team sits within the Market Planning and Research Group of Walgreens that reports to the CFO, she is charged with finding and accessing the best data from across the organization to answer particular questions. This interview discusses the challenges encountered in implementing an enterprise-wide location information strategy.

By LBx Staff | January 29, 2013 January 29, 2013

The Case for Tracking

Assets, People, and Pets

Securus, Inc. is a mobile safety and security products and services company that is taking machine-to-machine (M2M) hardware and software solutions to a new level. They have built an M2M software platform that enables a user to track any asset, person, or pet. The convergence of more efficient hardware, improved mobile connectivity, and other sensor technology innovations are redefining the possibilities and affordability of the location tracking market. We spoke with Chris Newton, President and CEO of Securus, Inc., about the market drivers for assets, people, and pet tracking.

By LBx Staff | January 9, 2013 January 9, 2013

Game Changer

Humans As Sensors

Adding the Time Dimension

As Di-ann is driving around the Bay Area she uses Waze (http://waze.com) to find her way. From Waze she gets routing, traffic and road closure information. In exchange, Waze tracks her location and knows her ultimate destination. It knows that she is going slower than expected on Highway 101 and that she is probably in traffic.

By Brady Forrest | January 13, 2010 January 13, 2010

Back Behind the Firewall

Net Technologies Move From Consumer to Enterprise

About five years ago, the group I worked for at Microsoft looked at what was happening in the blogosphere and decided to bring it in-house. We saw that the conversations needed a

By Brady Forrest, O'Reilly | May 25, 2009 May 25, 2009

On Minding The Store

Think Locally, Act Globally

It’s the Customer, Stupid!

There was a time, not too long ago, when “global” was a concept, but hardly a reality. As a corporation pushed its horizons beyond the relatively homogeneous local market, it encountered increased diversity and complexity, strange customs and even stranger legal environments. There were no global markets, no truly global products and few global brands. Corporations at best were multinational, jerry-built conglomerates of local institutions, each catering to relatively homogeneous local markets, each differing from the next.

By Robert Avila | August 3, 2011 August 3, 2011

Corporate Evolution

Are corporations prepared to go where their policies are taking them?

Corporations have been pursuing an implicit model that has shed much of the internal political, social and cultural qualities that characterized past corporations and have transformed themselves more and more into purely economic institutions. As this model has advanced, corporate loyalty, a largely political concept, has been replaced by the formal or “at will” employment contract, a purely economic arrangement.

By Robert Avila, Managing Director, Future Crunch | June 14, 2011 June 14, 2011

The Rebirth of Brand Management

It’s Not the Lead; It’s the Customer Experience that Matters

Brand is the social contract of business, the implicit agreement between the parties in a transaction about the nature of their long-term relationship. One is tempted to quote Hobbs to the effect that economic life devoid of brands tends to be “solitary, poor, nasty brutish and short,” a description eerily evocative of today’s commercial environment. As with political theory, when discussing brand it is easy to slip into morality tales. The recent collapse of the Tiger Woods and Toyota brands calls up images from Greek tragedy with choruses of talking heads lamenting their fall from greatness.

By Robert Avila | June 30, 2010 June 30, 2010