Visit additional Tabor Communication Publications
October 14, 2005
Oil companies could soon harness the power of supercomputers to tackle problems such as where to place equipment and how to clean up oil spills. For decades, the industry already has used computers to maximize profit and minimize environmental impact, so this represents a logical extension of computing capabilities.
Typically, companies take seismic measurements of an oil reservoir and simulate drilling scenarios on a local computer. Now, according to Tahsin Kurc, assistant professor of biomedical informatics at Ohio State University, he and his colleagues are developing a software system and related techniques to let supercomputers at different locations share the workload. The system runs simulations faster and in much greater detail and enables analysis of large amounts of data.
The OSU scientists are employing the same tools and techniques used to connect computing resources in biomedical research. Whether they are working with images from digitized microscopes or MRI machines, their focus is on creating software systems that pull important information from the available data. From that perspective, a seismic map of an oilfield isn't that different than a brain scan, Kurc said. Both involve complex analyses of large amounts of data.
In an oilfield, rock, water, oil and gas mingle in fluid pools underground that are hard to discern from the surface, and seismic measurements don't tell the whole story. Yet oil companies must couple those measurements to a computer model of how they can utilize the reservoir, so that they can accurately predict its output for years to come. And they can't even be certain that they're using exactly the right model for a field's particular geology.
"You never know the exact properties of the reservoir, so you have to make some guesses," Kurc said. "You have a lot of choices of what to do, so you want to run a lot of simulations."
The same problems arise when a company wants to minimize its effects on the environment around the reservoir, or track the path of an oil spill. Each simulation can require hours or even days on a PC, and generate tens of gigabytes of data. Oil companies have to simplify their computer models to handle such large datasets.
Kurc and his Ohio State colleagues -- Joel Saltz, professor and chair of the Department of Biomedical Informatics; assistant professor Umit Catalyurek; research programmer Benjamin Rutt and graduate student Xi Zhang -- are enabling technologies to spread that data around supercomputers at different institutions.
Their project is part of a larger collaboration with researchers at the University of Texas at Austin, Oregon State University, University of Maryland and Rutgers University. The institutions joined to utilize the TeraGrid network, which links supercomputer centers around the country for large-scale studies. Programs like OSU's DataCutter are considered "middleware," because they link different software components. The goal, Kurc said, is to design middleware that works with a range of applications.
"We try to come up with commonalities between the applications in that class," he said. "Do they have a similar way of querying the data, for instance? Then we develop algorithms and tools that will support that commonality."
DataCutter coordinates how data is processed on the network, and filters the data for users. The researchers tested DataCutter with an oilfield simulation program developed at the University of Texas at Austin. They ran three simulations over the TeraGrid: one to assess the economic value of an oilfield, one to locate sites of bypassed oil and one to evaluate different production strategies, such as the placement of pumps and outlets in an oil field.
The source data came from simulation-based oilfield studies at the UT-Austin. That data and the output data from the simulations were spread around three sites: the San Diego Supercomputer Center, the University of Maryland and Ohio State.
Using distributed computers, they were able to reduce the execution time of one simulation from days to hours and another from hours to several minutes. But Kurc feels that speed isn't the only benefit that oil companies would get from doing their simulations on computing infrastructures such as TeraGrid. They would also have access to geological models and datasets at member institutions, which could boost the accuracy of their simulations.
Jun 19, 2013 |
Supercomputer architectures have evolved considerably over the last 20 years, particularly in the number of processors that are linked together. One aspect of HPC architecture that hasn't changed is the MPI programming model.
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.