Last Updated on Tuesday, 09 October 2012 12:57
Pittsburgh Supercomputing Center Network Exchange Adds Robert Morris University
PITTSBURGH, June 1, 2011 — The Three Rivers Optical Exchange (3ROX), the high-performance Internet hub operated and managed by the Pittsburgh Supercomputing Center (PSC), which serves universities, research sites and K-12 schools in western Pennsylvania and West Virginia, has added Robert Morris University (RMU).
As a result, RMU now has access to Internet2 and to National LambdaRail, high-performance research and education networks that connect universities, corporations and research agencies nationally. Beyond this, said Wendy Huntoon, PSC director of networking, “Robert Morris will also receive all the 3ROX regional routes, thus enabling better connectivity with other universities and area school districts.”
“3ROX is the premier high-speed interconnection point for research and education networks in the region,” said Randy Johnson, RMU senior director of technical services. “We joined 3ROX primarily to gain access to the National LambdaRail TelePresence Exchange for the future U.S. Steel Videoconferencing and Technology Center, which will be based on Cisco TelePresence technology. We will also benefit from 'peering' with other exchange members to pass traffic locally instead of utilizing an Internet connection.”
More information about 3ROX: http://www.3rox.net
Last Updated on Monday, 18 June 2012 10:02
Pittsburgh Supercomputing Center Accelerates Machine Learning with GPUs
Researchers at the Pittsburgh Supercomputing Center and HP Labs achieve unprecedented speedup in a key machine-learning algorithm.
PITTSBURGH, May 23, 2011 — Computational scientists at the Pittsburgh Supercomputing Center (PSC) and HP Labs are achieving speedups of nearly 10 times with GPUs (graphic processing units) versus CPU-only code (and more than 1000 times versus an implementation in a high-level language) in k-means clustering, a critical operation for data analysis and machine learning.
A branch of artificial intelligence, machine learning enables computers to process and learn from vast amounts of empirical data through algorithms that can recognize complex patterns and make intelligent decisions based on them. For many machine-learning applications, a first step is identifying how data can be partitioned into related groups or “clustered.”
Ren Wu, principal investigator of the CUDA Research Center at HP Labs, developed advanced clustering algorithms that run on GPUs, which have advantages for many data-intensive applications. PSC scientific specialist Joel Welling recently applied Wu’s innovations to tackle a real-world machine-learning problem. Using data from Google’s “Books N-gram” dataset and working together, Wu and Welling were able to cluster all five-word sets of the one thousand most common words (“5-grams”) occurring in all books published in 2005. With this project, representative of many research efforts in natural-language processing and culturomics, the researchers demonstrated an extremely high-performance, scalable GPU implementation of k-means clustering, one of the most used approaches to clustering.
Wu and Welling ran on the latest “Fermi” generation of NVIDIA GPUs. Using MPI between nodes (three nodes, with three GPUs and two CPUs per node), they observed a speedup of 9.8 times relative to running an identical distributed k-means algorithm (written in C+MPI) on all CPU cores in the cluster, and thousands of times faster than the purely high-level language implementation commonly used in machine-learning research. Using their GPU implementation, the entire dataset with more than 15 million data points and 1000 dimensions can be clustered in less than nine seconds. This breakthrough in execution speed will enable researchers to explore new ideas and develop more complex algorithms layered atop k-means clustering.
“K-means is one of the most frequently used clustering methods in machine learning,” says William Cohen, professor of machine learning at Carnegie Mellon University. “It is often used as a subroutine in spectral clustering and other unsupervised or semi-supervised learning methods. Because some of these applications involve many clustering passes with different numbers of means or different randomized starting points a greatly accelerated k-means clustering method will be useful in many machine learning settings.” Cohen co-leads the Never-Ending Language Learning (NELL) and Read the Web projects (http://rtw.ml.cmu.edu/rtw/). The goal of NELL is to automate inferences based on continually “reading” natural-language text from the Web.
Machine learning is just one example of the exploding field of data analytics, notes PSC scientist Nick Nystrom. Other data-analytic applications range from understanding the results of traditional high-performance computing (HPC) simulations of global climate, engineering, and protein dynamics to emerging fields that need HPC such as genomics, social network analysis, and mining extensive datasets in the humanities.
“A substantial body of major application codes is already being developed specifically for NVIDIA GPUs,” notes Nystrom, PSC director of strategic applications. “Because NVIDIA GPUs are so widespread, those codes can run well on anything from a supercomputer to a netbook.” Nystrom has been instrumental in PSC’s work with advanced technologies for scientifically important, data-intensive problems. This application of NVIDIA GPUs to k-means clustering, he notes, is one example of how a pervasive technology that leverages broad markets can benefit important algorithms in science and data analysis.
This advanced clustering algorithm, notes Wu, also has the advantage of being easy to use, which facilitated rapid implementation with Welling. “I think that the CUDA programming model is a very nice framework,” says Wu, “well balanced on abstraction and expressing power, easy to learn but with enough control for advanced algorithm designers, and supported by hardware with exceptional performance (compared to other alternatives). The key for any high-performance algorithm on modern multi/many-core architecture is to minimize the data movement and to optimize against memory hierarchy. Keeping this in mind, CUDA is as easy, if not easier, than any other alternatives.”
Nystrom concurs and sees an exciting future for software developers: “There’s a rich software ecosystem supporting NVIDIA’s GPUs, ranging from easy-to-use compiler directives to explicit memory management to powerful performance tools. Add to that integration of general-purpose processors in this successful line of architectures, and the potential for developing transformative software architectures is extraordinary.”
Last Updated on Monday, 18 June 2012 10:01
PSC Observes 25 Years of Service and Accomplishment
PITTSBURGH, April 15, 2011 — Over a hundred guests, including students, representatives of government and industry, joined the Pittsburgh Supercomputing Center (PSC) staff today at PSC's 25th anniversary observance and Discover 11 Open House. Also present were participants from the TeraGrid/Blue Waters Symposium in Data Intensive Analysis, Analytics, and Informatics, held in Pittsburgh, which concluded at noon on April 15.
PSC scientific co-directors Ralph Roskies (left) and Michael Levine (right) with director of special projects James Kasdorf (center)
The Open House featured demonstrations of PSC research including 3D stereo movies of cellular interactions in a synapse and a zoom-in view of water molecules. PSC's biomedical group also highlighted the recent "wiring diagram of the brain" research featured on the cover of the March 10 issue of Nature, the prestigious international science journal. The event also included a look back at PSC supercomputers from 1986 until now, and a number of the highlight research projects those computing systems enabled. PSC's networking group demonstrated Cisco Telepresence, an advanced video conferencing system, that facilitates distance communication with a realistic sense of presence beyond other current systems.
At 1:00 pm officials from universities, industry and government convened for an event that included remarks about PSC:
- Introduced by PSC scientific co-director, Michael Levine, Dr. Jared Cohon, president of Carnegie Mellon, congratulated PSC and briefly highlighted, as an example of the range of research the center has supported, several projects that CMU researchers have carried out in collaboration with PSC — including Internet privacy, earthquake modeling, machine learning, particle physics and cosmology to computational chemistry.
- PSC scientific co-director Ralph Roskies introduced University of Pittsburgh Chancellor Mark Nordenberg, who spoke about the partnerships that have been important to PSC's continuing success, in particular the linkages between the two major research universities in the Oakland neighborhood of Pittsburgh, CMU and Pitt.
- Jim Kasdorf, PSC director of special projects, introduced Tom Moser, Manager of Infrastructure, Westinghouse Electric Company, who commented on parallels between the technological innovations of Westinghouse Corporation, now in its 125th years, and PSC, in its 25th year.
- Roskies, Levine and Kasdorf thanked the PSC staff for their many contributions to the sustained success of PSC.
- Mary Ann Eisenreich, Director, Governor's Southwest Office (representing the Honorable Tom Corbett, Governor, Commonwealth of Pennsylvania) commented on the importance of PSC's contribution to southwest Pennsylvania and read comments from Governor Corbett.
- The Honorable Mike Doyle, U. S. Representative, 14th Congressional District of Pennsylvania, presented his "heartfelt congratulations" by video.
- Dr. Irene Qualters, Program Director, Office of Cyberinfrastructure, National Science Foundation, acknowledged the many human contributions to PSC's success and brought warm congratulations from the NSF staff, including Ed Siedel, a former PSC researcher, and Irene Lombardo.
- Pennsylvania State Representative Joe Markosek presented PSC's directors with a copy of a Pennsylvania House of Representatives resolution officially commenting upon PSC's contributions to Pennsylvania.
Last Updated on Monday, 18 June 2012 10:01
PSC Featured in Pittsburgh Post-Gazette
PITTSBURGH, April 4, 2011 — The Sunday, April 3 issue of the Pittsburgh Post-Gazette includes a full-page editorial article by the three people who co-authored the proposal that led the National Science Foundation to fund the Pittsburgh Supercomputing Center 25 years ago.
PSC scientific co-directors Michael Levine and Ralph Roskies (left) and director of special projects James Kasdorf
The OpEd, by PSC's scientific directors Michael Levine and Ralph Roskies and PSC director of special projects James Kasdorf, is aimed at non-scientist readers. It outlines what's meant by “supercomputing” and discusses some of PSC's accomplishments.
You can read the article, here: http://www.post-gazette.com/pg/11093/1136305-109.stm