2015 Pennsylvania State Budget Includes $500,000 for the Pittsburgh Supercomputing Center
Monday, July 14, 2014
The Commonwealth of Pennsylvania budget for fiscal year 2015 includes $500,000 for the Pittsburgh Supercomputing Center (PSC).
“We are, of course, pleased and honored that the state has once again found PSC to be worthy of funding in this fiscally challenging year,” says Ralph Roskies, scientific director for PSC. “We’re grateful to the members of the General Assembly, the Allegheny County delegation and especially the critical bipartisan support of Senators Randy Vulakovich and Jay Costa and Representatives Mark Mustio and Joe Markosek.”
PSC directors discuss role of supercomputing in Post-Gazette op/ed
Monday, June 23, 2014
Michael Levine and Ralph Roskies, the Pittsburgh Supercomputing Center's scientific directors, have written an op/ed piece that appeared in yesterday's SundayPittsburgh Post-Gazette. You can read the editorial, which charts out the role played by supercomputing centers in delivering important discoveries and local benefits that other computing resources cannot, here.
PSC Recognizes Fox Chapel Students for Computation in Science Projects
Projects Use Latest Technology to Help Disabled, Visually Impaired People
Wednesday, May 28, 2014
Science projects by two students from Fox Chapel Area Senior High School, Pittsburgh, have earned special recognition from Pittsburgh Supercomputing Center (PSC) for excellence in computer programming.
Sonia Appasamy designed a computerized tool that helps people with visual impairment by automatically converting a camera feed or a photographic image to a simplified, more cartoon-like image with sharper boundaries and contrasts. Suvir Mirchandani created a web browsing system that scans eye movement and brain waves to allow people who do not have use of their arms to surf the Internet.
PSC, Hopkins Computer Model Helps Benin Vaccinate More Kids at Lower Cost
Monday, May 12, 2014
The HERMES Logistics Modeling Team, consisting of researchers from Pittsburgh Supercomputing Center (PSC), the University of Pittsburgh Swanson School of Engineering and the Johns Hopkins Bloomberg School of Public Health, have used HERMES, their modeling software, to help the Republic of Benin in West Africa determine how to bring more lifesaving vaccines to its children. The team reports its findings this month in the journal Vaccine (The benefits of redesigning Benin's vaccine supply chain, Vaccine, 9 May 2014).
Results from the HERMES model have helped the country enact some initial changes in their vaccine delivery system, which may lead to further changes nationwide.
PSC Developing Networking Tool to Speed Big Data Transfers
DANCES will create virtual "HOV lane" for larger scientific users in Internet2
Tuesday, April 8, 2014
A new, $1 million National Science Foundation grant will enable engineers at Pittsburgh Supercomputing Center (PSC), the National Institute for Computational Sciences, the Pennsylvania State University, the Georgia Institute of Technology, the Texas Advanced Computing Center and the National Center for Supercomputing Applications to create a new tool for high-volume scientific users to achieve faster data transfers over Internet2.
The Developing Applications with Networking Capabilities via End-to-End SDN (DANCES) project will add network bandwidth scheduling capability to the network infrastructure and the supercomputing applications used by the collaborating sites. The DANCES team will develop and integrate file system, scheduling and networking software along with advanced networking hardware. Their aim is to prevent “Big Data” users who are transferring vast amounts of data from being slowed or even halted by periodic surges in competing network traffic.
“There currently is no tool that schedules network resources automatically within our existing scheduling systems,” says Kathy Benninger, PSC Manager of Networking Research and principal investigator in DANCES. “You figure out when you think you need to start your data transfer and then you do it manually.”
But the egalitarian structure of the Internet—and the protocol underlying the majority of network traffic—causes problems for Big Data users. Such researchers and engineers must compete with many other users of all sizes on an equal footing. For example, a researcher transferringa 100-Terabyte data set over a 10 Gbps Internet2 research connection could do the transfer in just over 22 hours. A home user with a typical 15 Mbps Internet connection would need almost 1.7 years to complete the download. But even on the research-only Internet2, such a large user could bebumped and sometimes halted by surges of traffic by other users. An automatic tool that protects designated flows from local congestion—essentially creating a “high occupancy vehicle lane” for large-scale data by prioritizing their traffic—would provide dramatically faster network speeds for Big Data users.
“The idea behind the DANCES tool is that you have an idea of how much data you need to transfer, how long you want to take, and how long your computations will take,” says Joe Lappa, Operations Networking Manager for XSEDE. “So the tool will work backwards and grab the data you need from a site and a network path that isn’t crowded.”
“Instead of having a bunch of equal competing jobs at one time, you’ll be able to push priority data through at a guaranteed, predictable data rate,” Benninger adds.
In addition to developing new software, the DANCES team will use hardware upgrades at the participating institutions that will in essence provide high-speed on-ramps for Big Data users. While most of the chokepoints that the system is intended to bypass are expected to be at the level of the campuses, Internet2 is also participating by monitoring its network capacity, adding more bandwidth if necessary.
Ultimately, the system will provide larger benefits as well. With the Big Data transfers DANCES is designed to serve, the energy wasted and heat generated by slow network speeds is significant.
“It’s greener,” says Lappa. “Your machine’s not waiting. Everything is queued, everything is where it needs to be for a faster data transfer.”
PSC Projects Make Top Supercomputing Discovery List
Two public health projects at Pittsburgh Supercomputing Center have made HPCwire’s list of “The Top Supercomputing-Led Discoveries of 2013.” The HERMES project is analyzing vaccine supply chains in lower-income countries to identify and repair under-appreciated choke points. The VecNet Cyberinfrastructure project has created a prototype computational system to support a global malaria eradication effort.
Pittsburgh Supercomputing Center Receives Four HPCwire Awards
Awards Recognize Outstanding Achievements in Science and Technology
Monday, Nov. 18, 2013
Pittsburgh Supercomputing Center (PSC) has received top national honors in four categories of the 2013HPCwire Readers’ and Editors’ Choice Awards. HPCwire, the trade publication for the high performance computing (HPC) community, announced the winners at the start of the opening reception at the 2013 International Conference for High Performance Computing, Networking, Storage and Analysis (SC13), in Denver, Colorado.
Web10G Project Will Create User-Friendly “Dashboard” for Identifying, Fixing Data Slowdowns
Tuesday, Oct. 29, 2013
The Web10G Project has received a one-year, $178,000 Software Development for Cyberinfrastructure (SDCI) supplemental award from the National Science Foundation to develop a “dashboard” that will allow users of computer networks to identify when and where a networking problem is slowing or blocking their access. Web10G, funded by an earlier, three-year SDCI grant, is a collaboration between Pittsburgh Supercomputing Center (PSC) and the National Center for Supercomputing Applications.
“We’ve found that a lot of network users either have unrealistically high expectations or unrealistically low expectations for network performance,” says Chris Rapier, PSC network applications engineer. “Web10G has produced 127 different instruments that report on what’s going on with the network connection, ways in which it might be failing and ways in which it might be improved. With the supplemental grant, we’re going to automate that process to let users know what’s reasonable and then help them work with their network operations teams to actually get the performance they need.”