PSC Receives Best-Ever Six 2018 HPCwire Awards

PSC Receives Best-Ever Six 2018 HPCwire Awards

Awards Recognize Leaders in the Global High-Performance Computing (HPC) Community

Nov. 13, 2018

The Pittsburgh Supercomputing Center (PSC) has topped its best-ever performance of last year by receiving six 2018 HPCwire Readers’ and Editors’ Choice Awards. HPCwire presented the awards at the 2018 International Conference for High Performance Computing, Networking, Storage and Analysis (SC18), in Dallas, Texas. HPCwire revealed the list of winners at their booth at the event and on the HPCwire website, located at www.HPCwire.com.

Read more: PSC Receives Best-Ever...

DGX-2 Arrives at PSC

PSC's new Bridges-AI is ideally suited for deep learning, other kinds of machine learning, graph analytics, and data science. The system introduces 88 NVIDIA Volta GPUs in two types of new nodes. One of them, an NVIDIA DGX-2 enterprise research AI system, is the first of its kind available for open research. The DGX-2 tightly couples 16 NVIDIA Tesla V100 (Volta) GPUs with 32 GB of GPU memory connected by NVLink and NVSwitch, to provide maximum capability for the most demanding of AI challenges. The following images show the installation of PSC's DGX-2.


The DGX-2, ready for installation.
2 IMGP1627 small
Physically installing the DGX-2 in its Bridges cabinet. With a projected 2 petaflop-per-second processing speed, the unit will increase Bridges' overall speed considerably.
setupdgx
The unit with its interconnect in place. Each NVSwitch chip is an 18X18 port, fully connected crossbar offering 50 GB/s/port and 900 GB/s/chip bidirectional bandwidths. The total system bandwidth is 2.4 TB/s.
setupdgx2
Powered up now, the unit gets its firmware upgraded and diagnostics run. The relative ease of installation is paralleled by ease of use for users: PSC's DGX-2 will offer popular languages such as Python, Jupyter, R, MATLAB, Java, Spark and Hadoop.
6 IMGP1642 small
PSC's new DGX-2 unit, installed and ready to provide unsurpassed deep learning capabilities to users as part of Bridges-AI.

Stopping HIV in Its Tracks

PSC’s Bridges Helps Scientists Understand Monkey Protein that Confers Immunity to HIV

Nov. 12, 2018

Scientists have scored a number of victories against HIV, the virus that causes AIDS. But these victories are incomplete. We can hold the virus in check, but not cure it. We can reduce the chances someone will be infected, but do not have a surefire way to prevent infection. Scientists from the University of Delaware and the University of Pittsburgh are using the XSEDE resource Bridges at the Pittsburgh Supercomputing Center to investigate how one protein prevents HIV from infecting monkeys. Understanding how it does that, and why the human version of that protein doesn’t, promises a completely new avenue for stopping HIV in its tracks.

Read more: Stopping HIV in Its Tracks

PSC Arm of Genome Analysis Center Awarded NSF Funding

NCGAS logo print 2color

National Science Foundation Grant renewal will support expansion of programs supporting genome biology research

Oct. 15, 2018

The Pittsburgh Supercomputing Center (PSC) has received $289,203 in National Science Foundation (NSF) funding for its work as part of the National Center for Genome Analysis Support (NCGAS). The independent grant accompanies an additional $962,613 in NSF funding to NCGAS at Indiana University. Together the two sites will continue the center’s work aiding discovery and innovation in biological sciences that use genomic methods.

The renewal of the three-year grants will support NCGAS’s ongoing and expanding activities, including bioinformatics consulting, education and outreach programs on genome analysis and assembly, and long-term archival storage for genome biologists. The center currently serves researchers across the United States, enabling the analysis and utilization of currently available genomic information. NCGAS leverages Bridges, PSC’s converged HPC, Big Data and AI system, as well as other systems in the NSF-funded XSEDE ecosystem, to enable increasingly large and complex genome and metagenome analyses.

“We’re excited to continue our collaboration with Indiana University to lower barriers for researchers who need to analyze large-scale genomics data,” said Philip Blood, principal investigator of the collaborative NCGAS award and Senior Director of Computational Biology at PSC. “Through this new award, NCGAS will continue to provide biologists with expert help in applying advanced computing technologies to genome analysis that will drive discovery in their fields.”

Read the IU press release.

PSC Supplies Computation to Large Hadron Collider Group

ispy 13TeV 20May2015 min

Illustration of the CMS detector at the Large Hadron Collider, detecting the results of a proton-proton collision. Reproduced with permission from CERN.

CMS Experiment Using Bridges Supercomputer to Simulate Collisions for Upgraded LHC Particle Accelerator

Read more: PSC Supplies Computation...
Page 1 of 4

PSC Media Contacts

Media / Press Contact(s):

Kenneth Chiacchia
Pittsburgh Supercomputing Center
chiacchi@psc.edu
412-268-5869

Vivian Benton
Pittsburgh Supercomputing Center
benton@psc.edu
412.268.4960

Website Contact

Shandra Williams
Pittsburgh Supercomputing Center
shandraw@psc.edu
412.268.4960

Use of PSC materials: To request permission to use PSC materials, please complete this form.

Events Calendar

<<  December 2017  >>
 Su  Mo  Tu  We  Th  Fr  Sa 
       1  2
  3  4  5  6  7  8  9
10111213141516
17181920212223
24252627282930
31