Press Kit

SDSC: San Diego Supercomputer Center
Established: November 14, 1985
Employees: ~275

Web site: www.sdsc.edu

Leadership: Michael L. Norman, Director

SDSC’s Evolving Mission

Founded by the National Science Foundation (NSF) almost three decades ago as one of the nation’s first academic supercomputer centers, SDSC’s mission has since evolved and expanded, in part to include the creation and fostering of collaborations across the University of California system. As part of that effort, SDSC has worked to align itself with three UC principles when it comes to UC-wide research investments:

  • Act as one system of multiple campuses to enhance UC’s influence and advantage
  • Promote efficient inter-campus collaborations and system-wide economies of scale
  • Serve the State of California

SDSC’s portfolio of high-performance computing resources, along with its ‘big data’ expertise and outreach programs, are all essential ingredients to stimulating collaboration across the UC system, whether it is finding ways to better predict the impact of earthquakes and wildfires or developing new drugs to combat debilitating diseases.

Confronting such societal challenges requires collaboration among researchers who have the scientific vision, technological skill, and innovative approaches to advance discovery. To that end, in 2014 SDSC launched an initiative called UC@SDSC – an engagement strategy that highlights collaboration, innovation, and education while promoting the Center’s resources and technical expertise as a valuable asset to the entire UC system. While SDSC already has numerous engagement initiatives underway, here are some highlights, aligned with those three themes:

Collaboration

‘LHC@UC’

Frank Würthwein, a noted expert in high-energy particle physics and advanced computation, recently joined SDSC as head of the Distributed High-Throughput Computing Group. Würthwein’s mission is to develop and deploy a high-capacity, shared data and compute platform anchored at SDSC that will serve the entire UC system. The initiative is called ‘LHC@UC’ because in 2013, Würthwein and his team used SDSC’s Gordon supercomputer to provide auxiliary computing capacity to the Open Science Grid by processing massive data sets generated by the Compact Muon Solenoid (CMS), one of two particle detectors at the Large Hadron Collider (LHC).  One of the key benefits of such a UC network is that individual PIs across all UC campuses will have direct access to SDSC’s expertise and resources from their home institutions.

UC Collaborative Research Opportunity (CRO) Activity

This program allows SDSC experts interested in collaborating with UC researchers to apply for a CRO mini-grant to support collaborative work, in turn leading to an extramural grant proposal. In addition to the strategic ‘top down’ CRO LHC@UC mentioned above, SDSC currently has two PI-initiated (‘bottoms up’) CRO awards: SDSC Computational Scientist Yifeng Cui is collaborating on a seismic simulations proposal with UCR; and Ross Walker, an assistant research professor at SDSC, is coordinating a UCSD/UCR/UCI proposal for a GPU cluster to the NIH.

Innovation

‘Made in UC’ Initiative

This project focuses on the cataloguing of ‘Made in UC’ software and technologies that specifically relate to data science and computational science.  We are partnering with UC researchers on benchmarking various technologies and extending software so that they can be run on different types of clusters and be able to scale to big data problems.  This project has already spawned several collaboration brainstorming sessions between SDSC PIs and researchers at UC Irvine, UC Merced, UC Riverside, and UC Santa Cruz.

Pacific Research Platform & Integrated Digital Infrastructure (IDI) Initiative

SDSC has made significant contributions to the Pacific Research Platform, which engages all UC campuses including Lawrence Berkeley National Laboratory as well as other universities across California and the western region. The immediate objective is to develop a “regional Science DMZ” across the regional partners that opens up the capabilities of high-performance networking to advance data transfers and scientific collaborations for researchers across all scientific domains. This initiative is receiving high visibility across all campuses at the CIO and VCR levels. Working with Larry Smarr, the IDI Chair and Director of CalIT2, SDSC staff are active contributors, and participated in a recent high-profile demonstration of this capability at the CENIC 2015 conference earlier this month.

Education

SDSC Summer Institute

The theme for the SDSC Summer Institute week-long workshops is “HPC for the Long Tail of Science.” This is an ideal program for UC researchers who would like to become more familiar with advanced computation as it relates to data management, running jobs on SDSC resources, reproducibility, database systems, and other techniques for turning data into knowledge. Participants will receive hands-on training using SDSC’s Gordon and Comet supercomputers. The program is designed for individuals interested in data science and computational science - especially current and potential users of SDSC's data-intensive resources. Familiarity with UNIX/Linux environments is essential. Some programming experience in C/C++, Fortran, Java, R, Python, Perl, MATLAB or other languages is preferred. .

UCSD Research Experience for High School Students (REHS)

Since 2010, SDSC has sponsored research internships for talented high school students from all over San Diego county. These internships provide opportunities for qualified students to work side-by-side with SDSC staff and researchers, including some of the world's leading computational scientists, helping them solve some of the most challenging and important problems facing us today. Students spend eight weeks during the summer at SDSC applying existing skills and learning new ones doing real science in an exciting and inspiring academic environment. Students find great reward from the experience knowing they are making important contributions to society while at the same time learning many of the life skills they will need to excel in their future endeavors both in college and in their future careers. Their internship experience culminates with them presenting the results of their work to the broader SDSC community in the form of a professional scientific poster. To date, SDSC has sponsored internships for more than 300 high school students coming from a wide range of backgrounds and experiences. Learn more about the REHS Program and other K-12 education opportunities. 

Learn about SDSC’s high-performance compute systems

Learn about SDSC’s data storage systems

Learn about SDSC’s Centers of Excellence

Byte Basics - the anatomy of a byte:

  • Byte: A unit of computer information equal to one typed character.
  • Megabyte: A million bytes; equal in size to a short novel.
  • Gigabyte: A billion bytes; equal to information contained in a stack of books almost three stories high.
  • Terabyte: A trillion bytes; about equal to the information printed on paper made from 50,000 trees.
  • Petabyte: A quadrillion bytes. It would take 1,900 years to listen to a petabyte's worth of songs – if you had a large enough MP3 player.
  • Exabyte: One quintillion bytes; every word ever spoken by humans could be stored on five exabytes.
  • Zettabtye: One sextillion bytes; enough data to fill a stack of DVDs reaching halfway to Mars.

Rating a supercomputer's performance:

  • Megaflops: A million floating point operations per second. The original Cray-1 supercomputer was capable of 80 megaflops.
  • Gigaflops: A billion floating point operations per second. Today's personal computers are capable of gigaflops performance.
  • Teraflops: A trillion (1012) floating point operations per second. Most of today's supercomputers are capable of teraflops performance.
  • Petaflops: A quadrillion (1015) floating point operations per second. The latest supercomputer barrier to be broken. The fastest systems can now achieve about 2.5 petaflops.
  • Exaflops: A quintillion (1018) floating point operations per second, and the new frontier for supercomputers, provided we can make exascale supercomputers 100 to 1,000 times as energy-efficient as today's fastest machines.

Common supercomputer terms and (simple) definitions