TeraGrid Science Gateways Nancy Wilkins-Diehr TeraGrid Area Director for Science Gateways MURPA lecture, March 12, 2010

TeraGrid is one of the largest investments in shared CI from NSF’s Office of Cyberinfrastructure MURPA lecture, March 12, 2010

TeraGrid resources today include: Tightly Coupled Distributed Memory Systems, 2 systems in the top 10 at top500.org –Kraken (NICS): Cray XT5, 99,072 cores, 1.03 Pflop –Ranger (TACC): Sun Constellation, 62,976 cores, 579 Tflop, 123 TB RAM Shared Memory Systems –Cobalt (NCSA): Altix, 8 Tflop, 3 TB shared memory –Pople (PSC): Altix, 5 Tflop, 1.5 TB shared memory Clusters with Infiniband –Abe (NCSA): 90 Tflops –Lonestar (TACC): 61 Tflops –QueenBee (LONI): 51 Tflops Condor Pool (Loosely Coupled) –Purdue- up to 22,000 cpus Gateway hosting –Quarry (IU): virtual machine support Visualization Resources –TeraDRE (Purdue): 48 node nVIDIA GPUs –Spur (TACC): 32 nVIDIA GPUs Storage Resources –GPFS-WAN (SDSC) –Lustre-WAN (IU) –Various archival resources MURPA lecture, March 12, 2010 Source: Dan Katz, U Chicago New systems: Data Analysis and Vis systems Longhorn (TACC): Dell/NVIDIA, CPU and GPU Nautilus (NICS): SGI UltraViolet, 1024 cores, 4TB global shared memory Data-Intensive Computing Dash (SDSC): Intel Nehalem, 544 processors, 4TB flash memory FutureGrid Experimental computing grid and cloud test-bed to tackle research challenges in computer science Keeneland Experimental, high-performance computing system with NVIDIA Tesla accelerators

So how did the Gateway program develop? A natural result of the impact of the internet on worldwide communication and information retrieval Implications on the conduct of science are still evolving –1980’s, Early gateways, National Center for Biotechnology Information BLAST server, search results sent by , still a working portal today –1989 World Wide Web developed at CERN –1992 Mosaic web browser developed –1995 “International Protein Data Bank Enhanced by Computer Browser” –2004 TeraGrid project director Rick Stevens recognized growth in scientific portal development and proposed the Science Gateway Program –Today, Web 3.0 and programmatic exchange of data between web pages Simultaneous explosion of digital information –Growing analysis needs in many, many scientific areas –Sensors, telescopes, satellites, digital images, video, genomic sequencers –#1 machine on Top500 today over 1000x more powerful than all combined entries on the first list in 1993 MURPA lecture, March 12, 2010 Only 18 years since the release of Mosaic!

Access to supercomputers hasn’t changed much in 20 years But the world around them sure has! MURPA lecture, March 12, 2010

vt100 in the 1980s and a login window on Ranger today MURPA lecture, March 12, 2010

Why are gateways worth the effort? Increasing range of expertise needed to tackle the most challenging scientific problems –How many details do you want each individual scientist to need to know? PBS, RSL, Condor Coupling multi-scale codes Assembling data from multiple sources Collaboration frameworks MURPA lecture, March 12, 2010 #! /bin/sh #PBS -q dque #PBS -l nodes=1:ppn=2 #PBS -l walltime=00:02:00 #PBS -o pbs.out #PBS -e pbs.err #PBS -V cd /users/wilkinsn/tutorial/exercise_3../bin/mcell nmj_recon.main.mdl +( &(resourceManagerContact="tg- login1.sdsc.teragrid.org/jobmanager-pbs") (executable="/users/birnbaum/tutorial/bin/mcell") (arguments=nmj_recon.main.mdl) (count=128) (hostCount=10) (maxtime=2) (directory="/users/birnbaum/tutorial/exercise_3") (stdout="/users/birnbaum/tutorial/exercise_3/globus.out") (stderr="/users/birnbaum/tutorial/exercise_3/globus.err") ) ======= # Full path to executable executable=/users/wilkinsn/tutorial/bin/mcell # Working directory, where Condor-G will write # its output and error files on the local machine. initialdir=/users/wilkinsn/tutorial/exercise_3 # To set the working directory of the remote job, we # specify it in this globus RSL, which will be appended # to the RSL that Condor-G generates globusrsl=(directory='/users/wilkinsn/tutorial/exercise_3') # Arguments to pass to executable. arguments=nmj_recon.main.mdl # Condor-G can stage the executable transfer_executable=false # Specify the globus resource to execute the job globusscheduler=tg-login1.sdsc.teragrid.org/jobmanager- pbs # Condor has multiple universes, but Condor-G always uses globus universe=globus # Files to receive sdout and stderr. output=condor.out error=condor.err # Specify the number of copies of the job to submit to the condor queue. queue 1

Gateways democratize access to high end resources Almost anyone can investigate scientific questions using high end resources –Not just those in the research groups of those who request allocations –Gateways allow anyone with a web browser to explore Opportunities can be uncovered via google –My then 11-year-old son discovered nanoHUB.org when his science class was studying Bucky Balls Foster new ideas, cross-disciplinary approaches –Encourage students to experiment But used in production too –Significant number of papers resulting from gateways including GridChem, nanoHUB –Scientists can focus on challenging science problems rather than challenging infrastructure problems MURPA lecture, March 12, 2010

NSF understands the impact technology can have on science “Virtual environments have the potential to enhance collaboration, education, and experimentation in ways that we are just beginning to explore.” “In every discipline, we need new techniques that can help scientists and engineers uncover fresh knowledge from vast amounts of data generated by sensors, telescopes, satellites, or even the media and the Internet.” MURPA lecture, March 12, 2010 Gateways are a terrific example of interfaces that can support transformative science

Today, there are approximately 35 gateways using the TeraGrid MURPA lecture, March 12, 2010

Not just ease of use What can scientists do that they couldn’t do previously? Linked Environments for Atmospheric Discovery (LEAD) - access to radar data National Virtual Observatory (NVO) – access to sky surveys Ocean Observing Initiative (OOI) – access to sensor data PolarGrid – access to polar ice sheet data SIDGrid – expensive datasets, analysis tools GridChem –coupling multiscale codes How would this have been done before gateways? MURPA lecture, March 12, 2010

What makes a gateway a TeraGrid gateway? TeraGrid gateways are gateways that use TeraGrid resources Are they all developed by TeraGrid? –No, we don’t make gateways the gateways you use, we make the gateways you use better –The strength of the program lies in the development of end user interfaces by those in the community TeraGrid does provide staff to assist with gateway use of the resources –Anyone can request support via the same peer review process used to request CPU hours or a data allocation Assistance from a staff member dedicated to your project, multi-month time investment to really understand and help solve complex problems –Must have commitment from PIs Want to make sure work is incorporated into production codes and gateways –Good candidates for targeted support include: Large, high impact projects Ability to influence new communities Happy for feedback from directorates on important projects –Lessons learned move into training and documentation MURPA lecture, March 12, 2010

3 steps to connect a gateway to TeraGrid Request an allocation –Only a 1 paragraph abstract required for up to 200k CPU hours Register your gateway –Visibility on public TeraGrid page Request a community account –Run jobs for others via your portal Staff support is available! MURPA lecture, March 12, 2010

Tremendous Opportunities Using the Largest Shared Resources - Challenges too! What’s different when the resource doesn’t belong just to me? –Resource discovery –Accounting –Security –Proposal-based requests for resources (peer-reviewed access) Code scaling and performance numbers Justification of resources Gateway citations Tremendous benefits at the high end, but even more work for the developers Potential impact on science is huge –Small number of developers can impact thousands of scientists –But need a way to train and fund those developers MURPA lecture, March 12, 2010

When is a gateway appropriate? Researchers using defined sets of tools in different ways –Same executables, different input GridChem, CHARMM –Creating multi-scale workflows –Datasets Common data formats –National Virtual Observatory –Earth System Grid –Some groups have invested significant efforts here caBIG, extensive discussions to develop common terminology and formats BIRN, extensive data sharing agreements Difficult to access data/advanced workflows –Sensor/radar input LEAD, GEON MURPA lecture, March 12, 2010

How to get started? Conduct a needs assessment –Should I build a gateway? –Can I use an existing gateway? –What problems am I trying to solve? All gateways don’t need high end computing Decide on a software approach –Recommended software at Targeted effort by a few can benefit many –Could a pool of developers design gateways for different domain areas? Yes! TeraGrid staff assistance MURPA lecture, March 12, 2010

Gateways in the marketplace Kids control telescopes and share images “In seconds my computer screen was transformed into a live telescopic view” –“Slooh's users include newbies and professional astronomers in 70 countries” Observatories in the Canary Islands and Chile, Australia coming soon 5000 images/month since 2003 Increases public support for investment in these facilities MURPA lecture, March 12, 2010

Linked Environments for Atmospheric Discovery LEAD Providing tools that are needed to make accurate predictions of tornados and hurricanes Data exploration and Grid workflow MURPA lecture, March 12, 2010

Highlights: LEAD Inspires Students Advanced capabilities regardless of location A student gets excited about what he was able to do with LEAD “Dr. Sikora:Attached is a display of 2- m T and wind depicting the WRF's interpretation of the coastal front on 14 February It's interesting that I found an example using IDV that parallels our discussion of mesoscale boundaries in class. It illustrates very nicely the transition to a coastal low and the strong baroclinic zone with a location very similar to Markowski's depiction. I created this image in IDV after running a 5-km WRF run (initialized with NAM output) via the LEAD Portal. This simple 1-level plot is just a precursor of the many capabilities IDV will eventually offer to visualize high-res WRF output. Enjoy! Eric” ( , March 2007) MURPA lecture, March 12, 2010

PolarGrid brings CI to polar ice sheet measurement MURPA lecture, March 12, 2010 Cyberinfrastructure Center for Polar Science (CICPS) –Experts in polar science, remote sensing and cyberinfrastructure –Indiana, ECSU, CReSIS Satellite observations show disintegration of ice shelves in West Antarctica and speed-up of several glaciers in southern Greenland –Most existing ice sheet models, including those used by IPCC cannot explain the rapid changes

Components of PolarGrid –Expedition grid consisting of ruggedized laptops in a field grid linked to a low power multi-core base camp cluster –Prototype and two production expedition grids feed into a 17 Teraflops "lower 48" system at Indiana University and Elizabeth City State (ECSU) split between research, education and training. –Gives ECSU (a minority serving institution) a top-ranked 5 Teraflop high performance computing system Access to expensive data TeraGrid resources for analysis –Large level 0 and level 1 data sets require once and done processing and storage –Filters applied to level 1 data by users in real time via the web Student involvement MURPA lecture, March 12, 2010 Source: Geoffrey Fox

Social Informatics Data Grid Collaborative access to large, complex datasets SIDGrid is unique among social science data archive projects –Streaming data which change over time Voice, video, images (e.g. fMRI), text, numerical (e.g. heart rate, eye movement) –Investigate multiple datasets, collected at different time scales, simultaneously Large data requirements Sophisticated analysis tools MURPA lecture, March 12,

Viewing multimodal data like a symphony conductor “Music-score” display and synchronized playback of video and audio files –Pitch tracks –Text –Head nods, pause, gesture references Central archive of multi-modal data, annotations, and analyses –Distributed annotation efforts by multiple researchers working on a common data set History of updates Computational tools –Distributed acoustic analysis using Praat –Statistical analysis using R –Matrix computations using Matlab and Octave MURPA lecture, March 12, 2010 Source: Studying Discourse and Dialog with SIDGrid, Levow, 2008

SCEC Gateway used to produce realistic hazard map Probabilistic Seismic Hazard Analysis (PSHA) map for California –Created from Earthquake Rupture Forecasts (ERC) ~7000 ruptures can have 415,000 variations Warm colors indicate regions with a high probability of experiencing strong ground motion in the next 50 years Ground motion calculated using full 3-D waveform modeling for improved accuracy –Results in significant CPU use MURPA lecture, March 12, 2010

SCEC: Why a gateway? Calculations need to be done for each of the hundreds of thousands of rupture variations –SCEC has developed the “CyberShake computational platform” Hardware, software and people which combine to produce a useful scientific result –For each site of interest - two large-scale MPI calculations and hundreds of thousands of independent post-processing jobs with significant data generation »Jobs aggregated to appear as a single job to the TeraGrid »Workflow throughput optimizations and use of SCEC’s gateway “platform” reduced time to solution by a factor of three –Computationally-intensive tasks, plus the need for reduced time to solution is a priority make TeraGrid a good fit MURPA lecture, March 12, 2010 Source: S. Callahan et.al. “Reducing Time-to-Solution Using Distributed High-Throughput Mega- Workflows – Experiences from SCEC CyberShake”.

GridChem Understanding molecular structure and function increasingly important in many fields –Materials for electronics, biotechnology, medical devices, pharmaceutical design GridChem provides reliable infrastructure for computational chemists –NSF Middleware Initiative (NMI) project Requested and received advanced support from TeraGrid –Addressing issues which benefit all gateways, support team led by IU Common user environments for domain software access Standardized licensing Application performance characteristics Incorporation of additional data handling tools and data resources Fault tolerant workflows Scheduling policies for community users Remote visualization MURPA lecture, March 12, 2010

GridChem: Why a gateway? Integrates high end resources in a desktop environment –Client-server approach allows work to continue while disconnected (plane flights) –Ability to monitor jobs across sites –Access to individual allocations –In the future, linkage of multi-scale packages Focus on chemistry research without learning the intricacies of each system –Time limits, nodes, processors, memory, disk space, etc MURPA lecture, March 12, 2010

Robetta Gateway Protein structure prediction with an award-winning code Protein structure prediction is among many important problems in bioinformatics. The Rosetta code, from the David Baker laboratory, has performed very well at CASP (Critical Assessment of Techniques for Protein Structure Prediction) competitions –Available for use by any academic scientist via the Robetta server Robetta developers able to use TeraGrid’s existing gateway infrastructure, including community accounts and Globus –This very successful group needed no additional TeraGrid assistance to incorporate TeraGrid resources into the Robetta gateway Google scholar reports 601 references to the Robetta gateway, including many PubMed publications MURPA lecture, March 12, 2010

Robetta: Why a gateway? Bioinformatics has long history of web-based services –NCBI Blast server from the 1990s Easy input from the web Access to top modeling code for all researchers MURPA lecture, March 12, 2010

Using the TeraGrid to Understand the Stars and Search for Planets: Problem: The oscillations modes of stars give clues to the stellar interior. Accurate modeling of these oscillations can tell us the size, composition and age of stars, and in turn help interpret the data returned by NASA’s Kepler Mission in the hunt for Earth-like extrasolar planets. Solution: NCAR is working with the international science community to develop a TeraGrid science gateway to fit oscillation data with stellar models to determine these parameters automatically for large numbers of stars. Key Elements: international science impact, gateway technology. The turbulent solar atmosphere captured with NASA’s TRACE satellite is overlaid with a model of one of the millions of oscillation modes that allow scientists to deduce the Sun’s hidden internal structure and dynamics. Similar measurements are now being made for other solar-type stars. MURPA lecture, March 12, 2010 Source: Dr. Rich Loft, NCAR

Analytical Ultracentrifugation Emerging computational tool for the study of proteins The Center for Analytical Ultracentrifugation of Macromolecular Assemblies, UT Health Sciences –Major advances in the characterization of proteins and protein complexes as a result of new instrumentation and powerful software –Monitoring the sedimentation of macromolecules in real time in the centrifugal field allows their hydrodynamic and thermodynamic characterization in solution –Observations are electronically digitized and stored for further mathematical analysis – MURPA lecture, March 12, 2010 Source: Modern analytical ultracentrifugation in protein science: A tutorial review, Wikipedia

UltraScan provides a comprehensive data analysis environment Management of analytical ultracentrifugation data for single users or entire facilities Support for storage, editing, sharing and analysis of data –HPC facilities used for 2-D spectrum analysis and genetic algorithm analysis TeraGrid (~2M CPU hours used) Technische University of Munich Juelich Supercomputing Center Portable graphical user interface MySQL database backend for data management Over 30 active institutions TeraGrid advanced support –Fault tolerance, workflows, use of multiple TG resources, community account implementation MURPA lecture, March 12, 2010

Future Technical Areas Web technologies change fast –Must be able to adapt quickly Gateways and gadgets –Gateway components incorporated into any social networking page –75% of 18 to 24 year-olds have social networking websites iPhone apps? Web 3.0 –Beyond social networking and sharing content –Standards and querying interfaces to programmatically share data across sites Resource Description Framework (RDF), SPARQL MURPA lecture, March 12, 2010

Gateways can further investments in other projects Increase access –To instruments, expensive data collections Increase capabilities –To analyze data Improve workforce development –Can prepare students to function in today’s cross-disciplinary world Increase outreach Increase public awareness –Public sees value in investments in large facilities –Pew 2006 study indicates that half of all internet users have been to a site specializing in science –Those who seek out science information on the internet are more likely to believe that scientific pursuits have a positive impact on society MURPA lecture, March 12, 2010

But, sustained funding is a problem Gateway white paper provides recommendations Gateways can be used for the most challenging problems, but –Scientists won’t rely on something that they are not confident will be around for the duration We see this with software, but even more so with gateway infrastructure A sustained gateway program can –Reduce duplication of effort Sporadic development with many small programs –Increase diversity of end users –Increase skill set diversity of developers –Bring together teams to address the toughest problems MURPA lecture, March 12, 2010

Recommend 10-year program with interim reviews Characteristics of 5-year or less cycles –Build exciting prototypes with input from scientists –Work with early adopters to extend capabilities –Tools are publicized, more scientists interested –Funding ends –Scientists who invested their time to use new tools are disillusioned Less likely to try something new again –Start again on new short-term project Need to break this cycle EAGER grant to look at characteristics of successful gateways and domain areas where a gateway could have a big impact – MURPA lecture, March 12, 2010

Tremendous Potential for Gateways In only 18 years, the Web has fundamentally changed human communication Science Gateways can leverage this amazingly powerful tool to: –Transform the way scientists collaborate –Streamline conduct of science –Influence the public’s perception of science Reliability, trust, continuity are fundamental to truly change the conduct of science through the use of gateways –Study ongoing to identify characteristics of successful gateways The future is very exciting! –High end resources can have a profound impact MURPA lecture, March 12, 2010

Thank you for your attention! Questions? Nancy Wilkins-Diehr,