Cse new graduate_students2011

CITRIS 2011
Computational Science and Engineering (CSE) @ Berkeley
i4Science and CSE @ CITRIS
inspired by Science
Bounded by our imagination
innovation through Technology
Create Social impact
Masoud Nikravesh @ CITRIS and LBNL
CITRIS Director for CSE
Executive Director, DE-CSE @ Berkeley

CITRIS 2011
Outline
 Designated Emphasis (DE) in Computational Science
and Engineering (DE-CSE) @ Berkeley
 i4 Science @ CITRIS
 CITRIS

CITRIS 2011
Computational Science and Engineering (CSE)
inspired by Science
Jim Demmel
EECS & Math Departments
www.cs.berkeley.edu/~demmel

CITRIS 2011
What is CSE?
CSE is a rapidly growing multidisciplinary field that
encompasses real-world complex applications
(scientific, engineering, social, economic, policy),
computational mathematics, and computer science
and engineering. High performance computing
(HPC), large-scale simulations, and scientific
applications all play a central role in CSE.

CITRIS 2011
TOP 10 Sites for November 2010
Rank Site Computer
1
National Supercomputing Center in Tianjin
China
Tianhe-1A - NUDT TH MPP, X5670 2.93Ghz 6C, NVIDIA GPU,
FT-1000 8C
NUDT
2
DOE/SC/Oak Ridge National Laboratory
United States
Jaguar - Cray XT5-HE Opteron 6-core 2.6 GHz
Cray Inc.
3
National Supercomputing Centre in Shenzhen
(NSCS)
China
Nebulae - Dawning TC3600 Blade, Intel X5650, NVidia Tesla
C2050 GPU
Dawning
4
GSIC Center, Tokyo Institute of Technology
Japan
TSUBAME 2.0 - HP ProLiant SL390s G7 Xeon 6C X5670, Nvidia
GPU, Linux/Windows
NEC/HP
5
DOE/SC/LBNL/NERSC
United States
Hopper - Cray XE6 12-core 2.1 GHz
Cray Inc.
6
Commissariat a l'Energie Atomique (CEA)
France
Tera-100 - Bull bullx super-node S6010/S6030
Bull SA
7
DOE/NNSA/LANL
United States
Roadrunner - BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2
Ghz / Opteron DC 1.8 GHz, Voltaire Infiniband
IBM
8
National Institute for Computational
Sciences/University of Tennessee
United States
Kraken XT5 - Cray XT5-HE Opteron 6-core 2.6 GHz
Cray Inc.
9
Forschungszentrum Juelich (FZJ)
Germany
JUGENE - Blue Gene/P Solution
IBM
10
DOE/NNSA/LANL/SNL
United States
Cielo - Cray XE6 8-core 2.4 GHz
Cray Inc.

CITRIS 2011
TOP 10 Sites for June 2011
Rank Site Computer
1
RIKEN Advanced Institute for Computational
Science (AICS)
Japan
K computer, SPARC64 VIIIfx 2.0GHz, Tofu interconnect
Fujitsu
2
National Supercomputing Center in Tianjin
China
Tianhe-1A - NUDT TH MPP, X5670 2.93Ghz 6C, NVIDIA GPU, FT-
1000 8C
NUDT
3
DOE/SC/Oak Ridge National Laboratory
United States
Jaguar - Cray XT5-HE Opteron 6-core 2.6 GHz
Cray Inc.
4
National Supercomputing Centre in Shenzhen
(NSCS)
China
Nebulae - Dawning TC3600 Blade, Intel X5650, NVidia Tesla C2050
GPU
Dawning
5
GSIC Center, Tokyo Institute of Technology
Japan
TSUBAME 2.0 - HP ProLiant SL390s G7 Xeon 6C X5670, Nvidia
GPU, Linux/Windows
NEC/HP
6
DOE/NNSA/LANL/SNL
United States
Cielo - Cray XE6 8-core 2.4 GHz
Cray Inc.
7
NASA/Ames Research Center/NAS
United States
Pleiades - SGI Altix ICE 8200EX/8400EX, Xeon HT QC 3.0/Xeon
5570/5670 2.93 Ghz, Infiniband
SGI
8
DOE/SC/LBNL/NERSC
United States
Hopper - Cray XE6 12-core 2.1 GHz
Cray Inc.
9
Commissariat a l'Energie Atomique (CEA)
France
Tera-100 - Bull bullx super-node S6010/S6030
Bull SA
10
DOE/NNSA/LANL
United States
Roadrunner - BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz
/ Opteron DC 1.8 GHz, Voltaire Infiniband
IBM

CITRIS 2011
Computational Science and Engineering (CSE) @ Berkeley
Designated Emphasis (DE) in CSE Participants
~120 Faculty (CSE), ~120 Researchers (Cloud), ~22 Departments,
~60 Courses, more being developed
http://cse.berkeley.edu/ http://cloud.citris-uc.org/
http://citris-uc.org/ http://www.lbl.gov/cs

CITRIS 2011
Applications
Cloud-HPC
Computing
Analytics
Math
High performance computing
(HPC), large-scale simulations,
and scientific applications all
play a central role in CSE.
i4Science
CSE
The HPC/cloud computing initiative
and next generation data center
Extreme simulation, visual-data analytics,
data-enabled scientific discovery
Applications/real‐world complex applications (scientific, engineering, social, economic,
policy) using the future multi-core parallel computing ((i.e. E-Informatics, Earthquake Early
Warning, NextGenMaps, Genome Atlas, Genetic Facebook, Genomics Browser)
CSE
Berkeley and LBNL Partnership
HPC-Petascale and Exascale
systems are an indispensable
tool for exploring the frontiers of
science and technology for
social impact.

CITRIS 2011
4 Big Events
 Establishment of a new graduate program in Computational
Science and Engineering (CSE)
 “Multicore revolution”, requiring all software (where
performance matters!) to change
• ParLab
 Cloud computing
• RadLab  AMPLab
 XSEDE – organizes NSF ―cyberinfrastructure‖
 Extreme Science & Engineering Discover Environment
 Broadcasting our CSE courses nationwide

CITRIS 2011
Outline
 Goals
 Participants
117 faculty from 22 departments – so far
60 Courses, more being developed
 How the DE works
 Resources and Opportunities
 Details at cse.berkeley.edu

CITRIS 2011
Designated Emphasis (DE) in CSE
• New “graduate minor” – approved, starting July 1, 2008
• Motivation
– Widespread need to train PhD students in large scale
simulation, or analysis of large data sets
– Opportunities for collaboration, across campus and at LBNL
• Graduate students participate by
– Getting accepted into existing department/program
– Taking CSE course requirements
– Qualifying examination with CSE component
– Need to sign up before quals!
– Thesis with CSE component
– Receive “PhD in X with a DE in CSE”

CITRIS 2011
Participating Departments (1/2)
( # faculty by “primary affiliation”, # courses )
•Astronomy (7,3)
•Bioengineering (3,1)
•Biostatistics (2,0)
•Chemical & Biomolecular Engineering (6,0)
•Chemistry (8,1)
•Civil and Environmental Engineering (7,8)
•Earth and Planetary Science (6,3)
•EECS (19,14)
•IEOR (5,5)
•School of Information (1,0)

CITRIS 2011
Participating Departments (2/2)
• Integrative Biology (1,0)
•Materials Science and Engineering (2,1)
•Mathematics (15, 4)
•Mechanical Engineering (12, 6)
•Neuroscience (7,1)
•Nuclear Engineering (2,1)
•Optometry (2,0)
•Physics (1,1)
•Political Science (2,0)
•Statistics (5, 11)
•Biostatistics, Public Health

CITRIS 2011
Course Structure
 3 kinds of students, course requirements
 Applications, CS, Math
 Each kind of student has 3 course requirements in other two
fields
 Goal: enforce cross-disciplinary training
 Ex: Applications students takes courses from EECS, Math,
Statistics, IEOR
 We support new course development
 5 courses recently created/updated

CITRIS 2011
Example Course – CS267
 “Applications of Parallel Computing”
 see www.cs.berkeley.edu/~demmel/cs267_Spr11
 Taught every Spring, in Spr 09 semester to:
 UC Berkeley, UC Merced, UC Santa Cruz, UC Davis
 All lectures on web (slides + video), freely available
 38 Grad + 5 Undergrad
 2/3 from EECS, rest ME, Chem, BioE, BioPhys, IntBio
 Google “parallel computing course” to get older version
(CS267 ranked #1 !)

CITRIS 2011
A few sample CS267 Class Projects
(all posters and video on web page)
 Content based image recognition
 “Find me other pictures of the person in this picture”
 Faster molecular dynamics, applied to Alzheimer’s Disease
 Better speech recognition through a faster “inference engine”
 Faster algorithms to tolerate errors in new genome sequencers
 Faster simulation of marine zooplankton population
 Sharing cell-phone bandwidth for faster transfers

CITRIS 2011
3 Day Parallel BootCamp
 CS267 in 3 days – Aug 15-17, 2011
 261 registrants from 45 companies and 61 universities/labs
 Taught by ParLab faculty, Intel, Microsoft
 Covers multicore, distributed memory, GPU, cloud computing
 Hands-on Labs (accounts courtesy of NERSC,XSEDE)
 All webcast, video archived for later use
 parlab.eecs.berkeley.edu/2011bootcamp
 Offered annually
 Google ―parallel computing course‖: ranked #2 !

CITRIS 2011
Example Course: Ma221
 Numerical Linear Algebra
 How to solve linear systems, least squares, eigenvalue
problems, singular value problems …
 How to tell if you get the right answer
 How to do it faster
 New, faster, algorithms for most problems
Motivated by ideas in ParLab
 Large grants to incorporate them into standard
libraries

CITRIS 2011
New CSE Courses
 Python for science – AY250
 Josh Bloom (Astronomy)
 3 day summer short course + seminar
 Understanding Molecular Simulation
 Phil Geissler (Chem) and Berend Smit (ChemE)
 Matlab based, students from Chem, ChemE, MSE, ME, BioPhys
 Computer Simulations in the Earth Sciences – EPS109
 Burkhard Militzer (Earth & Planetary Science)
 Machine learning for understanding simulations/data sets, in Matlab
 Optimization Models in Engineering – EE127
 Laurent El Ghaoui (EECS)
 Matlab (CVX) based, models not algorithms
 SW Eng. for Scientific Computing – CS194/294
 Phil Colella (EECS,LBL)
 For non-CS grads and undergrads

CITRIS 2011
Some CSE Resources
 Chair Jim Demmel
 demmel@eecs.berkeley.edu
 Executive Director Masoud Nikravesh
 nikravesh@cs.berkeley.edu
 Student Affairs Officer Pat Berumen
 patbcoe@berkeley.edu
 Head Graduate Adviser Andy Packard
 pack@me.berkeley.edu
 Computing resources
 Cloud computing, start up allocations from LBNL/NERSC,
CITRIS-IBM, clusters …

CITRIS 2011
Computing Sciences at Berkeley Laboratory
Kathy Yelick
Associate Laboratory Director for Computing
Sciences

CITRIS 2011
National Energy Research Scientific Computing Facility
Department of Energy Office of Science
(unclassified) Facility
• 4000 users, 500 projects
• From 48 states; 65% from universities
• 1400 refereed publications per year
Systems designed for science
• 1.3 PF Hopper system (Cray XE6)
- 4th Fastest computer in US, 8th in world
• .5 PF in Franklin (Cray XT4), Carver (IBM
iDataplex) and other clusters

CITRIS 2011
NERSC Systems
Large-Scale Computing Systems
Franklin (NERSC-5): Cray XT4
• 9,532 compute nodes; 38,128 cores
• ~25 Tflop/s on applications; 356 Tflop/s peak
Hopper (NERSC-6): Cray XE6
• 6,384 compute nodes, 153,216 cores
• 120 Tflop/s on applications; 1.3 Pflop/s peak
HPSS Archival Storage
• 40 PB capacity
• 4 Tape libraries
• 150 TB disk cache
NERSC Global
Filesystem (NGF)
Uses IBM‘s GPFS
• 1.5 PB capacity
• 5.5 GB/s of bandwidth
Clusters
140 Tflops total
Carver
• IBM iDataplex cluster
PDSF (HEP/NP)
• ~1K core cluster
Magellan Cloud testbed
• IBM iDataplex cluster
GenePool (JGI)
• ~5K core cluster
Analytics
Euclid
(512 GB shared
memory)
Dirac GPU
testbed (48
nodes)
25

CITRIS 2011
The TOP10 of the TOP500
Rank Site Manufacturer Computer Country Cores
Rmax
[Pflops] [MW]
1
RIKEN Advanced
Institute for
Computational Science
Fujitsu
K Computer
SPARC64 VIIIfx 2.0GHz,
Tofu Interconnect
Japan 548,352 8.162 9.90
2
National
SuperComputer Center
in Tianjin
NUDT
Tianhe-1A
NUDT TH MPP,
Xeon 6C, NVidia, FT-1000 8C
China 186,368 2.566 4.04
3
Oak Ridge National
Laboratory
Cray
Jaguar
Cray XT5, HC 2.6 GHz
USA 224,162 1.759 6.95
4
National
Supercomputing Centre
in Shenzhen
Dawning
Nebulae
TC3600 Blade, Intel X5650,
NVidia Tesla C2050 GPU
China 120,640 1.271 2.58
5
GSIC, Tokyo Institute of
Technology
NEC/HP
TSUBAME-2
HP ProLiant, Xeon 6C, NVidia,
Linux/Windows
Japan 73,278 1.192 1.40
6 DOE/NNSA/LANL/SNL Cray
Cielo
Cray XE6, 8C 2.4 GHz
USA 142,272 1.110 3.98
7
NASA/Ames Research
Center/NAS
SGI
Pleiades
SGI Altix ICE 8200EX/8400EX
USA 111,104 1.088 4.10
8
DOE/SC/
LBNL/NERSC
Cray
Hopper
Cray XE6, 6C 2.1 GHz
USA 153,408 1.054 2.91
9
Commissariat a
l'Energie Atomique
(CEA)
Bull
Tera 100
Bull bullx super-node
S6010/S6030
France 138.368 1.050 4.59
10 DOE/NNSA/LANL IBM
Roadrunner
BladeCenter QS22/LS21
USA 122,400 1.042 2.34

CITRIS 2011
Computational Research Division
27
Applied Mathematics Computer Science
HPC architecture,
OS, and compilers
512
256
128
64
32
16
8
4
2
1024
1/16 1 2 4 8 16321/8
1/4
1/2
1/32
RTM/wave eqn.
NVIDIA C2050 (Fermi)
SpMV
7pt Stencil
27pt Stencil
DGEMM
GTC/chargei
GTC/pushi
Performance
& Autotuning
Visualization
and Data
Management
Cloud, grid &
distributed
computing
Mathematical
Models
Adaptive Mesh
Refinement
Linear
Algebra
Libraries and
Frameworks
Interface
Methods
NanoscienceCombustion Climate Cosmology &
Astrophysics
GenomicsEnergy &
Environment

CITRIS 2011
Parallel Computing Short Courses –
offered by LBNL
 12th Workshop on DOE Advanced CompuTational
Software (ACTS) Collection
 Aug 16-19 – this week!
 acts.nersc.gov/events/Workshop2011/
 How to use selected computational tools developed for
high performance computing
 ScaLAPACK, PETSc, Hypre, Zoltan, GlobalArrays, …
 Feel free to visit (their web site)

CITRIS 2011
From Teragrid to XSEDE
• Teragrid
• Easy access to NSF cyberinfrastructure
• Supercomputers, storage, visualization, networks
• Education, training and support of users
• XSEDE: Extreme Science and Engineering Discovery Environment
• Next-Generation Teragrid – www.xsede.org
• Started July 2011, 17 institutions, $121M over 5 years
• New, more integrated cyberinfrastructure
• More educational activities
• Assist curriculum development
• Help form new CSE degree programs
• Broadcast, provide computing facilities for selected courses
• 4 courses (so far) from Berkeley:
• Parallel bootcamp, CS267, ACTS Workshop, Keutzer‘s CS194

CITRIS 2011
Strategic Projects/
Shared Facilities,
Resources, Expertise
Technology
Streaming Data and
Visual Analytics
Core Group*
Core Scientific
Group*
Shared Facilities
VisLab+ Computing
Infrastructures
Delivery of Service
Mobile Devices,
Internet, and Cloud
Science/Applications
scientific,engineering,social,economic/business/finance
ACCESS- E-informatics
Earthquake Early
Warning
Next Generation
Dynamic Maps
Genome Atlas, Genetic
Facebook, Genomics
Browser, bioinformatics,
Immune System, …
Computational
Bioscience,
Neuroscience,
Nanoscience ,
Astrophysics , …
*core group of enabling computational scientists would stand at the heart of the center, and that they would both cross-
pollinate expertise among projects and provide great leverage in winning large federally-supported projects*.
Educational, Research, and Social Impacts; IT-Enabled Disaster Resilience
i4Science at CITRIS and LBNL
Intensive Computing, Immersive Visualization and Human Interaction
Data and Visual-enabled Scientific Discovery and Insight Accelerator
(~120 CSE Faculty, ~120 Cloud Researchers, and 22 Departments)
(~120 BCNM Faculty and 35 Departments)

CITRIS 2011
For more information about
Computational Science and Engineering:
cse.berkeley.edu

CITRIS 2011
Participating CSE Faculty

CITRIS 2011
Participating ME Faculty
 David Auslander
 Francesco Borrelli
 Michael Frenklach
 Tony Keaveny
 Philip Marcus
 Sara McMains
 Oliver O‘Reilly
 Andrew Packard
 Panos Papadopoulos
 David Steigmann
 Tarek Zohdi
 Paul Wright

CITRIS 2011
BioStat Participants
 Sandrine Dudoit
 Nicholas Jewel
 John Rice
 Bin Yu

CITRIS 2011
Nuclear Eng Participants
 John Verboncoeur
 Brian Wirth

CITRIS 2011
Helen Wills Neuroscience Institute
 Michael DeWeese
 Jack Gallant
 Tom Griffiths
 Robert Knight
 Bruno Olshausen
 Frederic Theunissen
 Dan Yang

CITRIS 2011
Astronomy Participants
 Jonathan Arons
 Josh Bloom
 Carl Heiles
 Richard Klein
 Elliot Quatert
 Donald Backer
 Chris McKee

CITRIS 2011
Math Faculty Participants
 Grigory Barenblatt
 Alexandre Chorin
 James Demmel
 David Eisenbud
 Craig Evans
 Steve Evans
 Alberto Grunbaum
 Ming Gu
 Ole Hald
 Olga Holtz
 Richard Karp
 Lior Pachter
 Per-Olof Persson
 James Sethian
 John Strain
 Bernd Sturmfels
 Jon Wilkening
 Maciej Zworski

CITRIS 2011
Vision Science Faculty Participants
Sources: 44
• Maneesh Agrawala (EECS)
• Yang Dan (Neuroscience, MCB)
• Jack Gallant (Neuroscience, Psychology)
• Stanley Klein (Optometry)
• Bruno Olshausen (Neuroscience, Optometry)
• Austin Roorda (Optometry)

CITRIS 2011
Participating EECS Faculty
 Maneesh Agrawala
 Ruzena Bajcsy
 Jose Carmena
 Paul Hilfinger
 Clark Nguyen
 James O’Brien
 Jaijeet Roychowdhury
 Jonathan Shewchuk
 Kathy Yelick
 Avideh Zakhor
 Edward lee
 Stuart Russell
 Shakar Sastry
 Laurent El-Ghaoui
 James Demmel
 Peter Bartlett
 Michael Jordan
 Richard Karp
 Alistair Sinclair
 Martin Wainwright
 Bin Yu

CITRIS 2011
Participating EPS Faculty
 William Collins
 Doug Dreger
 Inez Fung
 Michael Manga
 Burkhard Militzer
 Mark Richards
 Barbara Romanowicz
 David Romps

CITRIS 2011
(inspired, imagination, innovation, impact)
inspired by Science
Masoud Nikravesh @ CITRIS and LBNL
CITRIS Director for CSE
Executive Director, DE-CSE @ Berkeley

CITRIS 2011
i4Science: Vision
(Inspired, Imagination, Innovation, Impact)
To support the work of scientists and engineers as they
pursue complex -simulation, as well as computational,
data and visualization- intensive research to enhance
scientific, technological, and economic leadership while
improving our quality of life.
Inspired by Science
Bounded by our Imagination
Innovation through Technology
Create Social Impact

CITRIS 2011
i4Science: Mission
(Inspired, Imagination, Innovation, Impact)
 Conduct world-leading research in applied mathematics and
computer science to provide leadership in such areas as energy,
environment, health-information technology, climate, bioscience and
neuroscience, and intelligent cyber-physical infrastructure to name a
few.
 Be at the forefront of the development and use of ultra-efficient
largest-scale computer systems, focusing on discoveries and
solutions that link to the evolution of the commercial market for high-
performance and cloud computing and services.
 Allow industry collaborators to gain experience with computational
modeling / simulation and the effective use of HPC and Cloud
facilities and carrying back new expertise to their institutions. This
would enable the Industry partners to be ―first to market‖ with
important scientific and technological capabilities, breakthrough
ideas, and new hardware-software.

CITRIS 2011
Applications
Cloud-HPC Analytics
High performance computing
(HPC), large-scale simulations,
and scientific applications all
play a central role in CSE.
i4Science
CSE
The HPC/cloud computing initiative
and next generation data center
Extreme simulation, visual-data analytics,
data-enabled scientific discovery
Applications/real‐world complex applications (scientific, engineering, social, economic,
policy) using the future multi-core parallel computing ((i.e. E-Informatics, EarthQuake Early
Warning, NextGenMaps, Genome Atlas, Genetic Facebook, Genomics Browser)
i4Science
HPC-Petascale and Exascale
systems are an indispensable
tool for exploring the frontiers of
science and technology for
social impact.

CITRIS 2011
i4Science
UC Berkeley and LBNL have recently partnered in four areas of
research and education at the forefront of large-scale computation:
extreme simulation, [streaming] massive scale visual-data
analytics, (Insight Lab)
the cloud and mobile cloud computing initiative (and services
science),
the future of multi-core parallel computing (Tera+ applications,
+1,000 cores).
education of the next generation of interdisciplinary students and
industry leaders (CSE program and a new Professional Master
Program (PMS) to be developed)
In addition, Berkeley and LBNL have made major commitments to
develop our computational science infrastructure, which includes
computing clusters and advance visualization laboratory.

CITRIS 2011
i4Science
The i4Science Initiative a research based program is a
strategic partnership between CITRIS and LBNL.
i4Science will focus mainly on smaller subset of CSE
applications that within 3–5 years would be scalable
from 1000s to millions of processors and from tera to
exa-scale computing using emerging computing
technologies—HPC and Cloud.
The initiative will also explore the use of virtual reality,
including Second Life and SimCity, as well as other
social network technologies such as the Citizen
CyberScience to build community for education and
outreach, and for training decision-makers.

CITRIS 2011
i4Science: Initial Areas of Interest
 i4Science will focus mainly on smaller subset of CSE applications that within
3–5 years would be scalable from 1000s to millions of processors and from
tera to exa-scale computing using emerging computing technologies—HPC
and Cloud. In the areas of:
 i4Science – Data Enabled Discovery (Streaming Massive Scale Visual- Data
Analytics; Insight Lab and CDISC Proposal)
 i4Science – Cloud-Mobile Computing– Knowledge Mobilization (Services
Science and HPC Cloud)
 i4Science – Ecosystems and Urban Metabolism (Smart Cities- ACCESS
Proposal)
 i4Science – Financial and Economic Systems and Market
 i4Science – ICT-Enabled Disaster Resilience (Command and Control)
 i4Science – Healthcare - IT, Genetic, Monitoring and Life Sciences (P4-
Medicine)
 i4Science – Intelligent Cyber-Physical Infrastructure (People, Sensors,
Machines and Systems)
 i4Science – Education (CSE and Multi-Disciplinary Education)

CITRIS 2011
~120 Faculty (CSE),
~120 Researchers (Cloud),
~22 Departments,
~60 Courses, more being developed
http://cse.berkeley.edu/
Designated Emphasis (DE) in CSE
Participants

CITRIS 2011
CSE Participating Departments (1/2)
•Astronomy (7,3)
•Bioengineering (3,1)
•Biostatistics (2,0)
•Chemical Engineering (6,0)
•Chemistry (8,1)
•Civil and Environmental Engineering (7,8)
•Earth and Planetary Science (6,3)
•EECS (19,14)
•IEOR (5,5)
•School of Information (1,0)

CITRIS 2011
CSE Participating Departments (2/2)
• Integrative Biology (1,0)
•Materials Science and Engineering (2,1)
•Mathematics (15, 4)
•Mechanical Engineering (9, 6)
•Neuroscience (7,1)
•Nuclear Engineering (2,1)
•Physics (1,1)
•Political Science (2,0)
•Statistics (5, 11)
•New: Biostatistics, Public Health

CITRIS 2011
58
Cloud Initiative at Berkeley
~120 Faculty (CSE), ~120 Researchers (Cloud) , 22 Departments
Data Structure
Analytics
Service
Delivery

CITRIS 2011
Cloud
Infrastructure
Applications (scientific,
engineering, social,
economic/business/finance,
policy)
Delivery of
Services
Mobile Devices
Mobile CloudSoftware and Appliances
Cluster Scheduling &
Reliability
Network Research and
Security
Supercomputer
Public Cloud
Private Cloud
Volunteering Computing
Mobile Cloud
Streaming Data
Massive Data
Extreme Simulation
Large Scale Visualization
Machine Learning
Analytics
Intelligent Dynamic Maps
Early Warning
Social Networking
Second Life
Cyber Citizen
Personalized Services
Crowd Sourcing

CITRIS 2011
 Infrastructure – Cloud Cluster and Data Centers
 Delivery of Services – Mobile Cloud
 Applications
 Scientific
 Social
 Economics/Business
 Software and Appliances
 Cluster Scheduling & Reliability
 Network Research and Security
Mobile devices, Mobile Cloud, and Cloud Infrastructure
will be the device/tools of choice for delivery of services.

CITRIS 2011
CITRIS Cloud Computing Initiative
We will focus on three main areas:
 Machine Learning: Provide the general public with
machine learning analytics tools and algorithm runs in
cloud infrastructure.
 Streaming Data Analytics and Visualization: Analyses
and visualization of large-scale real time data sets such
as traffic information, online news sources, economics
data, and scientific data such as astrophysical data.
 Scientific Applications: Benchmarking and cataloging the
suitability of cloud computing for science and engineering
applications, including HPC applications.

CITRIS 2011
Initial Survey of Research Topics for “Cloud” (1/2)
 A small selection from among the 120 faculty
 Some ok on ―cloud,‖ others may require tighter coupling
 Astronomy (10 faculty)
 Some simulations (large scale, many smaller scale),
some large data sets (up to terabytes/day)
 Chemistry and Chemical Engineering (12 faculty)
 Some large-scale simulations, some less tightly coupled
 Ex: New materials for energy via QMC, chemical database
screening
 Neuroscience and Cognitive Computing (8 faculty)
 Some large scale simulations (of brain, auditory system)
 Some large data set analysis (crcns.org)

CITRIS 2011
Initial Survey of Research Topics for “Cloud” (2/2)
 Computational systems biology (9 faculty)
 ―Digital Human‖, many layers of simulation
 Econ/EECS/IEOR/Math/PoliSci/Stat (9 faculty)
 Statistical analysis and visualization of large scale
heterogeneous data bases of economic, financial, social data
 Ex: statnews.eecs.berkeley.edu/about/project for news analysis
 Economics (8 faculty, including 1 Nobelist)
 Econometric and social modeling
 Ultra-efficient Climate Computer (7 faculty + staff)
 Joint with LBNL
 100x lower power than current supercomputers

CITRIS 2011
64
i4Science
Insight Lab
Applications
Machine
Learning
Massive
Scale Data
Analytics and
Visualization

CITRIS 2011
Earthquake early warning
400 seismic stations
across California
Use existing seismic stations to
• detect the beginning of earthquakes
• estimate the location and magnitude
• predict damaging ground shaking
• issue a warning to those in harms way
Seconds to tens
of seconds warning,
up to 1 minute
• people move to safe zone (under table)
• slow and stop trains (BART)
• isolate hazards (equipment, chemicals)
new science + modern communications
Allen Richard

CITRIS 2011
Opinion Space:
Crowdsourcing Insights
Scalability: N Participants, N Viewpoints
Each Viewpoint is n-Dimensional
Dim. Reduction: 2D Map of Affinity/Similarity
Insight vs. Agreement: Nonlinear Scoring
N2 Peer to Peer Reviews
Source: Ken Goldberg and Alec Ross

CITRIS 2011
CISN
ShakeMap
Crowdsourcing + physical modeling + sensing + data assimilation
Physical modeling-based live maps, which contain real-time assessments of
situation integrating streaming data
Source: Alex Bayen
NextGenMap: The Value of Multi-disciplinary Research:
Invention, Societal-pull, Products, New Legislation

CITRIS 2011
Source: Paul Nerenberg
Molecular Dynamics Force Field Development
MD simulations of
peptides and small
molecules
New parameters for bonded
and non-bonded interactions
Comparison with
quantitative expt. data
Ultimate goal: to characterize the
structural ensembles of intrinsically
disordered proteins and peptides (e.g.,
amyloid β – the ―Alzheimer‘s protein‖)
using MD simulations in tandem with
biophysical experiments.

CITRIS 2011
 Real-time (machine-learned) classification of astronomical event data
 data deluge requires abstracting traditional roles of scientist in discovery
 working with real data now, towards a scaleable framework for the Large
Synoptic Survey (LSST) era
new statistical analytics
on sparse data
machine learning with noisy
& spurious feature sets
cloud-based ML with
massive databases
Source: Josh Bloom
Berkeley Time-Series Center

CITRIS 2011
Applied Mathematics and Statistics, UCSC
Geophysical and Astrophysical Fluid Dynamics (GAFD) esp. HPC simulations
THE SUN
Yohkoh
SOHO La Palma
LOCAL MODELS OF COMPRESSIBLE MHDOBSERVATIONAL DATA
Source: N. Brummell

CITRIS 2011
Diagnostic:
• moderate
pleomorphism
• high cellularity
Diagnostic:
• zonal
necrosis
The Cancer Genome Atlas
To Characterize Every Tumor Type
Molecular data (e.g., copy number,
methylation)
Histology section (e.g., apoptotic rate)
Sequence data
Source: Bahram Parvin

CITRIS 2011
Innovative visualizations for a topic‘s
summary in news across time
 Real-time summaries of topics across many news sources
 Global image of news landscape
 Interpretable results obtained via sparse machine learning techniques
 Massive data sets requires cloud computing
Real-time image of news sources or topics
Source: Laurent El Ghaoui
StatNews:
Analytics and Visualization of News Data

CITRIS 2011
Berkeley Teleimmersion Lab
Real-time 3D reconstruction
Cameras
• Tele-immersion connects remote users through a shared virtual environment
• Users are captured in real-time using stereo cameras to obtain their 3D avatar
• Geometry of the real world is preserved and mapped into virtual environment
Source: Ruzena Bajcsy

CITRIS 2011
Potential
NEGF
Poisson
Equation
Charge
GNR
GNR
m-CNT
Franklin
Simulations
Atomistic, Non-Equilibrium, Quantum Statistics-
Mechanical and Massively Parallel Simulation of
Electronic Transport for Energy Aware Electronics
•Massive parallelization
enables simulations of
realistic structures, starting
from every atom, previously
considered impossible
Results highlighted as a cover
story in Applied Phys Letters
(97, 03310,2, 2010.)
Source: S. Salahuddin

CITRIS 2011
3D/4D Modeling and Visualization
Prof. Avideh Zakhor, Video & Image Processing Lab
 Fast, automatic, scalable, 3D modeling
using heterogeneous sensors such as laser
scanners, cameras, IMUs, ….
 Building interiors
 City modeling at the street level
 Airborne modeling of cities
 4D modeling: x,y,z plus time:
 Build time varying model of an evolving
object or a scene
 Use camera/projector structured light
systems in one station
 Surround the scene by multiple stations
Capture
Area
4D modeling
Portable backpack for interior modeling
Source: A. Zakhor

CITRIS 2011
Development of Parallel Analytical Tools
Goal: Create new, scalable methods to
explore petascale climate data
Task: Combine 3 powerful methods –
• VisIt: a parallel visualization package
• R: a statistical computing environment
• CDAT: PCMDI‘s Climate Data Analysis Tools
Result: A highly concurrent analytical package
optimized for statistical characterization of
localized features in climate-change simulation.
Randall CRM GMAO ESM
Source: B. Collins

CITRIS 2011
78
Opportunities to Use
Visualization Facility
in Education

CITRIS 2011
Information School
 i247: Information Visualization and Presentation
 Prof. Marti Hearst, Dr. Cecelia Aragon
 http://courses.ischool.berkeley.edu/i247/s08/
 ―The goal of information visualization is the unveiling of the
underlying structure of large or abstract data sets using
visual representations that utilize the powerful processing
capabilities of the human visual perceptual system. We will
analyze the factors contributing to success or lack thereof,
as a means to determine how to devise future successful
visualizations.‖

CITRIS 2011
i247 Sample Class Project

CITRIS 2011
Civil & Environmental Eng
 Prof. Alex Bayen
 Teaching traffic engineering (highway flow modeling,
traffic data analytics), to help better understand the
physics of traffic, and relate it to flow models
 Next: ‗How to program your data analytics application'
with the application running on the cloud, querying our
central system, and displaying things on the viz wall.
 Later: research on large scale visualization of traffic.

CITRIS 2011
Civil & Environmental Eng
 Prof. Tina Chow
 CE 105 - Applied environmental fluid mechanics - new
grad/undergrad course for Spring 2011
 Hands-on, project based modeling class
 Public outreach efforts through the Lawrence Hall of Science
 First theme: weather in the Bay Area, using numerical models
to help understand flow patterns and explain "micro-climates"
due to topography etc. We will be running high-resolution
mesoscale atmospheric models for the Bay Area and have
lots of data to visualize.
 Use the visualization wall during class to
 explore the flow field in different regions in the Bay Area
 having student groups use it to help create an educational video
for posting online,
 hosting small groups of K-12 kids for live demos on the vis. wall.

CITRIS 2011
Statistics
 Prof. Bin Yu
 Stat 215A – first year graduate applied statistics
 Large data sets to visualize include
 Multi-angle satellite images (9 angles
and 4 bands) for arctic cloud detection
 Natural-image (and movie) MRI data
from V1, V2 and V4 and other visual regions of the human
brain
 Would also use in Stat 151AB, on linear models

CITRIS 2011
EECS
 Prof. Stuart Russell
 CS289 – Knowledge Representation
 Visualize data from global
seismic/infrasound/hydroacoustic monitoring, which I am
working on for the UN to detect nuclear explosions inter
alia. The images would be mostly map-based with heat-
map (probability) and point-cloud overlays etc., both
static and dynamic.

CITRIS 2011
EECS
 Prof Ruzena Bajcsy
 Distributed education for training health providers, eg
surgical training
 Training archeologists how to interpret archeological
findings
 Prof. James O‘Brien
 CS184 – computer graphics
 How to synchronize visual effects on a large scale

CITRIS 2011
86
Center Examples for i4Science
CDISC
ACCESS Insight

CITRIS 2011
87
CDISC: Center for Data-Driven Scientific Computing
Center Example for i4Science
Date-Driven
Scientific Computing
APPS
CORE
LIBRARIES
ANALYTICS
MACHINE
LEARNING
TRANINING &
EDUCATION
OUTREACH
Devices and Computing Environment

CITRIS 2011
88
Our Center will develop a wide array of computational tools to tackle the
challenges of data-intensive scientific research across multiple scientific
disciplines.
These tools will encapsulate state of the art machine learning and statistical
modeling algorithms into broadly applicable, high-level interfaces that can
be easily used by application scientists.
Our goal is to dramatically reduce the time needed to extract knowledge
from the floods of data science is facing, thanks to workflows that permit
exploratory and collaborative research to evolve into robustly reproducible
outcomes.
CDISC:
Center for Data-Driven Scientific Computing

CITRIS 2011
89
Our development will be driven by a collection of scientific problems that
share a common theme.
They all present major data-intensive challenges requiring significant
algorithmic breakthroughs and represent key questions within their field,
from rapid astronomical discovery of rare events to early warning
systems for natural hazards such as earthquakes or tsunamis.
Moving beyond the traditional domain of scientific computing, we will
tackle a collection of problems in social sciences and the digital
humanities, pushing the boundaries of quantitative scholarship in these
disciplines.
CDISC:
Center for Data-Driven Scientific Computing

CITRIS 2011
90
Berkeley ACCESS Themes
Center for Accelerating Environmental Synthesis and Solutions (ACCESS)
To enable synthesis, En Infomatics
(En= Environmental, Ecological, Epidemiological, Economic,
Engineering, Equitable, Ethical,… )
ACCESS: Center Example for i4Science

CITRIS 2011
ACCESS Focus
ACCESS will focus on five major domains critical
for human welfare and environmental quality:
freshwater, health, ecosystems, urban metabolism,
and food security; and will create and implement a
synthesis process that makes research tools and
understanding rapidly accessible across disciplines,
and foster new ways of thinking across disciplines
about critical environmental problems.
Source: Inez Fung

CITRIS 2011
Berkeley ACCESS Themes
Ecosystem trajectories over the past million years and in the future -
rate and nature - result principally 8000 generations of human
population growth and aspirations.
Underlying ecosystem trajectories are the changing supply and
demand of water and the need to harness energy to advance
civilization.
Urban metabolism: Theoretical models of cities as complex socio-
ecological systems with particular metabolic dynamics. Urban policy
is increasingly critical to building a more sustainable future.
The increasing ease of utilizing existing resources leads to their rapid
and unsustainable depletion, with many resulting intolerable impacts,
including those on
 Human and animal health
 Food security
Source: Inez Fung

CITRIS 2011
Urban Metabolism
Conceptual Frameworks for Urban Metabolism: Theoretical models of
cities as complex socio-ecological systems with particular metabolic
dynamics include approaches based in political economy, sociology, urban
ecology and biogeochemistry, and industrial ecology – many of which
remain disconnected from each other. In addition, because the inputs to
urban life are globalized, the geography of consumption and production
networks must be integrated into conceptual frameworks.
Data Integration: A rapidly expanding volume of geospatial data on urban
stocks and flows – about people, animals, vegetation, consumer products,
energy, waste, etc. – is available for synthesis and building models of the
complex metabolic cycles of cities.
Policy and Activism: Urban policy is increasingly critical to building a more
sustainable future, but the policy interventions and activist campaigns are
piecemeal remedies rather than solutions based on an understanding of
cities as complex socio-ecological systems.
Visualization and Decision-Support: Decision makers and stakeholders of
many types need to visuzlize model results quickly and effectively.
Generating sophisticated and insightful visualizations of urban systems is
an emergent and critical field.
Source: Inez Fung

CITRIS 2011
Environmental-Informatics
Seamless access to massively-distributed and diverse types of data (e.g.
satellite, museum specimens)
State-of-the-art visualization infrastructure
Collaborative analysis practices (e.g. textual and graphical annotation,
links, tags)
Scalable data transformations in a time concordant with interactive data
analysis
Cloud computing as well as large-scale simulations on super computers
Synthesis of imprecise E-data - societal values and decision making
Virtual reality and social networking for building enviro-community, for
education & outreach, and for training on the ground decision-makers
Source: Inez Fung

CITRIS 2011
To Enable Synthesis, En Infomatics
(En= Environmental, Ecological, Epidemiological, Economic,
Engineering, Equitable, Ethical,… )
To gather large volumes of data (e.g. Flu Trends on
google)
To browse and explore large volumes of diverse types of
data
For conceptual synthesis of diverse types of data (e.g.
satellite data, museum samples, anthropological data)
Cloud computing, Display wall, …
Source: Inez Fung

CITRIS 2011
96
“Sustainable California” –
a Return to the Golden State

CITRIS 2011
CITRIS Infrastructure can Support the
Critical Tasks
Data
Structure
Analytics
Service
Delivery
Colleges of Engineering, Letters and Sciences, LBNL, CSE
Computational science support in data, analytics, visualization and delivery
CITRIS, CoE, LBNL, Letters and Sciences, Public Health
Deep content knowledge for target systems
CITRIS
Platform for multi-campus, multidisciplinary, public/private collaboration
Haas, I-School
Services science and innovation
97

CITRIS 2011
Energy &
Environment
Health Care
New Media
Developing
Economies
Intelligent
Infrastructure
An Initial Look at Opportunities
98
 California
Telehealth
Network
 Statewide Energy Network California Watershed
 Traffic
 Earthquake
 Demand & Response
 Urban Metabolism
 Food
 Water
 Health
 Ecosystem
 Art, Music, Film & Culture
 Immersive Visualization
 Human Interaction
 Cloud & HPC
 Intensive Computing
 Massive Scale Visual-Data
Analytics
 Interactive Visualization
 Simulation and Modeling
 Services Science
& Engineering
(i4Science)

CITRIS 2011
California can improve the standard of living by applying
predictive simulation to critical problems facing the state
How can California respond to
rapidly changing environment,
climate change, economic forces
and demographics?
 water resources, public health,
natural disasters, energy
conservation
Predictive simulation can be used to
 understand the impacts of policy
choices
 create new technologies
and industries
 find more efficient solutions to
California‘s pressing infrastructure
problems

CITRIS 2011
“Sustainable California” –
a return to the Golden State
100
 building upon massive scale datasets
– streaming and static
 employing sophisticated analytics, with
an emphasis on modeling and simulation
A statewide initiative to create integrated
systems using advanced computational
science and engineering

CITRIS 2011
Strategic Partnership/Major Funding
Funding will support i4Science researchers to expand and accelerate
the on-going funded research, and to accelerate transfer of
technology to our sponsors.
A "core group" of enabling computational scientists would stand at the
heart of the center, and they will both cross-pollinate expertise
among projects and provide great leverage in winning large
federally-supported projects.
All this broad expertise would be available to our sponsors, allowing
them to better design their own hardware and software for the larger
CSE community.
This would enable our sponsors to be ―first to market‖ and/or ―first to
lead‖ with important scientific and technological capabilities,
breakthrough ideas, new hardware-software and potentially
expanding the impact of both of our science and of Sponsors‘ tools.

CITRIS 2011
i4Science: Funding
In order to realize our vision: funding for 5 years for the following three
objectives:
To support highly interdisciplinary research and focus mainly on
applications that within 3–5 years would be scalable from 1000s to millions
of processors and/or users, and from tera to exa-scale computing using
emerging computing technologies—HPC and Cloud.
To support many-core and accelerator-based computing: Emerging many-
core architectures—graphics processing units (GPUs), and many-core
CPUs
For technical and scientific support to accelerate the path to scientific
solution and to house and upgrade the current cloud infrastructure/initiative,
computing resources, and visualization lab.
Mobile devices, Mobile Cloud, and Cloud Infrastructure will be the device/tools
of choice for delivery of services.

CITRIS 2011
Computational Science and Engineering
(CSE) @ CITRIS
(inspired, imagination, innovation, impact)
inspired by Science

CITRIS 2011
An Introduction to CITRIS
Paul K. Wright, Director
Center for Information Technology in the
Interest of Society (CITRIS)

CITRIS 2011
CITRIS:
An Institute of Science & Innovation
10
History:
Created in 1999 by then-Governor Grey Davis
Research Focus:
• Energy
• Health Care
• Intelligent Infrastructure
• New Media
Berkeley
Davis
Merced
Santa Cruz

CITRIS 2011
The CITRIS Mission
―CITRIS creates information technology solutions
for many of our most pressing social, environmental
and health care challenges. CITRIS was created to
‗shorten the pipeline‘ between world class
laboratory research and the societal impact of
technology through its rapid transfer to established
companies, and the creation of start-ups and whole
industries.‖
106

CITRIS 2011
CITRIS Strategy
Solutions
for Social
Impact
“Big Bets”
Common
Processes &
Tools
Civic
Engagement

CITRIS 2011
CITRIS Strategy:
“Big Bets”
10
Focus on a small
number of topics:
• Multi-disciplinary
• Multi-campus
• Tangible social impact
• Potential to lead
internationally

CITRIS 2011
Big Bets
Delivering ―Quality Healthcare Everywhere‖
for Californians
Improving access and reducing disparities by
creating a statewide, trusted ―medical-grade‖ network.
109

CITRIS 2011
Big Bets
Systems for ―Adaptive Cities‖
Building water, air, traffic and noise management systems
for cities that support resilience to climate change and acute
disruptive events
110

CITRIS 2011
Big Bets
Equipping the ―Smart Grid‖
Designing and building information technology, sensors
and controls for facilities‘ ―Smart Grid‖
111

CITRIS 2011
Recent Developments
California Energy Commission grant to instrument
and monitor gas pipeline conditions
Green Millennium project at Sutardja Dai Hall
monitors energy usage, controls lighting
Novel printed batteries head
toward commercialization

CITRIS 2011
Proposed Strategy:
Common IT Tools & Processes
11
Instrument
& Sense
Extract
Data
Analyze
Visualize &
Communicate

CITRIS 2011
Water
Air
Energy
Earthquake
BWRC
Marvell
Lab
μSensors
TinyOS
Prototyping
Devices
and
Sensors
G/H
FEEDBACK
California Independent System (Cal ISO)
Cyberspace
Handhelds
Laptop/PC
Clusters
IBM/ room143
Cloud
+
+
+
Analytics
Algorithms
M/C Learning/A.I.
Statistical Analysis
Social Comp
Knowledge
Insight
Large-Scale
Information
Extraction
Delivery and
Service
Back to
Handhelds
Distributed
Systems
Visualization, Analytics
and Insight
Physical
World
Big Data
Streams
A Model of Infrastructure: Water

CITRIS 2011
Proposed Strategy:
Civic Engagement
11
Collect
Data
Build
Understanding
Motivate and
Reason
Share Opinions
Call to Action
“Data & Democracy”
Academia
Government
Business
Public

CITRIS 2011
CITRIS Strategy & Tactics
Domains &
“Big Bets”
Delivery of
Health Care
Intelligent Infrastructure/
Adaptive Cities
Energy
Delivering ―Quality
Healthcare Everywhere‖
Modeling and Decision
Support for Water
Equipping and Analyzing
the Smart Grid
IT Tools &
Processes
Instrument
& Sense
Extract
Data
Analyze
Data
Visualize &
Communicate
Civic
Engagement
―Data & Democracy‖
Collect
Data
Build
Understanding
Share
Opinions
Motivate
& Reason
Call to
Action
116

CITRIS 2011
CITRIS Leadership
 Dr. Paul K. Wright, Director
 Heidi Hallett, Director of Finance and Administration
 Dr. Hugh Aldridge, Director of Development and
Communications
 Steven DeMello, Director of Health Care
 Dr. Masoud Nikravesh, Director for Computational
Science and Engineering
117

CITRIS 2011
Fulfilling Our Mission
Transforming ideas into
technologies and services that
impact California and the world
118

Cse new graduate_students2011

Recomendados

Recomendados

Más contenido relacionado

La actualidad más candente

La actualidad más candente (12)

Destacado

Destacado (17)

Similar a Cse new graduate_students2011

Similar a Cse new graduate_students2011 (20)

Último

Último (20)

Cse new graduate_students2011