SlideShare uma empresa Scribd logo
1 de 4
Baixar para ler offline
Case Study: Allinea DDT Helps Drive the
Evolution of Geoscientific Model Development
Snapshot
Client: The University
at Buffalo’s Center for
Computational Research (CCR)
is one of the leading academic
supercomputing sites in the U.S.
Challenge: To gain a more
holistic view of the planet,
environmental scientists and
engineers are linking their
models together and bringing in
more data. The size, complexity
and distributed nature of their
projects make the traditional
methods of debugging
ineffective. Time and budget
constraints make the problem
seem insurmountable.
Solution: Allinea DDT – the
leading graphical debugging
tool – makes it easy to debug a
complex, multi-tiered project.
Results: A new framework for
debugging geosciences projects
was created with the help of an
undergraduate math major, who
had such a positive experience
with Allinea DDT she is switching
her discipline to computer
science.
Summary quote: “People
were impressed with the results
Christine achieved using Allinea
DDT and assumed she was
a highly educated computer
science technician; whereas, at
the time, I think she might have
taken just one ‘intro to computer
science’ course.” – Dr. Shawn
Matott, computational scientist,
University at Buffalo’s Center for
Computational Research.

Creating a holistic geoscientific model is
complicated enough. So when scientists
have to debug their computer code, they
turn to Allinea DDT, a tool easy enough for
undergraduates to use.
When it comes to modeling the
Earth, we aren’t in the Garden of
Eden anymore.
The days are gone when a
scientist could run a single
model that works for a collected
dataset and then publish
the results. Today’s teams of
geoscientists, hydrologists,
and engineers are using
supercomputers to link their
models together and create
experiments that are ever-more
complex.
“You want to get a large-scale
holistic picture,” says Dr. Shawn
Matott, computational scientist
at the Center for Computational
Research (CCR). “So, you want
the best-trained person making
the model for groundwater,
and you also want to see what
is happening with the fish
population, human cancer rates,
and so on. You’ve got to be able
to link these different disciplines
as represented by the computer
models.”

CCR has 8,000 cores capable
of more than 100 teraflops.
The center’s system is
heterogeneous: 384 cores have
access to GPUs while others can
access large memory stores.
As scientific models become
more sophisticated, so must
the tools for finding and solving
errors. To this end, CCR uses
Allinea DDT, the most advanced
debugging tool available for
scalar, multi-threaded and
large-scale parallel applications.
Allinea DDT is designed to
make solving even the most
complex multi-process, software
problems straightforward.
“You might have a model that
runs in parallel on a CUDAenabled GPU, and then the
optimizer runs in parallel using
MPI,” says Matott. “You need
tools that can manage that kind
of complexity.”

Christine Baxter,
undergraduate
student

Dr. Shawn Matott,
computational
scientist

University at
Buffalo’s Center
for Computational
Research

University at
Buffalo’s Center
for Computational
Research
Case Study: Allinea DDT Helps Drive the
Evolution of Geoscientific Model Development

Overcoming
Time and Budget
Constraints

Compute program, funded by
the National Science Foundation.
Students work 15 hours a week
on a research project alongside
their regular courses.

Time and budget constraints
add even more challenges.
Organizations like CCR need
a debugging tool that is both
robust and easy to use.

Matott had four undergraduate
math students, two from the
University at Buffalo and two
from Buffalo State College. He
met with the group once a week
to talk about their progress and
answer questions.

“You really can’t afford to stick
a PhD or Master’s student on
something like debugging code,
because their expertise lies more
in the science side of bringing
these models together, building
a better optimizer or better
algorithms,” says Matott.
He often finds assistants through
the Undergraduate Research
Group Experience, or URGE to

The group tested five different
optimizing algorithms on
15 different test functions,
generating 200,000 simulations.
Not all of the experiments ran
successfully. Matott trained
undergraduate Christine Baxter
to write Bash scripts to isolate
roughly 1,000 simulations that
failed and then let her loose on

Allinea DDT to debug several
thousand lines of code. She
discovered the bug in the sort
function of one algorithm.
“She had two weeks of training
on Bash scripting, and basically
no training on Allinea DDT. I
just told her how to launch the
software and, working through
the GUI, she was able to figure it
out,” says Matott. “I think if she’d
had to use one of the commandline debuggers, it would have
meant another two weeks of
training to get her up to speed.”
Once Baxter completed the
debugging, she and Matott
constructed the idea of a
framework, which generalized
her process so other
computational scientists could
benefit from it.

Center for Computational Research Machine Room in the NYS Center
of Excellence in Bioinformatics and Life Sciences
Case Study: Allinea DDT Helps Drive the
Evolution of Geoscientific Model Development

Positive Experience
with Allinea
DDT Inspires
Undergraduate
It was a heady experience for
an undergraduate to contribute
to the evolution of geoscientific
model development.
Baxter took the debugging
framework to the fall meeting of
the American Geophysical Union
with 25,000 attendees, where
she displayed and defended her
results in a poster session.
“Here were these
undergraduates standing sideby-side with professors, PhD
students, and post-docs. People
were impressed with the results
Christine achieved using Allinea
DDT and assumed she was
a highly educated computer
science technician; whereas, at
the time, I think she might have
taken just one ‘intro to computer
science’ course,” says Matott.
Baxter had such a positive
experience using Allinea DDT
and developing the debugging
framework, she decided to
switch majors from math to
computer science.

Center for Computational Research’s Computer Visualization Laboratory

Ease-of-Use
Makes Scientists
More Independent
As for the future of the
debugging framework, Matott
says he is considering publishing
a paper along with a case study
of Baxter’s experience. He may
even write a software package to
help geoscientists implement the
debugging framework.
In the meantime, he’s looking
forward to trying out Allinea MAP
,
a performance analysis tool
that uses the same interface as
Allinea DDT.
Matott says he could benefit
from MAP’s problems-at-aglance approach. He’s also keen
on the tool because part of his
job is to help other researchers

run their experiments on the
supercomputing cluster.
“Right now I have a lot of
meetings with the users. If they
are in a different discipline, they
often need to train me about their
area of study before I can help
them,” says Matott. “It would be
nice if I could turn them loose
on a product as user-friendly
as Allinea DDT. They could
independently find out where in
the code they’re spending all
their time and we could take it
from there.”
Allinea DDT and Allinea MAP
combine robust capability with
unmatched ease-of-use so that
scientists like Shawn Matott
can focus on grand challenges
like pushing the evolution of
geosciences modeling so we
can make better decisions about
managing planet Earth.
the
environment

Allinea Software Inc.
2033 Gateway Pl Ste. 500, San Jose,
CA. 95110 USA
Tel: +1 (408) 884 0282
www.allinea.com • info@allinea.com

Allinea Software Ltd.
The Innovation Centre, Warwick Technology Park,
Gallows Hill, Warwick CV34 6UW UK
Tel: +44 (0)1926 623 231 Fax: +44 (0)1926 623 232

For more information about
the Allinea environment, visit
www.allinea.com

Mais conteúdo relacionado

Mais procurados

ReComp and P4@NU: Reproducible Data Science for Health
ReComp and P4@NU: Reproducible Data Science for HealthReComp and P4@NU: Reproducible Data Science for Health
ReComp and P4@NU: Reproducible Data Science for HealthPaolo Missier
 
CI image processing mns
CI image processing mnsCI image processing mns
CI image processing mnsMeenakshi Sood
 
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...IRJET Journal
 
Survey: Biological Inspired Computing in the Network Security
Survey: Biological Inspired Computing in the Network SecuritySurvey: Biological Inspired Computing in the Network Security
Survey: Biological Inspired Computing in the Network SecurityEswar Publications
 
Artificial Intelligence and Anaesthesia
Artificial Intelligence and AnaesthesiaArtificial Intelligence and Anaesthesia
Artificial Intelligence and AnaesthesiaFaizaBuhari
 
Prospects of Deep Learning in Medical Imaging
Prospects of Deep Learning in Medical ImagingProspects of Deep Learning in Medical Imaging
Prospects of Deep Learning in Medical ImagingGodswll Egegwu
 
Performance analysis of data mining algorithms with neural network
Performance analysis of data mining algorithms with neural networkPerformance analysis of data mining algorithms with neural network
Performance analysis of data mining algorithms with neural networkIAEME Publication
 
Towards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsTowards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsManuel Martín
 
Deep learning for biomedical discovery and data mining II
Deep learning for biomedical discovery and data mining IIDeep learning for biomedical discovery and data mining II
Deep learning for biomedical discovery and data mining IIDeakin University
 
Cognitive Computing at University Osnabrück
Cognitive Computing at University OsnabrückCognitive Computing at University Osnabrück
Cognitive Computing at University OsnabrückSteven Miller
 
Deep learning for medical imaging
Deep learning for medical imagingDeep learning for medical imaging
Deep learning for medical imaginggeetachauhan
 

Mais procurados (11)

ReComp and P4@NU: Reproducible Data Science for Health
ReComp and P4@NU: Reproducible Data Science for HealthReComp and P4@NU: Reproducible Data Science for Health
ReComp and P4@NU: Reproducible Data Science for Health
 
CI image processing mns
CI image processing mnsCI image processing mns
CI image processing mns
 
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
 
Survey: Biological Inspired Computing in the Network Security
Survey: Biological Inspired Computing in the Network SecuritySurvey: Biological Inspired Computing in the Network Security
Survey: Biological Inspired Computing in the Network Security
 
Artificial Intelligence and Anaesthesia
Artificial Intelligence and AnaesthesiaArtificial Intelligence and Anaesthesia
Artificial Intelligence and Anaesthesia
 
Prospects of Deep Learning in Medical Imaging
Prospects of Deep Learning in Medical ImagingProspects of Deep Learning in Medical Imaging
Prospects of Deep Learning in Medical Imaging
 
Performance analysis of data mining algorithms with neural network
Performance analysis of data mining algorithms with neural networkPerformance analysis of data mining algorithms with neural network
Performance analysis of data mining algorithms with neural network
 
Towards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive SystemsTowards Automatic Composition of Multicomponent Predictive Systems
Towards Automatic Composition of Multicomponent Predictive Systems
 
Deep learning for biomedical discovery and data mining II
Deep learning for biomedical discovery and data mining IIDeep learning for biomedical discovery and data mining II
Deep learning for biomedical discovery and data mining II
 
Cognitive Computing at University Osnabrück
Cognitive Computing at University OsnabrückCognitive Computing at University Osnabrück
Cognitive Computing at University Osnabrück
 
Deep learning for medical imaging
Deep learning for medical imagingDeep learning for medical imaging
Deep learning for medical imaging
 

Semelhante a University at Buffalo’s Center for Computational Research

Lifelong Personal Health Data And Application Software Via...
Lifelong Personal Health Data And Application Software Via...Lifelong Personal Health Data And Application Software Via...
Lifelong Personal Health Data And Application Software Via...Lindsey Campbell
 
Research methodology 3-sps
Research methodology  3-spsResearch methodology  3-sps
Research methodology 3-spssanjay shekhawat
 
Measuring The Value Of The Parent Class
Measuring The Value Of The Parent ClassMeasuring The Value Of The Parent Class
Measuring The Value Of The Parent ClassMelissa Hewitt
 
Speech Conversion Using Neural Networks
Speech Conversion Using Neural NetworksSpeech Conversion Using Neural Networks
Speech Conversion Using Neural NetworksJessica Moore
 
Click here to read article
Click here to read articleClick here to read article
Click here to read articlebutest
 
Reproducibility Analytics Lab
Reproducibility Analytics Lab Reproducibility Analytics Lab
Reproducibility Analytics Lab Verena139
 
Computers Have Been Integrated Into Almost Every Aspect
Computers Have Been Integrated Into Almost Every AspectComputers Have Been Integrated Into Almost Every Aspect
Computers Have Been Integrated Into Almost Every AspectTiffany Young
 
10 06-03 uva boone-technical report
10 06-03 uva boone-technical report10 06-03 uva boone-technical report
10 06-03 uva boone-technical reportSean Casey, USRA
 
Computational Fluid Dynamics Paper
Computational Fluid Dynamics PaperComputational Fluid Dynamics Paper
Computational Fluid Dynamics PaperMiz Hester
 
H2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupH2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupSri Ambati
 
Synergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software EngineeringSynergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software EngineeringTao Xie
 
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...A New Model for Informed Consent - Participant Centered Consent - Broad Insti...
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...john wilbanks
 
Application For Master Degree In Theory And Computational...
Application For Master Degree In Theory And Computational...Application For Master Degree In Theory And Computational...
Application For Master Degree In Theory And Computational...Veronica Hall
 
Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...ijitjournal
 
Role of computers in research
Role of computers in researchRole of computers in research
Role of computers in researchSaravana Kumar
 
SCCAI- A Student Career Counselling Artificial Intelligence
SCCAI- A Student Career Counselling Artificial IntelligenceSCCAI- A Student Career Counselling Artificial Intelligence
SCCAI- A Student Career Counselling Artificial Intelligencevivatechijri
 

Semelhante a University at Buffalo’s Center for Computational Research (20)

Lifelong Personal Health Data And Application Software Via...
Lifelong Personal Health Data And Application Software Via...Lifelong Personal Health Data And Application Software Via...
Lifelong Personal Health Data And Application Software Via...
 
Research methodology 3-sps
Research methodology  3-spsResearch methodology  3-sps
Research methodology 3-sps
 
Notebooks in IBM
Notebooks in IBMNotebooks in IBM
Notebooks in IBM
 
Measuring The Value Of The Parent Class
Measuring The Value Of The Parent ClassMeasuring The Value Of The Parent Class
Measuring The Value Of The Parent Class
 
Speech Conversion Using Neural Networks
Speech Conversion Using Neural NetworksSpeech Conversion Using Neural Networks
Speech Conversion Using Neural Networks
 
Click here to read article
Click here to read articleClick here to read article
Click here to read article
 
Reproducibility Analytics Lab
Reproducibility Analytics Lab Reproducibility Analytics Lab
Reproducibility Analytics Lab
 
Computers Have Been Integrated Into Almost Every Aspect
Computers Have Been Integrated Into Almost Every AspectComputers Have Been Integrated Into Almost Every Aspect
Computers Have Been Integrated Into Almost Every Aspect
 
10 06-03 uva boone-technical report
10 06-03 uva boone-technical report10 06-03 uva boone-technical report
10 06-03 uva boone-technical report
 
COMPUTERS.pptx
COMPUTERS.pptxCOMPUTERS.pptx
COMPUTERS.pptx
 
Computational Fluid Dynamics Paper
Computational Fluid Dynamics PaperComputational Fluid Dynamics Paper
Computational Fluid Dynamics Paper
 
H2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User GroupH2O with Erin LeDell at Portland R User Group
H2O with Erin LeDell at Portland R User Group
 
Synergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software EngineeringSynergy of Human and Artificial Intelligence in Software Engineering
Synergy of Human and Artificial Intelligence in Software Engineering
 
Disease Prediction Using Machine Learning
Disease Prediction Using Machine LearningDisease Prediction Using Machine Learning
Disease Prediction Using Machine Learning
 
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...A New Model for Informed Consent - Participant Centered Consent - Broad Insti...
A New Model for Informed Consent - Participant Centered Consent - Broad Insti...
 
Application For Master Degree In Theory And Computational...
Application For Master Degree In Theory And Computational...Application For Master Degree In Theory And Computational...
Application For Master Degree In Theory And Computational...
 
Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...Survey on evolutionary computation tech techniques and its application in dif...
Survey on evolutionary computation tech techniques and its application in dif...
 
Role of computers in research
Role of computers in researchRole of computers in research
Role of computers in research
 
SCCAI- A Student Career Counselling Artificial Intelligence
SCCAI- A Student Career Counselling Artificial IntelligenceSCCAI- A Student Career Counselling Artificial Intelligence
SCCAI- A Student Career Counselling Artificial Intelligence
 
DMDI
DMDIDMDI
DMDI
 

Último

SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTSIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTxtailishbaloch
 
UiPath Studio Web workshop series - Day 1
UiPath Studio Web workshop series  - Day 1UiPath Studio Web workshop series  - Day 1
UiPath Studio Web workshop series - Day 1DianaGray10
 
Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.IPLOOK Networks
 
My key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIMy key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIVijayananda Mohire
 
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - Tech
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - TechWebinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - Tech
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - TechProduct School
 
Flow Control | Block Size | ST Min | First Frame
Flow Control | Block Size | ST Min | First FrameFlow Control | Block Size | ST Min | First Frame
Flow Control | Block Size | ST Min | First FrameKapil Thakar
 
TrustArc Webinar - How to Live in a Post Third-Party Cookie World
TrustArc Webinar - How to Live in a Post Third-Party Cookie WorldTrustArc Webinar - How to Live in a Post Third-Party Cookie World
TrustArc Webinar - How to Live in a Post Third-Party Cookie WorldTrustArc
 
Technical SEO for Improved Accessibility WTS FEST
Technical SEO for Improved Accessibility  WTS FESTTechnical SEO for Improved Accessibility  WTS FEST
Technical SEO for Improved Accessibility WTS FESTBillieHyde
 
The Importance of Indoor Air Quality (English)
The Importance of Indoor Air Quality (English)The Importance of Indoor Air Quality (English)
The Importance of Indoor Air Quality (English)IES VE
 
Automation Ops Series: Session 2 - Governance for UiPath projects
Automation Ops Series: Session 2 - Governance for UiPath projectsAutomation Ops Series: Session 2 - Governance for UiPath projects
Automation Ops Series: Session 2 - Governance for UiPath projectsDianaGray10
 
Extra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfExtra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfInfopole1
 
Oracle Database 23c Security New Features.pptx
Oracle Database 23c Security New Features.pptxOracle Database 23c Security New Features.pptx
Oracle Database 23c Security New Features.pptxSatishbabu Gunukula
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxNeo4j
 
How to release an Open Source Dataweave Library
How to release an Open Source Dataweave LibraryHow to release an Open Source Dataweave Library
How to release an Open Source Dataweave Libraryshyamraj55
 
Where developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingWhere developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingFrancesco Corti
 
Top 10 Squarespace Development Companies
Top 10 Squarespace Development CompaniesTop 10 Squarespace Development Companies
Top 10 Squarespace Development CompaniesTopCSSGallery
 
UiPath Studio Web workshop series - Day 4
UiPath Studio Web workshop series - Day 4UiPath Studio Web workshop series - Day 4
UiPath Studio Web workshop series - Day 4DianaGray10
 
From the origin to the future of Open Source model and business
From the origin to the future of  Open Source model and businessFrom the origin to the future of  Open Source model and business
From the origin to the future of Open Source model and businessFrancesco Corti
 
Explore the UiPath Community and ways you can benefit on your journey to auto...
Explore the UiPath Community and ways you can benefit on your journey to auto...Explore the UiPath Community and ways you can benefit on your journey to auto...
Explore the UiPath Community and ways you can benefit on your journey to auto...DianaGray10
 

Último (20)

SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENTSIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
SIM INFORMATION SYSTEM: REVOLUTIONIZING DATA MANAGEMENT
 
UiPath Studio Web workshop series - Day 1
UiPath Studio Web workshop series  - Day 1UiPath Studio Web workshop series  - Day 1
UiPath Studio Web workshop series - Day 1
 
Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.Introduction - IPLOOK NETWORKS CO., LTD.
Introduction - IPLOOK NETWORKS CO., LTD.
 
My key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAIMy key hands-on projects in Quantum, and QAI
My key hands-on projects in Quantum, and QAI
 
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - Tech
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - TechWebinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - Tech
Webinar: The Art of Prioritizing Your Product Roadmap by AWS Sr PM - Tech
 
Flow Control | Block Size | ST Min | First Frame
Flow Control | Block Size | ST Min | First FrameFlow Control | Block Size | ST Min | First Frame
Flow Control | Block Size | ST Min | First Frame
 
TrustArc Webinar - How to Live in a Post Third-Party Cookie World
TrustArc Webinar - How to Live in a Post Third-Party Cookie WorldTrustArc Webinar - How to Live in a Post Third-Party Cookie World
TrustArc Webinar - How to Live in a Post Third-Party Cookie World
 
Technical SEO for Improved Accessibility WTS FEST
Technical SEO for Improved Accessibility  WTS FESTTechnical SEO for Improved Accessibility  WTS FEST
Technical SEO for Improved Accessibility WTS FEST
 
SheDev 2024
SheDev 2024SheDev 2024
SheDev 2024
 
The Importance of Indoor Air Quality (English)
The Importance of Indoor Air Quality (English)The Importance of Indoor Air Quality (English)
The Importance of Indoor Air Quality (English)
 
Automation Ops Series: Session 2 - Governance for UiPath projects
Automation Ops Series: Session 2 - Governance for UiPath projectsAutomation Ops Series: Session 2 - Governance for UiPath projects
Automation Ops Series: Session 2 - Governance for UiPath projects
 
Extra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdfExtra-120324-Visite-Entreprise-icare.pdf
Extra-120324-Visite-Entreprise-icare.pdf
 
Oracle Database 23c Security New Features.pptx
Oracle Database 23c Security New Features.pptxOracle Database 23c Security New Features.pptx
Oracle Database 23c Security New Features.pptx
 
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptxGraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
GraphSummit Copenhagen 2024 - Neo4j Vision and Roadmap.pptx
 
How to release an Open Source Dataweave Library
How to release an Open Source Dataweave LibraryHow to release an Open Source Dataweave Library
How to release an Open Source Dataweave Library
 
Where developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is goingWhere developers are challenged, what developers want and where DevEx is going
Where developers are challenged, what developers want and where DevEx is going
 
Top 10 Squarespace Development Companies
Top 10 Squarespace Development CompaniesTop 10 Squarespace Development Companies
Top 10 Squarespace Development Companies
 
UiPath Studio Web workshop series - Day 4
UiPath Studio Web workshop series - Day 4UiPath Studio Web workshop series - Day 4
UiPath Studio Web workshop series - Day 4
 
From the origin to the future of Open Source model and business
From the origin to the future of  Open Source model and businessFrom the origin to the future of  Open Source model and business
From the origin to the future of Open Source model and business
 
Explore the UiPath Community and ways you can benefit on your journey to auto...
Explore the UiPath Community and ways you can benefit on your journey to auto...Explore the UiPath Community and ways you can benefit on your journey to auto...
Explore the UiPath Community and ways you can benefit on your journey to auto...
 

University at Buffalo’s Center for Computational Research

  • 1. Case Study: Allinea DDT Helps Drive the Evolution of Geoscientific Model Development Snapshot Client: The University at Buffalo’s Center for Computational Research (CCR) is one of the leading academic supercomputing sites in the U.S. Challenge: To gain a more holistic view of the planet, environmental scientists and engineers are linking their models together and bringing in more data. The size, complexity and distributed nature of their projects make the traditional methods of debugging ineffective. Time and budget constraints make the problem seem insurmountable. Solution: Allinea DDT – the leading graphical debugging tool – makes it easy to debug a complex, multi-tiered project. Results: A new framework for debugging geosciences projects was created with the help of an undergraduate math major, who had such a positive experience with Allinea DDT she is switching her discipline to computer science. Summary quote: “People were impressed with the results Christine achieved using Allinea DDT and assumed she was a highly educated computer science technician; whereas, at the time, I think she might have taken just one ‘intro to computer science’ course.” – Dr. Shawn Matott, computational scientist, University at Buffalo’s Center for Computational Research. Creating a holistic geoscientific model is complicated enough. So when scientists have to debug their computer code, they turn to Allinea DDT, a tool easy enough for undergraduates to use. When it comes to modeling the Earth, we aren’t in the Garden of Eden anymore. The days are gone when a scientist could run a single model that works for a collected dataset and then publish the results. Today’s teams of geoscientists, hydrologists, and engineers are using supercomputers to link their models together and create experiments that are ever-more complex. “You want to get a large-scale holistic picture,” says Dr. Shawn Matott, computational scientist at the Center for Computational Research (CCR). “So, you want the best-trained person making the model for groundwater, and you also want to see what is happening with the fish population, human cancer rates, and so on. You’ve got to be able to link these different disciplines as represented by the computer models.” CCR has 8,000 cores capable of more than 100 teraflops. The center’s system is heterogeneous: 384 cores have access to GPUs while others can access large memory stores. As scientific models become more sophisticated, so must the tools for finding and solving errors. To this end, CCR uses Allinea DDT, the most advanced debugging tool available for scalar, multi-threaded and large-scale parallel applications. Allinea DDT is designed to make solving even the most complex multi-process, software problems straightforward. “You might have a model that runs in parallel on a CUDAenabled GPU, and then the optimizer runs in parallel using MPI,” says Matott. “You need tools that can manage that kind of complexity.” Christine Baxter, undergraduate student Dr. Shawn Matott, computational scientist University at Buffalo’s Center for Computational Research University at Buffalo’s Center for Computational Research
  • 2. Case Study: Allinea DDT Helps Drive the Evolution of Geoscientific Model Development Overcoming Time and Budget Constraints Compute program, funded by the National Science Foundation. Students work 15 hours a week on a research project alongside their regular courses. Time and budget constraints add even more challenges. Organizations like CCR need a debugging tool that is both robust and easy to use. Matott had four undergraduate math students, two from the University at Buffalo and two from Buffalo State College. He met with the group once a week to talk about their progress and answer questions. “You really can’t afford to stick a PhD or Master’s student on something like debugging code, because their expertise lies more in the science side of bringing these models together, building a better optimizer or better algorithms,” says Matott. He often finds assistants through the Undergraduate Research Group Experience, or URGE to The group tested five different optimizing algorithms on 15 different test functions, generating 200,000 simulations. Not all of the experiments ran successfully. Matott trained undergraduate Christine Baxter to write Bash scripts to isolate roughly 1,000 simulations that failed and then let her loose on Allinea DDT to debug several thousand lines of code. She discovered the bug in the sort function of one algorithm. “She had two weeks of training on Bash scripting, and basically no training on Allinea DDT. I just told her how to launch the software and, working through the GUI, she was able to figure it out,” says Matott. “I think if she’d had to use one of the commandline debuggers, it would have meant another two weeks of training to get her up to speed.” Once Baxter completed the debugging, she and Matott constructed the idea of a framework, which generalized her process so other computational scientists could benefit from it. Center for Computational Research Machine Room in the NYS Center of Excellence in Bioinformatics and Life Sciences
  • 3. Case Study: Allinea DDT Helps Drive the Evolution of Geoscientific Model Development Positive Experience with Allinea DDT Inspires Undergraduate It was a heady experience for an undergraduate to contribute to the evolution of geoscientific model development. Baxter took the debugging framework to the fall meeting of the American Geophysical Union with 25,000 attendees, where she displayed and defended her results in a poster session. “Here were these undergraduates standing sideby-side with professors, PhD students, and post-docs. People were impressed with the results Christine achieved using Allinea DDT and assumed she was a highly educated computer science technician; whereas, at the time, I think she might have taken just one ‘intro to computer science’ course,” says Matott. Baxter had such a positive experience using Allinea DDT and developing the debugging framework, she decided to switch majors from math to computer science. Center for Computational Research’s Computer Visualization Laboratory Ease-of-Use Makes Scientists More Independent As for the future of the debugging framework, Matott says he is considering publishing a paper along with a case study of Baxter’s experience. He may even write a software package to help geoscientists implement the debugging framework. In the meantime, he’s looking forward to trying out Allinea MAP , a performance analysis tool that uses the same interface as Allinea DDT. Matott says he could benefit from MAP’s problems-at-aglance approach. He’s also keen on the tool because part of his job is to help other researchers run their experiments on the supercomputing cluster. “Right now I have a lot of meetings with the users. If they are in a different discipline, they often need to train me about their area of study before I can help them,” says Matott. “It would be nice if I could turn them loose on a product as user-friendly as Allinea DDT. They could independently find out where in the code they’re spending all their time and we could take it from there.” Allinea DDT and Allinea MAP combine robust capability with unmatched ease-of-use so that scientists like Shawn Matott can focus on grand challenges like pushing the evolution of geosciences modeling so we can make better decisions about managing planet Earth.
  • 4. the environment Allinea Software Inc. 2033 Gateway Pl Ste. 500, San Jose, CA. 95110 USA Tel: +1 (408) 884 0282 www.allinea.com • info@allinea.com Allinea Software Ltd. The Innovation Centre, Warwick Technology Park, Gallows Hill, Warwick CV34 6UW UK Tel: +44 (0)1926 623 231 Fax: +44 (0)1926 623 232 For more information about the Allinea environment, visit www.allinea.com