9
SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomp utingchallenge.or g Supercomputing Around Us: Sensors and Data 1

SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Embed Size (px)

Citation preview

Page 1: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 1

SUPERCOMPUTING CHALLENGEKICKOFF 2015

A Model for Computational Science Investigations

Oct 2015 © [email protected]

Page 2: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 2

Computational Science is the use of mathematics and computers to model “real world” problems in science, and conduct simulation experiments.

Oct 2015 © [email protected]

Computational Science?

Page 3: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 3

• Computational Science (CS) complements, but does not replace, field experimentation in scientific research. Each approach is appropriate in certain situations.

• CS is ideally suited to exploration of problems which are too expensive, too dangerous, too difficult to control, too fast, too slow, too… etc. for extensive experimentation in the field.

• CS allows us to perform large numbers of experiments, using alternative scenarios with different inputs. This can be used for “what if” analyses, as well as output-driven solutions to complex problems.

Oct 2015 © [email protected]

Computational Science

Page 4: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 4Oct 2015 © [email protected]

Real World Problem

WorkingModel

Mathematical/

BehavioralModel

Computational

Model

Results/Conclusions

Simplify

Represent

TranslateSimulate

Interpret

Computational Science Process

Page 5: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 5Oct 2015 © [email protected]

Role of Modeling

Real World Problem

WorkingModel

Mathematical/

BehavioralModel

Computational

Model

Results/Conclusions

Simplify the “real world” into an

abstracted form.

Represent the model in formal

mathematical and/or algorithmic terms.

Translate the equations and algorithms into computer code.

Simulate

Interpret

Page 6: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 6Oct 2015 © [email protected]

Implementation Approach:Modeling Orientation

Mathematical formulas and/or logical rules describing the global

behavior of the “world” as a whole.

Logical rules and/or mathematical formulas describing the local

behavior of the different kinds of individual objects in the “world”

How we describe the “world” of our chosen problem …

Procedural Programming (e.g. Fortran, C, BASIC)

Object-Oriented Programming (e.g. Java, C++, VisualBasic)

Agent-based Programming (e.g. StarLogo)

Page 7: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 7Oct 2015 © [email protected]

Implementation Approach:Technical Application

Device Control

Numerical Computing

Monte Carlo Simulation

Continuous Simulation

Discrete Event Simulation

Cellular Automata

Agent-based Simulation

Fortran

C

C++

Java

StarLogo

Page 8: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 8Oct 2015 © [email protected]

Research&Simplify

2. Develop an idea for a Working Model

3. Select Mathematical or Agent-based ModelRepresent

&Explain

* If no data could be collected from a model like this, go back to step #1.

Setup the Experiments

4. Design & Implement the Computational Model.

5. Run the Computational Model

ProduceData

6. Analyze the Data

* If the data doesn’t make sense, go back to step #4.

* If you cannot talk about your model, do not move on to the next step. 

Does the data describe the real world phenomena

Project Title: __________________________Team #: ____ School:___________________Team Members: _______________________Scientist: _____________________________

1. Select a Real World Problem:

TranslateIntoCode

Page 9: SUPERCOMPUTING CHALLENGE KICKOFF 2015 A Model for Computational Science Investigations Oct 2015 © consult@supercomputing challenge.org Supercomputing Around

Supercomputing Around Us: Sensors and Data 9Oct 2015 © [email protected]