An Overview of Computational Science: Definitions, Grand Challenges, and Applications, Slides of Computational Techniques

Download An Overview of Computational Science: Definitions, Grand Challenges, and Applications and more Slides Computational Techniques in PDF only on Docsity!

An Overview of Computational Science

What Is Computational Science?

•^

There is no accepted definition!!!

(but it is gelling)

•^

Ken Wilson’s definition, circa 1986: A common characteristic of thefield is that problems…–

Have a precise mathematical model.

-^

Are intractable by traditional methods.

-^

Are highly visible.

-^

Require in-depth knowledge of some field in science, engineering, or thearts.

•^

Computational science is neither computer science, mathematics, sometraditional field of science, engineering, a social science, nor ahumanities’ field. It is a blend.

Is There a Computational Science

Community?

•^

Computational science projects are always multidisciplinary.–

Applied math, computer science, and…

-^

One or more science or engineering fields are involved.

•^

Computer science’s role tends to be–

A means of getting the low level work done efficiently.

-^

Similar to mathematics in solving problems in engineering.

-^

Oh, yuck… a service role if the computer science contributors are notcareful.

-^

Provides tools for data manipulation, visualization, and networking.

•^

Mathematics’ role is in providing analysis of (new?) numericalalgorithms to solve the problems, even if it is done by computerscientists.

New Field’s Responsibilities

•^

Computational science is still an evolving field–

There is a common methodology that is used in many disparate problems.

-^

Common tools will be useful to all of these related problems if thecommon denominator can be found.

•^

The field became unique when it solves some small collection ofproblem for which there is clearly no other solution methodology.

-^

The community is still trying to define the age old question, “Whatdefines a high quality result?” This is slowly being answered.

-^

An education program must be devised. This, too, is being worked on.

-^

Appropriate journals and conferences already exist and are being usedto guarantee that the field evolves.

-^

Various government programs throughout the world are pushing thefield.

Some Grand Challenge Areas

•^

Combustion

-^

Electronic structure of materials

-^

Turbulence

-^

Genome sequencing and structural biology

-^

Climate modeling–

Ocean modeling

-^

Atmospheric modeling

-^

Coupling the two

•^

Astrophysics

-^

Speech and language recognition

-^

Pharmaceutical designs

-^

Pollution tracking

-^

Oil and gas reservoir modeling

A Grand Challenge Example

•^

CHAMMP: http://www.epm.ornl.gov/chammp/chammpions.html–

Oak Ridge and Argonne National Labs and NCAR collaborated toimprove NCAR’s Community Climate Model (CCM2).

-^

A sample visualization of a computer run:

Three Basic Science Areas

•^

Theory–

Mathematical modeling.

-^

Physics, chemistry, engineering principals incorporated.

•^

Computation–

Provide input to what experiments to try.

-^

Provide feedback to theoreticians.

-^

Two way street with the other two areas.

•^

Experimentation–

Verify theory.

-^

Verify computations. Once verified, computations need not be verifiedagain in similar cases!

Why Computation?

•^

Numerical simulation fills a gap between physical experiments andtheoretical approaches.

-^

Many phenomena are too complex to be studied exhaustively by eithertheory or experiments. Besides complexity, many are too expensive tostudy experimentally, either from a hard currency or time point ofview. Consider astrophysics, when experiments may be impossible.

-^

Computational approaches allow many outstanding issues to beaddressed that cannot be considered by the traditional approaches oftheory and experimentation alone.

-^

Problems that computation is driving as the state of the art willeventually lead to computational science being an accepted, new field.

Parallel Languages

•^

While there are not too many differences between most Fortran and Cprograms doing the same thing, this is not always true in parallelFortran variants and parallel C variants.

-^

High Performance Fortran (HPF), a variant of Fortran 90, allows forparallelization of many dense matrix operations trivially and quiteefficiently. Unfortunately, most problems do not result in densematrices, making HPF an orphan.

-^

Many parallel C’s can make good use of C’s superior data structureabilities. Similar comments can be said about parallel C++’s.

-^

MPI and OpenMP work with Fortran, C, and C++ to provide portableparallel codes for distributed memory (MPI) or shared memory(OpenMP) architectures, though MPI works well on shared memorymachines, too. Both require the user to do communications in anassembly language manner.

Three Styles of Parallel Programming

•^

Data parallelism–

Simple extensions to serial languages to add parallelism.

-^

These are the easiest to learn and debug.

-^

HPF, C*, MPL, pc++, OpenMP, …

•^

Parallel libraries–

PVM, MPI, P4, Charm++, Linda, …

•^

High level languages with implicit parallelism–

Functional and logic programming languages.

-^

This requires the programmer to learn a new paradigm of programming,not just a new language syntax.

-^

Adherents claim that this is worth the extra effort, but others cite exampleswhere it is a clear loser.

•^

Computational science is splintered over a programming approach andlanguage of choice.

Computational Scientist Requirements

•^

Command of an applied discipline.

-^

Familiarity of leading edge computer architectures and data structuresappropriate to those architectures.

-^

Good understanding of analysis and implementation of numericalalgorithms, including how they map onto the data structures needed onthe architectures.

-^

Familiarity with visualization methods and options.

Current Trends in Architectures

-^

Parallel supercomputers–

Multiple processors per node with shared memory on the node (anode is a motherboard with memory and processors on it).– Very fast electrical network between nodes with direct memoryaccess and communications processors just for moving data.– SGI Origin 3000, IBM SP4, SUN Sunfire, HP Superdome.– Cluster of PC’s Take many of your favorite computers andconnect them with a fast ethernet running 100-1000 Mbs.– Usually runs Linux, IRIX, True64 UNIX, HP-UX, AIX-L, Solaris,or Windows 2000/XP with MPI and/or PVM.– Intel (IA32 and IA64), Alpha, or SPARC processors. Intel IA32 isthe most common in clusters of cheap micros.

Network Speeds

Transmission Time (seconds)

Name

Speed (bps)

24 bit screen

Bible

EncyclopediaBritannica

T

45M

Cable modem

30M/10M/2M

T

1.544M

30 min

56kbs

7 min

1 hour

2 days

NSF Supercomputing Program (PACI/Terascale)

•^

NCSA–

1536 SGI Origin 2000 processors, 12

32 processor SP4 (NCSA)

-^

1500 IA32 processor cluster, 1500 IA64 Itanium cluster (NCSA).

-^

PC clusters (UNM, UW).

-^

192 SGI Origin 2000 processors, 256 processor SP4 (BU).

-^

224 HP Superdome processors (UK).

•^

SDSC (U. San Diego)–

IBM SP3 (1.5 Tflops).

-^

Cray T90, 16 processors.

-^

Sun Fire Server.

•^

PSC (Pittsburgh)–

3000 Compaq AlphaServer processors: 6 Tflops.

•^

DTF (NCSA, SDSC, Caltech, Argonne National Lab)–

13 Tflops.