Rong Ge Marquette University Supercomputing in plain English Personal computers and limited capability Supercomputers for solving scientific problems Supercomputing and speed Supercomputing for high school students ID: 416147
Download Presentation The PPT/PDF document "Supercomputing and Sciences" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Supercomputing and Sciences
Rong
Ge
Marquette UniversitySlide2
Supercomputing in plain English
Personal computers and limited capability
Supercomputers for solving scientific problems Supercomputing and speedSupercomputing for high school studentsWhy should HS students careSupercomputing for HS in the country
RoadmapSlide3
Personal Computer
Output device
Input device
Input device
Network cableSlide4
Opening the BoxSlide5
Processor: control and ALU
Memory
InputO
utput
Like human organs
Five Classic ComponentsSlide6
Processor: number cruncher
Speed: 2GHz-4GHz?
Duo core or quad core?Memory: data storage8GB?These hardware parameters largely determine how fast a computer is.
Typical PC ConfigurationsSlide7
Are Long to compute
Need
large quantity of memorylarge quantity of runsAre Time Critical
Not All Programs can Run on PCSlide8
Slide
8
Example 2: Fluid dynamics calculations (1000
1000
1000 lattice)109 lattice points 1000 FLOP/point
10 000 time steps = 1016 FLOP
Example 3: Monte Carlo simulation of nuclear reactor1011 particles to track (for 1000 escapes)
10
4
FLOP/particle = 10
15
FLOP
Decentralized supercomputing
( from
Mathworld News
, 2006/4/7 ):
Grid of tens of thousands networked computers discovers 2
30
402
457 – 1, the 43rd Mersenne prime, as the largest known prime (9 152 052 digits )
Example 1: Southern oceans heat Modeling
(10-minute iterations)300 GFLOP per iteration 300 000 iterations per 6 yrs = 1016 FLOP
4096 E-W regions
1024 N-S
regions
12 layersin depth
Exemplar ProgramsSlide9
Physics and Astrophysics
Biophysics
Geophysics and Earth imagingMedical Physics and MedicineChemistry and BiochemistryChemical and nuclear reactions Weather and climate Mechanical
devices - from prosthetics to spacecraft
Manufacturing
processes
Traditional Scientific and Engineering ProblemsSlide10
Top 1 in June 2012
Speed: 10
16 operations per second todayBig: 4500 square feet
SupercomputersSlide11
Supercomputers in the Past
Source: Jack
Dongarra
Slide12
Source: Supercomputing
in Plain English:
Overview by Neeman at OU12
Parallelism for Speed
Less fish …
More fish!
Parallelism
means doing multiple things at the same time: you can get more work done in the same time.Slide13
Jigsaw analogy
Person: CPU
Jigsaw pieces: data in memoryOne personSerial computing, one hourTwo personsParallel computing, about a half hourFour persons
A little more than a quarter hour
Eight persons
?
13Diminishing Returns
Source: Supercomputing in Plain English: Overview by Neeman at OU
1000 jigsaw piecesSlide14
Two person, each having on his own table with half of the puzzle pieces
Two persons can work completely independently, without any contention for a shared resource.
BUT, they need
S
ame number of pieces first – workload decomposition and balance
Communication, which is costly
Supercomputing in Plain English: OverviewTue
Jan 25 201114
Distributed Parallelism & OverheadSlide15
Supercomputing in plain English
Personal computers and limited capability
Supercomputers for solving scientific problems Supercomputing and speedSupercomputing for high school studentsWhy should HS students careSupercomputing for HS in the country
RoadmapSlide16
Tomorrow’s PCs may be today’s supercomputers
During the past 10 years, the trends indicated by ever faster networks, distributed systems, and multi-processor computer architectures (even at the desktop level) clearly show that
parallelism is the future of computing.
Why Should We or Our Students Care
Reason ISlide17
Slide
17
CPU Performance
The
exponential growth of microprocessor performance, known as Moore’s Law, shown over the past two decades (extrapolated).
Slide18
Slide
18
CPU Speed Projection in 2001
From the 2001 edition of the roadmap [Alla02]
Calendar year
2001
2004
2007
2010
2013
2016
Halfpitch (nm)
140
90
65
45
32
22
Clock freq. (GHz)
2
4
7
12
20
30
Wiring levels
7
8
9
10
10
10
Power supply (V)
1.1
1.0
0.8
0.7
0.6
0.5
Max. power (W)
130
160
190
220
250
290Slide19
The Truth
Microprocessor speed stops increasing
around 2003 due to physical difficultiesSlide20
Multiple, slow cores on a chip
Intel
Up to 80 coresAMDIntegrated CPU and GPU cores (50+ cores)nVidiaHundreds of GPU coresParallel computing is required to achieve fast execution for a single program
20
The Resulting Multicore ProcessorsSlide21
Thousand years ago – experimental Science
Description of natural phenomena
Last few hundred years – Theoretical ScienceNewton’s Laws, Maxwell’s Equation
Last few decades – Computational Science
Simulation of complex phenomena
Today – Data intensive Science
Scientists overwhelmed with data setsReason II – Scientific ApproachesSlide22
Need to solve grand challenge problems with supercomputing
Disaster preparedness
Climate changeClean energyNational security and defense
Reason III: The Burden of Next Generation ScientistsSlide23
Particle PhysicsSlide24
Swine Flu – Pandemic Flu SimulationSlide25
NSF and DOE
N
ational supercomputing centers NCSA at UIUCSan Diego supercomputer centerthe National Center for Supercomputing Applications
Technical supercomputing conferences
IEEE/ACM Supercomputing
XSEDE conference
IndustryIntel Brings Parallel Computing to High SchoolSupercomputing for HS ProgramsSlide26
Supercomputing OrganizationsSlide27
Marquette University
Several computer clusters
Guest accounts availableCondor poolTechnical helpSeWhip: Southeast Wisconsin high performance computing
Local ResourcesSlide28
https://
www.xsede.org/web/xup/online-training
http://www.citutor.org/http://www.tacc.utexas.edu/user-services/training
https
://
www.xsede.org/web/xsede12/students
http://sc12.supercomputing.org/http://hpcuniversity.org/
Online Training OpportunitiesSlide29
Thank you