8/29/200118/29/2001 CS267 Lecture 1: Intro 1CS267Applications of Parallel ComputersLecture 1: IntroductionKathy [email protected]://www.cs.berkeley.edu/~yelick8/29/2001 CS267 Lecture 1: Intro 2Outline• Introduction• Large important problems require powerful computers • Why powerful computers must be parallel processors • Principles of parallel computing performance• Structure of the course 8/29/2001 CS267 Lecture 1: Intro 3Administrative Information• Instructors:- Kathy Yelick, 777 Soda, [email protected] TA: David Bindel, 515 Soda, [email protected]• Accounts – fill out online registration!• Class survey – fill out today • Lecture notes are based on previous semester notes:- Jim Demmel, David Culler, David Bailey, Bob Lucas, and myself• Discussion section only “on-demand”• Most class material and lecture notes are at: - http://www.cs.berkeley.edu/~dbindel/cs267ta8/29/2001 CS267 Lecture 1: Intro 4Why we need powerful computers8/29/2001 CS267 Lecture 1: Intro 5Simulation: The Third Pillar of Science • Traditional scientific and engineering paradigm:1) Do theoryor paper design.2) Perform experiments or build system.• Limitations:- Too difficult -- build large wind tunnels.- Too expensive -- build a throw-away passenger jet.- Too slow -- wait for climate or galactic evolution.- Too dangerous -- weapons, drug design, climate experimentation.• Computational science paradigm:3) Use high performance computer systems to simulate the phenomenon- Base on known physical laws and efficient numerical methods.8/29/2001 CS267 Lecture 1: Intro 6Some Particularly Challenging Computations• Science- Global climate modeling- Astrophysical modeling- Biology: Genome analysis; protein folding (drug design)• Engineering- Crash simulation- Semiconductor design- Earthquake and structural modeling• Business- Financial and economic modeling- Transaction processing, web services and search engines• Defense- Nuclear weapons -- test by simulations- Cryptography8/29/200128/29/2001 CS267 Lecture 1: Intro 7Units of Measure in HPC• High Performance Computing (HPC) units are:- Flop/s: floating point operations- Bytes: size of data• Typical sizes are millions, billions, trillions…Mega Mflop/s = 106flop/sec Mbyte = 106byte(also 220= 1048576)Giga Gflop/s = 109flop/sec Gbyte = 109byte (also 230= 1073741824)Tera Tflop/s = 1012flop/sec Tbyte = 1012byte (also 240= 10995211627776)Peta Pflop/s = 1015flop/sec Pbyte = 1015byte (also 250= 1125899906842624)8/29/2001 CS267 Lecture 1: Intro 8Economic Impact of HPC• Airlines:- System-wide logistics optimization systems on parallel systems.- Savings: approx. $100 million per airline per year.• Automotive design:- Major automotive companies use large systems (500+ CPUs) for:- CAD-CAM, crash testing, structural integrity and aerodynamics.- One company has 500+ CPU parallel system.- Savings: approx. $1 billion per company per year.• Semiconductor industry:- Semiconductor firms use large systems (500+ CPUs) for- device electronics simulation and logic validation - Savings: approx. $1 billion per company per year.• Securities industry:- Savings: approx. $15 billion per year for U.S. home mortgages.8/29/2001 CS267 Lecture 1: Intro 9Global Climate Modeling Problem• Problem is to compute:f(latitude, longitude, elevation, time) àtemperature, pressure, humidity, wind velocity• Approach:- Discretize the domain, e.g., a measurement point every 1km- Devise an algorithm to predict weather at time t+1 given t• Uses:- Predict major events, e.g., El Nino- Use in setting air emissions standardsSource: http://www.epm .ornl.gov /chammp /chammp.html8/29/2001 CS267 Lecture 1: Intro 10Global Climate Modeling Computation• One piece is modeling the fluid flow in the atmosphere- Solve Navier-Stokes problem- Roughly 100 Flops per grid point with 1 minute timestep• Computational requirements:- To match real-time, need 5x 1011flops in 60 seconds = 8 Gflop/s- Weather prediction (7 days in 24 hours) à 56 Gflop/s- Climate prediction (50 years in 30 days) à 4.8 Tflop/s- To use in policy negotiations (50 years in 12 hours) à 288 Tflop/s• To double the grid resolution, computation is at least 8x • Current models are coarser than this8/29/2001 CS267 Lecture 1: Intro 11Heart Simulation• Problem is to compute blood flow in the heart• Approach:- Modeled as an elastic structure in an incompressible fluid.- The “immersed boundary method” due to Peskin and McQueen.- 20 years of development in model- Many applications other than the heart: blood clotting, inner ear, paper making, embryo growth, and others- Use a regularly spaced mesh (set of points) for evaluating the fluid• Uses- Current model can be used to design artificial heart valves- Can help in understand effects of disease (leaky valves)- Related projects look at the behavior of the heart during a heart attack- Ultimately: real-time clinical work8/29/2001 CS267 Lecture 1: Intro 12Heart Simulation CalculationThe involves solving Navier-Stokes equations- 64^3 was possible on Cray YMP, but 128^3 required for accurate model (would have taken 3 years).- Done on a Cray C90 -- 100x faster and 100x more memory- Until recently, limited to vector machines- Needs more features:- Electrical model of the heart, and details of muscles, E.g., - Chris Johnson- Andrew McCulloch- Lungs, circulatory systems8/29/200138/29/2001 CS267 Lecture 1: Intro 13Parallel Computing in Web Search• Functional parallelism: crawling, indexing, sorting• Parallelism between queries: multiple users• Finding information amidst junk• Preprocessing of the web data set to help find information• General themes of sifting through large, unstructured data sets:- when to put white socks on sale- what advertisements should you receive- finding medical problems in a community8/29/2001 CS267 Lecture 1: Intro 14Document Retrieval Computation • Approach:- Store the documents in a large (sparse) matrix- Use Latent Semantic Indexing (LSI), or related algorithms to “partition” - Needs large sparse matrix-vector multiply# keywords~100K# documents ~= 10 M24 65 18•Matrix is compressed•“Random” memory access•Scatter/gather vs. cache miss per 2FlopsTen million documents in typical matrix. Web storage increasing 2x every 5 months.Similar ideas may apply to image retrieval.x8/29/2001 CS267 Lecture 1: Intro 15Transaction Processing• Parallelism is natural in relational
View Full Document
Unlocking...