CS267/E233 Applications of Parallel Computers Lecture 1: IntroductionOutlineWhy we need powerful computersSimulation: The Third Pillar of ScienceSome Particularly Challenging ComputationsUnits of Measure in HPCEconomic Impact of HPCGlobal Climate Modeling ProblemGlobal Climate Modeling ComputationSlide 10A 1000 Year Climate SimulationSlide 12Astrophysics: Binary Black Hole DynamicsSlide 14Heart SimulationHeart Simulation CalculationSlide 17Parallel Computing in Data AnalysisTransaction ProcessingWhy powerful computers are parallelTunnel Vision by ExpertsTechnology Trends: Microprocessor CapacityImpact of Device ShrinkageMicroprocessor Transistors per ChipPerformance on Linpack BenchmarkSIA Projections for MicroprocessorsBut there are limiting forces: Increased cost and difficulty of manufacturingHow fast can a serial computer be?Much of the Performance is from Parallelism“Automatic” Parallelism in Modern MachinesMeasuring PerformanceImproving Real PerformancePerformance LevelsPerformance Levels (for example on NERSC-3)Course OrganizationWho is in the class?First AssignmentSchedule of TopicsReading MaterialsRequirementsWhat you should get out of the courseAdministrative Information01/19/2005 CS267-Lecture 11CS267/E233Applications of Parallel ComputersLecture 1: IntroductionJames [email protected]/~demmel/cs267_Spr0501/19/2005 CS267-Lecture 12Outline•Introduction•Large important problems require powerful computers •Why powerful computers must be parallel processors •Principles of parallel computing performance•Structure of the course01/19/2005 CS267-Lecture 13Why we need powerful computers01/19/2005 CS267-Lecture 14 Simulation: The Third Pillar of Science •Traditional scientific and engineering paradigm:1) Do theory or 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.01/19/2005 CS267-Lecture 15Some Particularly Challenging Computations•Science-Global climate modeling-Biology: genomics; protein folding; drug design-Computational Chemistry-Astrophysical modeling-Computational Material Sciences and Nanosciences•Engineering-Semiconductor design-Earthquake and structural modeling-Computation fluid dynamics (airplane design)-Combustion (engine design)-Crash simulation•Business-Financial and economic modeling-Transaction processing, web services and search engines•Defense-Nuclear weapons -- test by simulations-Cryptography01/19/2005 CS267-Lecture 16Units of Measure in HPC•High Performance Computing (HPC) units are:-Flops: floating point operations-Flop/s: floating point operations per second-Bytes: size of data (a double precision floating point number is 8)•Typical sizes are millions, billions, trillions…Mega Mflop/s = 106 flop/sec Mbyte = 220 = 1048576 ~ 106 bytesGiga Gflop/s = 109 flop/sec Gbyte = 230 ~ 109 bytesTera Tflop/s = 1012 flop/sec Tbyte = 240 ~ 1012 bytes Peta Pflop/s = 1015 flop/sec Pbyte = 250 ~ 1015 bytesExaEflop/s = 1018 flop/sec Ebyte = 260 ~ 1018 bytesZetta Zflop/s = 1021 flop/sec Zbyte = 270 ~ 1021 bytesYotta Yflop/s = 1024 flop/sec Ybyte = 280 ~ 1024 bytes01/19/2005 CS267-Lecture 17Economic 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.01/19/2005 CS267-Lecture 18Global Climate Modeling Problem•Problem is to compute:f(latitude, longitude, elevation, time) temperature, pressure, humidity, wind velocity• Approach:-Discretize the domain, e.g., a measurement point every 10 km-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.html01/19/2005 CS267-Lecture 19Global 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 1011 flops in 60 seconds = 8 Gflop/s-Weather prediction (7 days in 24 hours) 56 Gflop/s-Climate prediction (50 years in 30 days) 4.8 Tflop/s-To use in policy negotiations (50 years in 12 hours) 288 Tflop/s•To double the grid resolution, computation is at least 8x, possible 16x •State of the art models require integration of atmosphere, ocean, sea-ice, land models, plus possibly carbon cycle, geochemistry and more•Current models are coarser than thisHigh Resolution Climate Modeling on NERSC-3 – P. Duffy, et al., LLNL01/19/2005 CS267-Lecture 111A 1000 Year Climate Simulation•Warren Washington and Jerry Meehl, National Center for Atmospheric Research; Bert Semtner, Naval Postgraduate School; John Weatherly, U.S. Army Cold Regions Research and Engineering Lab Laboratory et al. •http://www.nersc.gov/aboutnersc/pubs/bigsplash.pdf•Demonstration of the Community Climate Model (CCSM2)•A 1000-year simulation shows long-term, stable representation of the earth’s climate. •760,000 processor hours used•Temperature change shown01/19/2005 CS267-Lecture 112Climate Modeling on the Earth Simulator SystemDevelopment of ES started in 1997 in order to make a comprehensive understanding of global environmental changes such as global warming.26.58Tflops was obtained by a global atmospheric circulation code.35.86Tflops (87.5% of the peak performance) is achieved in the Linpack benchmark.Its construction was completed at the end of February, 2002 and the practical operation started from March 1, 200201/19/2005 CS267-Lecture 113Astrophysics: Binary Black Hole Dynamics•Massive supernova cores
View Full Document