Evaluating the Performance of the Community Atmosphere Model at High Resolutions
|
|
- Tamsin Kelley
- 6 years ago
- Views:
Transcription
1 Evaluating the Performance of the Community Atmosphere Model at High Resolutions Soumi Manna MS candidate, University of Wyoming Mentor: Dr. Ben Jamroz National Center for Atmospheric Research Boulder, CO August 2, 2013
2 Overview Background Community Atmosphere Model (CAM5) High-Order Method Modeling Environment (HOMME) Space-filling curves (SFC) How well Space-filling curve work on refined and non refined mesh Performance statistics using Python Scalasca performance data Conclusion Future Work
3 CAM(Community Atmosphere Model) Developed primarily at NCAR for climate research communities One of multiple component models in the Community Earth System Model (CESM) 3
4 CAM(Community Atmosphere Model) Efforts focused on increasing resolution of CAM5 Use of mesh refinement in CAM5 through High-Order Method Modeling Environment (HOMME) dynamical core Allow for regions with extremely high-resolution Produce a challenge to the current parallel domain decomposition algorithm 4
5 Project Goals Analyze performance of HOMME on high and variable resolutions Investigate quality of domain decompositions produced by space-filling curve algorithms for refined and unrefined meshes Evaluate performance metrics of realistic simulations on these meshes using automatic trace analysis tool Scalasca 5
6 HOMME (High Order Method Modeling Environment) A scalable and efficient spectral-element-based atmospheric dynamical core ( Spectral Elements: A quadrilateral patch of gridpoints Elements are currently squares on a cube, projected onto a sphere using gnomonic projection 6
7 SFC (Space-Filling Curves) A curve whose range contains entire 2-dimensional unit square Hilbert Curve Peano Curve Hilbert-Peano Curve 7
8 Space-Filling Curve on Non Refined Mesh
9 SFC on Refined Mesh Existing algorithm for quasi-uniform was extended to refined mesh Performance has not been analyzed Elements get mapped to the closest point on the SFC Elements are in non uniform order and can be very close to each other Refined regions require a high resolution SFC Impact quality of the decomposition of the coarse region 9
10 Statistics for Measuring Quality of Domain Decomposition Load balancing Each Processor gets equal amount of work Communication pattern Maximum point to point communication Number of neighboring processes Total Edgecut Build communication matrix Calculate communication pattern Edgecut Neighbors 1 2 Maximum P2P Communication
11 Implementation Modify HOMME to output the space filling curve ordering for elements Write python program to analyze the quality of the domain decomposition Maximum Point to Point Communication Edge Cut Number of Neighbors Run profiling tool Scalasca to see the communication cost Correlate profile data with statistics 11
12 SFC on Quasi-uniform Maximum number of neighbors for Ne120 Fewer neighbors for even number of element per partition 12
13 SFC on Quasi-uniform Average number of neighbors for Ne120 Number of neighbors (latency) dominate communication 13
14 SFC on Quasi-uniform Ratio of maximum to average point to point communication for Ne120 Optimal Edgecut for even number of element per partition 14
15 Refined Mesh (ARM) Refined grid over Atmospheric Radiation Measurement [ARM] sites Incorporating ARM observations into climate simulation Alternative to nested models for regional climate 15
16 Refined Mesh (ARM) Refined grid over Atmospheric Radiation Measurement [ARM] sites Incorporating ARM observations into climate simulation Alternative to nested models for regional climate 16
17 SFC on Refined Mesh Average number of neighbors for Ne120 and ARM Number of neighbors does not vary much for ARM Larger average communication partners for Ne120 17
18 SFC on Refined Mesh Maximum number of neighbors for Ne120 and ARM Maximum neighbors is higher for refined mesh 18
19 SFC on Refined Mesh Larger P2P communication for refined mesh Increases bandwidth cost 19
20 SFC on Refined Mesh gives Discontinuous Decomposition Increases number of neighbors (latency cost) Increases P2P communication (bandwidth cost) 20
21 SFC on Refined Mesh gives Discontinuous Decomposition Increases number of neighbors (latency cost) Increases P2P communication (bandwidth cost) 21
22 Scalasca Performance Data Used profiling tool Scalasca to measure communication Realistic atmosphere simulation on 300 MPI processes Calculated statistics accurately predicts amount of communication 22
23 Communication time does not agree with estimation Calculated communication statistics accurately predict communication pattern Expect communication time of simulations to agree with our statistics Unfortunately we do not see this 23
24 Communication Time Although we accurately predict communication pattern, communication time is erratic No spatial pattern independent of refined mesh 24
25 Node Dependent Communication Time Some nodes have wait time 5x Without this imbalance simulation runs 40% faster 25
26 Conclusion Quasi-uniform mesh: Fewer neighbors for even number of element per partition Number of neighbors (latency) dominate communication Optimal Edgecut for factor of two Refined mesh: Number of neighbors does not vary much SFC gives Discontinuous decomposition Increases the max number of neighbors(latency) Increases the interprocess edgecut (bandwidth) Statistics accurately calculates communication pattern Latency between nodes dominates communication cost 26
27 Future Work Use different machine to analyze performance data Look at the performance of modification of existing space-filling curve Investigate different partitioning methods 27
28 References
29 1. Dr. Ben Jamroz 2. Dr. John Dennis 3. All ASAP group members 4. Jennifer Williamson 5. Kristin Mooney 6. SIParCS 2013 Interns 7. NCAR/UCAR 8. University of Colorado 9. University of Wyoming Acknowledgement 29
30 Thank You Contact: Soumi Manna MS Student University of Wyoming 30
Partitioning with Space-Filling Curves on the Cubed-Sphere
Partitioning with Space-Filling Curves on the Cubed-Sphere John M. Dennis Scientific Computing Division National Center for Atmospheric Research P.O. Box 3000 Boulder, CO 80307 dennis@ucar.edu Abstract
More informationA Scalable Adaptive Mesh Refinement Framework For Parallel Astrophysics Applications
A Scalable Adaptive Mesh Refinement Framework For Parallel Astrophysics Applications James Bordner, Michael L. Norman San Diego Supercomputer Center University of California, San Diego 15th SIAM Conference
More informationImplementing a new suite of remapping functions within NCL
Implementing a new suite of remapping functions within NCL Mohammad Abouali SIPARCS Intern at CISL/NCAR, 2011 Computational Science Ph.D. Student at Joint Program between SDSU & CGU Mentor: David Brown
More informationDesigning Parallel Programs. This review was developed from Introduction to Parallel Computing
Designing Parallel Programs This review was developed from Introduction to Parallel Computing Author: Blaise Barney, Lawrence Livermore National Laboratory references: https://computing.llnl.gov/tutorials/parallel_comp/#whatis
More informationExtending scalability of the community atmosphere model
Journal of Physics: Conference Series Extending scalability of the community atmosphere model To cite this article: A Mirin and P Worley 2007 J. Phys.: Conf. Ser. 78 012082 Recent citations - Evaluation
More informationCharm++ Workshop 2010
Charm++ Workshop 2010 Eduardo R. Rodrigues Institute of Informatics Federal University of Rio Grande do Sul - Brazil ( visiting scholar at CS-UIUC ) errodrigues@inf.ufrgs.br Supported by Brazilian Ministry
More informationA Semi-Lagrangian Discontinuous Galerkin (SLDG) Conservative Transport Scheme on the Cubed-Sphere
A Semi-Lagrangian Discontinuous Galerkin (SLDG) Conservative Transport Scheme on the Cubed-Sphere Ram Nair Computational and Information Systems Laboratory (CISL) National Center for Atmospheric Research
More informationFast Methods with Sieve
Fast Methods with Sieve Matthew G Knepley Mathematics and Computer Science Division Argonne National Laboratory August 12, 2008 Workshop on Scientific Computing Simula Research, Oslo, Norway M. Knepley
More informationA Scalable Parallel LSQR Algorithm for Solving Large-Scale Linear System for Seismic Tomography
1 A Scalable Parallel LSQR Algorithm for Solving Large-Scale Linear System for Seismic Tomography He Huang, Liqiang Wang, Po Chen(University of Wyoming) John Dennis (NCAR) 2 LSQR in Seismic Tomography
More informationParallel Quality Meshes for Earth Models
Parallel Quality Meshes for Earth Models John Burkardt Department of Scientific Computing Florida State University... 04 October 2016, Virginia Tech... http://people.sc.fsu.edu/ jburkardt/presentations/......
More informationCESM Projects Using ESMF and NUOPC Conventions
CESM Projects Using ESMF and NUOPC Conventions Cecelia DeLuca NOAA ESRL/University of Colorado CESM Annual Workshop June 18, 2014 Outline ESMF development update Joint CESM-ESMF projects ESMF applications:
More informationUsing Automated Performance Modeling to Find Scalability Bugs in Complex Codes
Using Automated Performance Modeling to Find Scalability Bugs in Complex Codes A. Calotoiu 1, T. Hoefler 2, M. Poke 1, F. Wolf 1 1) German Research School for Simulation Sciences 2) ETH Zurich September
More informationGraph Partitioning for High-Performance Scientific Simulations. Advanced Topics Spring 2008 Prof. Robert van Engelen
Graph Partitioning for High-Performance Scientific Simulations Advanced Topics Spring 2008 Prof. Robert van Engelen Overview Challenges for irregular meshes Modeling mesh-based computations as graphs Static
More informationParallel Computing. Slides credit: M. Quinn book (chapter 3 slides), A Grama book (chapter 3 slides)
Parallel Computing 2012 Slides credit: M. Quinn book (chapter 3 slides), A Grama book (chapter 3 slides) Parallel Algorithm Design Outline Computational Model Design Methodology Partitioning Communication
More informationInterconnection Networks: Topology. Prof. Natalie Enright Jerger
Interconnection Networks: Topology Prof. Natalie Enright Jerger Topology Overview Definition: determines arrangement of channels and nodes in network Analogous to road map Often first step in network design
More informationDetermining Optimal MPI Process Placement for Large- Scale Meteorology Simulations with SGI MPIplace
Determining Optimal MPI Process Placement for Large- Scale Meteorology Simulations with SGI MPIplace James Southern, Jim Tuccillo SGI 25 October 2016 0 Motivation Trend in HPC continues to be towards more
More informationThree-Dimensional Shapes
Lesson 11.1 Three-Dimensional Shapes Three-dimensional objects come in different shapes. sphere cone cylinder rectangular prism cube Circle the objects that match the shape name. 1. rectangular prism 2.
More informationCS 475: Parallel Programming Introduction
CS 475: Parallel Programming Introduction Wim Bohm, Sanjay Rajopadhye Colorado State University Fall 2014 Course Organization n Let s make a tour of the course website. n Main pages Home, front page. Syllabus.
More informationEnzo-P / Cello. Formation of the First Galaxies. San Diego Supercomputer Center. Department of Physics and Astronomy
Enzo-P / Cello Formation of the First Galaxies James Bordner 1 Michael L. Norman 1 Brian O Shea 2 1 University of California, San Diego San Diego Supercomputer Center 2 Michigan State University Department
More informationGraph Partitioning for Scalable Distributed Graph Computations
Graph Partitioning for Scalable Distributed Graph Computations Aydın Buluç ABuluc@lbl.gov Kamesh Madduri madduri@cse.psu.edu 10 th DIMACS Implementation Challenge, Graph Partitioning and Graph Clustering
More informationContents. I The Basic Framework for Stationary Problems 1
page v Preface xiii I The Basic Framework for Stationary Problems 1 1 Some model PDEs 3 1.1 Laplace s equation; elliptic BVPs... 3 1.1.1 Physical experiments modeled by Laplace s equation... 5 1.2 Other
More informationImplementation of a 3D Hilbert SFC into a Parallel Cartesian- Grid Flow Solver
Implementation of a 3D Hilbert SFC into a Parallel Cartesian- Grid Flow Solver Stephen M. Ruffin and Jinwook Lee* Abstract - The efficient parallel computation of unstructured grid flow solver requires
More informationEmpirical Analysis of Space Filling Curves for Scientific Computing Applications
Empirical Analysis of Space Filling Curves for Scientific Computing Applications Daryl DeFord 1 Ananth Kalyanaraman 2 1 Dartmouth College Department of Mathematics 2 Washington State University School
More informationPorting The Spectral Element Community Atmosphere Model (CAM-SE) To Hybrid GPU Platforms
Porting The Spectral Element Community Atmosphere Model (CAM-SE) To Hybrid GPU Platforms http://www.scidacreview.org/0902/images/esg13.jpg Matthew Norman Jeffrey Larkin Richard Archibald Valentine Anantharaj
More informationAsynchronous Communication in Spectral Element and Discontinuous Galerkin Methods for Atmospheric Dynamics
Asynchronous Communication in Spectral Element and Discontinuous Galerkin Methods for Atmospheric Dynamics Benjamin F. Jamroz Robert Klöfkorn NCAR Technical Notes NCAR/TN 516+STR National Center for Atmospheric
More informationParallel Multigrid on Cartesian Meshes with Complex Geometry +
Parallel Multigrid on Cartesian Meshes with Complex Geometry + Marsha Berger a and Michael Aftosmis b and Gedas Adomavicius a a Courant Institute, New York University, 251 Mercer St., New York, NY 10012
More informationDynamic Load Partitioning Strategies for Managing Data of Space and Time Heterogeneity in Parallel SAMR Applications
Dynamic Load Partitioning Strategies for Managing Data of Space and Time Heterogeneity in Parallel SAMR Applications Xiaolin Li and Manish Parashar The Applied Software Systems Laboratory Department of
More informationsimulation framework for piecewise regular grids
WALBERLA, an ultra-scalable multiphysics simulation framework for piecewise regular grids ParCo 2015, Edinburgh September 3rd, 2015 Christian Godenschwager, Florian Schornbaum, Martin Bauer, Harald Köstler
More informationJoint Advanced Student School 2007 Martin Dummer
Sierpiński-Curves Joint Advanced Student School 2007 Martin Dummer Statement of the Problem What is the best way to store a triangle mesh efficiently in memory? The following points are desired : Easy
More informationDesign of Parallel Programs Algoritmi e Calcolo Parallelo. Daniele Loiacono
Design of Parallel Programs Algoritmi e Calcolo Parallelo Web: home.dei.polimi.it/loiacono Email: loiacono@elet.polimi.it References q The material in this set of slide is taken from two tutorials by Blaise
More informationRadial Basis Function-Generated Finite Differences (RBF-FD): New Opportunities for Applications in Scientific Computing
Radial Basis Function-Generated Finite Differences (RBF-FD): New Opportunities for Applications in Scientific Computing Natasha Flyer National Center for Atmospheric Research Boulder, CO Meshes vs. Mesh-free
More informationAlgorithms for GIS: Space filling curves
Algorithms for GIS: Space filling curves Z-order visit quadrants recursively in this order: NW, NE, SW, SE Z-order visit quadrants recursively in this order: NW, NE, SW, SE Z-order visit quadrants recursively
More informationDense Matrix Algorithms
Dense Matrix Algorithms Ananth Grama, Anshul Gupta, George Karypis, and Vipin Kumar To accompany the text Introduction to Parallel Computing, Addison Wesley, 2003. Topic Overview Matrix-Vector Multiplication
More informationPrinciple Of Parallel Algorithm Design (cont.) Alexandre David B2-206
Principle Of Parallel Algorithm Design (cont.) Alexandre David B2-206 1 Today Characteristics of Tasks and Interactions (3.3). Mapping Techniques for Load Balancing (3.4). Methods for Containing Interaction
More informationScalable Dynamic Load Balancing of Detailed Cloud Physics with FD4
Center for Information Services and High Performance Computing (ZIH) Scalable Dynamic Load Balancing of Detailed Cloud Physics with FD4 Minisymposium on Advances in Numerics and Physical Modeling for Geophysical
More informationEfficient Storage and Processing of Adaptive Triangular Grids using Sierpinski Curves
Efficient Storage and Processing of Adaptive Triangular Grids using Sierpinski Curves Csaba Attila Vigh, Dr. Michael Bader Department of Informatics, TU München JASS 2006, course 2: Numerical Simulation:
More informationEmpirical Analysis of Space Filling Curves for Scientific Computing Applications
Empirical Analysis of Space Filling Curves for Scientific Computing Applications Daryl DeFord 1 Ananth Kalyanaraman 2 1 Department of Mathematics 2 School of Electrical Engineering and Computer Science
More informationAn evaluation of the Performance and Scalability of a Yellowstone Test-System in 5 Benchmarks
An evaluation of the Performance and Scalability of a Yellowstone Test-System in 5 Benchmarks WRF Model NASA Parallel Benchmark Intel MPI Bench My own personal benchmark HPC Challenge Benchmark Abstract
More informationParallel Algorithms: Adaptive Mesh Refinement (AMR) method and its implementation
Parallel Algorithms: Adaptive Mesh Refinement (AMR) method and its implementation Massimiliano Guarrasi m.guarrasi@cineca.it Super Computing Applications and Innovation Department AMR - Introduction Solving
More informationDistributed Newest Vertex Bisection
Distributed Newest Vertex Bisection in Dune-ALUGrid Martin Alkämper and Robert Klöfkorn Dune User Meeting 2015 Algorithm Some Analysis Experiments Problem In Dune-ALUGrid (among others) we provide an adaptive,
More informationDr. John Dennis
Dr. John Dennis dennis@ucar.edu June 23, 2011 1 High-resolution climate generates a large amount of data! June 23, 2011 2 PIO update and Lustre optimizations How do we analyze high-resolution climate data
More information3-D Wind Field Simulation over Complex Terrain
3-D Wind Field Simulation over Complex Terrain University Institute for Intelligent Systems and Numerical Applications in Engineering Congreso de la RSME 2015 Soluciones Matemáticas e Innovación en la
More informationLearning from Home Activity Booklet
Year 2 Maths Geometry Properties of Shapes Learning from Home Activity Booklet Year 2 Programme of Study Statistics Statutory requirements Activity Sheet Page Number Notes Identify and describe the properties
More informationOptimizing Molecular Dynamics
Optimizing Molecular Dynamics This chapter discusses performance tuning of parallel and distributed molecular dynamics (MD) simulations, which involves both: (1) intranode optimization within each node
More informationInteractive Analysis of Large Distributed Systems with Scalable Topology-based Visualization
Interactive Analysis of Large Distributed Systems with Scalable Topology-based Visualization Lucas M. Schnorr, Arnaud Legrand, and Jean-Marc Vincent e-mail : Firstname.Lastname@imag.fr Laboratoire d Informatique
More information3D Finite Difference Time-Domain Modeling of Acoustic Wave Propagation based on Domain Decomposition
3D Finite Difference Time-Domain Modeling of Acoustic Wave Propagation based on Domain Decomposition UMR Géosciences Azur CNRS-IRD-UNSA-OCA Villefranche-sur-mer Supervised by: Dr. Stéphane Operto Jade
More informationDevelopment and Testing of a Next Generation Spectral Element Model for the US Navy
Development and Testing of a Next Generation Spectral Element Model for the US Navy Alex Reinecke 1, Kevin Viner 1, James Doyle 1, Sasa Gabersek 1, Matus Martini 2, John Mickalakes 3, Dave Ryglicki 4,
More informationLoad Balancing Techniques for Asynchronous Spacetime Discontinuous Galerkin Methods
Load Balancing Techniques for Asynchronous Spacetime Discontinuous Galerkin Methods Aaron K. Becker (abecker3@illinois.edu) Robert B. Haber Laxmikant V. Kalé University of Illinois, Urbana-Champaign Parallel
More informationParallel Graph Partitioning and Sparse Matrix Ordering Library Version 4.0
PARMETIS Parallel Graph Partitioning and Sparse Matrix Ordering Library Version 4.0 George Karypis and Kirk Schloegel University of Minnesota, Department of Computer Science and Engineering Minneapolis,
More informationSCALING A DISTRIBUTED SPATIAL CACHE OVERLAY. Alexander Gessler Simon Hanna Ashley Marie Smith
SCALING A DISTRIBUTED SPATIAL CACHE OVERLAY Alexander Gessler Simon Hanna Ashley Marie Smith MOTIVATION Location-based services utilize time and geographic behavior of user geotagging photos recommendations
More informationSpace Filling Curves
Algorithms for GIS Space Filling Curves Laura Toma Bowdoin College A map from an interval to a square Space filling curves Space filling curves https://mathsbyagirl.wordpress.com/tag/curve/ A map from
More informationGeneric Topology Mapping Strategies for Large-scale Parallel Architectures
Generic Topology Mapping Strategies for Large-scale Parallel Architectures Torsten Hoefler and Marc Snir Scientific talk at ICS 11, Tucson, AZ, USA, June 1 st 2011, Hierarchical Sparse Networks are Ubiquitous
More informationGPU-optimized computational speed-up for the atmospheric chemistry box model from CAM4-Chem
GPU-optimized computational speed-up for the atmospheric chemistry box model from CAM4-Chem Presenter: Jian Sun Advisor: Joshua S. Fu Collaborator: John B. Drake, Qingzhao Zhu, Azzam Haidar, Mark Gates,
More informationIntegration of airborne LiDAR and hyperspectral remote sensing data to support the Vegetation Resources Inventory and sustainable forest management
Integration of airborne LiDAR and hyperspectral remote sensing data to support the Vegetation Resources Inventory and sustainable forest management Executive Summary This project has addressed a number
More informationOptimizing Weather Model Radiative Transfer Physics for the Many Integrated Core and GPGPU Architectures
Optimizing Weather Model Radiative Transfer Physics for the Many Integrated Core and GPGPU Architectures John Michalakes NOAA/NCEP/Environmental Modeling Center (IM Systems Group) University of Colorado
More informationHigh-Performance Computing Applications and Future Requirements for Army Rotorcraft
Presented to: HPC User Forum April 15, 2015 High-Performance Computing Applications and Future Requirements for Army Rotorcraft Dr. Roger Strawn US Army Aviation Development Directorate (AMRDEC) Ames Research
More informationKevin J. Barker. Scott Pakin and Darren J. Kerbyson
Experiences in Performance Modeling: The Krak Hydrodynamics Application Kevin J. Barker Scott Pakin and Darren J. Kerbyson Performance and Architecture Laboratory (PAL) http://www.c3.lanl.gov/pal/ Computer,
More informationLecture 7: Linear Regression (continued)
Lecture 7: Linear Regression (continued) Reading: Chapter 3 STATS 2: Data mining and analysis Jonathan Taylor, 10/8 Slide credits: Sergio Bacallado 1 / 14 Potential issues in linear regression 1. Interactions
More informationApplication / User Viewpoint
SC 07 Reno, Nevada November 15, 2007 Fortran@50 Application / User Viewpoint Henry Tufo Computer Science Section Head Associate Professor and Director, Computational Science Center Department of Computer
More information6LPXODWLRQÃRIÃWKHÃ&RPPXQLFDWLRQÃ7LPHÃIRUÃDÃ6SDFH7LPH $GDSWLYHÃ3URFHVVLQJÃ$OJRULWKPÃRQÃDÃ3DUDOOHOÃ(PEHGGHG 6\VWHP
LPXODWLRQÃRIÃWKHÃ&RPPXQLFDWLRQÃLPHÃIRUÃDÃSDFHLPH $GDSWLYHÃURFHVVLQJÃ$OJRULWKPÃRQÃDÃDUDOOHOÃ(PEHGGHG \VWHP Jack M. West and John K. Antonio Department of Computer Science, P.O. Box, Texas Tech University,
More informationVIII. Communication costs, routing mechanism, mapping techniques, cost-performance tradeoffs. April 6 th, 2009
VIII. Communication costs, routing mechanism, mapping techniques, cost-performance tradeoffs April 6 th, 2009 Message Passing Costs Major overheads in the execution of parallel programs: from communication
More informationCompressing CESM Data while Preserving Information
National Center for Atmospheric Research Compressing CESM Data while Preserving Information Allison H. Baker Dorit Hammerling Haiying Xu Computational Information Systems Laboratory National Center for
More informationPath Optimization in Stream-Based Overlay Networks
Path Optimization in Stream-Based Overlay Networks Peter Pietzuch, prp@eecs.harvard.edu Jeff Shneidman, Jonathan Ledlie, Mema Roussopoulos, Margo Seltzer, Matt Welsh Systems Research Group Harvard University
More informationProgress on Advanced Dynamical Cores for the Community Atmosphere Model. June 2010
Progress on Advanced Dynamical Cores for the Community Atmosphere Model June 2010 Art Mirin, P. O. Box 808, Livermore, CA 94551 This work performed under the auspices of the U.S. Department of Energy by
More informationOn Partitioning Dynamic Adaptive Grid Hierarchies. Manish Parashar and James C. Browne. University of Texas at Austin
On Partitioning Dynamic Adaptive Grid Hierarchies Manish Parashar and James C. Browne Department of Computer Sciences University of Texas at Austin fparashar, browneg@cs.utexas.edu (To be presented at
More informationA Cost-Space Approach to Distributed Query Optimization in Stream Based Overlays
A Cost-Space Approach to Distributed Query Optimization in Stream Based Overlays Jeffrey Shneidman, Peter Pietzuch, Matt Welsh, Margo Seltzer, Mema Roussopoulos Systems Research Group Harvard University
More informationGeometry. Students at Dommerich Elementary helped design and construct a mosaic to show parts of their community and local plants and animals.
Geometry Describing and analyzing two-dimensional shapes Students at Dommerich Elementary helped design and construct a mosaic to show parts of their community and local plants and animals. 479 Make a
More informationOverlapping Computation and Communication for Advection on Hybrid Parallel Computers
Overlapping Computation and Communication for Advection on Hybrid Parallel Computers James B White III (Trey) trey@ucar.edu National Center for Atmospheric Research Jack Dongarra dongarra@eecs.utk.edu
More informationIntroduction to MAPPER
Introduction to MAPPER Leyda Almodóvar You will find Mapper and instructions to download it and install it here: http://danifold.net/mapper Or see page 2 of this document Make sure to look at http://danifold.net/mapper/installation/index.html
More informationABSTRACT OF THE THESIS
ABSTRACT OF THE THESIS Evaluation and Optimization of Load Balancing/Distribution Techniques for Dynamic Adaptive Grid Hierarchies. By MAUSUMI SHEE Thesis Director: Professor Manish Parashar Dynamically
More informationUniversity of Florida CISE department Gator Engineering. Clustering Part 4
Clustering Part 4 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville DBSCAN DBSCAN is a density based clustering algorithm Density = number of
More informationForestClaw : Mapped, multiblock adaptive quadtrees
ForestClaw : Mapped, multiblock adaptive quadtrees Donna Calhoun (Boise State University) Carsten Burstedde (Univ. of Bonn) HPC 3 November 9-13, 2014 KAUST - Saudi Arabia The ForestClaw Project Project
More informationImproving climate model coupling through complete mesh representation
Improving climate model coupling through complete mesh representation Robert Jacob, Iulian Grindeanu, Vijay Mahadevan, Jason Sarich July 12, 2018 3 rd Workshop on Physics Dynamics Coupling Support: U.S.
More information8. Hardware-Aware Numerics. Approaching supercomputing...
Approaching supercomputing... Numerisches Programmieren, Hans-Joachim Bungartz page 1 of 48 8.1. Hardware-Awareness Introduction Since numerical algorithms are ubiquitous, they have to run on a broad spectrum
More informationSpace-Filling Curves An Introduction
Department of Informatics Technical University Munich Space-Filling Curves An Introduction Paper accompanying the presentation held on April nd 005 for the Joint Advanced Student School (JASS) in St. Petersburg
More informationLesson 99. Three-Dimensional Shapes. sphere cone cylinder. Circle the objects that match the shape name.
Three-Dimensional Shapes Lesson 99 COMMON CORE STANDARD CC.2.G.1 Lesson Objective: Identify threedimensional shapes. Three-dimensional objects come in different shapes. sphere cone cylinder rectangular
More information8. Hardware-Aware Numerics. Approaching supercomputing...
Approaching supercomputing... Numerisches Programmieren, Hans-Joachim Bungartz page 1 of 22 8.1. Hardware-Awareness Introduction Since numerical algorithms are ubiquitous, they have to run on a broad spectrum
More informationClustering Part 4 DBSCAN
Clustering Part 4 Dr. Sanjay Ranka Professor Computer and Information Science and Engineering University of Florida, Gainesville DBSCAN DBSCAN is a density based clustering algorithm Density = number of
More informationIncluding the Size of Regions in Image Segmentation by Region Based Graph
International Journal of Emerging Engineering Research and Technology Volume 3, Issue 4, April 2015, PP 81-85 ISSN 2349-4395 (Print) & ISSN 2349-4409 (Online) Including the Size of Regions in Image Segmentation
More informationAdaptive Refinement of Quadrilateral Finite Element Meshes Based on MSC.Nastran Error Measures
Adaptive Refinement of Quadrilateral Finite Element Meshes Based on MSC.Nastran Error Measures Mark E. Botkin GM R&D Center Warren, MI 48090-9055 Rolf Wentorf and B. Kaan Karamete Rensselaer Polytechnic
More informationPlainfield Public School District Mathematics/3 rd Grade Curriculum Guide
NJCCCS: STANDARD 4.2 (GEOMETRY AND MEASUREMENT) ALL STUDENTS WILL DEVELOP SPATIAL SENSE AND THE ABILITY TO USE GEOMETRIC PROPERTIES, RELATIONSHIPS, AND MEASUREMENT TO MODEL, DESCRIBE AND ANALYZE PHENOMENA.
More informationBig Orange Bramble. August 09, 2016
Big Orange Bramble August 09, 2016 Overview HPL SPH PiBrot Numeric Integration Parallel Pi Monte Carlo FDS DANNA HPL High Performance Linpack is a benchmark for clusters Created here at the University
More informationCoupling of Smooth Faceted Surface Evaluations in the SIERRA FEA Code
Coupling of Smooth Faceted Surface Evaluations in the SIERRA FEA Code Timothy J. Tautges Steven J. Owen Sandia National Laboratories University of Wisconsin-Madison Mini-symposium on Computational Geometry
More informationParallel FEM Computation and Multilevel Graph Partitioning Xing Cai
Parallel FEM Computation and Multilevel Graph Partitioning Xing Cai Simula Research Laboratory Overview Parallel FEM computation how? Graph partitioning why? The multilevel approach to GP A numerical example
More informationDynamic load balancing in OSIRIS
Dynamic load balancing in OSIRIS R. A. Fonseca 1,2 1 GoLP/IPFN, Instituto Superior Técnico, Lisboa, Portugal 2 DCTI, ISCTE-Instituto Universitário de Lisboa, Portugal Maintaining parallel load balance
More informationThe ICON project: Design and performance of an unstructured grid approach for a global triangular grid model
The ICON project: Design and performance of an unstructured grid approach for a global triangular grid model Luis Kornblueh, Luca Bonaventura, and Peter Sanders,... ICON : ICOsahedral, Nonhdyrostatic model
More informationMIT Monte-Carlo Ray Tracing. MIT EECS 6.837, Cutler and Durand 1
MIT 6.837 Monte-Carlo Ray Tracing MIT EECS 6.837, Cutler and Durand 1 Schedule Review Session: Tuesday November 18 th, 7:30 pm bring lots of questions! Quiz 2: Thursday November 20 th, in class (one weeks
More informationHPC Algorithms and Applications
HPC Algorithms and Applications Dwarf #5 Structured Grids Michael Bader Winter 2012/2013 Dwarf #5 Structured Grids, Winter 2012/2013 1 Dwarf #5 Structured Grids 1. dense linear algebra 2. sparse linear
More informationIntroduction to parallel Computing
Introduction to parallel Computing VI-SEEM Training Paschalis Paschalis Korosoglou Korosoglou (pkoro@.gr) (pkoro@.gr) Outline Serial vs Parallel programming Hardware trends Why HPC matters HPC Concepts
More informationWorkloads Programmierung Paralleler und Verteilter Systeme (PPV)
Workloads Programmierung Paralleler und Verteilter Systeme (PPV) Sommer 2015 Frank Feinbube, M.Sc., Felix Eberhardt, M.Sc., Prof. Dr. Andreas Polze Workloads 2 Hardware / software execution environment
More informationA Test Suite for GCMs: An Intercomparison of 11 Dynamical Cores
A Test Suite for GCMs: An Intercomparison of 11 Dynamical Cores Christiane Jablonowski 1, Peter Lauritzen 2, Mark 3 Taylor, Ram Nair 2 1 University of Michigan, 2 National Center for Atmospheric Research,
More informationBuilding a Global Data Federation for Climate Change Science The Earth System Grid (ESG) and International Partners
Building a Global Data Federation for Climate Change Science The Earth System Grid (ESG) and International Partners 24th Forum ORAP Cite Scientifique; Lille, France March 26, 2009 Don Middleton National
More informationAnnouncements. Written Assignment2 is out, due March 8 Graded Programming Assignment2 next Tuesday
Announcements Written Assignment2 is out, due March 8 Graded Programming Assignment2 next Tuesday 1 Spatial Data Structures Hierarchical Bounding Volumes Grids Octrees BSP Trees 11/7/02 Speeding Up Computations
More informationOverview. Spectral Processing of Point- Sampled Geometry. Introduction. Introduction. Fourier Transform. Fourier Transform
Overview Spectral Processing of Point- Sampled Geometry Introduction Fourier transform Spectral processing pipeline Spectral filtering Adaptive subsampling Summary Point-Based Computer Graphics Markus
More informationParametric. Practices. Patrick Cunningham. CAE Associates Inc. and ANSYS Inc. Proprietary 2012 CAE Associates Inc. and ANSYS Inc. All rights reserved.
Parametric Modeling Best Practices Patrick Cunningham July, 2012 CAE Associates Inc. and ANSYS Inc. Proprietary 2012 CAE Associates Inc. and ANSYS Inc. All rights reserved. E-Learning Webinar Series This
More informationAteles performance assessment report
Ateles performance assessment report Document Information Reference Number Author Contributor(s) Date Application Service Level Keywords AR-4, Version 0.1 Jose Gracia (USTUTT-HLRS) Christoph Niethammer,
More informationPartitioning and Partitioning Tools. Tim Barth NASA Ames Research Center Moffett Field, California USA
Partitioning and Partitioning Tools Tim Barth NASA Ames Research Center Moffett Field, California 94035-00 USA 1 Graph/Mesh Partitioning Why do it? The graph bisection problem What are the standard heuristic
More informationHPC Methods for Coupling Spectral Cloud Microphysics with the COSMO Model
Center for Information Services and High Performance Computing (ZIH) HPC Methods for Coupling Spectral Cloud Microphysics with the COSMO Model Max Planck Institute for Meteorology 17 March 2011 Matthias
More informationThe Red Storm System: Architecture, System Update and Performance Analysis
The Red Storm System: Architecture, System Update and Performance Analysis Douglas Doerfler, Jim Tomkins Sandia National Laboratories Center for Computation, Computers, Information and Mathematics LACSI
More informationComparing the OpenMP, MPI, and Hybrid Programming Paradigm on an SMP Cluster
Comparing the OpenMP, MPI, and Hybrid Programming Paradigm on an SMP Cluster G. Jost*, H. Jin*, D. an Mey**,F. Hatay*** *NASA Ames Research Center **Center for Computing and Communication, University of
More information