Paralleliza(on Challenges for Ensemble Data Assimila(on
|
|
- Marjorie Murphy
- 5 years ago
- Views:
Transcription
1 Paralleliza(on Challenges for Ensemble Data Assimila(on Helen Kershaw Institute for Mathematics Applied to Geophysics, National Center for Atmospheric Research
2 What am I going to talk about? What s ensemble data assimilation? What s DART? What s parallel about DART? What s not so parallel about DART? Data decomposition IO Algorithm and communication Software engineering concerns
3 What s ensemble data assimila(on?
4 Ensemble Data Assimila(on group of model forecasts
5 Ensemble Data Assimila(on group of model forecasts Measurements
6 Ensemble Data Assimila(on group of model forecasts Measurements Improved estimate
7 What s DART?
8 DART is used at: Public domain sobware for Data Assimila(on Well- tested, portable, extensible, free! Models Toy to HUGE 43 UCAR member universi(es More than 100 other sites Observa(ons Real, synthe(c, novel An extensive Tutorial With examples, exercises, explana(ons People: The DAReS Team
9 The State
10 The State
11 The State
12 The State pressure temperature vapor mixing ratio
13 The State DART state vector pressure temperature vapor mixing ratio
14 The State pressure temperature vapor mixing ratio multiple copies
15 The State pressure temperature vapor mixing ratio multiple copies
16 The State pressure temperature vapor mixing ratio multiple copies
17 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
18 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
19 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
20 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
21 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
22 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
23 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
24 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
25 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
26 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
27 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
28 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
29 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
30 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
31 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
32 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
33 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
34 Assimilation Apply the updates in parallel Round robin layout for load balancing - localization
35 Data decomposi(ons Whole model state available to a single processor All copies of some variables available to a single processor
36 Data decomposi(ons Whole model state available to a single processor All copies of some variables available to a single processor
37 Data decomposi(ons Whole model state available to a single processor All copies of some variables available to a single processor
38 Why do we need to change anything?
39 What does DART look like in memory? Whole model state available to a single processor All copies of some variables available to a single processor
40 What does DART look like in memory? Ensemble size = 4 memory tasks have a whole copy of the model state Other tasks do not task
41 Why do we use this decomposi(on? Calculation of the forward operator
42 Why do we use this decomposi(on? Calculation of the forward operator What the model thinks the observation should be
43 Why do we use this decomposi(on? Calculation of the forward operator What the model thinks the observation should be
44 Why do we use this decomposi(on? Calculation of the forward operator What the model thinks the observation should be
45 Limita(ons of having these two decomposi(ons: Hard minimum on calculation time Hard maximum on model size You have to move all your data
46 Idea: Only use the assimilation decomposition
47 Idea: Only use the assimilation decomposition Use one sided communication to grab state elements when needed
48 Idea: Only use the assimilation decomposition Use one sided communication to grab state elements when needed Reduce data movement Removes hard memory limit
49 Idea: Only use the assimilation decomposition Use one sided communication to grab state elements when needed Reduce data movement Removes hard memory limit Vectorization of forward operator calculations
50 More scalable forward operator Memory
51 More scalable forward operator Memory
52 More scalable forward operator Memory
53 More scalable forward operator Memory Calculation 4 tasks doing all observations for 1 copy
54 More scalable forward operator Memory Calculation 4 tasks doing all observations for 1 copy Lots of tasks doing some observations for all copies
55 Lorenz_96 forward operator observations observations state complete distributed state 1500 state complete distributed state observations wall clock get obs ens (s) wall clock get obs ens (s) 10 1 core seconds get obs ens (s) number of processors number of processors number of processors wall clock core seconds
56 CAM FV forward operator Specific humidity only : observations processors state complete 1.01s 0.96s distributed state 0.73s 0.18s
57 WRF forward operator 54, 400 observations processors state complete 0.6s 0.6s distributed 2.0s 0.7s
58 IO
59 IO Models do not run ensemble complete 1 3 2
60 IO Models do not run ensemble complete 1 3 2
61 IO Models do not run ensemble complete 1 3 2
62 IO Models do not run ensemble complete 1 3 2
63 IO Models do not run ensemble complete You have to move data from the model to DART
64 IO Ideally:
65 IO Ideally: Never looks like this in memory
66 IO All DART requires is that there are multiple model forecasts
67 IO time Multiple model forecasts to create the ensemble
68 IO model run time Multiple model forecasts to create the ensemble
69 IO model run time Multiple model forecasts to create the ensemble
70 IO model run time Multiple model forecasts to create the ensemble
71 IO model run time Multiple model forecasts to create the ensemble
72 IO model run time when you can start DART Multiple model forecasts to create the ensemble
73 IO IO for each ensemble member time when you can start DART Multiple model forecasts to create the ensemble
74 IO ensemble members Model run ~1000 tasks time Multiple model forecasts to create the ensemble
75 IO ensemble members Model run ~1000 tasks when you can start DART time Multiple model forecasts to create the ensemble
76 IO ensemble members Model run ~1000 tasks when you can start DART time Multiple model forecasts to create the ensemble
77 IO ensemble members CESM Model run ~10000 tasks time Multi-instance forecasts to create the ensemble
78 IO ensemble members CESM Model run ~10000 tasks Restart files for each model time Multi-instance forecasts to create the ensemble
79 IO ensemble members CESM Model run ~10000 tasks Restart files for each model time Multi-instance forecasts to create the ensemble
80 IO Model run ~10000 tasks ensemble members CESM DART CESM DART CESM time Multi-instance forecasts to create the ensemble
81 IO Model run ~10000 tasks ensemble members CESM DART CESM DART CESM time Should the IO speed drive the data layout?
82 Algorithm choice and communica(on The forward operator parallelizes The assimilation parallelizes
83 Algorithm choice and communica(on The forward operator parallelizes The assimilation parallelizes Communication does not scale
84 Broadcasts do i = 1:number of observations 1 observation i = 1 end do
85 Broadcasts do i = 1:number of observations i = 1 1 owner end do
86 Broadcasts do i = 1:number of observations i = 1 1 end do
87 Broadcasts do i = 1:number of observations i = 2 2 end do
88 Broadcasts do i = 1:number of observations i = 3 3 end do
89 Broadcasts do i = 1:number of observations i = 4 4 end do
90 Broadcasts do i = 1:number of observations i = 5 5 end do
91 Broadcasts do i = 1:number of observations i = 6 6 end do
92 Broadcasts do i = 1:number of observations i = 7 7 end do
93 Broadcasts do i = 1:number of observations i = 8 8 end do
94 Further Complica(ons
95 Further Complica(ons Or, software engineering concerns
96 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is?
97 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is? Allow whole state to be stored if the memory is available
98 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is? Allow whole state to be stored if the memory is available Does this mean a vectorized and non-vectorized version of the forward operator for each model?
99 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is? Allow whole state to be stored if the memory is available Need to remain user extensible
100 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is? Allow whole state to be stored if the memory is available Need to remain user extensible Backward compatible?
101 Further Complica(ons Or, software engineering concerns What about all the users who are happy with DART as it is? Allow whole state to be stored if the memory is available Need to remain user extensible Backward compatible? Manageable code
102 Collaborators?
103 Learn more about DART at:
104 Parallel Observa(on Processing
105 Parallel Observa(on Processing
106 Parallel Observa(on Processing Uniform: 127,000 obs Radar: 25,000 obs. 0.2 Radar: 25,000 obs Satellite track: 25,000 obs.
107 Parallel Observa(on Processing Observations that are more than 0.05 apart are independent.
108 Parallel Observa(on Processing Find minimum number of subsets of independent observations Mutual exclusion scheduling problem Use greedy algorithm: Decreasing Greedy Mutual Exclusion (DGME)
109 Parallel Observa(on Processing Red shows observations in a given subset Observations in Color Observations in Color Irregular Observations -> Load Balance Challenges
110 Parallel Observa(on Processing Last subsets only have a few observations each. -These are in regions where satellite and radar overlapped. - May be significant load balance issue. 400 Observations per Color Color
111 Observations 1 December 2006 GPS ACARS and Aircraft Radiosondes Sat Winds
112 Parallel netcdf Can we use this to transpose during IO? Simple for DART restart files Not simple for model restart files
113 Parallel netcdf Can we use this to transpose during IO? Simple for DART restart files - stride through a vector Not simple for model restart files
114 Parallel netcdf Can we use this to transpose during IO? Simple for DART restart files - stride through a vector Not simple for model restart files - can t ignore the dimensionality of each variable
115 Parallel netcdf Can we use this to transpose during IO? Simple for DART restart files - stride through a vector Not simple for model restart files - can t ignore the dimensionality of each variable
116 Parallel netcdf Can we use this to transpose during IO? Simple for DART restart files - stride through a vector Not simple for model restart files - can t ignore the dimensionality of each variable Should the IO speed drive the assimilation data layout?
117 Irregular Observa(ons - > Load Balance Challenges Simulate performance for idealized observation set (2% of obs shown) Uniform: 127,000 obs Radar: 25,000 obs. 0.2 Radar: 25,000 obs Satellite track: 25,000 obs.
118 IO You need to run a bunch of model forecasts Convert the model output to DART format Do data assimilation with DART Convert back to model input
119 Calcula(on of the Forward Operator
120 Calcula(on of the Forward Operator grid points at each model level
121 Calcula(on of the Forward Operator Observation at a vertical location in pressure/height/ grid points at each model level
122 Calcula(on of the Forward Operator Observation at a vertical location in pressure/height/ grid points at each model level The variables in the state determine the location of the observation
123 Calcula(on of the Forward Operator Observation at a vertical location in pressure/height/ grid points at each model level The variables in the state determine the location of the observation Interpolate to find the expected value of the observation
124 But vectorization is not perfect: An observation can be in different model levels depending on the state Observation
125 What s parallel about DART?
126 First, look at the serial version of the algorithm observation and error variance ensemble approximation of the observation updates
127 Algorithm choice and communica(on
128 Algorithm choice and communica(on Broadcast
129 IO Worst-case scenario
130 IO You need to run a bunch of model forecasts write to file
131 IO You need to run a bunch of model forecasts write to file Convert the model output to DART format read from file write to file
132 IO You need to run a bunch of model forecasts write to file Convert the model output to DART format read from file write to file Do data assimilation with DART read from file write to file
133 IO You need to run a bunch of model forecasts write to file Convert the model output to DART format read from file write to file Do data assimilation with DART read from file write to file Convert back to model input read from file write to file
134 IO Models do not run ensemble complete You have to move data from the model to DART
135 IO Scripting Queuing Scaling
136 IO ensemble members CESM Model run ~10000 tasks Restart files for each model time Should the IO speed drive the data layout?
137 Nota(on
138 What s parallel about DART? observation and error variance ensemble approximation of the observation updates
139 Why do we need to change anything? Or, what s not so parallel about DART? Multiple data decompositions IO Algorithm choice and communication
140 Limita(ons of having these two decomposi(ons: The forward operator does not scale beyond processors = ensemble members Users have models that are too large to fit into the memory of a single node You have to transpose data between decompositions
Observa(on Processing. Nancy Collins or
Observa(on Processing Nancy Collins nancy@ucar.edu or dart@ucar.edu Roadmap What s in an Observa(on Provided tools and capabili(es Observa(on sources Observa(on and representa(veness error Types, Kinds,
More informationDART Tutorial Sec'on 2: The DART Directory Tree
DART Tutorial Sec'on 2: The DART Directory Tree UCAR The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions or recommenda'ons expressed
More informationDART Tutorial Sec'on 21: Observa'on Types and Observing System Design
DART Tutorial Sec'on 21: Observa'on Types and Observing System Design UCAR 2014 The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions
More informationDART Tutorial Sec'on 25: A simple 1D advec'on model: Tracer Data Assimila'on
DART Tutorial Sec'on 25: A simple 1D advec'on model: Tracer Data Assimila'on UCAR The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions
More informationGSI fundamentals (4): Background Error Covariance and Observation Error
27 GSI Community Tutorial July 2, 27, College Park, MD GSI fundamentals (4): Background Error Covariance and Observation Error Ming Hu Developmental Testbed Center Outline GSI fundamentals (): Setup and
More informationGridded Data Speedwell Derived Gridded Products
Gridded Data Speedwell Derived Gridded Products Introduction Speedwell Weather offers access to a wide choice of gridded data series. These datasets are sourced from the originating agencies in their native
More informationDART Tutorial Sec'on 11: Crea'ng DART Executables
DART Tutorial Sec'on 11: Crea'ng DART Executables UCAR 2014 The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions or recommenda'ons
More informationSyed RH Rizvi.
Community Tools: gen_be Syed RH Rizvi National Center For Atmospheric Research NCAR/ESSL/MMM, Boulder, CO-80307, USA rizvi@ucar.edu 0 Talk overview What is gen_be? How it works? Some technical details
More informationDART Tutorial Sec'on 16: Diagnos'c Output
DART Tutorial Sec'on 16: Diagnos'c Output UCAR The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions or recommenda'ons expressed
More informationHPC Performance Advances for Existing US Navy NWP Systems
HPC Performance Advances for Existing US Navy NWP Systems Timothy Whitcomb, Kevin Viner Naval Research Laboratory Marine Meteorology Division Monterey, CA Matthew Turner DeVine Consulting, Monterey, CA
More informationSoftware Infrastructure for Data Assimilation: Object Oriented Prediction System
Software Infrastructure for Data Assimilation: Object Oriented Prediction System Yannick Trémolet ECMWF Blueprints for Next-Generation Data Assimilation Systems, Boulder, March 2016 Why OOPS? Y. Trémolet
More informationFMS: the Flexible Modeling System
FMS: the Flexible Modeling System Coupling Technologies for Earth System Modeling Toulouse FRANCE V. Balaji balaji@princeton.edu Princeton University 15 December 2010 Balaji (Princeton University) Flexible
More informationIntroduction to Objective Analysis
Chapter 4 Introduction to Objective Analysis Atmospheric data are routinely collected around the world but observation sites are located rather randomly from a spatial perspective. On the other hand, most
More informationMcIDAS-V Tutorial Displaying Gridded Data updated January 2016 (software version 1.5)
McIDAS-V Tutorial Displaying Gridded Data updated January 2016 (software version 1.5) McIDAS-V is a free, open source, visualization and data analysis software package that is the next generation in SSEC's
More informationBrandhall Primary School. Maths Long Term Overview
Brandhall Primary School Maths Long Term Overview 2017 2018 Autumn 1 Autumn 2 Spring 1 Spring 2 Summer 1 Summer 2 Nurs. Throughout the 6 half-terms children in Nursery will follow six different topics
More informationA simple OASIS interface for CESM E. Maisonnave TR/CMGC/11/63
A simple OASIS interface for CESM E. Maisonnave TR/CMGC/11/63 Index Strategy... 4 Implementation... 6 Advantages... 6 Current limitations... 7 Annex 1: OASIS3 interface implementation on CESM... 9 Annex
More informationDART Tutorial Sec'on 16: Diagnos'c Output
DART Tutorial Sec'on 16: Diagnos'c Output UCAR 214 The Na'onal Center for Atmospheric Research is sponsored by the Na'onal Science Founda'on. Any opinions, findings and conclusions or recommenda'ons expressed
More informationMcIDAS-V - A powerful data analysis and visualization tool for multi and hyperspectral environmental satellite data *
McIDAS-V - A powerful data analysis and visualization tool for multi and hyperspectral environmental satellite data * Thomas Achtor, Thomas Rink, Thomas Whittaker, David Parker and David Santek Space Science
More informationDriftsonde System Overview
Driftsonde System Overview Zero-pressure Balloon Gondola (24 sonde capacity) 6 hours between drops Terry Hock, Hal Cole, Charlie Martin National Center for Atmospheric Research Earth Observing Lab December
More informationClimate Precipitation Prediction by Neural Network
Journal of Mathematics and System Science 5 (205) 207-23 doi: 0.7265/259-529/205.05.005 D DAVID PUBLISHING Juliana Aparecida Anochi, Haroldo Fraga de Campos Velho 2. Applied Computing Graduate Program,
More informationRunning the model in production mode: using the queue.
Running the model in production mode: using the queue. 1) Codes are executed with run scripts. These are shell script text files that set up the individual runs and execute the code. The scripts will seem
More informationFlow and Heat Transfer in a Mixing Elbow
Flow and Heat Transfer in a Mixing Elbow Objectives The main objectives of the project are to learn (i) how to set up and perform flow simulations with heat transfer and mixing, (ii) post-processing and
More informationData Management in BMKG. Database Center, BMKG July 11, 2017
Data Management in BMKG Database Center, BMKG July 11, 2017 Let s think about 4 Everlasting used data The biggest data producer in Indonesia Many data resources Forecaster may false but Data can t! STATION
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 informationIntroduction to Data Assimilation
Introduction to Data Assimilation Eric Kostelich and David Kuhl MSRI Climate Change Summer School July 21, 2008 Introduction The goal of these exercises is to familiarize you with LETKF data assimilation.
More informationData Portal and Integra.on in JAMSTEC
Data Portal and Integra.on in JAMSTEC Yasunori Hanafusa Data Research Center for Marine-Earth Sciences (DrC) Agency for Marine-Earth Science and Technology (JAMSTEC) 1 Overview of Data Management in JAMSTEC
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 informationIntroduction to LETKF Data Assimilation
Introduction to LETKF Data Assimilation David Kuhl and Eric Kostelich AOSC614 November 12, 2008 Introduction The goal of these exercises is to familiarize you with LETKF data assimilation. We will first
More informationWorking with Scientific Data in ArcGIS Platform
Working with Scientific Data in ArcGIS Platform Sudhir Raj Shrestha sshrestha@esri.com Hong Xu hxu@esri.com Esri User Conference, San Diego, CA. July 11, 2017 What we will cover today Scientific Multidimensional
More informationConverging Remote Sensing and Data Assimilation through Data Fusion
Converging Remote Sensing and Data Assimilation through Data Fusion Benjamin T. Johnson, Ph.D. AER @ NOAA/STAR/JCSDA benjamin.t.johnson@noaa.gov The Team: Sid Boukabara Kevin Garrett Eric Maddy Ling Liu
More informationAutumn 1 Autumn 2 Spring 1 Spring 2 Summer 1 Summer 2 Shape. Addition. Addition Sequences. Sequences. Data Measure and Shape. Doubles And Halves
YEAR 1 Number and Place Value Number and Place Value Number and Place Value Shape Fractions Shape Money and Measure Data Number and Place Value Fractions Multiplication Data Measure and Shape Measure and
More informationCESM Workflow Refactor Project Land Model and Biogeochemistry Working Groups 2015 Winter Meeting CSEG & ASAP/CISL
CESM Workflow Refactor Project Land Model and Biogeochemistry Working Groups 2015 Winter Meeting Alice Bertini Sheri Mickelson CSEG & ASAP/CISL CESM Workflow Refactor Project Who s involved? Joint project
More informationIntroduction to Parallel Computing
Introduction to Parallel Computing Bootcamp for SahasraT 7th September 2018 Aditya Krishna Swamy adityaks@iisc.ac.in SERC, IISc Acknowledgments Akhila, SERC S. Ethier, PPPL P. Messina, ECP LLNL HPC tutorials
More informationToward the Development of a Comprehensive Data & Information Management System for THORPEX
Toward the Development of a Comprehensive Data & Information Management System for THORPEX Mohan Ramamurthy, Unidata Steve Williams, JOSS Jose Meitin, JOSS Karyn Sawyer, JOSS UCAR Office of Programs Boulder,
More informationInterfaces Module Exploration Systems Engineering, version 1.0
nterfaces Module Exploration Systems Engineering, version 1.0 Exploration Systems Engineering: nterfaces Module Module Purpose: nterfaces Define interfaces, how they are described and why it is important
More informationCollabora've Development
Collabora've Development Ricardo Todling NASA GMAO 2013 Joint DTC- EMC- JCSDA GSI Workshop 1 In the Beginning NCEP: SSI (late 1980 s) Spectral formula'on of background error cov Direct assimila'on of radiances
More informationLecture 13: Memory Consistency. + a Course-So-Far Review. Parallel Computer Architecture and Programming CMU , Spring 2013
Lecture 13: Memory Consistency + a Course-So-Far Review Parallel Computer Architecture and Programming Today: what you should know Understand the motivation for relaxed consistency models Understand the
More informationCommon Infrastructure for Modeling Earth (CIME) and MOM6. Mariana Vertenstein CESM Software Engineering Group
Common Infrastructure for Modeling Earth (CIME) and MOM6 Mariana Vertenstein CESM Software Engineering Group Outline What is CIME? New CIME coupling infrastructure and MOM6 CESM2/DART Data Assimilation
More informationUsing ODHeuristics To Solve Hard Mixed Integer Programming Problems. Alkis Vazacopoulos Robert Ashford Optimization Direct Inc.
Using ODHeuristics To Solve Hard Mixed Integer Programming Problems Alkis Vazacopoulos Robert Ashford Optimization Direct Inc. February 2017 Summary Challenges of Large Scale Optimization Exploiting parallel
More informationEvaluating the Performance of the Community Atmosphere Model at High Resolutions
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,
More informationDistributed Systems. 05. Clock Synchronization. Paul Krzyzanowski. Rutgers University. Fall 2017
Distributed Systems 05. Clock Synchronization Paul Krzyzanowski Rutgers University Fall 2017 2014-2017 Paul Krzyzanowski 1 Synchronization Synchronization covers interactions among distributed processes
More informationTopic: Topic 1-Numeration
Suggested Blocks of Instruction: 10 days /September Use place value understanding and properties of operations to perform multi-digit arithmetic. 3.NBT.1. Use place value understanding to round whole numbers
More informationCompsci 590.3: Introduction to Parallel Computing
Compsci 590.3: Introduction to Parallel Computing Alvin R. Lebeck Slides based on this from the University of Oregon Admin Logistics Homework #3 Use script Project Proposals Document: see web site» Due
More informationUpdate on Topology Aware Scheduling (aka TAS)
Update on Topology Aware Scheduling (aka TAS) Work done in collaboration with J. Enos, G. Bauer, R. Brunner, S. Islam R. Fiedler Adaptive Computing 2 When things look good Image credit: Dave Semeraro 3
More informationComputing Seminar Introduction Oct
Computing Seminar Introduction Oct 6 2010 Outline today Programming/computing basics terminology, high level concepts (variables, control flow, input/output) Before next week... Make sure you can login
More informationEPICSTUDIO QUICK START INSTRUCTIONS PC CONFIGURATION PC NOT CONFIGURED BY TRANS LUX PN REV
EPICSTUDIO QUICK START INSTRUCTIONS PN 98 0086 02 1 REV 1703.07 PC CONFIGURATION PC CONFIGURED BY TRANS LUX If your PC was configured at the factory, then proceed to OVERVIEW on page 2. PC NOT CONFIGURED
More information30 Nov Dec Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy
Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy Why serial is not enough Computing architectures Parallel paradigms Message Passing Interface How
More informationCPU GPU. Regional Models. Global Models. Bigger Systems More Expensive Facili:es Bigger Power Bills Lower System Reliability
Xbox 360 Successes and Challenges using GPUs for Weather and Climate Models DOE Jaguar Mark GoveM Jacques Middlecoff, Tom Henderson, Jim Rosinski, Craig Tierney CPU Bigger Systems More Expensive Facili:es
More informationA/D Converter. Sampling. Figure 1.1: Block Diagram of a DSP System
CHAPTER 1 INTRODUCTION Digital signal processing (DSP) technology has expanded at a rapid rate to include such diverse applications as CDs, DVDs, MP3 players, ipods, digital cameras, digital light processing
More informationcdo Data Processing (and Production) Luis Kornblueh, Uwe Schulzweida, Deike Kleberg, Thomas Jahns, Irina Fast
cdo Data Processing (and Production) Luis Kornblueh, Uwe Schulzweida, Deike Kleberg, Thomas Jahns, Irina Fast Max-Planck-Institut für Meteorologie, DKRZ September 24, 2014 MAX-PLANCK-GESELLSCHAFT Data
More informationEnKF implementation at NRL Stennis
Hans E. Ngodock (DMS/USM) Ole Martin Smedstad (PSI) In collaboration with Laurent Bertino and Knut A. Lisæter (NERSC) Geir Evensen (NORSK HYDRO) Address the need of advanced data assimilation techniques
More informationMPAS-O: Plan for 2013
MPAS-O: Plan for 2013 Todd Ringler Theoretical Division Los Alamos National Laboratory Climate, Ocean and Sea-Ice Modeling Project http://public.lanl.gov/ringler/ringler.html Staffing, Effort and Focus
More informationMcIDAS-V Tutorial Displaying Gridded Data updated June 2015 (software version 1.5)
McIDAS-V Tutorial Displaying Gridded Data updated June 2015 (software version 1.5) McIDAS-V is a free, open source, visualization and data analysis software package that is the next generation in SSEC's
More informationEssentials for Modern Data Analysis Systems
Essentials for Modern Data Analysis Systems Mehrdad Jahangiri, Cyrus Shahabi University of Southern California Los Angeles, CA 90089-0781 {jahangir, shahabi}@usc.edu Abstract Earth scientists need to perform
More informationIntroduction to Parallel Programming in OpenMp Dr. Yogish Sabharwal Department of Computer Science & Engineering Indian Institute of Technology, Delhi
Introduction to Parallel Programming in OpenMp Dr. Yogish Sabharwal Department of Computer Science & Engineering Indian Institute of Technology, Delhi Lecture - 01 Introduction to Parallel Computing Architectures
More informationVerdandi: a Generic Data Assimilation Library
: a Generic Data Assimilation Library Claire Mouton, Vivien Mallet In collaboration with Dominique Chapelle, Philippe Moireau and Marc Fragu Second ADAMS Meeting October 27 th 2009 Claire Mouton, Vivien
More informationThe ECMWF forecast model, quo vadis?
The forecast model, quo vadis? by Nils Wedi European Centre for Medium-Range Weather Forecasts wedi@ecmwf.int contributors: Piotr Smolarkiewicz, Mats Hamrud, George Mozdzynski, Sylvie Malardel, Christian
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 information16 th Annual CESM Workshop s Software Engineering Working Group. Parallel Analysis of GeOscience Data Status and Future
16 th Annual CESM Workshop s Software Engineering Working Group Parallel Analysis of GeOscience Data Status and Future Jeff Daily PI: Karen Schuchardt, in collaboration with Colorado State University s
More informationA Scalable, Numerically Stable, High- Performance Tridiagonal Solver for GPUs. Li-Wen Chang, Wen-mei Hwu University of Illinois
A Scalable, Numerically Stable, High- Performance Tridiagonal Solver for GPUs Li-Wen Chang, Wen-mei Hwu University of Illinois A Scalable, Numerically Stable, High- How to Build a gtsv for Performance
More informationMPI & OpenMP Mixed Hybrid Programming
MPI & OpenMP Mixed Hybrid Programming Berk ONAT İTÜ Bilişim Enstitüsü 22 Haziran 2012 Outline Introduc/on Share & Distributed Memory Programming MPI & OpenMP Advantages/Disadvantages MPI vs. OpenMP Why
More informationWebomania Solutions Pvt. Ltd. 2017
There are different types of Websites. To understand the types, one need to understand what is a website? What is a Website? A website is an online HTML Document, accessible publicly and it contains certain
More informationDay 11: Workflows with DAGMan
Day 11: Workflows with DAGMan Suggested reading: Condor 7.7 Manual: http://www.cs.wisc.edu/condor/manual/v7.7/ Section 2.10: DAGMan Applications Chapter 9: condor_submit_dag 1 Turn In Homework 2 Homework
More informationCS 43: Computer Networks. 27: Media Access Contd. December 3, 2018
CS 43: Computer Networks 27: Media Access Contd. December 3, 2018 Last Class The link layer provides lots of functionality: addressing, framing, media access, error checking could be used independently
More informationA Survey of Ensemble Filtering in the Data Assimilation Research Testbed
1 A Survey of Ensemble Filtering in the Data Assimilation Research Testbed (Note: In the following, input that students need to enter are in bold, underlined text. Text that will be output to a workstation
More informationOcean Simulations using MPAS-Ocean
Ocean Simulations using MPAS-Ocean Mark Petersen and the MPAS-Ocean development team Los Alamos National Laboratory U N C L A S S I F I E D Slide 1 Progress on MPAS-Ocean in 2010 MPAS-Ocean is a functioning
More informationMcIDAS-V Tutorial Installation and Introduction updated September 2015 (software version 1.5)
McIDAS-V Tutorial Installation and Introduction updated September 2015 (software version 1.5) McIDAS-V is a free, open source, visualization and data analysis software package that is the next generation
More informationPrinciples of the Global Positioning System Lecture 15" Propagation Medium: Neutral atmosphere" Basic atmospheric structure"
12.540 Principles of the Global Positioning System Lecture 15" Prof. Thomas Herring" Room 54-820A; 253-5941" tah@mit.edu" http://geoweb.mit.edu/~tah/12.540 " Propagation Medium: Neutral atmosphere" Summary"
More informationGSI Setup, Run and Namelist
GSI Setup, Run and Namelist Hui Shao GSI Community Tutorial, June 28-30, 2010, Boulder, CO Observation Error Observation Observation processing and assimilation PrepBUFR and BUFR processing: 06/29, Tue
More informationModule 5: Performance Issues in Shared Memory and Introduction to Coherence Lecture 9: Performance Issues in Shared Memory. The Lecture Contains:
The Lecture Contains: Data Access and Communication Data Access Artifactual Comm. Capacity Problem Temporal Locality Spatial Locality 2D to 4D Conversion Transfer Granularity Worse: False Sharing Contention
More informationR Number Recognise numbers
Maths R Recognise numbers to 12, 8. 4 and counting Identifying numerals. Match corresponding numeral to quantity. Use number names correctly in play and everyday life. Begin to form numbers correctly.
More informationVersion 3 Updated: 10 March Distributed Oceanographic Match-up Service (DOMS) User Interface Design
Distributed Oceanographic Match-up Service (DOMS) User Interface Design Shawn R. Smith 1, Jocelyn Elya 1, Adam Stallard 1, Thomas Huang 2, Vardis Tsontos 2, Benjamin Holt 2, Steven Worley 3, Zaihua Ji
More informationCrockerne Church of England Primary Non-Negotiables. Mathematics
Key Skills To be able to solve problems using a range of strategies. To reason mathematically, following a line of enquiry. Mathematical language and targets Mathematics Number (Number and Place value)
More informationDistributed Systems. Communica3on and models. Rik Sarkar Spring University of Edinburgh
Distributed Systems Communica3on and models Rik Sarkar Spring 2018 University of Edinburgh Models Expecta3ons/assump3ons about things Every idea or ac3on anywhere is based on a model Determines what can
More informationSchool District of Marshfield Mathematics Standards
MATHEMATICS Counting and Cardinality, Operations and Algebraic Thinking, Number and Operations in Base Ten, Measurement and Data, and Geometry Operations and Algebraic Thinking Represent and Solve Problems
More informationGetting the code to work: Proof of concept in an interactive shell.
Getting the code to work: Proof of concept in an interactive shell. 1) Codes are executed with run scripts. These are shell script text files that set up the individual runs and execute the code. The scripts
More informationHigh Spectral Resolution Infrared Radiance Modeling Using Optimal Spectral Sampling (OSS) Method
High Spectral Resolution Infrared Radiance Modeling Using Optimal Spectral Sampling (OSS) Method J.-L. Moncet, G. Uymin and H. Snell 1 Parameteriation of radiative transfer equation is necessary for operational
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 informationAppendix A: Graph Types Available in OBIEE
Appendix A: Graph Types Available in OBIEE OBIEE provides a wide variety of graph types to assist with data analysis, including: Pie Scatter Bar Area Line Radar Line Bar Combo Step Pareto Bubble Each graph
More informationScalable Algorithmic Techniques Decompositions & Mapping. Alexandre David
Scalable Algorithmic Techniques Decompositions & Mapping Alexandre David 1.2.05 adavid@cs.aau.dk Introduction Focus on data parallelism, scale with size. Task parallelism limited. Notion of scalability
More informationExample: CPU-bound process that would run for 100 quanta continuously 1, 2, 4, 8, 16, 32, 64 (only 37 required for last run) Needs only 7 swaps
Interactive Scheduling Algorithms Continued o Priority Scheduling Introduction Round-robin assumes all processes are equal often not the case Assign a priority to each process, and always choose the process
More informationScalable Software Components for Ultrascale Visualization Applications
Scalable Software Components for Ultrascale Visualization Applications Wes Kendall, Tom Peterka, Jian Huang SC Ultrascale Visualization Workshop 2010 11-15-2010 Primary Collaborators Jian Huang Tom Peterka
More informationMITOCW watch?v=penh4mv5gag
MITOCW watch?v=penh4mv5gag PROFESSOR: Graph coloring is the abstract version of a problem that arises from a bunch of conflict scheduling situations. So let's look at an example first and then define the
More informationMcIDAS-V Tutorial Using Simulated ABI Data updated July 2016 (software version 1.6)
McIDAS-V Tutorial Using Simulated ABI Data updated July 2016 (software version 1.6) McIDAS-V is a free, open source, visualization and data analysis software package that is the next generation in SSEC's
More informationIn this exercise, you ll create a netcdf raster layer using the variable tmin. You will change the display by selecting a different time step.
Learning to Work with Temporal Data in ArcGIS Working with a netcdf File in ArcGIS Objective NetCDF (network Common Data Form) is a file format for storing multidimensional scientific data (variables)
More informationPick a time window size w. In time span w, are there, Multiple References, to nearby addresses: Spatial Locality
Pick a time window size w. In time span w, are there, Multiple References, to nearby addresses: Spatial Locality Repeated References, to a set of locations: Temporal Locality Take advantage of behavior
More informationThe Community Land Model (CLM)
The Community Land Model (CLM) Cecile Hannay, CAM Science Liaison Atmospheric Modeling and Predictability Section Climate and Global Dynamics Division Outline CESM: workflow reminder Archiving results/long
More informationThe Development of Modeling, Simulation and Visualization Services for the Earth Sciences in the National Supercomputing Center of Korea
icas2013 (September 9~12, Annecy/France) The Development of Modeling, Simulation and Visualization Services for the Earth Sciences in the National Supercomputing Center of Korea Min-Su Joh, Joon-Eun Ahn,
More informationEnKF Fundamentals (2b): Applications
2015 EnKF Community Tutorial August 13-14, 2015. Boulder, CO EnKF Fundamentals (2b): Applications Kathryn Newman Ming Hu, and Chunhua Zhou Developmental Testbed Center (DTC) Outline EnKF fundamentals (1):
More informationHigh Performance Computing
The Need for Parallelism High Performance Computing David McCaughan, HPC Analyst SHARCNET, University of Guelph dbm@sharcnet.ca Scientific investigation traditionally takes two forms theoretical empirical
More informationGeneration of WRF-ARW Background Errors (BE) For GSI
Generation of WRF-ARW Background Errors (BE) For GSI 1. Introduction: Syed RH Rizvi, Zhiquan Liu and Xiang-Yu Huang NCAR/ESSL/MMM, Boulder, CO Currently NCEP global background errors are used for running
More informationWRF-Var System. WRF-Var Tutorial July 21-22, Xin Zhang and Syed RH Rizvi. Michael Duda
System Tutorial July 21-22, 2008 Xin Zhang and Syed RH Rizvi Michael Duda Outline in the WRF Modeling System Software Code Overview 1 in the WRF Modeling System 2 in the WRF Modeling System Blue --> Supported
More informationDistributed Information Processing
Distributed Information Processing 1 st Lecture Eom, Hyeonsang ( 엄현상 ) Department of Computer Science & Engineering Seoul National University Copyrights 2017 Eom, Hyeonsang All Rights Reserved Outline
More informationRegCM-ROMS Tutorial: Introduction to ROMS Ocean Model
RegCM-ROMS Tutorial: Introduction to ROMS Ocean Model Ufuk Utku Turuncoglu ICTP (International Center for Theoretical Physics) Earth System Physics Section - Outline Outline Introduction Grid generation
More informationParallel I/O Libraries and Techniques
Parallel I/O Libraries and Techniques Mark Howison User Services & Support I/O for scientifc data I/O is commonly used by scientific applications to: Store numerical output from simulations Load initial
More informationC-Coupler2: a flexible and user-friendly community coupler for model coupling and nesting
https://doi.org/10.5194/gmd-11-3557-2018 Author(s) 2018. This work is distributed under the Creative Commons Attribution 4.0 License. C-Coupler2: a flexible and user-friendly community coupler for model
More informationThinking parallel. Decomposition. Thinking parallel. COMP528 Ways of exploiting parallelism, or thinking parallel
COMP528 Ways of exploiting parallelism, or thinking parallel www.csc.liv.ac.uk/~alexei/comp528 Alexei Lisitsa Dept of computer science University of Liverpool a.lisitsa@.liverpool.ac.uk Thinking parallel
More informationThe challenges of new, efficient computer architectures, and how they can be met with a scalable software development strategy.! Thomas C.
The challenges of new, efficient computer architectures, and how they can be met with a scalable software development strategy! Thomas C. Schulthess ENES HPC Workshop, Hamburg, March 17, 2014 T. Schulthess!1
More informationThe Impact of Inter-node Latency versus Intra-node Latency on HPC Applications The 23 rd IASTED International Conference on PDCS 2011
The Impact of Inter-node Latency versus Intra-node Latency on HPC Applications The 23 rd IASTED International Conference on PDCS 2011 HPC Scale Working Group, Dec 2011 Gilad Shainer, Pak Lui, Tong Liu,
More informationWCS2.1 Met-Ocean. 16 th Workshop on Operational Systems. Crown copyright Met Office
WCS2.1 Met-Ocean 16 th Workshop on Operational Systems Crown copyright Met Office A Revolutionary Approach to Multi- Dimensional Data Access of Gridded Datasets Using Current and Proposed OGC Web Coverage
More information