Sustained Simulation Performance 2016 : Proceedings of the Joint Workshop on Sustained Simulation Performance, University of Stuttgart (HLRS) and Tohoku University 2016.

By: Resch, Michael MContributor(s): Bez, Wolfgang | Focht, Erich | Patel, Nisarg | Kobayashi, HiroakiMaterial type: TextTextPublisher: Cham : Springer, 2016Copyright date: ©2016Description: 1 online resource (191 pages)Content type: text Media type: computer Carrier type: online resourceISBN: 9783319467351Subject(s): Operating systems (Computers)Genre/Form: Electronic books.Additional physical formats: Print version:: Sustained Simulation Performance 2016 : Proceedings of the Joint Workshop on Sustained Simulation Performance, University of Stuttgart (HLRS) and Tohoku University 2016DDC classification: 003.3 LOC classification: QA1-939Online resources: Click here to view book
Contents:
Intro -- Preface -- Contents -- Part I Exploitation of Existing HPC Systems: Potentiality, Performance and Productivity -- Parallel Algorithms: Theory, Practice and Education -- 1 Introduction -- 2 What is a Complete Description of the Algorithm Properties? -- 3 Why Is It Hard to Describe Algorithms? -- 4 Conclusion -- References -- High Performance Computing and High Performance Data Analytics---What is the Missing Link? -- 1 Introduction -- 2 The Evolution of High Performance Computing -- 2.1 Traditional High Performance Computing -- 2.2 Evolution Over Time -- 3 Towards High Performance Data Analytics -- 3.1 Where Is It Needed? -- 3.2 HPDA Concepts and Technologies -- 3.3 A Practical Application Making Use of HPC and HPDA -- 4 The Missing Link -- 4.1 Cognitive Computing -- 4.2 Benefits -- 4.3 Available Technologies -- 5 Conclusions -- References -- A Use Case of a Code Transformation Rule Generator for Data Layout Optimization -- 1 Introduction -- 2 Data Layout Optimization -- 3 Code Transformation Rule Generation with Xevtgen -- 4 Discussions -- 5 Conclusions -- References -- APES on SX-ACE -- 1 Introduction -- 2 Porting of Musubi -- 2.1 Porting of the Kernel -- 2.2 Porting of the Initialization -- 2.3 Porting of the IO -- 2.4 Porting of Boundary Conditions -- 2.5 Parallel Performance -- 3 Some Notes on the Porting of Ateles -- 4 Summary -- References -- Dealing with Non-linear Terms in a Modal High-Order Discontinuous Galerkin Method -- 1 Introduction -- 2 The High Order Discontinuous Galerkin Method -- 3 Choice of Basis Function -- 4 The Projection Algorithms -- 4.1 Direct L2 Projection -- 4.2 Fast Polynomial Transformation -- 4.3 Spherical Harmonic Transform Using Fast Multipole Method -- 5 Hybrid Parallelization of the Projection Algorithms -- 6 Comparison of Different Algorithms -- 7 Conclusion -- References.
Efficient Coupling of Fluid and Acoustic Interaction on Massive Parallel Systems -- 1 Introduction -- 2 Governing Equations -- 2.1 Fluid Equations -- 2.2 Acoustic Equations -- 3 Methodology -- 3.1 High-Order Solver Ateles -- 3.2 Partitioned Coupling -- 4 Results -- 4.1 Simulation Setup -- 4.2 Numerical Results -- 5 Conclusion -- References -- The Spectral Structure of a Nonlinear Operator and Its Approximation II -- 1 Introduction -- 2 The Koopman Operator -- 2.1 Unusual properties of the Koopman-Operator -- 3 The Numerical Approach: The Space of Observables -- 3.1 Relation to the Koopman Operator -- 3.2 Hankel Matrices -- 3.3 Convolution of Polynom Coefficient Vectors -- 4 The Decomposition of a Signal in Koopman Modes -- 4.1 Vandermonde Decomposition for a Polynom Coefficient Vector -- 5 The Koopman Eigenvectors for a Decomposition -- 5.1 Wiener-Wintner Eigenfunctions and Decomposition -- 6 Polynom Coefficient Vector and Hankel Matrix -- 6.1 Approximatve Decomposition of a Signal in Modes -- 6.2 Simplified Approach -- 7 Remarks -- 8 Conclusions -- References -- Implementation of a Parallel Sparse Direct Solver on Vector Architecture -- 1 Introduction -- 2 Factorization of Sparse and Dense Sub-matrices -- 2.1 Recursive Computation of Schur Complement -- 2.2 Tridiagonal Block Structure for Sparse Sub-matrix -- 2.3 Block Strategy to Enforce Parallelization for Dense Factorization -- 3 Efficiency of the Solver on Both Super-Scalar and Vector Architecture -- 4 Conclusion -- References -- Directive Translation for Various HPC Systems Using the Xevolver Framework -- 1 Introduction -- 2 Utilization of Directive Sets for HPC Systems -- 3 Directive Translation using Xevolver Code Translation Framework -- 4 Translation of a Placeholder into OpenMP Directives -- 5 Conclusions -- References.
An Automatic Performance Tracking System for Large-Scale Numerical Applications -- 1 Introduction -- 2 Performance Portability of HPC Applications -- 2.1 Finding the Cause of Performance Degradation on Execution Systems -- 2.2 Application Performance on Execution Systems -- 2.3 Source Codes Synchronization Among Multiple Building Systems -- 3 An Automatic Performance Tracking System -- 3.1 Overview of the Automatic Performance Tracking System -- 3.2 Performance Tracking Function Along with Source Code Modifications -- 4 Evaluation of the Automatic Performance Tracking System -- 4.1 Evaluation Setups of Finding the Cause of Degrading Performance portability -- 4.2 Results of Analysing the Degradation of the Performance Portability -- 5 Conclusions and Future Work -- References -- Part II Numerical Computations and Approach Towards Multi-physics Applications -- A Case Study of Urgent Computing on SX-ACE: Design and Development of a Real-Time Tsunami Inundation Analysis System for Disaster Prevention and Mitigation -- 1 Introduction -- 2 A Real-Time Tsunami Inundation Analysis System -- 3 Performance Evaluation -- 4 Summary -- References -- CFD/CAA Simulations on HPC Systems -- 1 Introduction -- 2 Governing Equations -- 2.1 Navier-Stokes Equations -- 2.2 Acoustic Perturbation Equations -- 3 Numerical Methods -- 3.1 Hierarchical Mesh Topology -- 3.2 Discontinuous Galerkin Approximation of the APE -- 3.3 Finite-Volume Method for the Flow Simulation -- 4 Coupling Strategy -- 4.1 Spatial Coupling -- 4.2 Temporal Coupling -- 4.3 Data Transfer -- 5 Results -- 5.1 Validation of the Aeroacoustics Solver -- 5.2 Parallel Performance Analysis -- 6 Conclusions -- References -- HPC Applications for Manufacturing Innovation in Aerospace Fields -- 1 Introduction -- 2 JAXA's Supercomputer System 2 -- 2.1 System Overview -- 2.2 Performance Measurements.
3 Application to the Project -- 4 Conclusions -- References -- High Resolution Climate Projections Using the WRF Model on the HLRS -- 1 Introduction -- 2 Simulation Setup with WRF and Forcing Data -- 3 Results -- 3.1 Historical Temperatures -- 3.2 Projections for Temperature Changes -- 4 Conclusion -- References -- Towards Aerodynamic Characteristics Investigation Based on Cartesian Methods for Low-Reynolds Number Flow Simulation -- 1 Introduction -- 2 Building-Cube Method -- 3 Computational Model and Conditions -- 4 Results and Discussion -- 4.1 Aerodynamic Computations of a Flat Plate -- 4.2 Aerodynamic Computations of NACA0012 -- 4.3 Aerodynamic Computations of Circular Arc -- 5 Concluding Remarks -- References.
Tags from this library: No tags from this library for this title. Log in to add tags.
Item type Current location Call number URL Status Date due Barcode
Electronic Book UT Tyler Online
Online
QA1-939 (Browse shelf) http://ebookcentral.proquest.com/lib/uttyler/detail.action?docID=4755383 Available EBC4755383

Intro -- Preface -- Contents -- Part I Exploitation of Existing HPC Systems: Potentiality, Performance and Productivity -- Parallel Algorithms: Theory, Practice and Education -- 1 Introduction -- 2 What is a Complete Description of the Algorithm Properties? -- 3 Why Is It Hard to Describe Algorithms? -- 4 Conclusion -- References -- High Performance Computing and High Performance Data Analytics---What is the Missing Link? -- 1 Introduction -- 2 The Evolution of High Performance Computing -- 2.1 Traditional High Performance Computing -- 2.2 Evolution Over Time -- 3 Towards High Performance Data Analytics -- 3.1 Where Is It Needed? -- 3.2 HPDA Concepts and Technologies -- 3.3 A Practical Application Making Use of HPC and HPDA -- 4 The Missing Link -- 4.1 Cognitive Computing -- 4.2 Benefits -- 4.3 Available Technologies -- 5 Conclusions -- References -- A Use Case of a Code Transformation Rule Generator for Data Layout Optimization -- 1 Introduction -- 2 Data Layout Optimization -- 3 Code Transformation Rule Generation with Xevtgen -- 4 Discussions -- 5 Conclusions -- References -- APES on SX-ACE -- 1 Introduction -- 2 Porting of Musubi -- 2.1 Porting of the Kernel -- 2.2 Porting of the Initialization -- 2.3 Porting of the IO -- 2.4 Porting of Boundary Conditions -- 2.5 Parallel Performance -- 3 Some Notes on the Porting of Ateles -- 4 Summary -- References -- Dealing with Non-linear Terms in a Modal High-Order Discontinuous Galerkin Method -- 1 Introduction -- 2 The High Order Discontinuous Galerkin Method -- 3 Choice of Basis Function -- 4 The Projection Algorithms -- 4.1 Direct L2 Projection -- 4.2 Fast Polynomial Transformation -- 4.3 Spherical Harmonic Transform Using Fast Multipole Method -- 5 Hybrid Parallelization of the Projection Algorithms -- 6 Comparison of Different Algorithms -- 7 Conclusion -- References.

Efficient Coupling of Fluid and Acoustic Interaction on Massive Parallel Systems -- 1 Introduction -- 2 Governing Equations -- 2.1 Fluid Equations -- 2.2 Acoustic Equations -- 3 Methodology -- 3.1 High-Order Solver Ateles -- 3.2 Partitioned Coupling -- 4 Results -- 4.1 Simulation Setup -- 4.2 Numerical Results -- 5 Conclusion -- References -- The Spectral Structure of a Nonlinear Operator and Its Approximation II -- 1 Introduction -- 2 The Koopman Operator -- 2.1 Unusual properties of the Koopman-Operator -- 3 The Numerical Approach: The Space of Observables -- 3.1 Relation to the Koopman Operator -- 3.2 Hankel Matrices -- 3.3 Convolution of Polynom Coefficient Vectors -- 4 The Decomposition of a Signal in Koopman Modes -- 4.1 Vandermonde Decomposition for a Polynom Coefficient Vector -- 5 The Koopman Eigenvectors for a Decomposition -- 5.1 Wiener-Wintner Eigenfunctions and Decomposition -- 6 Polynom Coefficient Vector and Hankel Matrix -- 6.1 Approximatve Decomposition of a Signal in Modes -- 6.2 Simplified Approach -- 7 Remarks -- 8 Conclusions -- References -- Implementation of a Parallel Sparse Direct Solver on Vector Architecture -- 1 Introduction -- 2 Factorization of Sparse and Dense Sub-matrices -- 2.1 Recursive Computation of Schur Complement -- 2.2 Tridiagonal Block Structure for Sparse Sub-matrix -- 2.3 Block Strategy to Enforce Parallelization for Dense Factorization -- 3 Efficiency of the Solver on Both Super-Scalar and Vector Architecture -- 4 Conclusion -- References -- Directive Translation for Various HPC Systems Using the Xevolver Framework -- 1 Introduction -- 2 Utilization of Directive Sets for HPC Systems -- 3 Directive Translation using Xevolver Code Translation Framework -- 4 Translation of a Placeholder into OpenMP Directives -- 5 Conclusions -- References.

An Automatic Performance Tracking System for Large-Scale Numerical Applications -- 1 Introduction -- 2 Performance Portability of HPC Applications -- 2.1 Finding the Cause of Performance Degradation on Execution Systems -- 2.2 Application Performance on Execution Systems -- 2.3 Source Codes Synchronization Among Multiple Building Systems -- 3 An Automatic Performance Tracking System -- 3.1 Overview of the Automatic Performance Tracking System -- 3.2 Performance Tracking Function Along with Source Code Modifications -- 4 Evaluation of the Automatic Performance Tracking System -- 4.1 Evaluation Setups of Finding the Cause of Degrading Performance portability -- 4.2 Results of Analysing the Degradation of the Performance Portability -- 5 Conclusions and Future Work -- References -- Part II Numerical Computations and Approach Towards Multi-physics Applications -- A Case Study of Urgent Computing on SX-ACE: Design and Development of a Real-Time Tsunami Inundation Analysis System for Disaster Prevention and Mitigation -- 1 Introduction -- 2 A Real-Time Tsunami Inundation Analysis System -- 3 Performance Evaluation -- 4 Summary -- References -- CFD/CAA Simulations on HPC Systems -- 1 Introduction -- 2 Governing Equations -- 2.1 Navier-Stokes Equations -- 2.2 Acoustic Perturbation Equations -- 3 Numerical Methods -- 3.1 Hierarchical Mesh Topology -- 3.2 Discontinuous Galerkin Approximation of the APE -- 3.3 Finite-Volume Method for the Flow Simulation -- 4 Coupling Strategy -- 4.1 Spatial Coupling -- 4.2 Temporal Coupling -- 4.3 Data Transfer -- 5 Results -- 5.1 Validation of the Aeroacoustics Solver -- 5.2 Parallel Performance Analysis -- 6 Conclusions -- References -- HPC Applications for Manufacturing Innovation in Aerospace Fields -- 1 Introduction -- 2 JAXA's Supercomputer System 2 -- 2.1 System Overview -- 2.2 Performance Measurements.

3 Application to the Project -- 4 Conclusions -- References -- High Resolution Climate Projections Using the WRF Model on the HLRS -- 1 Introduction -- 2 Simulation Setup with WRF and Forcing Data -- 3 Results -- 3.1 Historical Temperatures -- 3.2 Projections for Temperature Changes -- 4 Conclusion -- References -- Towards Aerodynamic Characteristics Investigation Based on Cartesian Methods for Low-Reynolds Number Flow Simulation -- 1 Introduction -- 2 Building-Cube Method -- 3 Computational Model and Conditions -- 4 Results and Discussion -- 4.1 Aerodynamic Computations of a Flat Plate -- 4.2 Aerodynamic Computations of NACA0012 -- 4.3 Aerodynamic Computations of Circular Arc -- 5 Concluding Remarks -- References.

Description based on publisher supplied metadata and other sources.

There are no comments on this title.

to post a comment.