Cantitate/Preț
Produs
Total produse
Vezi coșul
Parallel Processing and Applied Mathematics, Part I: 8th International Conference, PPAM 2009, Wroclaw, Poland, September 13-16, 2009 de Roman Wyrzykowski

Parallel Processing and Applied Mathematics, Part I: 8th International Conference, PPAM 2009, Wroclaw, Poland, September 13-16, 2009: Lecture Notes in Computer Science, cartea 6067

Editat de Roman Wyrzykowski, Jack Dongarra, Konrad Karczewski, Jerzy Wasniewski
en Limba Engleză Paperback – 7 iul 2010

În domeniul High-Performance Computing (HPC) și al matematicii aplicate, lucrarea Parallel Processing and Applied Mathematics, Part I reprezintă un punct de referință tehnic, sintetizând cercetările prezentate la ediția a opta a conferinței PPAM. Volumul, editat de specialiști precum Jack Dongarra și Roman Wyrzykowski, se concentrează pe utilizarea eficientă a arhitecturilor moderne de calcul distribuit și pe algoritmii necesari pentru aplicații la scară largă. Ca și Jack Dongarra în Applied Parallel Computing. Computations in Physics, Chemistry and Engineering Science, autorii de față distilează experiența reală în principii acționabile, oferind soluții pentru optimizarea performanței pe sisteme complexe.

Structura acestui prim volum indică o progresie logică de la hardware la software. Ne-a atras atenția secțiunea dedicată arhitecturilor paralele și mobile, care debutează cu evaluări de performanță pe procesoare Intel® Xeon® din familia 5500, continuând cu analize asupra rețelelor optice și a rutării în hypercube-uri. Această abordare practică este completată de o secțiune extinsă de algoritmi numerici, unde sunt explicate strategii de replicare parțială a datelor pentru transformata wavelet discretă și metode de echilibrare dinamică a sarcinii (load balancing) pentru probleme de flux paralel.

Apreciem rigoarea academică a volumului, reflectată în rata de selecție a lucrărilor, ceea ce garantează un conținut tehnic dens, axat pe soluționarea ecuațiilor diferențiale parțiale neliniare și pe modelarea rețelelor Petri. Lucrarea se aliniază tematic cu titluri precum Algorithms and Architectures for Parallel Processing de Arrems Hua, însă PPAM pune un accent mai puternic pe intersecția dintre matematica computațională și arhitecturile hardware emergente de la finalul primei decade a secolului XXI.

Citește tot Restrânge

Din seria Lecture Notes in Computer Science

Preț: 63764 lei

Preț vechi: 79705 lei
-20%

Puncte Express: 956

Carte disponibilă

Livrare economică 01-15 mai

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783642143892
ISBN-10: 364214389X
Pagini: 628
Ilustrații: XXIV, 628 p. 242 illus.
Dimensiuni: 9 x 91 x 30 mm
Greutate: 0.91 kg
Ediția:2010
Editura: Springer Berlin, Heidelberg
Colecția Springer
Seriile Lecture Notes in Computer Science, Theoretical Computer Science and General Issues

Locul publicării:Berlin, Heidelberg, Germany

Public țintă

Research

De ce să citești această carte

Recomandăm această resursă cercetătorilor și inginerilor software care dezvoltă sisteme de calcul paralel. Cititorul câștigă acces la metodologii riguroase de optimizare a algoritmilor numerici și la studii de caz privind performanța hardware în medii HPC. Este un instrument esențial pentru înțelegerea evoluției arhitecturilor distribuite și a fundamentelor matematice necesare pentru simulări complexe de inginerie.

Cuprins

Parallel/Distributed Architectures and Mobile Computing.- Evaluating Performance of New Quad-Core Intel®Xeon®5500 Family Processors for HPC.- Interval Wavelength Assignment in All-Optical Star Networks.- Graphs Partitioning: An Optimal MIMD Queueless Routing for BPC-Permutations on Hypercubes.- Probabilistic Packet Relaying in Wireless Mobile Ad Hoc Networks.- Numerical Algorithms and Parallel Numerics.- On the Performance of a New Parallel Algorithm for Large-Scale Simulations of Nonlinear Partial Differential Equations.- Partial Data Replication as a Strategy for Parallel Computing of the Multilevel Discrete Wavelet Transform.- Dynamic Load Balancing for Adaptive Parallel Flow Problems.- A Balancing Domain Decomposition Method for a Discretization of a Plate Problem on Nonmatching Grids.- Application Specific Processors for the Autoregressive Signal Analysis.- A Parallel Non-square Tiled Algorithm for Solving a Kind of BVP for Second-Order ODEs.- Graph Grammar Based Petri Nets Model of Concurrency for Self-adaptive hp-Finite Element Method with Rectangular Elements.- Numerical Solution of the Time and Rigidity Dependent Three Dimensional Second Order Partial Differential Equation.- Hardware Implementation of the Exponent Based Computational Core for an Exchange-Correlation Potential Matrix Generation.- Parallel Implementation of Conjugate Gradient Method on Graphics Processors.- Iterative Solution of Linear and Nonlinear Boundary Problems Using PIES.- Paralel and Distributed Non-numerical Algorithms.- Implementing a Parallel Simulated Annealing Algorithm.- Parallel Computing Scheme for Graph Grammar-Based Syntactic Pattern Recognition.- Extended Cascaded Star Schema for Distributed Spatial Data Warehouse.- Parallel Longest Increasing Subsequences in Scalable Timeand Memory.- A Scalable Parallel Union-Find Algorithm for Distributed Memory Computers.- Tools and Environments for Parallel/Distributed/Grid Computing.- Extracting Both Affine and Non-linear Synchronization-Free Slices in Program Loops.- A Flexible Checkpoint/Restart Model in Distributed Systems.- A Formal Approach to Replica Consistency in Directory Service.- Software Security in the Model for Service Oriented Architecture Quality.- Automatic Program Parallelization for Multicore Processors.- Request Distribution in Hybrid Processing Environments.- Vine Toolkit - Grid-Enabled Portal Solution for Community Driven Computing Workflows with Meta-scheduling Capabilities.- Applications of Parallel/Distributed Computing.- GEM – A Platform for Advanced Mathematical Geosimulations.- Accelerating the MilkyWay@Home Volunteer Computing Project with GPUs.- Vascular Network Modeling - Improved Parallel Implementation on Computing Cluster.- Parallel Adaptive Finite Element Package with Dynamic Load Balancing for 3D Thermo-Mechanical Problems.- Parallel Implementation of Multidimensional Scaling Algorithm Based on Particle Dynamics.- Particle Model of Tumor Growth and Its Parallel Implementation.- Applied Mathematics and Neural Networks.- Modular Neuro-Fuzzy Systems Based on Generalized Parametric Triangular Norms.- Application of Stacked Methods to Part-of-Speech Tagging of Polish.- Computationally Efficient Nonlinear Predictive Control Based on State-Space Neural Models.- Relational Type-2 Interval Fuzzy Systems.- Properties of Polynomial Bases Used in a Line-Surface Intersection Algorithm.- Minisymposium on GPU Computing.- A GPU Approach to the Simulation of Spatio–temporal Dynamics in Ultrasonic Resonators.- Reduction to Condensed Forms for Symmetric Eigenvalue Problems onMulti-core Architectures.- On Parallelizing the MRRR Algorithm for Data-Parallel Coprocessors.- Fast In-Place Sorting with CUDA Based on Bitonic Sort.- Finite Element Numerical Integration on GPUs.- Modeling and Optimizing the Power Performance of Large Matrices Multiplication on Multi-core and GPU Platform with CUDA.- Stream Processing on GPUs Using Distributed Multimedia Middleware.- Simulations of the Electrical Activity in the Heart with Graphic Processing Units.- Parallel Minimax Tree Searching on GPU.- A Fast GPU Implementation for Solving Sparse Ill-Posed Linear Equation Systems.- The Second Minisymposium on Cell/B.E. Technologies.- Monte Carlo Simulations of Spin Glass Systems on the Cell Broadband Engine.- Montgomery Multiplication on the Cell.- An Exploration of CUDA and CBEA for Einstein@Home.- Introducing the Semi-stencil Algorithm.- Astronomical Period Searching on the Cell Broadband Engine.- Finite Element Numerical Integration on PowerXCell Processors.- The Implementation of Regional Atmospheric Model Numerical Algorithms for CBEA-Based Clusters.- Adaptation of Double-Precision Matrix Multiplication to the Cell Broadband Engine Architecture.- Optimization of FDTD Computations in a Streaming Model Architecture.- Workshop on Memory Issues on Multi- and Manycore Platforms.- An Orthogonal Matching Pursuit Algorithm for Image Denoising on the Cell Broadband Engine.- A Blocking Strategy on Multicore Architectures for Dynamically Adaptive PDE Solvers.- Affinity-On-Next-Touch: An Extension to the Linux Kernel for NUMA Architectures.- Multi–CMP Module System Based on a Look-Ahead Configured Global Network.- Empirical Analysis of Parallelism Overheads on CMPs.- An Implementation of Parallel 3-D FFT with 2-D Decomposition on a Massively Parallel Cluster ofMulti-core Processors.- Introducing a Performance Model for Bandwidth-Limited Loop Kernels.

Caracteristici

Up-to-date results Fast track conference proceedings State-of-the-art report

Descriere

Wearepleasedtopresenttheproceedingsofthe8thInternationalConferenceon Parallel Processing and Applied Mathematics PPAM 2009, which was held in Wroc law, Poland, September 13 16, 2009. It was organized by the Department ofComputer andInformationSciencesof theCzestochowaUniversity ofTechno- logy, withthehelpoftheWroc lawUniversityofTechnology, FacultyofComputer Science and Management. The main organizer was Roman Wyrzykowski. PPAM is a biennial conference. Seven previous events have been held in di'erentplacesinPolandsince1994.Theproceedingsofthelastfourconferences havebeenpublishedbySpringerintheLectureNotes in Computer Science series (Nal ecz ow, 2001, vol.2328;Czestochowa,2003, vol.3019;Poznan, 2005, vol.3911; Gdan sk, 2007, vol. 4967). The PPAM conferences have become an international forum for exchanging ideasbetweenresearchersinvolvedinparallelanddistributedcomputing, incl- ing theory and applications, as well as applied and computational mathematics. The focus of PPAM 2009 was on models, algorithms, and software tools which facilitate e'cient and convenient utilization of modern parallel and distributed computing architectures, as well as on large-scale applications. Thismeeting gatheredmorethan210participantsfrom 32countries.A strict refereeing process resulted in the acceptance of 129 contributed presentations, while approximately46% of the submissionswere rejected. Regular tracksof the conference covered such important ?elds of parallel/distributed/grid computing and applied mathematics as: Parallel/distributed architectures and mobile computing Numerical algorithms and parallel numerics Parallel and distributed non-numerical algorithms Tools and environments for parallel/distributed/grid computing Applications of parallel/distributed computing Applied mathematics and neural networks Plenary and Invited Speakers The plenary and invited talks were presented by: Srinivas Aluru from the Iowa State University (USA) Dominik Behr from AMD (USA) Ewa Deelman from the University of Southern California (USA) Jack Dongarra from the University of Tennessee and Oak Ridge National"