Cantitate/Preț
Produs
Total produse
Vezi coșul
Network and Parallel Computing: IFIP International Conference, NPC 2010, Zhengzhou, China, September 13-15, 2010, Proceedings de Chen Ding

Network and Parallel Computing: IFIP International Conference, NPC 2010, Zhengzhou, China, September 13-15, 2010, Proceedings: Lecture Notes in Computer Science, cartea 6289

Editat de Chen Ding, Zhiyuan Shao, Ran Zheng
en Limba Engleză Paperback – 30 aug 2010

În analiza volumului Network and Parallel Computing, coordonat de Chen Ding și Zhiyuan Shao, observăm o metodologie riguroasă de selecție a cercetărilor, axată pe optimizarea performanței în sisteme distribuite și arhitecturi multi-core. Notăm cu interes că acest volum, parte a seriei Lecture Notes in Computer Science, nu se rezumă doar la aspecte teoretice, ci propune soluții concrete de design patterns pentru paralelizare, cum ar fi vectorizarea pentru Java sau optimizarea funcțiilor matriceale în bibliotecile BLAS. Structura este una progresivă, debutând cu discursuri cheie despre mediile de calcul virtuale bazate pe Internet și continuând cu sesiuni tehnice de mare densitate informațională. Prima sesiune se concentrează pe optimizarea la nivel de compilator și migrarea datelor în sisteme de stocare tier-ed, în timp ce secțiunile următoare explorează algoritmi paraleli pentru sisteme de crawling web și politici de scheduling eficiente energetic. Complementar lui High Performance Computing - HiPC 2008, care pune un accent major pe rețele de senzori și managementul resurselor, acest volum acoperă în profunzime nișa arhitecturilor Network on Chip (NoC), integrând procedurile atelierului IWNoC 2010. Putem afirma că diversitatea geografică a autorilor și procesul de recenzare (până la șase recenzii per lucrare) garantează o perspectivă globală asupra provocărilor din calculul paralel, de la execuția pe procesoare eterogene până la predicția performanței dispozitivelor de stocare.

Citește tot Restrânge

Din seria Lecture Notes in Computer Science

Preț: 63209 lei

Preț vechi: 79011 lei
-20%

Puncte Express: 948

Carte disponibilă

Livrare economică 22 mai-05 iunie

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783642156717
ISBN-10: 3642156711
Pagini: 504
Ilustrații: XII, 492 p. 275 illus.
Dimensiuni: 10 x 93 x 28 mm
Greutate: 0.75 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

Professional/practitioner

De ce să citești această carte

Recomandăm această resursă cercetătorilor și dezvoltatorilor care doresc să înțeleagă fundamentele arhitecturale ale calculului paralel modern. Cititorul câștigă acces la studii de caz empirice despre descompunerea LU pe procesoare Cell și strategii de optimizare JIT, esențiale pentru construirea unor sisteme software de înaltă performanță. Este un instrument valoros pentru cei care lucrează la intersecția dintre designul de procesor și optimizarea software.

Cuprins

Keynote Speech.- Building a Domain-Knowledge Guided System Software Environment to Achieve High-Performance of Multi-core Processors.- Internet-Based Virtual Computing Environment.- Session 1: Parallelization and Optimization.- Vectorization for Java.- Just-in-Time Compiler Assisted Object Reclamation and Space Reuse.- Optimization of Triangular Matrix Functions in BLAS Library on Loongson2F.- Exposing Tunable Parameters in Multi-threaded Numerical Code.- LU Decomposition on Cell Broadband Engine: An Empirical Study to Exploit Heterogeneous Chip Multiprocessors.- FDTM: Block Level Data Migration Policy in Tiered Storage System.- Session 2: Parallel Algorithms.- Scale-Adaptable Recrawl Strategies for DHT-Based Distributed Web Crawling System.- Power Efficient Scheduling for Hard Real-Time Systems on a Multiprocessor Platform.- Storage Device Performance Prediction with Selective Bagging Classification and Regression Tree.- Embedding Algorithms for Bubble-Sort, Macro-star, and Transposition Graphs.- An Efficient Simulation Algorithm for Cache of Random Replacement Policy.- DABGPM: A Double Auction Bayesian Game-Based Pricing Model in Cloud Market.- Session 3: Network.- NPA-BT: A Network Performance Aware BitTorrent Traffic Optimization Mechanism.- User Behavior Pattern Analysis and Prediction Based on Mobile Phone Sensors.- ServiceStore: A Peer-to-Peer Framework for QoS-Aware Service Composition.- Identifying Nearest Neighbor Nodes and Connectivity in Three-Dimensional Wireless Sensor Networks Using Poisson Point Field.- A Novel Trust Evaluation Model for Mobile P2P Networks.- Session 4: Parallelization and Optimization (Cluster).- Evaluating and Optimizing I/O Virtualization in Kernel-based Virtual Machine (KVM).- Distributed Stream Processing with DUP.- CCIndex: A Complemental Clustering Index on Distributed Ordered Tables for Multi-dimensional Range Queries.- Online Event Correlations Analysis in System Logs of Large-Scale Cluster Systems.- Differentiated Replication Strategy in Data Centers.- Efficient Pipelining Parallel Methods for Image Compositing in Sort-Last Rendering.- Session 5: GPU and Multicore.- memCUDA: Map Device Memory to Host Memory on GPGPU Platform.- Adaptive Line Size Cache for Irregular References on Cell Multicore Processor.- Software-Hardware Cooperative DRAM Bank Partitioning for Chip Multiprocessors.- Energy-Efficient Scheduling of Real-Time Periodic Tasks in Multicore Systems.- The Core Degree Based Tag Reduction on Chip Multiprocessor to Balance Energy Saving and Performance Overhead.- Session 6: Cloud and Grid Infrastructure.- Improve Throughput of Storage Cluster Interconnected with a TCP/IP Network Using Intelligent Server Grouping.- Evaluate the Performance and Scalability of Image Deployment in Virtual Data Center.- A Resource Discovery Algorithm in Mobile Grid Computing Based on IP-Paging Scheme.- JAMILA: A Usable Batch Job Management System to Coordinate Heterogeneous Clusters and Diverse Applications over Grid or Cloud Infrastructure.- User-Centric Privacy Preservation in Data-Sharing Applications.- Software Metrics Reduction for Fault-Proneness Prediction of Software Modules.- Session 7: Network on Chip.- A Methodology for Design of Unbuffered Router Microarchitecture for S-Mesh NoC.- A Worst Case Performance Model for TDM Virtual Circuit in NoCs.- Convex-Based DOR Routing for Virtualization of NoC.- MPSoC Architecture-Aware Automatic NoC Topology Design.- ERA: An Efficient Routing Algorithm for Power, Throughput and Latency in Network-on-Chips.

Caracteristici

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

Descriere

The IFIP International Conference on Network and Parallel Computing is an international conference, aimed at providing an exciting platform and forum for researchers and developers from academia and industry to present their latest research in the ?eld of parallel computing systems and applications. This year NPC received 89 submissions from authors in 11 countries. The papers were reviewed by a 51-member Program Committee, with 26 members from USA, 9 from mainland China, and the rest from Canada, Hong Kong, Taiwan, Korea, Japan, UK, andFrance.Eachpaperreceivedthreetosixreviews. Basedona totalof 287reviews, the ProgramCo-chairsaccepted papersinto two categories: Select papers: 23 papers passed the most stringent selection. Each paper is up to 15 pages in the conference proceedings. The acceptance rate for select papers is 25.8%. Regular papers: 11 additional papers are of su?cient publishable quality. Each paperisupto10pages. For the main conference, we invited three distinguished speakers: XiaodongZhang(OhioStateUniversity, USA): BuildingaDomain-Knowledge Guided System Software Environment to Achieve High Performance of MulticoreProcessors HuaiminWang(NationalUniversityofDefenseTechnology, China): Internet- Based Virtual Computing Environment Jesse Fang (Intel Labs, China) One workshop was held in conjunction with the NPC 2010 conference: the International Workshop on Network on Chip (IWNoC 2010). The workshop was chairedbyHuaxiGuandJiangXu.Theproceedingsoftheworkshopareincluded in this volume."