Muutke küpsiste eelistusi

E-raamat: Grid Computing: Experiment Management, Tool Integration, and Scientific Workflows

  • Formaat: PDF+DRM
  • Sari: Lecture Notes in Computer Science 4340
  • Ilmumisaeg: 26-Apr-2007
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • Keel: eng
  • ISBN-13: 9783540692621
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 55,56 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Formaat: PDF+DRM
  • Sari: Lecture Notes in Computer Science 4340
  • Ilmumisaeg: 26-Apr-2007
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • Keel: eng
  • ISBN-13: 9783540692621
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Grid computing has become a topic of significant interest in the scientific community as a means of enabling application developers to aggregate resources scattered around the globe for solving large-scale scientific problems. This monograph addresses four critical software development aspects for the engineering and execution of applications on parallel and Grid architectures.A new directive-based language called ZEN is proposed for compact specification of wide value ranges of interest for arbitrary application parameters, including problem or machine sizes, array or loop distributions, software libraries, interconnection networks, or target execution machines. Based on the ZEN language, a novel experiment management tool called ZENTURIO is developed for automatic experiment management of large-scale performance and parameter studies on parallel and Grid architectures. This tool has been validated with respect to functionality and usefulness on several real-world parallel applications from various domains, including theoretical chemistry, photonics, finances, and numerical mathematics.Depending on the ZENTURIO experiment management architecture a generic optimization framework is built up that integrates general-purpose meta-heuristics for solving NP-complete performance and parameter optimization problems in an exponential search space specified using the ZEN experiment specification language. Finally a timely approach is proposed for modeling and executing scientific workflows in dynamic and heterogeneous Grid environments, introducing an abstract formal model for hierarchical representation of complex directed graph-based workflows.Thus this monograph contributes to various research areas related to integrated tool development for efficient engineering and high performance execution of scientific applications in Grid environments.

This monograph addresses four critical software development aspects for the engineering and execution of applications on parallel and Grid architectures.A new directive-based language called ZEN is proposed for compact specification of wide value ranges of interest for arbitrary application parameters. The monograph contributes to various research areas related to integrated tool development for efficient engineering and high performance execution of scientific applications in Grid environments.

Arvustused

From the reviews:









"Grid computing is a type of parallel computing. The book includes numerous current references, and also includes a helpful index. The book includes many tables and figures, some of which are in color. The monograph is a useful contribution to those research areas that are related to integrated tool development for effective engineering, and high-performance execution of scientific applications in grid environments. I recommend this work for theorists and practitioners in grid computing." (S. V. Nagaraj, ACM Computing Reviews, Vol. 49 (8), August, 2008)

1 Introduction
1
1.1 Motivation
2
1.1.1 Performance Tuning
2
1.1.2 Parameter Studies
3
1.1.3 Optimisation
3
1.1.4 Scheduling
3
1.1.5 Parametrisation Language
4
1.1.6 Instrumentation
4
1.1.7 Portability
5
1.1.8 Tool Interoperability
5
1.1.9 Grid Services
5
1.1.10 Scientific Workflows
6
1.2 Goals
6
1.2.1 Experiment Specification Language
6
1.2.2 Experiment Management Tool
7
1.2.3 Optimisation
8
1.2.4 Scientific Workflows
8
1.2.5 Service-Oriented Grid Architecture
9
1.2.6 Grid Services
10
1.3 Outline
10
2 Model
13
2.1 Introduction
13
2.2 Distributed Technology History
14
2.3 Web Services
15
2.3.1 Web Services Stack
16
2.3.2 Web Services Runtime Environment
18
2.4 Grid Security Infrastructure
19
2.5 Globus Toolkit
20
2.6 Grid Architectural Model
22
2.6.1 Machine Layer
22
2.6.2 Grid Services Layer
28
2.6.3 Application Layer
30
2.7 Summary
35
3 The ZEN Experiment Specification Language
37
3.1 Functionality and Use Cases
37
3.1.1 Shared Memory Application Scalability
38
3.1.2 ZEN Transformation System
39
3.1.3 Shared Memory Loop Scheduling
40
3.1.4 Distributed Processor Arrays
41
3.1.5 Distributed Memory Arrays
41
3.1.6 Work Distribution
43
3.1.7 Parameter Studies
43
3.2 Formal Language Specification
44
3.2.1 ZEN Set
44
3.2.2 ZEN Directives
49
3.2.3 ZEN Substitute Directive
50
3.2.4 Local Substitute Directive
51
3.2.5 Homonym ZEN Variables
51
3.2.6 ZEN Assignment Directive
53
3.2.7 Multi-dimensional Value Set
54
3.2.8 ZEN Constraint Directive
55
3.2.9 ZEN Performance Directive
59
3.2.10 Parameter Study Experiment
62
3.2.11 Experiment Generation Algorithm
62
3.2.12 Online Monitoring and Analysis
65
3.3 Summary
68
4 ZENTURIO Experiment Management Tool
69
4.1 User Portal Functionality
69
4.1.1 ZEN Editor
70
4.1.2 Experiment Preparation
71
4.1.3 Experiment Monitor
73
4.1.4 Application Data Visualiser
73
4.2 Performance Studies
76
4.2.1 Ocean Simulation
76
4.2.2 Linearised Augmented Plane Wave
79
4.2.3 Three-Dimensional Particle-in-Cell
84
4.2.4 Benders Decomposition
86
4.2.5 Three-Dimensional FFT Benchmarks
89
4.3 Parameter Studies
94
4.3.1 Backward Pricing
94
4.4 Architecture
105
4.4.1 Experiment Generator
107
4.4.2 Experiment Executor
108
4.4.3 Experiment State Transition Diagram
110
4.4.4 Experiment Data Repository
110
4.5 Summary
111
5 Tool Integration
113
5.1 Architecture
114
5.2 Interoperable Tool Set
116
5.2.1 Object Code Browser
117
5.2.2 Function Profiler (Z_prof)
117
5.2.3 Function Tracer (Z_trace)
118
5.2.4 Function Coverager (Z_cov)
119
5.2.5 Sequential Debugger (Z_debug)
121
5.2.6 Memory Allocation Tool (ZJVIAT)
121
5.2.7 Resource Tracker (ZRT2)
122
5.2.8 Deadlock Detector (Z_deadlock)
122
5.3 Tool Interoperability
122
5.3.1 Classification
122
5.3.2 Interaction with a Browser
123
5.3.3 Performance Steering
124
5.3.4 Just-in-Time Debugging
126
5.3.5 Interaction with a Debugger
127
5.4 The Monitoring Layer
128
5.4.1 Dynamic Instrumentation
128
5.4.2 The Process Manager
130
5.4.3 Dynamic Instrumentation of MPI Applications
134
5.5 The Grid Services Layer
136
5.5.1 Web Application and Services Platform (WASP)
138
5.5.2 Service Repository
139
5.5.3 Abstract Grid Service
140
5.5.4 Factory
142
5.5.5 Registry
143
5.5.6 WSDL Compatibility
144
5.5.7 Dynamic Instrumentor
144
5.5.8 Aggregator
145
5.6 Event Framework
146
5.6.1 Representation
146
5.6.2 Implementation
149
5.6.3 Filters
151
5.7 Firewall Management
151
5.8 WASP Versus GT3 Technology Evaluation
152
5.8.1 Stub Management
153
5.8.2 Service Lifecycle
154
5.8.3 UDDI-Based Service Repository
155
5.8.4 Service Data
155
5.8.5 Events
155
5.8.6 Registry
156
5.8.7 Security
159
5.8.8 Grid Service Throughput
160
5.8.9 Comparison
163
5.9 Summary
164
6 Optimisation Framework
165
6.1 Workflow Scheduling
167
6.1.1 Schedule Dependencies
169
6.1.2 Objective Function
170
6.2 Genetic Search Engine
174
6.2.1 Initial Population
175
6.2.2 Selection
177
6.2.3 Crossover
177
6.2.4 Mutation
178
6.2.5 Elitist Model
178
6.2.6 Fitness Scaling
179
6.2.7 Convergence Criterion
180
6.3 Genetic Workflow Scheduling
180
6.3.1 WIEN2k
180
6.4 Throughput Scheduling
192
6.5 Performance Tuning of Parallel Applications
194
6.5.1 Parallel Applications on the Grid
195
6.6 Summary
201
7 Scientific Grid Workflows
203
7.1 Workflow Model
204
7.1.1 Computational Activity
205
7.1.2 Control Flow Dependencies
206
7.1.3 Data Flow Dependencies
207
7.1.4 Conditional Activity
207
7.1.5 Parallel Loop Activity
208
7.1.6 Sequential Loop Activity
211
7.1.7 Workflow Activity
213
7.2 Scheduler
214
7.2.1 Workflow Converter
911
7.2.2 Scheduling Engine
220
7.2.3 Layered Partitioning
226
7.2.4 W1EN2k
227
7.2.5 Invmod
231
7.3 Enactment Engine
235
7.3.1 -Workflow Partitioning
236
7.3.2 Control Flow Management
241
7.3.3 Data Flow Management
242
7.3.4 Virtual Single Execution Environment
293
7.3.5 Workflow Steering
244
7.3.6 Fault Tolerance
248
7.3.7 WIEN2k Execution Experiments
253
7.3.8 Steering Experiments
255
7.4 Overhead Analysis
260
7.4.1 Experiments
263
7.5 Summary
269
8 Related Work
271
8.1 Experiment Management
271
8.2 Performance Study
271
8.3 Parameter Study
273
8.4 Optimisation and Scheduling
273
8.5 Tool Integration
274
8.5.1 Scientific Workflows
276
9 Conclusions
279
9.1 Contributions
279
9.1.1 Experiment Specification
279
9.1.2 Experiment Management
280
9.1.3 Optimisation
281
9.1.4 Tool Integration Design
281
9.1.5 Web Services for the Grid
283
9.1.6 Scientific Workflows
283
10 Appendix 285
10.1 Notations
285
10.2 Code Regions
288
10.3 Abbreviations
289
10.4 Performance Metrics
292
References 297
Index 311