This book constitutes the thoroughly refereed joint post-workshop proceedings of three international events: the International Workshop on Highly Parallel Processing on a Chip, HPPC 2007, the UNICORE Summit 2007, and the Workshop on Virtualization/Xen in High-Performance Cluster and Grid Computing, VHPC 2007, held in Rennes, France, in August 2007 within the scope of Euro-Par 2007, the 13th International Conference on Parallel Computing.
The 8 papers of the HHPC 2007 workshop address all aspects of existing and emerging/envisaged multi-core processors with a significant amount of parallelism, especially to considerations on novel paradigms and models and the related architectural and linguistic support. The 8 papers presented at the UNICORE Summit 2007 show current developments and implementations of the UNICORE middleware system - a grid technology, providing a seamless, secure, and intuitive access to distributed Grid resources. UNICORE is a full-grown and well-tested Grid middleware system, which today is used in daily production worldwide. The 9 papers of the VHPC 2007 workshop present new models for implementing high-performance computing (HPC) architectures in both cluster and grid environments and cover areas including performance of virtual machine monitors (VMM), VMM architecture and implementation, cluster and grid VMM applications, management of VM-based computing resources, and hardware support for virtualization.
Author(s): Luc Bougé, Martti Forsell, Jesper Larsson Träff, Achim Streit, Wolfgang Ziegler, Michael Alexander, Stephen Childs
Edition: 1
Publisher: Springer
Year: 2008
Language: English
Pages: 243
front-matter......Page 1
HPPC 2007: Workshop on Highly Parallel Processing on a Chip......Page 15
Toward Realizing a PRAM-on-a-Chip Vision......Page 17
Societies of Cores and Their Computing Culture......Page 19
Motivation......Page 20
HTMOS Architecture......Page 21
Software......Page 22
Hardware......Page 24
Transactional Read......Page 25
Transactional Write......Page 26
Commit Transaction......Page 27
Conclusions and Future Work......Page 28
Introduction......Page 30
Iterator Classes......Page 31
Split Points......Page 33
Speculative Execution......Page 34
Examples......Page 35
Implementation on the Cell BE......Page 36
Experimental Results......Page 37
Combining Writes......Page 38
Conclusion......Page 39
Introduction......Page 40
Reconfigurable Cache......Page 41
Physical Implementation......Page 42
Experimental Methodology......Page 44
Application to Adaptive CMPs with Private L2 Cache......Page 46
Related Work......Page 47
Conclusions......Page 48
Introduction......Page 50
Requirements......Page 52
The Microgrid Multi-core Chip......Page 53
Memory Hierarchy Design......Page 54
On-Chip COMA Cache-Coherence Protocol......Page 56
Consistency Model......Page 57
Conclusion and Future Work......Page 58
Introduction......Page 61
Algorithms......Page 62
Parallel Bulk Insertion......Page 63
Analysis......Page 64
Dynamic Load-Balancing......Page 65
Experimental Results......Page 67
Conclusion and Future Work......Page 70
UNICORE Summit 2007......Page 71
Introduction......Page 72
Measuring the Overhead Imposed by the Middleware......Page 73
Comparison Across Different Middlewares......Page 74
Design of the Middleware Evaluation Tool......Page 75
Components of the Evaluation Tool......Page 76
Middleware Specific Details for the Test Tool......Page 77
Initial Test Scenarios......Page 78
Summary and Future Work......Page 80
Introduction......Page 82
Review......Page 84
The World Wide Web......Page 85
Grid Computing with UNICORE/w3......Page 87
Outlook and Summary......Page 89
Introduction......Page 92
Application Scenarios......Page 93
Workflow Processing......Page 97
Data Management......Page 98
Security Considerations......Page 100
The Chemomentum Testbed......Page 101
Conclusions and Outlook......Page 102
Introduction......Page 104
The UGSF Platform......Page 105
UGSF Architecture......Page 106
UGSF Streaming Server......Page 107
Generic Functionality......Page 108
Plugins......Page 111
Conclusions and Future Work......Page 112
Introduction......Page 114
Implementation of the Proposed Enhancement......Page 115
Validation Testing......Page 117
Towards Grid Middleware Interoperability......Page 118
The CONDOR-UNICORE Bridge......Page 119
Conclusion......Page 120
Introduction......Page 122
Evolution of Virtual Organization Membership Services......Page 123
Using SAML-Based VOMS with UNICORE 6......Page 125
VOMS as Attribute Authority for UNICORE......Page 126
Use Case Scenario: Role-Based Authorization in Collaborative Visualization and Steering Sessions......Page 127
Related Work......Page 128
Conclusions......Page 129
Introduction......Page 131
Related Work......Page 132
Virtual Organization Membership Service (VOMS)......Page 133
Shibboleth......Page 134
UNICORE Authentication and Authorisation Model......Page 135
The Integrated Architecture of VOMS and UNICORE......Page 136
UNICORE Integration with Shibboleth......Page 137
Necessary Changes of the Shibboleth-Framework......Page 138
Future Work......Page 139
Introduction......Page 141
Related Work and Background......Page 143
Workflow Framework System......Page 144
Design of a New Workflow......Page 145
Converting BPMN into a Workflow Language: BPMN2BPEL......Page 146
Workflow Grounding: BPEL Modeler......Page 147
The A-WARE Infrastructure......Page 148
References......Page 149
VHPC 2007: Workshop on Virtualization/Xen in High-Performance Cluster and Grid Computing......Page 151
Introduction......Page 152
Cluster-Based Network Emulation Systems......Page 153
FreeBSD Jails......Page 155
OpenVZ......Page 156
Virtualization for Node Multiplexing......Page 157
Virtualization Techniques for Link Multiplexing Compared......Page 158
Conclusions......Page 160
Virtual Computing Facilities......Page 162
Cybersar......Page 163
Physical Resources Management......Page 164
Virtual Resources Management......Page 165
Virtual Resources Implementation......Page 166
Preliminary Testbed......Page 168
Target Testbed......Page 169
Conclusions......Page 170
Introduction......Page 172
Architecture Overview......Page 173
Requirements Specification......Page 174
Scheduler......Page 175
Network Virtualization......Page 176
Parallel Application Use Case (parcomp)......Page 177
Internetworking Laboratory Use Case (netlab)......Page 178
Conclusion......Page 179
Introduction......Page 182
Related Work......Page 183
Overview......Page 184
Information Collector......Page 186
Test Bed......Page 188
Test Results......Page 189
Conclusion and Future Work......Page 190
Introduction......Page 193
Virtual Clusters......Page 194
Related Work......Page 195
XCM Client......Page 196
Xen Cluster Manager in Action......Page 197
Automatic Load Balancing......Page 198
Node Maintenance......Page 199
XCM Experiment......Page 200
References......Page 201
Introduction......Page 203
Xen Site Manager......Page 204
Deployment......Page 205
Management......Page 206
Monitoring......Page 208
Performance Evaluation......Page 209
Related Work......Page 210
Conclusions and Future Work......Page 211
Introduction......Page 213
SmartDomains, a Novel Approach......Page 214
Launching a Virtual Pool......Page 215
Describing a Virtual Pool......Page 216
Measurements and Future Work on Performance......Page 217
Administration: Specialize by Composing and Pre-configuring......Page 218
Development: Enriching SD by Plugging in New Logic and Composite Structures......Page 219
Conclusion......Page 220
Introduction......Page 222
VM Configuration......Page 223
Network Bootloader......Page 225
Putting It All Together......Page 227
Conclusion......Page 229
Introduction......Page 232
Acceleration Architecture......Page 233
Security......Page 235
Implementation for Solarstorm Controllers......Page 236
Accelerated Receive......Page 237
Performance......Page 238
Solarstorm and User-Level Networking......Page 239
Conclusion......Page 240
back-matter......Page 242
