Euro-Par 2007 workshops : parallel processing : HPPC 2007, Unicore Summit 2007, and VHPC 2007, Rennes, France, August 28-31, 2007 : revised selected papers

Parallelanddistributedprocessing,althoughwithinthefocusofcomputerscience researchforalongtime,isgainingmoreandmoreimportanceinawidespectrum of applications. These proceedings aim to demonstrate the use of parallel and distributed processing concepts in di?erent application ?elds, and attempt to spark interest in novel research directions to advance the embracing model of high-performance computing research in general. The objective of these workshops is to speci?cally address researchers c- ing from university, industry and governmental research organizations and application-oriented companies, in order to close the gap between purely s- enti?c research and the applicability of the research ideas to real-life problems. Euro-Par is an annual series of international conferences dedicated to the promotionandadvancementofallaspectsofparallelanddistributedcomputing. The 2007 event was the 13th issue of the conference. Euro-Par has for a long time been eager to attract colocated events sharing the same goal of promoting the development of parallel and distributed computing, both as an industrial technique and an academic discipline, extending the frontier of both the state of the art and the state of the practice. Since 2006, Euro-Par o?ers researchersthe chance to colocate advanced technical workshops back-to-back with the main conference. This is for a mutual bene?t: the workshops can take advantage of all technical and social facilities which are set up for the conference, so that the organizational tasks are kept to a minimal level; the conference can rely on workshopstoexperimentwithspeci?careasofresearchwhicharenotyetmature enough, or too speci?c, to lead to an o?cial, full-?edged topic at the conference. Front Matter....Pages - Front Matter....Pages 1-1 HPPC 2007: Workshop on Highly Parallel Processing on a Chip....Pages 3-4 Toward Realizing a PRAM-on-a-Chip Vision....Pages 5-6 Societies of Cores and Their Computing Culture....Pages 7-7 Hardware Transactional Memory with Operating System Support, HTMOS....Pages 8-17 Auto-parallelisation of Sieve C++ Programs....Pages 18-27 Adaptive L2 Cache for Chip Multiprocessors....Pages 28-37 On-Chip COMA Cache-Coherence Protocol for Microgrids of Microthreaded Cores....Pages 38-48 Parallelization of Bulk Operations for STL Dictionaries....Pages 49-58 Front Matter....Pages 59-59 UNICORE Summit 2007....Pages 61-61 A Black-Box Approach to Performance Analysis of Grid Middleware....Pages 62-71 UNICORE/w3....Pages 72-81 Chemomentum - UNICORE 6 Based Infrastructure for Complex Applications in Science and Technology....Pages 82-93 Flexible Streaming Infrastructure for UNICORE....Pages 94-103 Extending UNICORE 5 Authentication Model by Supporting Proxy Certificate Profile Extensions....Pages 104-111 Using SAML-Based VOMS for Authorization within Web Services-Based UNICORE Grids....Pages 112-120 Attributes and VOs: Extending the UNICORE Authorisation Capabilities....Pages 121-130 A Business-Oriented Grid Workflow Management System....Pages 131-140 Front Matter....Pages 141-141 VHPC 2007: Workshop on Virtualization/Xen in High-Performance Cluster and Grid Computing....Pages 143-143 Virtualization Techniques in Network Emulation Systems....Pages 144-153 SOA Based Control Plane for Virtual Clusters....Pages 154-163 Front Matter....Pages 141-141 Grid Virtual Laboratory Architecture....Pages 164-173 Information Service of Virtual Machine Pool for Grid Computing....Pages 174-184 Virtual Cluster Management with Xen....Pages 185-194 Deploying and Managing Xen Sites with XSM....Pages 195-204 Xen Management with SmartFrog....Pages 205-213 Integrating Xen with the Quattor Fabric Management System....Pages 214-223 Getting 10 Gb/s from Xen: Safe and Fast Device Access from Unprivileged Domains....Pages 224-233 Back Matter....Pages - Parallelanddistributedprocessing, althoughwithinthefocusofcomputerscience researchforalongtime, isgainingmoreandmoreimportanceinawidespectrum of applications. These proceedings aim to demonstrate the use of parallel and distributed processing concepts in di?erent application?elds, and attempt to spark interest in novel research directions to advance the embracing model of high-performance computing research in general. The objective of these workshops is to speci?cally address researchers c- ing from university, industry and governmental research organizations and application-oriented companies, in order to close the gap between purely s- enti?c research and the applicability of the research ideas to real-life problems. Euro-Par is an annual series of international conferences dedicated to the promotionandadvancementofallaspectsofparallelanddistributedcomputing. The 2007 event was the 13th issue of the conference. Euro-Par has for a long time been eager to attract colocated events sharing the same goal of promoting the development of parallel and distributed computing, both as an industrial technique and an academic discipline, extending the frontier of both the state of the art and the state of the practice. Since 2006, Euro-Par o?ers researchersthe chance to colocate advanced technical workshops back-to-back with the main conference. This is for a mutual bene?t: the workshops can take advantage of all technical and social facilities which are set up for the conference, so that the organizational tasks are kept to a minimal level; the conference can rely on workshopstoexperimentwithspeci?careasofresearchwhicharenotyetmature enough, or too speci?c, to lead to an o?cial, full-?edged topic at the conference

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.

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