2004
Conference article
Restricted
Targeting heterogeneous architectures in ASSIST: experimental results
Aldinucci M, Campa S, Coppola M, Magini S, Pesciullesi P, Potiti L, Ravazzolo R, Torquati M, Zoccolo C
We describe how the ASSIST parallel programming environment can be used to run parallel programs on collections of heterogeneous workstations and evaluate the scalability of one task-farm real application and a data-parallel benchmark, comparing the actual performance figures measured when using homogeneous and heterogeneous workstation clusters. We describe also the ASSIST approach to heterogeneous distributed shared memory and provide preliminary performance figures of the current implementation.
Aldinucci M, Campa S, Coppola M, Magini S, Pesciullesi P, Potiti L, Ravazzolo R, Torquati M, Zoccolo C
We describe how the ASSIST parallel programming environment can be used to run parallel programs on collections of heterogeneous workstations and evaluate the scalability of one task-farm real application and a data-parallel benchmark, comparing the actual performance figures measured when using homogeneous and heterogeneous workstation clusters. We describe also the ASSIST approach to heterogeneous distributed shared memory and provide preliminary performance figures of the current implementation.
2003
Conference article
Restricted
ASSIST demo: an high level, high performance, portable, structured parallel programming environment at work
Aldinucci M, Campa S, Ciullo P, Coppola M, Danelutto M, Pesciullesi P, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
This work summarizes the possibilities offered by parallel programming environment ASSIST by outlining some of the features that will be demonstrated at the conference demo session. We'll substantially show how this environment can be deployed on a Linux workstation network/cluster, how applications can be compiled and run using ASSIST and eventually, we'll discuss some ASSIST scalability and performance features. We'll also outline how the ASSIST environment can be used to target GRID architectures.
Aldinucci M, Campa S, Ciullo P, Coppola M, Danelutto M, Pesciullesi P, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
This work summarizes the possibilities offered by parallel programming environment ASSIST by outlining some of the features that will be demonstrated at the conference demo session. We'll substantially show how this environment can be deployed on a Linux workstation network/cluster, how applications can be compiled and run using ASSIST and eventually, we'll discuss some ASSIST scalability and performance features. We'll also outline how the ASSIST environment can be used to target GRID architectures.
See at:
CNR IRIS 
| CNR IRIS | link.springer.com
2003
Conference article
Restricted
The Implementation of ASSIST, an Environment for Parallel and Distributed Programming
Aldinucci M, Campa S, Ciullo P, Coppola M, Magini S, Pesciullesi P, Potiti L, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
We describe the implementation of ASSIST, a programming environment for parallel and distributed programs. Its coordination language is based of the parallel skeleton model, extended with new features to enhance expressiveness, parallel software reuse, software component integration and interfacing to external resources. The compilation process and the structure of the run-time support of ASSIST are discussed with respect to the issues introduced by the new characteristics, presenting an analysis of the first test results.
Aldinucci M, Campa S, Ciullo P, Coppola M, Magini S, Pesciullesi P, Potiti L, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
We describe the implementation of ASSIST, a programming environment for parallel and distributed programs. Its coordination language is based of the parallel skeleton model, extended with new features to enhance expressiveness, parallel software reuse, software component integration and interfacing to external resources. The compilation process and the structure of the run-time support of ASSIST are discussed with respect to the issues introduced by the new characteristics, presenting an analysis of the first test results.
2003
Contribution to book
Restricted
Hierarchical models and software tools for parallel programming
Coppola M, Schmollinger M
Hierarchically structured architectures are becoming more and more pervasive in the field of parallel and high performance computing. While memory hierarchies have been recognized for a long-time, only in the last years hierarchical parallel structures have gained importance, mainly as a result of the trend towards cluster architectures and high-performance application of computational grids.
Coppola M, Schmollinger M
Hierarchically structured architectures are becoming more and more pervasive in the field of parallel and high performance computing. While memory hierarchies have been recognized for a long-time, only in the last years hierarchical parallel structures have gained importance, mainly as a result of the trend towards cluster architectures and high-performance application of computational grids.
See at:
CNR IRIS | CNR IRIS | link.springer.com
2004
Conference article
Restricted
A parallel knowledge discovery system for customer profiling
Coppola M, Pesciullesi P, Ravazzolo R, Zoccolo C
We describe a parallel KDD architecture we are developing as part of an open-source based customer relationship management system, in the framework of the SAIB industrial research pro ject. The design of the prototype, leveraging on the features of the ASSIST programming environment, results in a high-performance parallel data mining core, tightly integrated with parallel data management and interfaced to business standard technologies and systems.
Coppola M, Pesciullesi P, Ravazzolo R, Zoccolo C
We describe a parallel KDD architecture we are developing as part of an open-source based customer relationship management system, in the framework of the SAIB industrial research pro ject. The design of the prototype, leveraging on the features of the ASSIST programming environment, results in a high-performance parallel data mining core, tightly integrated with parallel data management and interfaced to business standard technologies and systems.
See at:
CNR IRIS | CNR IRIS | www.springerlink.com
2008
Journal article
Restricted
Virtual organization support within a grid-wide operating system
Coppola M, Jegou Y, Matthews B, Morin C, Prieto L P, Sánchez Ó D, Yang E Y, Yu H
Despite grids' popularity, virtual organizations (VOs) have yet to become a commodity technology in modern computing environments due to the complexity of managing them and difficulty of assuring user and VO isolation. Here, the authors describe the VO management approach taken by XtreemOS, a new grid operating system with native support for VOs that supports a wide range of computing resources, from clusters to mobiles. They also discuss the requirements for the VO model and management within XtreemOS and intro duce an expandable VO model and a system architecture that supports it.Source: IEEE INTERNET COMPUTING, vol. 12 (issue 2), pp. 20-28
Coppola M, Jegou Y, Matthews B, Morin C, Prieto L P, Sánchez Ó D, Yang E Y, Yu H
Despite grids' popularity, virtual organizations (VOs) have yet to become a commodity technology in modern computing environments due to the complexity of managing them and difficulty of assuring user and VO isolation. Here, the authors describe the VO management approach taken by XtreemOS, a new grid operating system with native support for VOs that supports a wide range of computing resources, from clusters to mobiles. They also discuss the requirements for the VO model and management within XtreemOS and intro duce an expandable VO model and a system architecture that supports it.Source: IEEE INTERNET COMPUTING, vol. 12 (issue 2), pp. 20-28
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2004
Conference article
Restricted
A framework for experimenting with structured parallel programming environment design
Aldinucci M, Campa S, Ciullo P, Coppola M, Danelutto M, Pesciullesi P, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
ASSIST is a parallel programming environment aimed at providing programmers of complex parallel application with a suitable and effective programming tool. Being based on algoritmical skeletons and coordination languages technologies, the programming environment relieves the programmer from a number of cumbersome, error prone activities that are required when using traditional parallel programming environments. ASSIST has been specically designed to be easily customizable in order to experiment different implementation techniques, solutions, algorithms or back-ends any time new features are required or new technologies become available. In this work we discuss how this goal has been achieved and how the current ASSIST programming environment has been already used to experiment solutions not implemented in the first version of the tool.Source: ADVANCES IN PARALLEL COMPUTING. Dresden, Germany, September 2003
Aldinucci M, Campa S, Ciullo P, Coppola M, Danelutto M, Pesciullesi P, Ravazzolo R, Torquati M, Vanneschi M, Zoccolo C
ASSIST is a parallel programming environment aimed at providing programmers of complex parallel application with a suitable and effective programming tool. Being based on algoritmical skeletons and coordination languages technologies, the programming environment relieves the programmer from a number of cumbersome, error prone activities that are required when using traditional parallel programming environments. ASSIST has been specically designed to be easily customizable in order to experiment different implementation techniques, solutions, algorithms or back-ends any time new features are required or new technologies become available. In this work we discuss how this goal has been achieved and how the current ASSIST programming environment has been already used to experiment solutions not implemented in the first version of the tool.Source: ADVANCES IN PARALLEL COMPUTING. Dresden, Germany, September 2003
See at:
CNR IRIS | CNR IRIS | www.di.unipi.it
2005
Conference article
Restricted
An experiment with high performance components for grid applications
Coppola M, Pasquali M, Presti L, Vanneschi M
In this paper we describe an experiment in build- ing Grid-aware software components as basic blocks for high- performance, adaptive Grid computations. Within the Grid.it project we are working to the enhancement of the coordination language approach of the ASSIST parallel programming environment to support high-performance software components, that can react to the changes occurring on dynamic execution platforms. We are currently evaluating expressiveness and performance issues also by integrating ASSIST compilation tools with various component frameworks. In the paper we discuss results about a graphical application made up of four CCM components, each one produced by automatic encapsulation of a parallel program. We evaluate performance behaviour by comparing the composite application with the equivalent ASSIST one, on three different testbeds: homogeneous and heterogeneous clusters, and a small Grid over a WAN. We also report first results about an Application Manager component that applies a simple adaptive policy, reacting to pipeline unbalance, to vary the amount of employed computa- tional resources.
Coppola M, Pasquali M, Presti L, Vanneschi M
In this paper we describe an experiment in build- ing Grid-aware software components as basic blocks for high- performance, adaptive Grid computations. Within the Grid.it project we are working to the enhancement of the coordination language approach of the ASSIST parallel programming environment to support high-performance software components, that can react to the changes occurring on dynamic execution platforms. We are currently evaluating expressiveness and performance issues also by integrating ASSIST compilation tools with various component frameworks. In the paper we discuss results about a graphical application made up of four CCM components, each one produced by automatic encapsulation of a parallel program. We evaluate performance behaviour by comparing the composite application with the equivalent ASSIST one, on three different testbeds: homogeneous and heterogeneous clusters, and a small Grid over a WAN. We also report first results about an Application Manager component that applies a simple adaptive policy, reacting to pipeline unbalance, to vary the amount of employed computa- tional resources.
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2006
Conference article
Restricted
Parallel program/component adaptivity management
Coppola M, Aldinucci M, André F, Buisson J, Campa S, Danelutto M, Zoccolo C
Grid computing platforms require to handle dynamic behaviour of computing resources within complex parallel applications. We introduce a formalization of adaptive behaviour that separates the abstract model of the application from the implementation design. We exemplify the abstract adaptation schema on two applications, and we show how two quite different approaches to adaptivity, the ASSIST environment and the AFPAC framework, easily map to this common schema.
Coppola M, Aldinucci M, André F, Buisson J, Campa S, Danelutto M, Zoccolo C
Grid computing platforms require to handle dynamic behaviour of computing resources within complex parallel applications. We introduce a formalization of adaptive behaviour that separates the abstract model of the application from the implementation design. We exemplify the abstract adaptation schema on two applications, and we show how two quite different approaches to adaptivity, the ASSIST environment and the AFPAC framework, easily map to this common schema.
2006
Conference article
Open Access
A parallel data management layer for data mining
Coppola M, Pesciullesi P, Presti L, Ravazzolo R, Vanneschi M
We propose the design of a data management abstraction level to implement a full set of parallel KDD applications with minimal performance overhead and greater scalability than conventional DBMS, providing a high-level parallel API to be exploited by parallel and out-of-core data mining algorithms. We describe an existing prototype and report examples and first test results with mining algorithms.
Coppola M, Pesciullesi P, Presti L, Ravazzolo R, Vanneschi M
We propose the design of a data management abstraction level to implement a full set of parallel KDD applications with minimal performance overhead and greater scalability than conventional DBMS, providing a high-level parallel API to be exploited by parallel and out-of-core data mining algorithms. We describe an existing prototype and report examples and first test results with mining algorithms.
2007
Conference article
Restricted
The co-replication methodology and its application to structured parallel programs
Coppola M, Bertolli C, Zoccolo C
We introduce Co-Replication, a technique exploiting abstract properties of a computation to allow parallel replicas of a software module to cooperate, enhancing both the reliability and availability of the resulting component, and providing a flexible trade-off among the two properties. In Co-Replication a complete partial ordering is defined on the computation state. The formal expression of the state combination operation among replicas allows them to compute independently as a co-algorithm, and to exploit low-overhead, opportunistic strategies for spreading results and surviving to faults. Co-Replication suits structured parallel and component based programming, as it needs a high level description of the computation properties, and thus can ease exploitation of non fault-free, parallel platforms like large clusters and Grids. We describe the theoretical foundations of Co-Replication, and investigate the use of random gossiping strategies for the state combination. To show the applicability of the technique, we discuss the modelization of Master- Slave and task farm computations, and report test results over two applications.
Coppola M, Bertolli C, Zoccolo C
We introduce Co-Replication, a technique exploiting abstract properties of a computation to allow parallel replicas of a software module to cooperate, enhancing both the reliability and availability of the resulting component, and providing a flexible trade-off among the two properties. In Co-Replication a complete partial ordering is defined on the computation state. The formal expression of the state combination operation among replicas allows them to compute independently as a co-algorithm, and to exploit low-overhead, opportunistic strategies for spreading results and surviving to faults. Co-Replication suits structured parallel and component based programming, as it needs a high level description of the computation properties, and thus can ease exploitation of non fault-free, parallel platforms like large clusters and Grids. We describe the theoretical foundations of Co-Replication, and investigate the use of random gossiping strategies for the state combination. To show the applicability of the technique, we discuss the modelization of Master- Slave and task farm computations, and report test results over two applications.
See at:
dl.acm.org | CNR IRIS | CNR IRIS
2007
Conference article
Restricted
Virtual organization management in XtreemOS: an overview
Coppola M, Yang E Y, Matthews B, Lakhani A, Jegou Y, Morin C, Sanchez O D, Franke C, Robinson P, Hohl A, Scheuermann B, Vladusic D, Yu H, Qin A, Lee R, Focht E
XtreemOS aims to build and promote a Linux based operating system to provide native Virtual Organization (VO) support in the next generation Grids. XtreemOS takes a different approach from many existing Grid middleware by: first, recognizing the fundamental role of VO in Grid computing and hence taking VO support into account from the very beginning of our design; and, second, getting around the overheads brought by layers of existing Grid middleware by enabling native VO support in the Linux operating system. This paper presents our vision of VOs in a Grid operating system and describes various aspects of VO management in our system architecture, ranging from lifecycle management, application execution management, security, to node-level enforcement mechanisms in operating system.
Coppola M, Yang E Y, Matthews B, Lakhani A, Jegou Y, Morin C, Sanchez O D, Franke C, Robinson P, Hohl A, Scheuermann B, Vladusic D, Yu H, Qin A, Lee R, Focht E
XtreemOS aims to build and promote a Linux based operating system to provide native Virtual Organization (VO) support in the next generation Grids. XtreemOS takes a different approach from many existing Grid middleware by: first, recognizing the fundamental role of VO in Grid computing and hence taking VO support into account from the very beginning of our design; and, second, getting around the overheads brought by layers of existing Grid middleware by enabling native VO support in the Linux operating system. This paper presents our vision of VOs in a Grid operating system and describes various aspects of VO management in our system architecture, ranging from lifecycle management, application execution management, security, to node-level enforcement mechanisms in operating system.
2003
Contribution to book
Restricted
Parallel and distributed data mining through parallel skeletons and distributed objects
Coppola M, Vanneschi M
We consider the application of parallel programming environments to develop portable and efficient high performance data mining (DM) tools. We first assess the need of parallel and distributed DM applications, by pointing out the problems of scalability of some mining techniques and the need to mine large, eventually geographically distributed databases. We discuss the main issues of exploiting parallel and distributed computation for DM algorithms. A high-level programming language enhances the software engineering aspects of parallel DM, and it simplifies the problems of integration with existing sequential and parallel data management systems, thus leading to programming-efficient and high-performance implementations of applications. We describe a programming environment we have implemented that is based on the parallel skeleton model, and we examine the addition of object-like interfaces toward external libraries and system software layers. This kind of abstractions will be included in the forthcoming programming environment ASSIST. In the main part of the chapter, as a proof-of-concept we describe three well-known DM algorithms, STET Apriori, C4.5, and DBSCAN. For each problem, we explain the sequential algorithm and a structured parallel version, which is discussed and compared to parallel solutions found in the literature. We also discuss the potential gain in performance and expressiveness from the addition of external objects on the basis of the experiments we performed so far. We evaluate the approach with respect to performance results, design, and implementation considerations.
Coppola M, Vanneschi M
We consider the application of parallel programming environments to develop portable and efficient high performance data mining (DM) tools. We first assess the need of parallel and distributed DM applications, by pointing out the problems of scalability of some mining techniques and the need to mine large, eventually geographically distributed databases. We discuss the main issues of exploiting parallel and distributed computation for DM algorithms. A high-level programming language enhances the software engineering aspects of parallel DM, and it simplifies the problems of integration with existing sequential and parallel data management systems, thus leading to programming-efficient and high-performance implementations of applications. We describe a programming environment we have implemented that is based on the parallel skeleton model, and we examine the addition of object-like interfaces toward external libraries and system software layers. This kind of abstractions will be included in the forthcoming programming environment ASSIST. In the main part of the chapter, as a proof-of-concept we describe three well-known DM algorithms, STET Apriori, C4.5, and DBSCAN. For each problem, we explain the sequential algorithm and a structured parallel version, which is discussed and compared to parallel solutions found in the literature. We also discuss the potential gain in performance and expressiveness from the addition of external objects on the basis of the experiments we performed so far. We evaluate the approach with respect to performance results, design, and implementation considerations.
2006
Contribution to book
Restricted
ASSIST as a research framework for high-performance grid programming environments
Marco Aldinucci, Massimo Coppola, Marco Vanneschi, Corrado Zoccolo, Marco Danelutto
The research activity of our group at the Department of Computer Science, University of Pisa, is focused on programming models and environments for the development of high-performance multidisciplinary applications. The enabling computing platforms we are considering are complex distributed architectures, whose nodes are parallel machines of any kind, including PC/workstation clusters.
Marco Aldinucci, Massimo Coppola, Marco Vanneschi, Corrado Zoccolo, Marco Danelutto
The research activity of our group at the Department of Computer Science, University of Pisa, is focused on programming models and environments for the development of high-performance multidisciplinary applications. The enabling computing platforms we are considering are complex distributed architectures, whose nodes are parallel machines of any kind, including PC/workstation clusters.
See at:
CNR IRIS | CNR IRIS | www.springerlink.com
2006
Contribution to book
Restricted
Structured implementation of component based grid programming environments
Coppola M, Aldinucci M, Campa S, Danelutto M, Vanneschi M, Zoccolo C
The design, implementation and deployment of efficient high performance applications on Grids is usually a quite hard task, even in the case that modern and efficient grid middleware systems are used. We claim that most of the difficulties involved in such process can be moved away from programmer responsibility by following a structured programming model approach. The proposed approach relies on the development of a layered, component based execution environment. Each layer deals with distinct features and problems related to the implementation of GRID applications, exploiting the more appropriate techniques. Static optimizations are introduced in the compile layer, dynamic optimization are introduced in the run time layer, whereas modern grid middleware features are simply exploited using standard middleware systems as the final target architecture. We first discuss the general idea, then we discuss the peculiarities of the approach and eventually we discuss the preliminary results achieved in the GRID.it project, where a prototype high performance, component based, GRID programming environment is being developed using this approach.
Coppola M, Aldinucci M, Campa S, Danelutto M, Vanneschi M, Zoccolo C
The design, implementation and deployment of efficient high performance applications on Grids is usually a quite hard task, even in the case that modern and efficient grid middleware systems are used. We claim that most of the difficulties involved in such process can be moved away from programmer responsibility by following a structured programming model approach. The proposed approach relies on the development of a layered, component based execution environment. Each layer deals with distinct features and problems related to the implementation of GRID applications, exploiting the more appropriate techniques. Static optimizations are introduced in the compile layer, dynamic optimization are introduced in the run time layer, whereas modern grid middleware features are simply exploited using standard middleware systems as the final target architecture. We first discuss the general idea, then we discuss the peculiarities of the approach and eventually we discuss the preliminary results achieved in the GRID.it project, where a prototype high performance, component based, GRID programming environment is being developed using this approach.
2007
Contribution to book
Restricted
An abstract schema modeling adaptivity management
Coppola M, Aldinucci M, André F, Buisson J, Campa S, Danelutto M, Zoccolo C
Nowadays, component application adaptivity in Grid environments has been afforded in different ways, such those provided by the Dynaco/AFPAC framework and by the ASSIST environment. We propose an abstract schema that catches all the designing aspects a model for parallel component applications on Grid should define in order to uniformly handle the dynamic behavior of computing resources within complex parallel applications. The abstraction is validated by demonstrating how two different approaches to adaptivity, ASSIST and Dynaco/AFPAC, easily map to such schema.
Coppola M, Aldinucci M, André F, Buisson J, Campa S, Danelutto M, Zoccolo C
Nowadays, component application adaptivity in Grid environments has been afforded in different ways, such those provided by the Dynaco/AFPAC framework and by the ASSIST environment. We propose an abstract schema that catches all the designing aspects a model for parallel component applications on Grid should define in order to uniformly handle the dynamic behavior of computing resources within complex parallel applications. The abstraction is validated by demonstrating how two different approaches to adaptivity, ASSIST and Dynaco/AFPAC, easily map to such schema.
See at:
CNR IRIS | CNR IRIS | www.springerlink.com
2009
Conference article
Open Access
Highly available and scalable Grid services
Pierre G, Schütt T, Domaschka J, Coppola M
Researchers who build Grid computing infrastructures constantly face scalability issues, both at the system-level of the Grid's internals and at the user-level to support complex end-user applications. XtreemOS is an E.U. research project that aims at "Building and Promoting a Linux-based Operating System to Support Virtual Organizations for Next Generation Grids". One of the explicit goals of the project is to address scalability issues by abstracting these issues as much as possible from the internal implementation of the system. This is an ambitious goal, since in the most general case scalability issues must be addressed within each component of a distributed system. To a certain extent, it is possible to build scalable abstractions that allow other programmers to build system-level and application-level functionalities while giving less thought to scalability issues. This paper discusses a number of highly available and scalable Grid services that are being built to support this idea. They can be classified in three separate categories: (i) services to store/query structured data in a scalable fashion; (ii) services to communicate in a scalable fashion; (iii) services to (partially) hide the effects of scale.
Pierre G, Schütt T, Domaschka J, Coppola M
Researchers who build Grid computing infrastructures constantly face scalability issues, both at the system-level of the Grid's internals and at the user-level to support complex end-user applications. XtreemOS is an E.U. research project that aims at "Building and Promoting a Linux-based Operating System to Support Virtual Organizations for Next Generation Grids". One of the explicit goals of the project is to address scalability issues by abstracting these issues as much as possible from the internal implementation of the system. This is an ambitious goal, since in the most general case scalability issues must be addressed within each component of a distributed system. To a certain extent, it is possible to build scalable abstractions that allow other programmers to build system-level and application-level functionalities while giving less thought to scalability issues. This paper discusses a number of highly available and scalable Grid services that are being built to support this idea. They can be classified in three separate categories: (i) services to store/query structured data in a scalable fashion; (ii) services to communicate in a scalable fashion; (iii) services to (partially) hide the effects of scale.
See at:
dl.acm.org 
| CNR IRIS | CNR IRIS
2010
Conference article
Restricted
Information processing at work: on energy-aware algorithm design
Cisternino A, Ferragina P, Morelli D, Coppola M
It is common experience to upgrade firmware of mobile devices and obtain longer battery life, living proof of how software affects power consumption of a device. Despite this empirical observation, there is a lack for models and methodologies correlating computations with power consumption. In this paper we propose a methodology for conducting measures which result independent of the underlying system running the algorithm/software to be tested. Early experimental results are presented and discussed, showing that this methodology is robust and can be used in many settings. We thus adopt it to study the impact of computation and pattern of memory accesses onto the energy-profile of an algorithm when executed on different processors and architectures, thus achieving some surprising insights on green algorithm design.
Cisternino A, Ferragina P, Morelli D, Coppola M
It is common experience to upgrade firmware of mobile devices and obtain longer battery life, living proof of how software affects power consumption of a device. Despite this empirical observation, there is a lack for models and methodologies correlating computations with power consumption. In this paper we propose a methodology for conducting measures which result independent of the underlying system running the algorithm/software to be tested. Early experimental results are presented and discussed, showing that this methodology is robust and can be used in many settings. We thus adopt it to study the impact of computation and pattern of memory accesses onto the energy-profile of an algorithm when executed on different processors and architectures, thus achieving some surprising insights on green algorithm design.
2009
Conference article
Restricted
A high level development, modeling and simulation methodology for complex multicore Network Processors
Antichi G, Callegari C, Di Pietro A, Ficara D, Giordano S, Vitucci F, Meneghin M, Torquati M, Vanneschi M, Coppola M
Network processors (NPs) are attracting and powerful platforms for the fast development of high performance network applications. However, despite their greater flexibility and limited cost with respect to specialized hardware design, NP still face developers with significant difficulties. As they target complex and high performance applications, programmers are often forced to write assembly code in order to better exploit the hardware. In this paper we propose an approach to NP programming which is based on a three phase development methodology, and we apply it to Intel NPs of the IXP2XXX family. By exploiting a composition of software tools, a high level definition of the application is turned first into a distributed program, then into an NP prototype, and finally into an efficient NP executable. The methodology we describe takes advantage of the Assist technology, which allows for the porting, testing, modeling and profiling of parallel applications on a cluster of standard PCs. We developed a C library that acts as a communication layer, hiding the hardware details of NP programming and allowing for high performance code development. The ultimate goal of this approach is to let programmers write C code, exploiting Assist provided hints to perform functional debugging and performance analysis and to experiment with different parallel structures. The resulting code can be then directly compiled for the NP without modifications, largely reducing the overall coding effort.
Antichi G, Callegari C, Di Pietro A, Ficara D, Giordano S, Vitucci F, Meneghin M, Torquati M, Vanneschi M, Coppola M
Network processors (NPs) are attracting and powerful platforms for the fast development of high performance network applications. However, despite their greater flexibility and limited cost with respect to specialized hardware design, NP still face developers with significant difficulties. As they target complex and high performance applications, programmers are often forced to write assembly code in order to better exploit the hardware. In this paper we propose an approach to NP programming which is based on a three phase development methodology, and we apply it to Intel NPs of the IXP2XXX family. By exploiting a composition of software tools, a high level definition of the application is turned first into a distributed program, then into an NP prototype, and finally into an efficient NP executable. The methodology we describe takes advantage of the Assist technology, which allows for the porting, testing, modeling and profiling of parallel applications on a cluster of standard PCs. We developed a C library that acts as a communication layer, hiding the hardware details of NP programming and allowing for high performance code development. The ultimate goal of this approach is to let programmers write C code, exploiting Assist provided hints to perform functional debugging and performance analysis and to experiment with different parallel structures. The resulting code can be then directly compiled for the NP without modifications, largely reducing the overall coding effort.
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2013
Contribution to book
Restricted
Contrail: distributed application deployment under SLA in federated heterogeneous clouds
Cascella R G, Blasi L, Jegou Y, Coppola M, Morin C
Cloud computing market is in rapid expansion due to the opportunities to dynamically allocate a large amount of resources when needed and to pay only for their effective usage. However, many chal- lenges, in terms of interoperability, performance guarantee, and depend- ability, should still be addressed to make cloud computing the right solution for companies. In this chapter we first discuss these challenges and then we present three components developed in the framework of the Contrail project: Contrail federation; SLA manager; and Virtual Execu- tion Platform (VEP). These components provide solutions to guarantee interoperability in a cloud federation and to deploy distributed appli- cations over a federation of heterogeneous cloud providers. The key to success of our solutions is the possibility to negotiate performance and security guarantees for an application and then map them on the physical resources.Project(s): CONTRAIL
Cascella R G, Blasi L, Jegou Y, Coppola M, Morin C
Cloud computing market is in rapid expansion due to the opportunities to dynamically allocate a large amount of resources when needed and to pay only for their effective usage. However, many chal- lenges, in terms of interoperability, performance guarantee, and depend- ability, should still be addressed to make cloud computing the right solution for companies. In this chapter we first discuss these challenges and then we present three components developed in the framework of the Contrail project: Contrail federation; SLA manager; and Virtual Execu- tion Platform (VEP). These components provide solutions to guarantee interoperability in a cloud federation and to deploy distributed appli- cations over a federation of heterogeneous cloud providers. The key to success of our solutions is the possibility to negotiate performance and security guarantees for an application and then map them on the physical resources.Project(s): CONTRAIL
See at:
CNR IRIS | CNR IRIS | link.springer.com