GridCoord DoW



Yüklə 0,53 Mb.
səhifə22/22
tarix27.10.2017
ölçüsü0,53 Mb.
#15514
1   ...   14   15   16   17   18   19   20   21   22

Targeted audience




Intended target

Grid researchers

Other scientists

Industrials

Others

Which specific application domains does it target?












Are you aware of applications developed by other with it?

Yes

No







Examples of such applications












References












Feel free to add comments or suggestions












Please place me on your mailing list:














Grid Middleware database


Giving a complete dump of the whole base would take something like 20 pages, written in very small font. Instead, please use the search interface offered on the web, which allows seeing all the entries, in short mode, to compare them with each other, or in full mode, to see all the detail of a given entry. The address is http://www-sop.inria.fr/oasis/GridCoord/search-middleware.php

Here is a screenshot of that interface:




Here is a list of the middleware entered, with only part of the information which is available. We only show here the names, functionalities and application domain. The reader interested by more will refer to the previously mentioned web page.




Company name

Middleware name

Functionality

Application domain

INRIA

ProActive

Super middleware with security, mobility, group communication and more features.

ProActive is a 100 % Java library for parallel, distributed, and concurrent computing, also featuring mobility and security in a uniform framework. With a reduced set of simple primitives, ProActive provides a comprehensive API allowing to simplify the programming of applications that are distributed on Local Area Network (LAN), on cluster of workstations, or on Internet Grids.



Concurrent Grid applications

Universite catholique de Louvain

P2PS: Peer-to-Peer System

The P2PS library provides the developer with the ability of building and working with P2P overlay applications. It is providing the distributed peer-to-peer applications with a means to organize themselves in large scale structured overlay networks as well as providing them with management and communication primitives (one-to-one and one-to-many) whose costs evolve logarithmically with
the system size. P2PS offers different overlay communication primitives and services for P2P applications dealing with highly dynamic network topologies, and scalable with respect to the number of
nodes in the system. Although independent of the underlying peer-to-peer technology, P2PS currently only implements Tango. Tango is a peer-to-peer algorithm, that we developed, to better structure relative exponential networks to increase their scalability. It extends and improves Chord. P2PS was developed in Mozart/Oz, an advanced development platform for intelligent, distributed applications.

Large scale collaborative applications, Deployable network services

Fujitsu Laboratories

Unicore

UNICORE provides seamless access to applications accessible on various supercomputing systems. A sophisticated security model allows for a flexible authorisation model without intrusive adaptations to site-specific security policies.

Mostly scientific, simulations

Belfast e-Science Centre

GeneGrid Data Manager

Integration of public ally available biological data available in relational and flat file format into a grid infrastructure.

Database Access Database Inte

HLRS

PACX-MPI

PACX-MPI is a middleware to seamlessly couple high-performance compute resources into one single-system image for MPI-standard compliant parallel applications making them run on a Computational Grid.

All MPI-compliant applications. The application programmer should be aware, that communication should be optimized for G

Belfast e-Science Centre

GeneGrid Application Manager

Integration of public ally available biological applications into a grid infrastructure.

Protein Prediction Sequence A

Belfast E-Science, Q

GEDDM

Grid enablement of existing data mining engines as well as providing grid access and conversion of unstructured Flat File data to a common output format for further mining.

Data mining applications

Belfast eScience centre

Gridcast

- Using a Grid Architecture to distribute programmes between broadcast sites, concentrating initially on recorded material
- Using a Grid Architecture to monitor and facilitate programme production
- Using a Grid Architecture to facilitate access and use of broadcasting resources in television programme production







Company name

Middleware name

Functionality

Application domain

AIST

Ninf-G

Ninf-G is a reference implementation of Grid RPC system using the Globus Toolkit. Ninf-G provides Grid RPC APIs which are discussed for the standardization at the Advanced Programming Models Research Group of the Global Grid Forum. The details of the standardization of the Grid RPC APIs is reported on the GGF Working Group Document.

Scientific computing

ChinaGrid

CGSP







Zuse Institute Berlin

Information Providers

Distributing compute jobs to Grid resources, e.g. clusters, supercomputers or workstations, requires the discovery of resources that match the job's requirements. Resources advertise themselves by reporting their system properties and status to meta data services. So-called, Information Providers fed these meta data services by retrieving the necessary data from underlying cluster batch systems and configuration values.

--

KTH/PDC Stockholm

SweGrid Accounting System (SGAS)

Real-time resource quota enforcement, account management, and resource usage tracking

High Performance Computing

HLRS

MARMOT

MARMOT is a library that is linked to the MPI-application in addition to the existing MPI-library and that allows a detailed analysis of this application at runtime. Currently, the complete MPI-1.2 standard is supported. MARMOT generates a human-readable log file:

* Violations of the MPI-standard are reported as error.


* Unusual behaviour or possible problems is reported as warnings.
* Notes are displayed when harmless but remarkable behaviour occurs.
* The MPI-calls are traced on each node throughout the whole application.
* When detecting a deadlock the last few calls (as configured by the user) can be traced back on each node.




Globus Alliance

Globus Toolkit Community Authorization Service

Building on GSI, the CAS component of the Globus Toolkit allows resource providers to specify course-grained access control policies in terms of communities as a whole, delegating fine-grained access control policy management to the community itself. Resource providers maintain ultimate authority over their resources but are spared day-to-day policy administration tasks (e.g. adding and deleting users, modifying user privileges).

Distributed collaboration in g

Globus Alliance

Globus Toolkit Community Authorization Service

Building on GSI, the CAS component of the Globus Toolkit allows resource providers to specify course-grained access control policies in terms of communities as a whole, delegating fine-grained access control policy management to the community itself. Resource providers maintain ultimate authority over their resources but are spared day-to-day policy administration tasks (e.g. adding and deleting users, modifying user privileges).

Distributed collaboration in g

Globus Alliance

Globus Toolkit Delegation Service

Building on the Grid Security Infrastructure (GSI) and the WSRF framework, the delegation service delegates user credentials for use by remote services.

Distributed collaboration in g

Globus Alliance

Globus Toolkit SimpleCA




Distributed collaboration in g

Zuse Institute Berlin

GridLab Metadata Service

Storage and querying of attribute based metadata of objects.




HLRS

FTM (File Transfer and Management)

A system for the uniform, secure, interactive Access, Transfer, and Management of informational resources in a network or Grid consisting of facilities at distributed Virtual Organizations. The extension of this system also supports computational workflows.

No specific application domain




Company name

Middleware name

Functionality

Application domain

Zuse-institute-Berlin

nsync

nsync is command-line tool for efficient data distribution and synchronization. Based on gossip theory it calculates a synchronization plan which takes the network topology into account. This plan will then be executed using bzip2 and rsync to increase the performance.

The tool is application domain

Facultad de Informatica (UPM)

MAPFS-Grid

MAPFS-Grid is a multiagent I/O architecture for data-intensive applications in a grid environment. Its main features are:
dynamic reconfiguration of the nodes, by means of the use of storage groups; access pattern and hints specification; and I/O caching and prefetching.

Data-intensive applications

Zuse Institute Berlin (ZIB)

GuiGen

GuiGen is a comprehensive set of tools for creating customized graphical user interfaces (GUIs). It draws from the concept of computing portals, which are here seen as interfaces to application-specific computing services for user communities. While GuiGen was originally designed for the use in computational grids, it can be used in client/server environments as well.

Compared to other GUI generators, GuiGen is more versatile and more portable. It can be employed in many different application domains and on different target platforms. With GuiGen, application experts (rather than computer scientists) are able to create their own individually tailored GUIs.



New interfaces to legacy codes

Imperial College London

ICENI

The goal within ICENI is to provide high-level abstractions for e-science (scientific computing) which will allow users to construct and define their own applications through a graphical composition tool integrated with distributed component repositories and to deliver this environment across a range of platforms and devices. The distributed component repositories will allow developers to contribute their software to the wider community and easily incorporate other work into their own components or applications. The ICENI middleware federates the underlying resources that enable the e-scientist to carry out their work by allowing sophisticated and extensible access and usage policies to be specified.

Scientific applications

INRIA

DIET (Distributed Interactive Engineering Toolbox)

The aim of the DIET project is to develop a set of tools to build computational servers. DIET provides a numerical simulation infrastructure, as it is a grid-oriented problem solving environment.

Simulation, bioinformatics, ...

INRIA

PadicoTM




Code coupling application on Grids

HLRS

COVISE

COVISE stands for COllaborative Visualization and Simulation Environment. It is an extendable distributed software environment to integrate simulations, postprocessing and visualization functionalities in a seamless manner. From the beginning COVISE was designed for collaborative working allowing engineers and scientists to spread on a network infrastructure. In COVISE an application is divided into several processing steps, which are represented by COVISE modules. These modules, being implemented as separate processes, can be arbitrarily spread across different heterogeneous machine platforms. Major emphasis was put on the usage of high performance infrastructures such as parallel and vector computers and fast networks. Thus COVISE can make optimal use of varying infrastructure characteristics.

Visualization VR AR Computational steering

INRIA

PaCO++

PaCO++ provides an implementation of the parallel object concept applied to CORBA. Its objectives are to allow a simple and efficient embedding of a SPMD code into a parallel CORBA object and to allow parallel communication flows and data redistribution during an operation invocation on such a parallel CORBA object.

Code coupling applications like multiphysics application.




Company name

Middleware name

Functionality

Application domain

Universidad Complutense de Madrid

GridWay

GridWay is a Globus based framework that allows an easier and more efficient execution of jobs in a submit and forget fashion. The GridWay framework automatically performs the steps involved in job submission, namely: resource discovery and selection; and job preparation, submission, monitoring, and termination. GridWay also watches over the efficient execution of each job.

General purpose

LIFO, Université d'Orléans

CARAML libraries

Libraries for declarative parallel programming in CAML or C++ with predictable and scalable performance. Library for parallel processing of relational queries with predictable and scalable performance.

Relational queries in databases, numerical computation, symbolic computation.

AIST, KEK, Tokyo Institute of

Gfarm

Gfarm provides a global virtual file system (Gfarm file system) for file sharing by integrating local file systems in a Grid. It also supports the parallel and distributed data computing feature by associating compute nodes with file servers.

All applications

Forschungszentrum Juelich

UNICORE

Vertically integrated Grid software with integrated end-to-end security based on X.509 certificates, graphical User Interface for job creation and monitoring, extensible application support through plug-ins; no changes to existing applications required; support for complex multi-system, multi-site workflows, including conditional execution and controlled loops; full control and synchronisation by UNICORE and automatic transfers of data between systems and sites. Single sign-on; no changes required to established
administrative processes and policies; full site autonomy for authorisation of access to resources; Interfaces to available to many operating systems and batch system on execution servers; interoperable with Globus 2 and 3. OSGA compliance under development in EU project UniGrids.

UNICORE is not domain specific; It has been demonstrated in life sciences, engineering, computational chemistry, drug de

INRIA Futurs, Grand-Large Team

mpich-v

MPICH-V aims project aims to compare different fault-tolerant
protocols designed for MPI. The MPICH-V middleware provides a generic communication driver for MPICH-1.2.5 which includes a set of hooks sufficient to design efficient fault-tolerant protocols and compare their performances.

Fault Tolerance and HPC

INRIA

XtremWeb

XtremWeb is a research project belonging to light weight Grid systems. It’s a Free Open Source and non-profit software platform to explore scientific issues and applications of Desktop Grid, Global Computing and Peer to Peer distributed systems.
Like the other Distributed System Platforms, an XW platform uses a) remote resources (PCs, workstations, servers) connected to Internet or b) a pool of resources (PCs, workstations, servers) inside a LAN.
Participants of an XW platform cooperate by providing their CPU idle time.




Community Grids Lab, Indiana University

Narada

Brokering



The NaradaBrokering project at the Community Grids Lab is an open source project that researches fundamental issues pertaining to distributed middleware systems. These include, among others, issues of efficient routing, support for complex interactions, robustness, resilience, ordering, security and trust. NaradaBrokering aims to provide a unified messaging environment that integrates grid services, web services, peer-to-peer interactions and traditional middleware operations.




University of California

BOINC (Berkeley Open Infrastructure for Network Computing)

Complete system (server, client, web) for public-resource distributed computing and storage.







Company name

Middleware name

Functionality

Application domain

Consorzio CRMPA

GRASP

The Grid-based Application Service Provision (GRASP) project aims at studying, designing, developing and validating a new advanced system infrastructure for adding value and supporting innovative business models for Application Service Provision (ASP), based on the concepts of collaborative Virtual Organizations.

Building on top of existing OGSA compliant middleware (in the GRASP prototype implementation we used OGSI.NET) the key functionality of Location, Instantiation and Orchestration of Grid Services is extended to handle the Gateway concept:


- Location Subsystem: to enable a dynamic search of Grid Services based on functional, performance, technological and business related criteria (SLA).
- Instantiation Subsystem: to attend the properly instantiation of Grid Services performing Load Balancing and invocation of other related subsystems such as Accounting or SLA monitoring.
- Orchestration Subsystem: to support the ASP in the provision of new business services achieved by means of the composition and coordination of existing Grid Services. It implements the workflow that encapsulates the business logic of the ASP application (described as BPEL business processes).

Further business functionality is provided as part of the GRASP Framework by means of a number of services classified in different subsystems that address core business support operations including:


- SLA management Subsystem: to support a SLA management system including the use of SLA templates for negotiating service provision based on QoS criteria, and to monitor the fulfilment of contract associated to each Grid Service instances regarding QoS which are based on technical and business metrics in the vision of GRASP.
- Accounting Subsystem to perform the charging of service usage based on service related contracts between service users and service providers, obviously a must for ASPs. This GRASP subsystem works out the composite account of all services that are being executed on behalf of a client. It takes care of the collection of raw performance/resource data (shared with SLA monitoring); merging different costings and applying explicitly defined pricing algorithms.
- Security Subsystem: to offer flexible security perimeters in which GRASP infrastructure secures complete Application Service (multiple distributed component Grid Services). It handles securely life-time and addition and expulsion of component Grid service instances collectively executing a complete application.

Business (e-learning, e-health, e-business, etc.)

Research Centre Juelich

VISIT

VISIT is a library that supports the development of interactive simulations. It provides functions for establishing a connection between a simulation and visualization, exchanging data and eventually shutting down the connection again. VISIT provides support for AVS/Express and Perl/Tk visualization systems and C, Fortran, and Perl language bindings. An integration of VISIT into UNICORE is under construction in the UniGrids project.

Scientific and technical simulations that require or benefit from interactive visualisation/application steering

University of Westminster

GEMLCA

GEMLCA is a general solution in order to deploy existing legacy code applications written in any programming language as a Grid service

Making legacy codes available onto the Grid




Yüklə 0,53 Mb.

Dostları ilə paylaş:
1   ...   14   15   16   17   18   19   20   21   22




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©muhaz.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin