Started during summer 2004, aIOLi is a "French recipe" Blink to handle parallel I/O in a multi-application and distributed environment. It is based on popular parallel I/O concepts (collective and anticipatory I/O) and includes an advanced scheduling algorithm to improve global performance and provide fairness between applications.

aIOLi has been designed as a generic and universal I/O scheduler that can easily be plugged in any software project (there are only 3 functions in the API!)


Kadeploy is a fast and scalable deployment system for clusters and grids. It provides a set of tools for cloning, configuring (post installation) and managing a set of nodes. Currently it can successfully deploy Linux, *BSD, Windows and Solaris on x86 and 64 bits computers.


NFSP tries and implements a distributed NFS2 server. Two versions are available a user mode one based on the user mode NFS daemon and a kernel mode one based on the kernel mode NFS daemon. A node is chosen to act as server of metadata (and will run the *nfsd), other nodes have to be chosen to be I/O nodes and have to run a storage server (iodng). Every other node (but the metadata sever) may be a client, using a standard mount -t nfs.


The OAR batch scheduler is based on a database (MySQL), a script language (Perl) and an optional scalable administrative tool (component of Taktuk framework). It is composed of modules which interact only with database and are executed as independent programs. So formally, there is no API, the system is completely defined by the database schema. This approach eases the development of specific modules. Indeed, each module (such as schedulers) may be developed in any language having a database access library.


The Pajé generic tool provides interactive and scalable behavioral visualizations of parallel and distributed applications, helping to capture the dynamics of their executions; because of its genericity, it can be used unchanged in a large variety of contexts.


The main objective of PEPS is to facilitate the solution of large discrete event systems, in situations where classical methods fail. PEPS may be applied to the modelling of computer systems, telecommunication systems, road traffic, or manufacturing systems.


PSI (Perfect Simulator) is a simulation software of markovian models. It be able to simulate discrete and continuous time models to provide a perfect sampling of the stationary distribution or directly a sampling of functional of this distribution. The simulation kernel is based on the CFTP algorithm, and the internal simulation of transitions on the Aliasing method.


SimGrid is a toolkit that provides core functionalities for the simulation of distributed applications in heterogeneous distributed environments. The specific goal of the project is to facilitate research in the area of distributed and parallel application scheduling on distributed computing platforms ranging from simple network of workstations to Computational Grids.


Taktuk is a parallel and scalable remote execution tool for cluster. It works by propagating the execution of a parallel program on all target nodes, using standard remote execution protocols (rsh, ssh, etc...). Remote call scheduling automatically adapts its behavior to the remote execution protocol used, and to the load of the network and remote hosts.


FlowVR eases development and execution of virtual reality applications distributed on clusters and grids. FlowVR enables parallel code coupling and advanced coherency control between data flows.


Kaapi means Kernel for Adaptative, Asynchronous Parallel Interface. It is a C++ library that allows to mix, at very high performance, data flow graph unfolding operations with multithreaded computation.


FlowCert is a softwre that provides a distributed checkpoint/restart mechanism of a macro dataflow execution. It is used to: tolerate resources resilience; certification of global computation; backtrack scheduling decision.