From: Sébastien Miquée Date: Fri, 14 Jan 2011 13:26:02 +0000 (+0100) Subject: Version finale X-Git-Url: http://info.iut-bm.univ-fcomte.fr/pub/gitweb/gpc2011.git/commitdiff_plain/3baad0b0f8d5d6a502d6056167bba0511f418654?ds=sidebyside Version finale Quelques modifications et corrections mineures. Ajout des références manquantes. --- diff --git a/biblio.bib b/biblio.bib index 20457c0..b3e0bcf 100644 --- a/biblio.bib +++ b/biblio.bib @@ -420,3 +420,38 @@ Radiotherapy}, year = "2011" } + +@incollection {xwch, + author = {N. Abdennadher and R. Boesch}, + affiliation = {University of Applied Sciences, Geneva Switzerland}, + title = {Towards a Peer-To-Peer Platform for High Performance Computing}, + booktitle = {Advances in Grid and Pervasive Computing}, + series = {Lecture Notes in Computer Science}, + editor = {C\'{e}rin, Christophe and Li, Kuan-Ching}, + publisher = {Springer Berlin / Heidelberg}, + isbn = {}, + pages = {412-423}, + volume = {4459}, + year = {2007} +} + + +@article{xtremweb, +author = {G. Fedak and C. Germain and V. Neri and F. Cappello}, +title = {XtremWeb: A Generic Global Computing System}, +journal ={Cluster Computing and the Grid, IEEE International Symposium on}, +volume = {0}, +isbn = {0-7695-1010-8}, +year = {2001}, +pages = {582}, +publisher = {IEEE Computer Society}, +address = {Los Alamitos, CA, USA}, +} + + +@misc{seti, + AUTHOR = {}, + TITLE = {Seti@Home}, + + note = {\url{http://setiathome.ssl.berkeley.edu}} +} diff --git a/gpc2011.tex b/gpc2011.tex index f8cd63b..fc4e16a 100644 --- a/gpc2011.tex +++ b/gpc2011.tex @@ -107,30 +107,30 @@ subdomains. The decomposition has the advantage to significantly reduce the complexity of the target functions to approximate. Now, as there exist several classes of distributed/parallel -architectures (supercomputers, clusters, global computing...) we have -to choose the best suited one for the parallel Neurad application. -The volunteer (or global) computing model seems to be an interesting -approach. Here, the computing power is obtained by aggregating unused -(or volunteer) public resources connected to the Internet. For our -case, we can imagine for example, that a part of the architecture will -be composed of some of the different computers of the hospital. This -approach presents the advantage to be clearly cheaper than a more -dedicated approach like the use of supercomputers or -clusters. Furthermore and as we will see in the remainder, the studied -parallel algorithm fits well this computation model. +architectures (supercomputers, clusters, global computing\dots{}) we +have to choose the best suited one for the parallel Neurad +application. The volunteer (or global) computing model seems to be an +interesting approach. Here, the computing power is obtained by +aggregating unused (or volunteer) public resources connected to the +Internet. For our case, we can imagine for example, that a part of the +architecture will be composed of some of the different computers of +the hospital. This approach presents the advantage to be clearly +cheaper than a more dedicated approach like the use of supercomputers +or clusters. Furthermore and as we will see in the remainder, the +studied parallel algorithm fits well this computation model. The aim of this paper is to propose and evaluate a gridification of the Neurad application (more precisely, of the most time consuming -part, the learning step) using a volunteer computing approach. For this, -we focus on the XtremWeb-CH environment\cite{}. We choose this environment -because it tackles the centralized aspect of other global computing -environments such as XtremWeb\cite{} or Seti\cite{}. It tends to a -peer-to-peer approach by distributing some components of the -architecture. For instance, the computing nodes are allowed to -directly communicate. Experiments were conducted on a real global -computing testbed. The results are very encouraging. They exhibit an -interesting speed-up and show that the overhead induced by the use of -XtremWeb-CH is very acceptable. +part, the learning step) using a volunteer computing approach. For +this, we focus on the XtremWeb-CH environment\cite{xwch}. We choose +this environment because it tackles the centralized aspect of other +global computing environments such as XtremWeb\cite{xtremweb} or +Seti\cite{seti}. It tends to a peer-to-peer approach by distributing +some components of the architecture. For instance, the computing nodes +are allowed to directly communicate. Experiments were conducted on a +real global computing testbed. The results are very encouraging. They +exhibit an interesting speed-up and show that the overhead induced by +the use of XtremWeb-CH is very acceptable. The paper is organized as follows. In Section 2 we present the Neurad application and particularly its most time consuming part, i.e. the @@ -252,12 +252,20 @@ density. This part is out of the scope of this paper. The second step of the application, and the most time consuming, is the learning itself. This is the one which has been parallelized, using the XWCH environment. As exposed in the section 2, the -parallelization relies on a partitionning of the global -dataset. Following this partitionning all learning tasks are executed +parallelization relies on a partitioning of the global +dataset. Following this partitioning all learning tasks are executed in parallel independently with their own local data part, with no communication, following the fork/join model. Clearly, this computation fits well with the model of the chosen middleware. +\begin{figure}[ht] + \centering + \includegraphics[width=8cm]{figures/neurad_gridif} + \caption{The proposed Neurad gridification} + \label{fig:neurad_grid} +\end{figure} + + The execution scheme is then the following (see Figure \ref{fig:neurad_grid}): \begin{enumerate} @@ -267,7 +275,7 @@ The execution scheme is then the following (see Figure \item When a worker (W) is ready to compute, it requests a task to execute to the coordinator (Coord.); \item The coordinator assigns the worker a task. This last one retrieves the -application and its assigned data and so can start the computation. +application and its assigned data and so can start the computation; \item At the end of the learning process, the worker sends the result to a warehouse. \end{enumerate} @@ -276,12 +284,6 @@ weighted neural networks) and exploit them through a dose distribution process. -\begin{figure}[ht] - \centering - \includegraphics[width=8cm]{figures/neurad_gridif} - \caption{The proposed Neurad gridification} - \label{fig:neurad_grid} -\end{figure} \section{Experimental results} \label{sec:neurad_xp} diff --git a/xwch.tex b/xwch.tex index f3230e3..bdc94e8 100644 --- a/xwch.tex +++ b/xwch.tex @@ -10,8 +10,9 @@ The coordinator is the main component of the XWCH platform. It controls user access and schedules jobs to workers. It provides a web interface for managing jobs and users, and a set of web services. These are user service and worker/warehouse services -implemented using WSDL (Web Service Description Language) \cite{WebServ2002}, that simplifies -client development for languages that support it (and most popular programming languages do). +implemented using WSDL (Web Service Description Language) +\cite{WebServ2002}, that simplifies client development for languages +that support it (and most popular programming languages do). A worker is a Java daemon that runs on the user machine. Assumed to be volatile, the workers report periodically themselves to the