renomme un fichier figure

diff --git a/biblio.bib b/biblio.bib
index 6f6fd4c87e824e740f1cb5f70a69dd9a0a186aab..492d5ce4ae2c75fbe10efd505d6ecc8c9a648886 100644 (file)
--- a/biblio.bib
+++ b/biblio.bib
@@ -126,3 +126,24 @@ year = {1986},
 
 }
 
+
+
+@article{zkcgb+14:ij,
+inhal = {no},
+domainehal = {INFO:INFO_DC, INFO:INFO_CR, INFO:INFO_MO},
+equipe = {and},
+classement = {ACLI},
+impact-factor ={0.917},
+isi-acro = {J SUPERCOMPUT},
+author = {Ziane Khodja, L. and Couturier, R. and Giersch, A. and Bahi, J.},
+title = {Parallel sparse linear solver with {GMRES} method using minimization techniques of communications for {GPU} clusters},
+journal = {The journal of Supercomputing},
+pages = {200--224},
+volume = 69,
+number = 1,
+doi = {10.1007/s11227-014-1143-8},
+url = {http://dx.doi.org/10.1007/s11227-014-1143-8},
+publisher = {Springer},
+year = 2014,
+
+}
\ No newline at end of file

diff --git a/krylov_multi_reviewed.tex b/krylov_multi_reviewed.tex
index 02d1acaaa59d40a61b4227935bf1475445990db9..79345018f4a9c66e356086ab5e35794a212b5d93 100644 (file)
--- a/krylov_multi_reviewed.tex
+++ b/krylov_multi_reviewed.tex
@@ -84,16 +84,16 @@ thousands of cores are used.
 
 Traditional parallel iterative solvers are based on fine-grain computations that
 frequently  require  data exchanges  between  computing  nodes  and have  global
-synchronizations  that penalize  the  scalability. Particularly,  they are  more
-penalized on large  scale architectures or on distributed  platforms composed of
-distant  clusters interconnected  by  a high-latency  network.  It is  therefore
-imperative to develop coarse-grain based algorithms to reduce the communications
-in the  parallel iterative  solvers. Two possible  solutions consists  either in
-using  asynchronous  iterative  methods~\cite{ref18}  or in  using  multisplitting
-algorithms.  In this  paper,  we will  reconsider  the use  of a  multisplitting
-method. In opposition to traditional multisplitting method that suffer from slow
-convergence, as  proposed in~\cite{huang1993krylov},  the use of  a minimization
-process can drastically improve the convergence.\\
+synchronizations that penalize the scalability~\cite{zkcgb+14:ij}. Particularly,
+they are more penalized on large scale architectures or on distributed platforms
+composed of  distant clusters interconnected  by a high-latency network.   It is
+therefore  imperative to  develop coarse-grain  based algorithms  to  reduce the
+communications  in  the  parallel  iterative  solvers.  Two  possible  solutions
+consists either in using asynchronous iterative methods~\cite{ref18} or in using
+multisplitting  algorithms.  In  this paper,  we will  reconsider the  use  of a
+multisplitting method.  In opposition to traditional  multisplitting method that
+suffer from slow convergence,  as proposed in~\cite{huang1993krylov}, the use of
+a minimization process can drastically improve the convergence.\\
 
 
 %%% AJOUTE************************
@@ -380,7 +380,7 @@ respectively. The size of the Krylov subspace basis $S$ is fixed to 10 vectors.
 \begin{figure}[htbp]
 \centering
 \begin{tabular}{c}
-\includegraphics[width=0.8\textwidth]{weak_scaling_280k} \\ \includegraphics[width=0.8\textwidth]{weak_scaling_280K}\\
+\includegraphics[width=0.8\textwidth]{weak_scaling_280k} \\ \includegraphics[width=0.8\textwidth]{weak_scaling_280K2}\\
 \end{tabular}
 \caption{Weak scaling with 3 blocks of 4 cores each to solve a 3D Poisson problem with approximately 280K components per core}
 \label{fig:002}
@@ -476,7 +476,7 @@ to 115. So it is not different from GMRES.
 \begin{figure}[htbp]
 \centering
   \includegraphics[width=0.7\textwidth]{nb_iter_sec}
-\caption{Number of iterations per second  with the same parameters as in Table~\ref{tab1} (weak scaling) with only 2 blocks of cores}
+\caption{Number of iterations per second  with the same parameters as in Table~\ref{tab1} (weak scaling) with only  blocks of cores}
 \label{fig:01}
 \end{figure}
 

diff --git a/weak_scaling_280K.pdf b/weak_scaling_280K2.pdf
similarity index 100%
rename from weak_scaling_280K.pdf
rename to weak_scaling_280K2.pdf