updates

[mpi-energy.git] / paper.tex

diff --git a/paper.tex b/paper.tex
index 5ba8cc7b592dbd5c46aab3b6dfc2931b806e3b1c..61d95c6232a8e08cf3b0fff75438afee2ffdb09b 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -10,6 +10,9 @@
 \usepackage{colortbl}
 \usepackage{amsmath}
 
 \usepackage{colortbl}
 \usepackage{amsmath}
 

+\usepackage{url}
+\DeclareUrlCommand\email{\urlstyle{same}}
+

 \usepackage[autolanguage,np]{numprint}
 \renewcommand*\npunitcommand[1]{\text{#1}}
 
 \usepackage[autolanguage,np]{numprint}
 \renewcommand*\npunitcommand[1]{\text{#1}}
 


@@ -34,7 +37,7 @@
     University of Franche-Comté\\
     IUT de Belfort-Montbéliard, 19 avenue du Maréchal Juin, BP 527, 90016 Belfort cedex, France\\
     Fax  : +33~3~84~58~77~32\\
     University of Franche-Comté\\
     IUT de Belfort-Montbéliard, 19 avenue du Maréchal Juin, BP 527, 90016 Belfort cedex, France\\
     Fax  : +33~3~84~58~77~32\\

-    Email: \{jean-claude.charr,raphael.couturier,ahmed.fanfakh\_badri\_muslim,arnaud.giersch\}@univ-fcomte.fr
+    Email: \email{{jean-claude.charr,raphael.couturier,ahmed.fanfakh_badri_muslim,arnaud.giersch}@univ-fcomte.fr}

    }
   }
 
    }
   }
 


@@ -154,7 +157,7 @@ To maintain the performance of the parallel program , they
 set the  processor with the biggest load to the highest gear and then compute the scaling  factor values for the rest of the processors. Although this model was built for parallel architectures, it can be adapted  to distributed architectures by taking into account the communications. 
 The primary contribution of this paper is presenting a new online scaling factor selection method which has the following characteristics :
 \begin{enumerate}
 set the  processor with the biggest load to the highest gear and then compute the scaling  factor values for the rest of the processors. Although this model was built for parallel architectures, it can be adapted  to distributed architectures by taking into account the communications. 
 The primary contribution of this paper is presenting a new online scaling factor selection method which has the following characteristics :
 \begin{enumerate}

-\item Based on Rauber's analytical model to predict the energy consumption and the execution time of the application with different frequency gears. 
+\item Based on Rauber and Rünger analytical model to predict the energy consumption and the execution time of the application with different frequency gears. 

 \item Selects the frequency scaling factor for simultaneously optimizing energy reduction and maintaining performance.
 \item Well adapted to distributed architectures because it takes into account the communication time.
 \item Well adapted to distributed applications with imbalanced tasks.
 \item Selects the frequency scaling factor for simultaneously optimizing energy reduction and maintaining performance.
 \item Well adapted to distributed architectures because it takes into account the communication time.
 \item Well adapted to distributed applications with imbalanced tasks.


@@ -176,8 +179,8 @@ we consider execution of the synchronous tasks on distributed homogeneous
 platform. These tasks can exchange the data via synchronous message passing.
 \begin{figure*}[t]
   \centering
 platform. These tasks can exchange the data via synchronous message passing.
 \begin{figure*}[t]
   \centering

-  \subfloat[Sync. imbalanced communications]{\includegraphics[scale=0.67]{commtasks}\label{fig:h1}}
-  \subfloat[Sync. imbalanced computations]{\includegraphics[scale=0.67]{compt}\label{fig:h2}}
+  \subfloat[Sync. imbalanced communications]{\includegraphics[scale=0.67]{fig/commtasks}\label{fig:h1}}
+  \subfloat[Sync. imbalanced computations]{\includegraphics[scale=0.67]{fig/compt}\label{fig:h2}}

   \caption{Parallel tasks on homogeneous platform}
   \label{fig:homo}
 \end{figure*}
   \caption{Parallel tasks on homogeneous platform}
   \label{fig:homo}
 \end{figure*}


@@ -238,7 +241,7 @@ new frequency value~(\emph {P-state}) in the governor. The CPU governor is an
 interface driver supplied by the operating system's kernel to
 lower a core's frequency.  This factor reduces
 quadratically the dynamic power which may cause degradation in performance and thus, the increase of the static energy because the execution time is increased~\cite{36}. If the tasks are sorted according to their execution times before scaling in a descending order,   the total energy consumption model for a parallel
 interface driver supplied by the operating system's kernel to
 lower a core's frequency.  This factor reduces
 quadratically the dynamic power which may cause degradation in performance and thus, the increase of the static energy because the execution time is increased~\cite{36}. If the tasks are sorted according to their execution times before scaling in a descending order,   the total energy consumption model for a parallel

-homogeneous platform, as  presented by Rauber et al.~\cite{3}, can be written as a function of   the scaling factor \emph S,   as in EQ~(\ref{eq:energy}).
+homogeneous platform, as  presented by Rauber and Rünger~\cite{3}, can be written as a function of   the scaling factor \emph S,   as in EQ~(\ref{eq:energy}).

 
 \begin{equation}
   \label{eq:energy}
 
 \begin{equation}
   \label{eq:energy}


@@ -342,10 +345,10 @@ performance as follows:
 \begin{figure*}
   \centering
   \subfloat[Converted relation.]{%
 \begin{figure*}
   \centering
   \subfloat[Converted relation.]{%

-    \includegraphics[width=.4\textwidth]{file.eps}\label{fig:r1}}%
+    \includegraphics[width=.4\textwidth]{fig/file}\label{fig:r1}}%

   \qquad%
   \subfloat[Real relation.]{%
   \qquad%
   \subfloat[Real relation.]{%

-    \includegraphics[width=.4\textwidth]{file3.eps}\label{fig:r2}}
+    \includegraphics[width=.4\textwidth]{fig/file3}\label{fig:r2}}

   \label{fig:rel}
   \caption{The energy and performance relation}
 \end{figure*}
   \label{fig:rel}
   \caption{The energy and performance relation}
 \end{figure*}


@@ -468,10 +471,10 @@ time values. These scaling factors are computed by dividing the maximum
 frequency by the new one see EQ~(\ref{eq:s}). 
 \begin{figure*}[t]
   \centering
 frequency by the new one see EQ~(\ref{eq:s}). 
 \begin{figure*}[t]
   \centering

-  \includegraphics[width=.328\textwidth]{cg_per.eps}\hfill%
-  \includegraphics[width=.328\textwidth]{mg_pre.eps}\hfill%
- % \includegraphics[width=.4\textwidth]{bt_pre.eps}\qquad%
-  \includegraphics[width=.328\textwidth]{lu_pre.eps}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/cg_per}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/mg_pre}\hfill%
+ % \includegraphics[width=.4\textwidth]{fig/bt_pre}\qquad%
+  \includegraphics[width=.328\textwidth]{fig/lu_pre}\hfill%

   \caption{Comparing predicted to real execution time}
   \label{fig:pred}
 \end{figure*}
   \caption{Comparing predicted to real execution time}
   \label{fig:pred}
 \end{figure*}


@@ -491,7 +494,7 @@ respectively.
 Depending on EQ~(\ref{eq:energy}), we measure the energy consumption for all
 the NAS MPI programs while assuming the power dynamic with the highest frequency is equal to \np[W]{20} and
 the power static is equal to \np[W]{4} for all experiments. These power values were also
 Depending on EQ~(\ref{eq:energy}), we measure the energy consumption for all
 the NAS MPI programs while assuming the power dynamic with the highest frequency is equal to \np[W]{20} and
 the power static is equal to \np[W]{4} for all experiments. These power values were also

-used by Rauber and Rünger in~\cite{3}.   The results showed that the algorithm selected
+used by Rauber and Rünger in~\cite{3}.  The results showed that the algorithm selected

 different scaling factors for each program depending on the communication
 features of the program as in the plots~(\ref{fig:nas}). These plots illustrate that
 there are different distances between the normalized energy and the normalized
 different scaling factors for each program depending on the communication
 features of the program as in the plots~(\ref{fig:nas}). These plots illustrate that
 there are different distances between the normalized energy and the normalized


@@ -509,12 +512,12 @@ energy saving percent and the minimum performance degradation percent at the
 same time from all available scaling factors.
 \begin{figure*}[t]
   \centering
 same time from all available scaling factors.
 \begin{figure*}[t]
   \centering

-  \includegraphics[width=.328\textwidth]{ep.eps}\hfill%
-  \includegraphics[width=.328\textwidth]{cg.eps}\hfill%
-  \includegraphics[width=.328\textwidth]{sp.eps}
-  \includegraphics[width=.328\textwidth]{lu.eps}\hfill%
-  \includegraphics[width=.328\textwidth]{bt.eps}\hfill%
-  \includegraphics[width=.328\textwidth]{ft.eps}
+  \includegraphics[width=.328\textwidth]{fig/ep}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/cg}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/sp}
+  \includegraphics[width=.328\textwidth]{fig/lu}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/bt}\hfill%
+  \includegraphics[width=.328\textwidth]{fig/ft}

   \caption{Optimal scaling factors for the predicted energy and performance of NAS benchmarks}
   \label{fig:nas}
 \end{figure*}
   \caption{Optimal scaling factors for the predicted energy and performance of NAS benchmarks}
   \label{fig:nas}
 \end{figure*}


@@ -693,9 +696,9 @@ gives the highest positive energy to performance trade-offs while Rauber and Rü
 EP.
 \begin{figure*}[t]
   \centering
 EP.
 \begin{figure*}[t]
   \centering

-  \includegraphics[width=.328\textwidth]{compare_class_A.pdf}
-  \includegraphics[width=.328\textwidth]{compare_class_B.pdf}
-  \includegraphics[width=.328\textwidth]{compare_class_c.pdf}
+  \includegraphics[width=.328\textwidth]{fig/compare_class_A}
+  \includegraphics[width=.328\textwidth]{fig/compare_class_B}
+  \includegraphics[width=.328\textwidth]{fig/compare_class_C}

   \caption{Comparing our method to Rauber and Rünger methods}
   \label{fig:compare}
 \end{figure*}
   \caption{Comparing our method to Rauber and Rünger methods}
   \label{fig:compare}
 \end{figure*}


@@ -707,8 +710,8 @@ In the near future, we would like to adapt this scaling factor selection method
 
 
 \section*{Acknowledgment}
 
 
 \section*{Acknowledgment}

-\AG{Jean-Claude, why did you remove the Mésocentre here?}
-As a PhD student, M. Ahmed Fanfakh, would like to thank the University of
+Computations have been performed on the supercomputer facilities of the
+Mésocentre de calcul de Franche-Comté. As a PhD student, M. Ahmed Fanfakh, would like to thank the University of

 Babylon (Iraq) for supporting his work.
 
 % trigger a \newpage just before the given reference
 Babylon (Iraq) for supporting his work.
 
 % trigger a \newpage just before the given reference