Merge branch 'master' of ssh://info.iut-bm.univ-fcomte.fr/mpi-energy2

[mpi-energy2.git] / mpi-energy2-extension / Heter_paper.tex

diff --git a/mpi-energy2-extension/Heter_paper.tex b/mpi-energy2-extension/Heter_paper.tex
index 6b3fbb1fda6a1fd8cd7a382ab3fa909e466ba5fc..caa294f079fa8d0df9d0bd7c99606e1c44716840 100644 (file)
--- a/mpi-energy2-extension/Heter_paper.tex
+++ b/mpi-energy2-extension/Heter_paper.tex
@@ -214,7 +214,7 @@ scaling (DVFS) is one of them. It can be used to reduce the power consumption of
   The proposed algorithm is evaluated on a real grid, the grid'5000 platform, while
   running the NAS parallel benchmarks.  The experiments show that it reduces the
   energy consumption on average by \np[\%]{30} while  the performance  is only degraded
   The proposed algorithm is evaluated on a real grid, the grid'5000 platform, while
   running the NAS parallel benchmarks.  The experiments show that it reduces the
   energy consumption on average by \np[\%]{30} while  the performance  is only degraded

-  on average by \np[\%]{3}. Finally, the algorithm is 
+  on average by \np[\%]{3.2}. Finally, the algorithm is 

   compared to an existing method. The comparison results show that it outperforms the
   latter in terms of energy consumption reduction and performance.
 \end{abstract}
   compared to an existing method. The comparison results show that it outperforms the
   latter in terms of energy consumption reduction and performance.
 \end{abstract}


@@ -662,9 +662,9 @@ equation, as follows:
 \begin{figure}
   \centering
   \subfloat[Homogeneous cluster]{%
 \begin{figure}
   \centering
   \subfloat[Homogeneous cluster]{%

-    \includegraphics[width=.33\textwidth]{fig/homo}\label{fig:r1}} \hspace{2cm}%
+    \includegraphics[width=.4\textwidth]{fig/homo}\label{fig:r1}} \hspace{2cm}%

   \subfloat[Heterogeneous grid]{%
   \subfloat[Heterogeneous grid]{%

-    \includegraphics[width=.33\textwidth]{fig/heter}\label{fig:r2}}
+    \includegraphics[width=.4\textwidth]{fig/heter}\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}


@@ -999,16 +999,7 @@ Table \ref{tab:sc} shows the number of nodes used from each cluster for each sce
 \end{table}
 
 
 \end{table}
 
 

-\begin{figure}
-  \centering
-  \subfloat[The energy consumption by the nodes wile executing the NAS benchmarks over different scenarios    
-           ]{%
-    \includegraphics[width=.4\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{1cm}%
-  \subfloat[The execution times of the NAS benchmarks over different scenarios]{%
-    \includegraphics[width=.4\textwidth]{fig/time_scenarios.eps}\label{fig:time_sen}}
-  \label{fig:exp-time-energy}
-  \caption{The  energy consumption and execution time of NAS  Benchmarks over different scenarios}
-\end{figure}
+

 
 The NAS parallel benchmarks are executed over these two platforms
  with different number of nodes, as in Table \ref{tab:sc}. 
 
 The NAS parallel benchmarks are executed over these two platforms
  with different number of nodes, as in Table \ref{tab:sc}. 


@@ -1034,18 +1025,6 @@ However, the  execution times and the energy consumptions of EP and MG benchmark
  in both scenarios. Even when the number of nodes is doubled. On the other hand, the communications of the rest of the benchmarks increases when using long distance communications between two sites or increasing the number of computing nodes.
 
 
  in both scenarios. Even when the number of nodes is doubled. On the other hand, the communications of the rest of the benchmarks increases when using long distance communications between two sites or increasing the number of computing nodes.
 
 

-\begin{figure}
-  \centering
-  \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{%
-    \includegraphics[width=.33\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{0.08cm}%
-  \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{%
-    \includegraphics[width=.33\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{0.08cm}%
-    \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks  
-      over different scenarios]{%
-    \includegraphics[width=.33\textwidth]{fig/dist.eps}\label{fig:dist}}
-  \label{fig:exp-res}
-  \caption{The experimental results of different scenarios}
-\end{figure}

 
 The energy saving percentage is computed as the ratio between the reduced 
 energy consumption, equation (\ref{eq:energy}), and the original energy consumption,
 
 The energy saving percentage is computed as the ratio between the reduced 
 energy consumption, equation (\ref{eq:energy}), and the original energy consumption,


@@ -1059,8 +1038,31 @@ is exponentially related to the CPU's frequency value. On the other side, the in
 increase the communication times and thus produces less energy saving depending on the 
 benchmarks being executed. The results of the benchmarks CG, MG, BT and FT show more 
 energy saving percentage in one site scenario when executed over 16 nodes comparing to 32 nodes. While, LU and SP consume more energy with 16 nodes than 32 in one site  because their computations to communications ratio is not affected by the increase of the number of local communications. 
 increase the communication times and thus produces less energy saving depending on the 
 benchmarks being executed. The results of the benchmarks CG, MG, BT and FT show more 
 energy saving percentage in one site scenario when executed over 16 nodes comparing to 32 nodes. While, LU and SP consume more energy with 16 nodes than 32 in one site  because their computations to communications ratio is not affected by the increase of the number of local communications. 

+\begin{figure}
+  \centering
+  \subfloat[The energy consumption by the nodes wile executing the NAS benchmarks over different scenarios    
+           ]{%
+    \includegraphics[width=.4\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{1cm}%
+  \subfloat[The execution times of the NAS benchmarks over different scenarios]{%
+    \includegraphics[width=.4\textwidth]{fig/time_scenarios.eps}\label{fig:time_sen}}
+  \label{fig:exp-time-energy}
+  \caption{The  energy consumption and execution time of NAS  Benchmarks over different scenarios}
+\end{figure}

 
 
 
 

+\begin{figure}
+  \centering
+  \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{%
+    \includegraphics[width=.4\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{2cm}%
+  \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{%
+    \includegraphics[width=.4\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{2cm}%
+    \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks  
+      over different scenarios]{%
+    \includegraphics[width=.4\textwidth]{fig/dist.eps}\label{fig:dist}}
+  \label{fig:exp-res}
+  \caption{The experimental results of different scenarios}
+\end{figure}
+

 The energy saving percentage is reduced for all the benchmarks because of the long distance communications in the two sites 
 scenario, except for the   EP benchmark which has  no communications. Therefore, the energy saving percentage of this benchmark is 
 dependent on the maximum difference between the computing powers of the heterogeneous computing nodes, for example 
 The energy saving percentage is reduced for all the benchmarks because of the long distance communications in the two sites 
 scenario, except for the   EP benchmark which has  no communications. Therefore, the energy saving percentage of this benchmark is 
 dependent on the maximum difference between the computing powers of the heterogeneous computing nodes, for example 


@@ -1077,9 +1079,9 @@ The best energy saving percentage was obtained in the one site scenario with 16
 
 Figure \ref{fig:per_d} presents the performance degradation percentages for all benchmarks over the two scenarios.
 The performance degradation percentage for the benchmarks running on two sites  with
 
 Figure \ref{fig:per_d} presents the performance degradation percentages for all benchmarks over the two scenarios.
 The performance degradation percentage for the benchmarks running on two sites  with

-16 or 32  nodes is on average equal to 8\% or 4\% respectively. 
+16 or 32  nodes is on average equal to 8.3\% or 4.7\% respectively. 

 For this scenario, the proposed scaling algorithm selects smaller frequencies for the executions with 32 nodes  without significantly degrading their performance because the communication times are higher with 32 nodes which results in smaller  computations to communications ratio.  On the other hand, the performance degradation percentage  for the benchmarks running  on one site  with
 For this scenario, the proposed scaling algorithm selects smaller frequencies for the executions with 32 nodes  without significantly degrading their performance because the communication times are higher with 32 nodes which results in smaller  computations to communications ratio.  On the other hand, the performance degradation percentage  for the benchmarks running  on one site  with

-16 or 32  nodes is on average equal to 3\% or 10\% respectively. In opposition to the two sites scenario, when the number of computing nodes is increased in the one site scenario, the performance degradation percentage is increased. Therefore, doubling the number of computing 
+16 or 32  nodes is on average equal to 3.2\% or 10.6\% respectively. In opposition to the two sites scenario, when the number of computing nodes is increased in the one site scenario, the performance degradation percentage is increased. Therefore, doubling the number of computing 

 nodes when the communications occur in high speed network does not decrease the computations to 
 communication ratio. 
 
 nodes when the communications occur in high speed network does not decrease the computations to 
 communication ratio. 
 


@@ -1091,7 +1093,7 @@ when the communication times increase and vice versa.
 
 Figure \ref{fig:dist} presents the  distance percentage between the energy saving  and the performance degradation for each benchmark  over both  scenarios. The tradeoff distance percentage can be 
 computed as in equation \ref{eq:max}. The one site scenario with 16 nodes gives the best energy and performance 
 
 Figure \ref{fig:dist} presents the  distance percentage between the energy saving  and the performance degradation for each benchmark  over both  scenarios. The tradeoff distance percentage can be 
 computed as in equation \ref{eq:max}. The one site scenario with 16 nodes gives the best energy and performance 

-tradeoff, on average it is equal to  26\%. The one site scenario using both 16 and 32 nodes had better energy and performance 
+tradeoff, on average it is equal to  26.8\%. The one site scenario using both 16 and 32 nodes had better energy and performance 

 tradeoff comparing to the two sites scenario  because the former has high speed local communications 
 which increase the computations to communications ratio  and the latter uses long distance communications which decrease this ratio. 
 
 tradeoff comparing to the two sites scenario  because the former has high speed local communications 
 which increase the computations to communications ratio  and the latter uses long distance communications which decrease this ratio. 
 


@@ -1177,12 +1179,12 @@ in the figure \ref{fig:dist-mc}. These  tradeoff distance between energy consump
 \begin{figure}
   \centering
     \subfloat[The energy saving of running NAS benchmarks over one core and multicores scenarios]{%
 \begin{figure}
   \centering
     \subfloat[The energy saving of running NAS benchmarks over one core and multicores scenarios]{%

-    \includegraphics[width=.33\textwidth]{fig/eng_s_mc.eps}\label{fig:eng-s-mc}} \hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/eng_s_mc.eps}\label{fig:eng-s-mc}} \hspace{2cm}%

     \subfloat[The performance degradation of running NAS benchmarks over one core and multicores scenarios
       ]{%
     \subfloat[The performance degradation of running NAS benchmarks over one core and multicores scenarios
       ]{%

-    \includegraphics[width=.33\textwidth]{fig/per_d_mc.eps}\label{fig:per-d-mc}}\hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/per_d_mc.eps}\label{fig:per-d-mc}}\hspace{2cm}%

     \subfloat[The tradeoff distance of running NAS benchmarks over one core and multicores scenarios]{%
     \subfloat[The tradeoff distance of running NAS benchmarks over one core and multicores scenarios]{%

-    \includegraphics[width=.33\textwidth]{fig/dist_mc.eps}\label{fig:dist-mc}}
+    \includegraphics[width=.4\textwidth]{fig/dist_mc.eps}\label{fig:dist-mc}}

   \label{fig:exp-res}
   \caption{The experimental results of one core and multi-cores scenarios}
 \end{figure}
   \label{fig:exp-res}
   \caption{The experimental results of one core and multi-cores scenarios}
 \end{figure}


@@ -1203,11 +1205,12 @@ In these experiments, the class D of the NAS parallel benchmarks are executed ov
 \begin{figure}
   \centering
   \subfloat[The energy saving percentages for the nodes executing the NAS benchmarks over the three power scenarios]{%
 \begin{figure}
   \centering
   \subfloat[The energy saving percentages for the nodes executing the NAS benchmarks over the three power scenarios]{%

-    \includegraphics[width=.33\textwidth]{fig/eng_pow.eps}\label{fig:eng-pow}} \hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/eng_pow.eps}\label{fig:eng-pow}} \hspace{2cm}%

   \subfloat[The performance degradation percentages for the NAS benchmarks over the three power scenarios]{%
   \subfloat[The performance degradation percentages for the NAS benchmarks over the three power scenarios]{%

-    \includegraphics[width=.33\textwidth]{fig/per_pow.eps}\label{fig:per-pow}}\hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/per_pow.eps}\label{fig:per-pow}}\hspace{2cm}%

     \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks over the three power scenarios]{%
     \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks over the three power scenarios]{%

-    \includegraphics[width=.33\textwidth]{fig/dist_pow.eps}\label{fig:dist-pow}}
+      
+    \includegraphics[width=.4\textwidth]{fig/dist_pow.eps}\label{fig:dist-pow}}

   \label{fig:exp-pow}
   \caption{The experimental results of different static power scenarios}
 \end{figure}
   \label{fig:exp-pow}
   \caption{The experimental results of different static power scenarios}
 \end{figure}


@@ -1267,11 +1270,11 @@ presented in the figures \ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-
 \begin{figure}
   \centering
   \subfloat[The energy reduction induced by the Maxdist method and the EDP method]{%
 \begin{figure}
   \centering
   \subfloat[The energy reduction induced by the Maxdist method and the EDP method]{%

-    \includegraphics[width=.33\textwidth]{fig/edp_eng}\label{fig:edp-eng}} \hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/edp_eng}\label{fig:edp-eng}} \hspace{2cm}%

     \subfloat[The performance degradation induced by  the Maxdist method and the EDP method]{%
     \subfloat[The performance degradation induced by  the Maxdist method and the EDP method]{%

-    \includegraphics[width=.33\textwidth]{fig/edp_per}\label{fig:edp-perf}}\hspace{0.08cm}%
+    \includegraphics[width=.4\textwidth]{fig/edp_per}\label{fig:edp-perf}}\hspace{2cm}%

     \subfloat[The tradeoff distance between the energy consumption reduction and the performance for the Maxdist method and the  EDP method]{%
     \subfloat[The tradeoff distance between the energy consumption reduction and the performance for the Maxdist method and the  EDP method]{%

-    \includegraphics[width=.33\textwidth]{fig/edp_dist}\label{fig:edp-dist}}
+    \includegraphics[width=.4\textwidth]{fig/edp_dist}\label{fig:edp-dist}}

   \label{fig:edp-comparison}
   \caption{The comparison results}
 \end{figure}
   \label{fig:edp-comparison}
   \caption{The comparison results}
 \end{figure}


@@ -1300,7 +1303,7 @@ of the distributed iterative message passing application running over a grid arc
 To evaluate the proposed method on a real heterogeneous grid platform, it was applied on the  
  NAS parallel benchmarks   and the  class D instance was executed over the  grid'5000 testbed platform. 
  The experimental results showed that the algorithm reduces  on average 30\% of the energy consumption
 To evaluate the proposed method on a real heterogeneous grid platform, it was applied on the  
  NAS parallel benchmarks   and the  class D instance was executed over the  grid'5000 testbed platform. 
  The experimental results showed that the algorithm reduces  on average 30\% of the energy consumption

-for all the NAS benchmarks   while  only degrading by 3\% on average  the performance. 
+for all the NAS benchmarks   while  only degrading by 3.2\% on average  the performance. 

 The Maxdist algorithm was also evaluated in different scenarios that vary in the distribution of the computing nodes between different clusters' sites or \textcolor{blue}{between using one core and multi-cores per node} or in the values of the consumed static power. The algorithm selects different vector of frequencies according to the 
 computations and communication times ratios, and  the values of the static and measured dynamic powers of the CPUs. 
 Finally, the proposed algorithm was compared to another method that uses
 The Maxdist algorithm was also evaluated in different scenarios that vary in the distribution of the computing nodes between different clusters' sites or \textcolor{blue}{between using one core and multi-cores per node} or in the values of the consumed static power. The algorithm selects different vector of frequencies according to the 
 computations and communication times ratios, and  the values of the static and measured dynamic powers of the CPUs. 
 Finally, the proposed algorithm was compared to another method that uses