Improve typesetting of equations.

diff --git a/paper.tex b/paper.tex
index 2ec1b17003f37e79550c20350f3d13d55e782705..efe0e3e201b490c2748737b7d68fb4d873498a00 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -9,6 +9,7 @@
 \usepackage{subfig}
 \usepackage{listings}
 \usepackage{colortbl}
 \usepackage{subfig}
 \usepackage{listings}
 \usepackage{colortbl}

+\usepackage{amsmath}

 % \usepackage{sectsty}
 % \usepackage{titlesec}
 % \usepackage{secdot}
 % \usepackage{sectsty}
 % \usepackage{titlesec}
 % \usepackage{secdot}


@@ -148,8 +149,9 @@ amounts of data on each processor as an example see figure~(\ref{fig:h2}). In
 this case the fastest tasks have to wait at the synchronous barrier for the
 slowest tasks to finish their job. In both two cases the overall execution time
 of the program is the execution time of the slowest task as :
 this case the fastest tasks have to wait at the synchronous barrier for the
 slowest tasks to finish their job. In both two cases the overall execution time
 of the program is the execution time of the slowest task as :

-\begin{equation}  \label{eq:T1}
-  Program Time=MAX_{i=1,2,..,N} (T_i) \hfill
+\begin{equation}
+  \label{eq:T1}
+  \textit{Program Time} = \max_{i=1,2,\dots,N} T_i

 \end{equation}
 where $T_i$ is the execution time of process $i$.
 
 \end{equation}
 where $T_i$ is the execution time of process $i$.
 


@@ -160,21 +162,24 @@ dynamic and the static power. This general power formulation is used by many
 researchers see ~\cite{9,3,15,26}. The dynamic power of the CMOS processors
 $P_{dyn}$ is related to the switching activity $\alpha$, load capacitance $C_L$,
 the supply voltage $V$ and operational frequency $f$ respectively as follow :
 researchers see ~\cite{9,3,15,26}. The dynamic power of the CMOS processors
 $P_{dyn}$ is related to the switching activity $\alpha$, load capacitance $C_L$,
 the supply voltage $V$ and operational frequency $f$ respectively as follow :

-\begin{equation}  \label{eq:pd}
-  \displaystyle  P_{dyn} = \alpha . C_L . V^2 . f
+\begin{equation}
+  \label{eq:pd}
+  P_{dyn} = \alpha \cdot C_L \cdot V^2 \cdot f

 \end{equation}
 The static power $P_{static}$ captures the leakage power consumption as well as
 the power consumption of peripheral devices like the I/O subsystem.
 \end{equation}
 The static power $P_{static}$ captures the leakage power consumption as well as
 the power consumption of peripheral devices like the I/O subsystem.

-\begin{equation}  \label{eq:ps}
-  \displaystyle  P_{static}  = V . N . K_{design} . I_{leak}
+\begin{equation}
+  \label{eq:ps}
+  P_{static}  = V \cdot N \cdot K_{design} \cdot I_{leak}

 \end{equation}
 where V is the supply voltage, N is the number of transistors, $K_{design}$ is a
 design dependent parameter and $I_{leak}$ is a technology-dependent
 parameter. Energy consumed by an individual processor $E_{ind}$ is the summation
 of the dynamic and the static power multiply by the execution time for example
 see~\cite{36,15} .
 \end{equation}
 where V is the supply voltage, N is the number of transistors, $K_{design}$ is a
 design dependent parameter and $I_{leak}$ is a technology-dependent
 parameter. Energy consumed by an individual processor $E_{ind}$ is the summation
 of the dynamic and the static power multiply by the execution time for example
 see~\cite{36,15} .

-\begin{equation}  \label{eq:eind}
-  \displaystyle  E_{ind} = (P_{dyn} + P_{static} ) . T
+\begin{equation}
+  \label{eq:eind}
+  E_{ind} = ( P_{dyn} + P_{static} ) \cdot T

 \end{equation}
 The dynamic voltage and frequency scaling (DVFS) is a process that allowed in
 modern processors to reduce the dynamic power by scaling down the voltage and
 \end{equation}
 The dynamic voltage and frequency scaling (DVFS) is a process that allowed in
 modern processors to reduce the dynamic power by scaling down the voltage and


@@ -185,8 +190,9 @@ equation is used to study the change of the dynamic voltage with respect to
 various frequency values in~\cite{3}. The reduction process of the frequency are
 expressed by scaling factor \emph S. The scale \emph S is the ratio between the
 maximum and the new frequency as in EQ~(\ref{eq:s}).
 various frequency values in~\cite{3}. The reduction process of the frequency are
 expressed by scaling factor \emph S. The scale \emph S is the ratio between the
 maximum and the new frequency as in EQ~(\ref{eq:s}).

-\begin{equation}  \label{eq:s}
-  S=\:\frac{F_{max}}{F_{new}} \hfill  \newline
+\begin{equation}
+  \label{eq:s}
+  S = \frac{F_{max}}{F_{new}}

 \end{equation}
 The value of the scale \emph S is grater than 1 when changing the frequency to
 any new frequency value(\emph {P-state}) in governor. It is equal to 1 when the
 \end{equation}
 The value of the scale \emph S is grater than 1 when changing the frequency to
 any new frequency value(\emph {P-state}) in governor. It is equal to 1 when the


@@ -199,8 +205,11 @@ for any number of concurrent tasks develops by Rauber~\cite{3}. This model
 consider the two powers metric for measuring the energy of the parallel tasks as
 in EQ~(\ref{eq:energy}).
 
 consider the two powers metric for measuring the energy of the parallel tasks as
 in EQ~(\ref{eq:energy}).
 

-\begin{equation}  \label{eq:energy}
-  E= \displaystyle \;P_{dyn}\,.\,S_1^{-2}\;.\,(T_1+\sum\limits_{i=2}^{N}\frac{T_i^3}{T_1^2})+\;P_{static}\,.\,T_1\,.\,S_1\;\,.\,N
+\begin{equation}
+  \label{eq:energy}
+  E = P_{dyn} \cdot S_1^{-2} \cdot
+    \left( T_1 + \sum_{i=2}^{N} \frac{T_i^3}{T_1^2} \right) +
+    P_{static} \cdot T_1 \cdot S_1 \cdot N

  \hfill
 \end{equation}
 Where \emph N is the number of parallel nodes, $T_1 $ is the time of the slower
  \hfill
 \end{equation}
 Where \emph N is the number of parallel nodes, $T_1 $ is the time of the slower


@@ -208,11 +217,14 @@ task, $T_i$ is the time of the task $i$ and $S_1$ is the maximum scaling factor
 for the slower task. The scaling factor $S_1$, as in EQ~(\ref{eq:s1}), selects
 from the set of scales values $S_i$. Each of these scales are proportional to
 the time value $T_i$ depends on the new frequency value as in EQ~(\ref{eq:si}).
 for the slower task. The scaling factor $S_1$, as in EQ~(\ref{eq:s1}), selects
 from the set of scales values $S_i$. Each of these scales are proportional to
 the time value $T_i$ depends on the new frequency value as in EQ~(\ref{eq:si}).

-\begin{equation}  \label{eq:s1}
-  S_1=MAX_{i=1,2,..,F} (S_i) \hfill
+\begin{equation}
+  \label{eq:s1}
+  S_1 = \max_{i=1,2,\dots,F} S_i

 \end{equation}
 \end{equation}

-\begin{equation}  \label{eq:si}
-  S_i=\:S\: .\:(\frac{T_1}{T_i})=\: (\frac{F_{max}}{F_{new}}).(\frac{T_1}{T_i}) \hfill
+\begin{equation}
+  \label{eq:si}
+  S_i = S \cdot \frac{T_1}{T_i}
+      = \frac{F_{max}}{F_{new}} \cdot \frac{T_1}{T_i}

 \end{equation}
 Where $F$ is the number of available frequencies. In this paper we depend on
 Rauber's energy model EQ~(\ref{eq:energy}) for two reasons : 1-this model used
 \end{equation}
 Where $F$ is the number of available frequencies. In this paper we depend on
 Rauber's energy model EQ~(\ref{eq:energy}) for two reasons : 1-this model used


@@ -221,10 +233,11 @@ algorithm with Rauber's scaling model.  Rauber's optimal scaling factor for
 optimal energy reduction derived from the EQ~(\ref{eq:energy}). He takes the
 derivation for this equation (to be minimized) and set it to zero to produce the
 scaling factor as in EQ~(\ref{eq:sopt}).
 optimal energy reduction derived from the EQ~(\ref{eq:energy}). He takes the
 derivation for this equation (to be minimized) and set it to zero to produce the
 scaling factor as in EQ~(\ref{eq:sopt}).

-\begin{equation}  \label{eq:sopt}
-  S_{opt}= {\sqrt [3~]{\frac{2}{n} \frac{P_{dyn}}{P_{static}}  \Big(1+\sum\limits_{i=2}^{N}\frac{T_i^3}{T_1^3}\Big) }} \hfill
+\begin{equation}
+  \label{eq:sopt}
+  S_{opt} = \sqrt[3]{\frac{2}{n} \cdot \frac{P_{dyn}}{P_{static}} \cdot
+    \left( 1 + \sum_{i=2}^{N} \frac{T_i^3}{T_1^3} \right) }

 \end{equation}
 \end{equation}

-%[\Big 3]

 
 \section{Performance Evaluation of MPI Programs}
 
 
 \section{Performance Evaluation of MPI Programs}
 


@@ -252,9 +265,9 @@ must be precisely specifying communication time and the computation time for the
 slower task. Secondly, we use these times for predicting the execution time for
 any MPI program as a function of the new scaling factor as in the
 EQ~(\ref{eq:tnew}).
 slower task. Secondly, we use these times for predicting the execution time for
 any MPI program as a function of the new scaling factor as in the
 EQ~(\ref{eq:tnew}).

-\begin{equation}  \label{eq:tnew}
-  \displaystyle T_{new}= T_{Max \:Comp \:Old} \; . \:S \;+ \;T_{Max\: Comm\: Old}
-  \hfill
+\begin{equation}
+  \label{eq:tnew}
+  T_{new} = T_{\textit{Max Comp Old}} \cdot S + T_{\textit{Max Comm Old}}

 \end{equation}
 The above equation shows that the scaling factor \emph S has linear relation
 with the computation time without affecting the communication time. The
 \end{equation}
 The above equation shows that the scaling factor \emph S has linear relation
 with the computation time without affecting the communication time. The


@@ -306,12 +319,21 @@ is not straightforward. Moreover, they are not measured using the same metric.
 For solving this problem, we normalize the energy by calculating the ratio
 between the consumed energy with scaled frequency and the consumed energy
 without scaled frequency :
 For solving this problem, we normalize the energy by calculating the ratio
 between the consumed energy with scaled frequency and the consumed energy
 without scaled frequency :

-\begin{equation}  \label{eq:enorm}
-  E_{Norm}=\displaystyle\frac{E_{Reduced}}{E_{Orginal}}= \frac{\displaystyle \;P_{dyn}\,.\,S_i^{-2}\,.\,(T_1+\sum\limits_{i=2}^{N}\frac{T_i^3}{T_1^2})+\;P_{static}\,.\,T_1\,.\,S_i\;\,.\,N  }{\displaystyle \;P_{dyn}\,.\,(T_1+\sum\limits_{i=2}^{N}\frac{T_i^3}{T_1^2})+\;P_{static}\,.\,T_1\,\,.\,N   }
+\begin{equation}
+  \label{eq:enorm}
+  E_{Norm} = \frac{E_{Reduced}}{E_{Orginal}}
+          = \frac{ P_{dyn} \cdot S_i^{-2} \cdot
+               \left( T_1 + \sum_{i=2}^{N}\frac{T_i^3}{T_1^2}\right) +
+               P_{static} \cdot T_1 \cdot S_i \cdot N  }{
+              P_{dyn} \cdot \left(T_1+\sum_{i=2}^{N}\frac{T_i^3}{T_1^2}\right) +
+              P_{static} \cdot T_1\, \cdot N }

 \end{equation}
 By the same way we can normalize the performance as follows :
 \end{equation}
 By the same way we can normalize the performance as follows :

-\begin{equation}  \label{eq:pnorm}
-  P_{Norm}=\displaystyle \frac{T_{New}}{T_{Old}}=\frac{T_{Max \:Comp \:Old} \;. \:S \;+ \;T_{Max\: Comm\: Old}}{T_{Old}}    \;\;
+\begin{equation}
+  \label{eq:pnorm}
+  P_{Norm} = \frac{T_{New}}{T_{Old}}
+          = \frac{T_{\textit{Max Comp Old}} \cdot S +
+              T_{\textit{Max Comm Old}}}{T_{Old}}

 \end{equation}
 The second problem is the optimization operation for both energy and performance
 is not in the same direction. In other words, the normalized energy and the
 \end{equation}
 The second problem is the optimization operation for both energy and performance
 is not in the same direction. In other words, the normalized energy and the


@@ -328,8 +350,11 @@ optimize both energy and performance simultaneously without adding big
 overheads.  Our solution for this problem is to make the optimization process
 have the same direction. Therefore, we inverse the equation of normalize
 performance as follows :
 overheads.  Our solution for this problem is to make the optimization process
 have the same direction. Therefore, we inverse the equation of normalize
 performance as follows :

-\begin{equation}  \label{eq:pnorm_en}
-  \displaystyle P^{-1}_{Norm}= \frac{T_{Old}}{T_{New}}=\frac{T_{Old}}{T_{Max \:Comp \:Old} \;. \:S \;+ \;T_{Max\: Comm\: Old}}
+\begin{equation}
+  \label{eq:pnorm_en}
+  P^{-1}_{Norm} = \frac{T_{Old}}{T_{New}}
+               = \frac{T_{Old}}{T_{\textit{Max Comp Old}} \cdot S +
+                 T_{\textit{Max Comm Old}}}

 \end{equation}
 \begin{figure}
   \centering
 \end{equation}
 \begin{figure}
   \centering


@@ -344,8 +369,10 @@ curve EQ~(\ref{eq:pnorm_en}) over all available scaling factors. This represent
 the minimum energy consumption with minimum execution time (better performance)
 in the same time, see figure~(\ref{fig:r1}). Then our objective function has the
 following form:
 the minimum energy consumption with minimum execution time (better performance)
 in the same time, see figure~(\ref{fig:r1}). Then our objective function has the
 following form:

-\begin{equation}  \label{eq:max}
-  \displaystyle MaxDist = Max \;(\;\overbrace{P^{-1}_{Norm}}^{Maximize}\; -\; \overbrace{E_{Norm}}^{Minimize} \;)
+\begin{equation}
+  \label{eq:max}
+  \textit{MaxDist} = \max (\overbrace{P^{-1}_{Norm}}^{\text{Maximize}} -
+                           \overbrace{E_{Norm}}^{\text{Minimize}} )

 \end{equation}
 Then we can select the optimal scaling factor that satisfy the
 EQ~(\ref{eq:max}).  Our objective function can works with any energy model or
 \end{equation}
 Then we can select the optimal scaling factor that satisfy the
 EQ~(\ref{eq:max}).  Our objective function can works with any energy model or


@@ -377,11 +404,10 @@ scaling factor for both energy and performance at the same time.
       \State - Calculate all available scales $S_i$  depend on $S$ as in EQ~(\ref{eq:si}).
       \State - Select the maximum scale factor $S_1$ from the set of scales $S_i$.
       \State - Calculate the normalize energy $E_{Norm}=E_{R}/E_{O}$ as in EQ~(\ref{eq:enorm}).
       \State - Calculate all available scales $S_i$  depend on $S$ as in EQ~(\ref{eq:si}).
       \State - Select the maximum scale factor $S_1$ from the set of scales $S_i$.
       \State - Calculate the normalize energy $E_{Norm}=E_{R}/E_{O}$ as in EQ~(\ref{eq:enorm}).

-      \State - Calculate the normalize inverse of performance $P_{NormInv}=T_{old}/T_{new}$
-
-      as in EQ~(\ref{eq:pnorm_en}).
-      \If{  $(P_{NormInv}-E_{Norm}$ $>$ $Dist$) }
-        \State $S_{optimal}=S$
+      \State - Calculate the normalize inverse of performance\par
+               $P_{NormInv}=T_{old}/T_{new}$ as in EQ~(\ref{eq:pnorm_en}).
+      \If{  $(P_{NormInv}-E_{Norm} > Dist$) }
+        \State $S_{optimal} = S$

         \State $Dist = P_{NormInv} - E_{Norm}$
       \EndIf
     \EndFor
         \State $Dist = P_{NormInv} - E_{Norm}$
       \EndIf
     \EndFor


@@ -418,8 +444,9 @@ After obtaining the optimal scale factor from the EPSA algorithm. The program
 calculates the new frequency $F_i$ for each task proportionally to its time
 value $T_i$. By substitution of the EQ~(\ref{eq:s}) in the EQ~(\ref{eq:si}), we
 can calculate the new frequency $F_i$ as follows :
 calculates the new frequency $F_i$ for each task proportionally to its time
 value $T_i$. By substitution of the EQ~(\ref{eq:s}) in the EQ~(\ref{eq:si}), we
 can calculate the new frequency $F_i$ as follows :

-\begin{equation}  \label{eq:fi}
-  F_i=\frac{F_{max} \; . \;T_i}{S_{optimal} \; . \;T_{max}} \hfill
+\begin{equation}
+  \label{eq:fi}
+  F_i = \frac{F_{max} \cdot T_i}{S_{optimal} \cdot T_{max}}

 \end{equation}
 According to this equation all the nodes may have the same frequency value if
 they have balanced workloads. Otherwise, they take different frequencies when
 \end{equation}
 According to this equation all the nodes may have the same frequency value if
 they have balanced workloads. Otherwise, they take different frequencies when