X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy.git/blobdiff_plain/9cf953b2bfe1f9fdfbf76e564f4df0ad6f64b4ed..7efcd15c3006ff3285a51ee079808b452c969a39:/paper.tex diff --git a/paper.tex b/paper.tex index 29f175b..a405346 100644 --- a/paper.tex +++ b/paper.tex @@ -16,7 +16,6 @@ %\usepackage[font={footnotesize,bt}]{caption} %\usepackage[font=scriptsize,labelfont=bf]{caption} \usepackage{lmodern} - \usepackage{todonotes} \newcommand{\AG}[2][inline]{\todo[color=green!50,#1]{\sffamily\small\textbf{AG:} #2}} @@ -29,7 +28,7 @@ \AG{``Optimal'' is a bit pretentious in the title} \begin{abstract} - \AG{FIXME} + \AG{complete the abstract\dots} \end{abstract} \section{Introduction} @@ -294,8 +293,6 @@ with all available scaling factors on 8 or 9 nodes to produce real execution time values. These scaling factors are computed by dividing the maximum frequency by the new one see EQ~(\ref{eq:s}). In all tests, we use the simulator SimGrid/SMPI v3.10 to run the NAS programs. -\AG{Fig.~\ref{fig:pred} is hard to read when printed in black and white, - especially the ``Normalize Real Perf.'' curve.} \begin{figure}[width=\textwidth,height=\textheight,keepaspectratio] \centering \includegraphics[scale=0.60]{cg_per.eps} @@ -329,7 +326,7 @@ between the consumed energy with scaled frequency and the consumed energy without scaled frequency : \begin{equation} \label{eq:enorm} - E_{Norm} = \frac{E_{Reduced}}{E_{Original}} + E_\textit{Norm} = \frac{E_{Reduced}}{E_{Original}} = \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 }{ @@ -404,7 +401,7 @@ goal in discovering optimal scaling factor for both performance and energy at the same time. Therefore, we develop an energy to performance scaling algorithm (EPSA). This algorithm is simple and has a direct way to calculate the optimal scaling factor for both energy and performance at the same time. -\begin{algorithm}[t] +\begin{algorithm}[tp] \caption{EPSA} \label{EPSA} \begin{algorithmic}[1] @@ -438,24 +435,29 @@ for each task from the first iteration only. When these times are measured, the MPI program calls the EPSA algorithm to choose the new frequency using the optimal scaling factor. Then the program set the new frequency to the system. The algorithm is called just one time during the execution of the -program. The following example shows where and when the EPSA algorithm is called -in the MPI program : -\begin{minipage}{\textwidth} -\AG{Use the same format as for Algorithm~\ref{EPSA}} -\begin{lstlisting}[frame=tb] -FOR J:=1 to Some_iterations Do - -Computations Section. - -Communications Section. - IF (J==1) THEN - -Gather all times of computation and communication - from each node. - -Call EPSA with these times. - -Calculate the new frequency from optimal scale. - -Set the new frequency to the system. - ENDIF -ENDFOR -\end{lstlisting} -\end{minipage} +program. The DVFS algorithm~(\ref{dvfs}) shows where and when the EPSA algorithm is called +in the MPI program. +%\begin{minipage}{\textwidth} +%\AG{Use the same format as for Algorithm~\ref{EPSA}} + +\begin{algorithm}[tp] + \caption{DVFS} + \label{dvfs} + \begin{algorithmic} + \For {$J:=1$ to $Some-Iterations \; $} + \State -Computations Section. + \State -Communications Section. + \If {$(J==1)$} + \State -Gather all times of computation and\par + \State communication from each node. + \State -Call EPSA with these times. + \State -Calculate the new frequency from optimal scale. + \State -Set the new frequency to the system. + \EndIf +\EndFor +\end{algorithmic} +\end{algorithm} + 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 @@ -488,12 +490,11 @@ frequencies. \caption{Platform File Parameters} % title of Table \centering - \AG{Use e.g. $5\times 10^{-7}$ instead of 5E-7} \begin{tabular}{ | l | l | l |l | l |l |l | p{2cm} |} \hline Max & Min & Backbone & Backbone&Link &Link& Sharing \\ Freq. & Freq. & Bandwidth & Latency & Bandwidth& Latency&Policy \\ \hline - 2.5 &800 & 2.25 GBps &5E-7 s & 1 GBps & 5E-5 s&Full \\ + 2.5 &800 & 2.25 GBps &$5\times 10^{-7} s$& 1 GBps & $5\times 10^{-5}$ s&Full \\ GHz& MHz& & & & &Duplex \\\hline \end{tabular} \label{table:platform} @@ -539,13 +540,13 @@ same time over all available scales. \hline Program & Optimal & Energy & Performance&Energy-Perf.\\ Name & Scaling Factor& Saving \%&Degradation \% &Distance \\ \hline - CG & 1.56 &39.23 & 14.88 & 24.35\\ \hline - MG & 1.47 &34.97&21.7& 13.27 \\ \hline + CG & 1.56 &39.23&14.88 &24.35\\ \hline + MG & 1.47 &34.97&21.70 &13.27 \\ \hline EP & 1.04 &22.14&20.73 &1.41\\ \hline - LU & 1.388 &35.83&22.49 &13.34\\ \hline - BT & 1.315 &29.6&21.28 &8.32\\ \hline - SP & 1.388 &33.48 &21.36&12.12\\ \hline - FT & 1.47 &34.72 &19&15.72\\ \hline + LU & 1.38 &35.83&22.49 &13.34\\ \hline + BT & 1.31 &29.60&21.28 &8.32\\ \hline + SP & 1.38 &33.48&21.36 &12.12\\ \hline + FT & 1.47 &34.72&19.00 &15.72\\ \hline \end{tabular} \label{table:factors results} % is used to refer this table in the text @@ -575,39 +576,39 @@ benchmarks programs for classes A,B and C. \caption{Comparing Results for The NAS Class A} % title of Table \centering - \begin{tabular}{ | l | l | l |l | l |l| } + \begin{tabular}{ | l | l | l |l | l | l| } \hline Method&Program&Factor& Energy& Performance &Energy-Perf.\\ name &name&value& Saving \%&Degradation \% &Distance \\ \hline % \rowcolor[gray]{0.85} EPSA&CG & 1.56 &37.02 & 13.88 & 23.14\\ \hline - $Rauber_{E-P}$&CG &2.14 &42.77 & 25.27 & 17.5\\ \hline + $Rauber_{E-P}$&CG &2.14 &42.77 & 25.27 & 17.50\\ \hline $Rauber_{E}$&CG &2.14 &42.77&26.46&16.31\\ \hline EPSA&MG & 1.47 &27.66&16.82&10.84\\ \hline $Rauber_{E-P}$&MG &2.14&34.45&31.84&2.61\\ \hline - $Rauber_{E}$&MG &2.14&34.48&33.65&0.8 \\ \hline + $Rauber_{E}$&MG &2.14&34.48&33.65&0.80 \\ \hline EPSA&EP &1.19 &25.32&20.79&4.53\\ \hline $Rauber_{E-P}$&EP&2.05&41.45&55.67&-14.22\\ \hline - $Rauber_{E}$&EP&2.05&42.09&57.59&-15.5\\ \hline + $Rauber_{E}$&EP&2.05&42.09&57.59&-15.50\\ \hline EPSA&LU&1.56& 39.55 &19.38& 20.17\\ \hline - $Rauber_{E-P}$&LU&2.14&45.62&27&18.62 \\ \hline + $Rauber_{E-P}$&LU&2.14&45.62&27.00&18.62 \\ \hline $Rauber_{E}$&LU&2.14&45.66&33.01&12.65\\ \hline - EPSA&BT&1.315& 29.6&20.53&9.07 \\ \hline - $Rauber_{E-P}$&BT&2.1&45.53&49.63&-4.1\\ \hline - $Rauber_{E}$&BT&2.1&43.93&52.86&-8.93\\ \hline + EPSA&BT&1.31& 29.60&20.53&9.07 \\ \hline + $Rauber_{E-P}$&BT&2.10&45.53&49.63&-4.10\\ \hline + $Rauber_{E}$&BT&2.10&43.93&52.86&-8.93\\ \hline - EPSA&SP&1.388& 33.51&15.65&17.86 \\ \hline - $Rauber_{E-P}$&SP&2.11&45.62&42.52&3.1\\ \hline + EPSA&SP&1.38& 33.51&15.65&17.86 \\ \hline + $Rauber_{E-P}$&SP&2.11&45.62&42.52&3.10\\ \hline $Rauber_{E}$&SP&2.11&45.78&43.09&2.69\\ \hline - EPSA&FT&1.25& 25&10.8&14.2 \\ \hline - $Rauber_{E-P}$&FT&2.1&39.29&34.3&4.99 \\ \hline - $Rauber_{E}$&FT&2.1&37.56&38.21&-0.65\\ \hline + EPSA&FT&1.25&25.00&10.80&14.20 \\ \hline + $Rauber_{E-P}$&FT&2.10&39.29&34.30&4.99 \\ \hline + $Rauber_{E}$&FT&2.10&37.56&38.21&-0.65\\ \hline \end{tabular} \label{table:compare Class A} % is used to refer this table in the text @@ -622,8 +623,8 @@ benchmarks programs for classes A,B and C. name &name&value& Saving \%&Degradation \% &Distance \\ \hline % \rowcolor[gray]{0.85} - EPSA&CG & 1.66 &39.23&16.63&22.6 \\ \hline - $Rauber_{E-P}$&CG &2.15 &45.34&27.6&17.74\\ \hline + EPSA&CG & 1.66 &39.23&16.63&22.60 \\ \hline + $Rauber_{E-P}$&CG &2.15 &45.34&27.60&17.74\\ \hline $Rauber_{E}$&CG &2.15 &45.34&28.88&16.46\\ \hline EPSA&MG & 1.47 &34.98&18.35&16.63\\ \hline @@ -631,24 +632,24 @@ benchmarks programs for classes A,B and C. $Rauber_{E}$&MG &2.14&43.56&37.07&6.49 \\ \hline EPSA&EP &1.08 &20.29&17.15&3.14 \\ \hline - $Rauber_{E-P}$&EP&2&42.38&56.88&-14.5\\ \hline - $Rauber_{E}$&EP&2&39.73&59.94&-20.21\\ \hline + $Rauber_{E-P}$&EP&2.00&42.38&56.88&-14.50\\ \hline + $Rauber_{E}$&EP&2.00&39.73&59.94&-20.21\\ \hline EPSA&LU&1.47&38.57&21.34&17.23 \\ \hline - $Rauber_{E-P}$&LU&2.1&43.62&36.51&7.11 \\ \hline - $Rauber_{E}$&LU&2.1&43.61&38.54&5.07 \\ \hline + $Rauber_{E-P}$&LU&2.10&43.62&36.51&7.11 \\ \hline + $Rauber_{E}$&LU&2.10&43.61&38.54&5.07 \\ \hline - EPSA&BT&1.315& 29.59&20.88&8.71\\ \hline - $Rauber_{E-P}$&BT&2.1&44.53&53.05&-8.52\\ \hline - $Rauber_{E}$&BT&2.1&42.93&52.806&-9.876\\ \hline + EPSA&BT&1.31& 29.59&20.88&8.71\\ \hline + $Rauber_{E-P}$&BT&2.10&44.53&53.05&-8.52\\ \hline + $Rauber_{E}$&BT&2.10&42.93&52.80&-9.87\\ \hline - EPSA&SP&1.388&33.44&19.24&14.2 \\ \hline - $Rauber_{E-P}$&SP&2.15&45.69&43.2&2.49\\ \hline + EPSA&SP&1.38&33.44&19.24&14.20 \\ \hline + $Rauber_{E-P}$&SP&2.15&45.69&43.20&2.49\\ \hline $Rauber_{E}$&SP&2.15&45.41&44.47&0.94\\ \hline - EPSA&FT&1.388&34.4&14.57&19.83 \\ \hline + EPSA&FT&1.38&34.40&14.57&19.83 \\ \hline $Rauber_{E-P}$&FT&2.13&42.98&37.35&5.63 \\ \hline - $Rauber_{E}$&FT&2.13&43.04&37.9&5.14\\ \hline + $Rauber_{E}$&FT&2.13&43.04&37.90&5.14\\ \hline \end{tabular} \label{table:compare Class B} % is used to refer this table in the text @@ -666,31 +667,31 @@ benchmarks programs for classes A,B and C. % \rowcolor[gray]{0.85} EPSA&CG & 1.56 &39.23&14.88&24.35 \\ \hline $Rauber_{E-P}$&CG &2.15 &45.36&25.89&19.47\\ \hline - $Rauber_{E}$&CG &2.15 &45.36&26.7&18.66\\ \hline + $Rauber_{E}$&CG &2.15 &45.36&26.70&18.66\\ \hline - EPSA&MG & 1.47 &34.97&21.697&13.273\\ \hline - $Rauber_{E-P}$&MG &2.15&43.65&40.45&3.2 \\ \hline + EPSA&MG & 1.47 &34.97&21.69&13.27\\ \hline + $Rauber_{E-P}$&MG &2.15&43.65&40.45&3.20 \\ \hline $Rauber_{E}$&MG &2.15&43.64&41.38&2.26 \\ \hline EPSA&EP &1.04 &22.14&20.73&1.41 \\ \hline - $Rauber_{E-P}$&EP&1.92&39.4&56.33&-16.93\\ \hline - $Rauber_{E}$&EP&1.92&38.1&56.35&-18.25\\ \hline + $Rauber_{E-P}$&EP&1.92&39.40&56.33&-16.93\\ \hline + $Rauber_{E}$&EP&1.92&38.10&56.35&-18.25\\ \hline - EPSA&LU&1.388&35.83&22.49&13.34 \\ \hline - $Rauber_{E-P}$&LU&2.15&44.97&41&3.97 \\ \hline - $Rauber_{E}$&LU&2.15&44.97&41.8&3.17 \\ \hline + EPSA&LU&1.38&35.83&22.49&13.34 \\ \hline + $Rauber_{E-P}$&LU&2.15&44.97&41.00&3.97 \\ \hline + $Rauber_{E}$&LU&2.15&44.97&41.80&3.17 \\ \hline - EPSA&BT&1.315& 29.6&21.28&8.32\\ \hline - $Rauber_{E-P}$&BT&2.13&45.6&49.84&-4.24\\ \hline - $Rauber_{E}$&BT&2.13&44.9&55.16&-10.26\\ \hline + EPSA&BT&1.31& 29.60&21.28&8.32\\ \hline + $Rauber_{E-P}$&BT&2.13&45.60&49.84&-4.24\\ \hline + $Rauber_{E}$&BT&2.13&44.90&55.16&-10.26\\ \hline - EPSA&SP&1.388&33.48&21.35&12.12\\ \hline - $Rauber_{E-P}$&SP&2.1&45.69&43.6&2.09\\ \hline - $Rauber_{E}$&SP&2.1&45.75&44.1&1.65\\ \hline + EPSA&SP&1.38&33.48&21.35&12.12\\ \hline + $Rauber_{E-P}$&SP&2.10&45.69&43.60&2.09\\ \hline + $Rauber_{E}$&SP&2.10&45.75&44.10&1.65\\ \hline - EPSA&FT&1.47&34.72&19&15.72 \\ \hline - $Rauber_{E-P}$&FT&2.04&39.4&37.1&2.3\\ \hline - $Rauber_{E}$&FT&2.04&39.35&37.7&1.65\\ \hline + EPSA&FT&1.47&34.72&19.00&15.72 \\ \hline + $Rauber_{E-P}$&FT&2.04&39.40&37.10&2.30\\ \hline + $Rauber_{E}$&FT&2.04&39.35&37.70&1.65\\ \hline \end{tabular} \label{table:compare Class C} % is used to refer this table in the text @@ -726,7 +727,16 @@ than the first. \label{fig:compare} \end{figure} -\AG{\texttt{bibtex} gives many errors, please correct them} +\section{Conclusion} +\label{sec.conc} + +\AG{the conclusion needs to be written\dots{} one day} + +\section*{Acknowledgment} + +Computations have been performed on the supercomputer facilities of the +Mésocentre de calcul de Franche-Comté. + \bibliographystyle{plain} \bibliography{my_reference} \end{document} @@ -735,7 +745,7 @@ than the first. %%% mode: latex %%% TeX-master: t %%% fill-column: 80 -%%% ispell-local-dictionary: "american" +%%%ispell-local-dictionary: "american" %%% End: % LocalWords: Badri Charr FIXME Tianhe DVFS HPC NAS NPB SMPI Rauber's Rauber