X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/ThesisAhmed.git/blobdiff_plain/3dfa5bd4d94afee02f58fc41b9e95b4f2fc78133..HEAD:/thesis-presentation/AhmedSlides.tex?ds=inline diff --git a/thesis-presentation/AhmedSlides.tex b/thesis-presentation/AhmedSlides.tex index 2a57d28..6dbbd81 100644 --- a/thesis-presentation/AhmedSlides.tex +++ b/thesis-presentation/AhmedSlides.tex @@ -112,18 +112,13 @@ %%%%%%%%%%%%%%%%%%%% %% SLIDE 03 %% %%%%%%%%%%%%%%%%%%%% -\begin{frame}{Introduction and problem definition} +\begin{frame}{Definition of parallel computing} \section{\small {Introduction and Problem definition}} \centering \includegraphics[width=0.99\textwidth]{para.pdf} \end{frame} - - - - - \begin{frame}{Execution of synchronous parallel tasks} \vspace{-0.5 cm} @@ -175,7 +170,8 @@ \end{minipage}% \vspace{0.2cm} \begin{minipage}{0.5\textwidth} - \textcolor{blue}{2)} \small \bf \textcolor{black}{Increase the number of nodes.} + \textcolor{blue}{2)} \small \bf \textcolor{black}{Increase the number of computing + units.} \textcolor{black}{The supercomputer Tianhe-2 has more than 3 million cores and consumes around 17.8 megawatts.} @@ -289,10 +285,10 @@ for a warehouse-sized computer. \begin{itemize} \small \justifying - \item Studying the effect of the scaling factor on the \textbf{energy consumption and performance } of parallel applications with iterations. \medskip + \item Studying the effect of the frequency scaling on the \textbf{energy consumption and performance } of parallel applications with iterations. \medskip \item Discovering the \textbf{energy-performance trade-off relation} when changing the frequency of the processor.\medskip - \item Proposing an algorithm for selecting the scaling factor that produces \textbf {the optimal trade-off} between the energy consumption and the performance. \medskip + \item Proposing an algorithm for selecting the scaling factor that produces \textbf {the good trade-off} between the energy consumption and the performance. \medskip \item Comparing the proposed algorithm to existing methods. @@ -307,6 +303,38 @@ for a warehouse-sized computer. +%%%%%%%%%%%%%%%%%%%% +%% SLIDE 13 %% +%%%%%%%%%%%%%%%%%%%% +\begin{frame}{Performance evaluation of MPI programs} + +\small The frequency scaling factor is the ratio between the maximum and the new frequency, \textcolor{blue}{$S = \frac{F_{max}}{F_{new}}$}. + \vspace{5 mm} + + \begin{femtoBlock}{} + \vspace{-5 mm} + \begin{block}{\small Execution time prediction model} + \centering{ $ \textcolor{red}{T_{new}} = \textcolor{blue}{T_{Max Comp Old} \cdot S + T_{{Min Comm Old}}}$} + \end{block} + \vspace{5 mm} + \centering{\includegraphics[width=.4\textwidth]{c1/cg_per} + \quad% + \includegraphics[width=.4\textwidth]{c1/lu_pre}} + \vspace{1 mm} + + \small The maximum normalized error for CG=0.0073 \textbf{(the smallest)} and LU=0.031 \textbf{(the worst)}. + \end{femtoBlock} +\end{frame} + + + + + + + + + + @@ -316,32 +344,34 @@ for a warehouse-sized computer. %%%%%%%%%%%%%%%%%%%% \begin{frame}{Energy model for a homogeneous platform} The power consumed by a processor is divided into two power metrics: the dynamic (\textcolor{red}{$P_d$}) and the static - (\textcolor{red}{$P_s$}) power. + (\textcolor{red}{$P_s$}) powers. \begin{equation} \label{eq:pd} \textcolor{red}{ P_d} = \textcolor{blue}{\alpha \cdot CL \cdot V^2 \cdot F} \end{equation} \scriptsize \underline{Where}: \\ - \scriptsize {\textcolor{blue}{$\alpha$}: switching activity \hspace{15 mm} \textcolor{blue}{$CL$}: load capacitance\\ - \textcolor{blue}{$V$}: the supply voltage \hspace{14 mm} \textcolor{blue}{$F$}: operational frequency} + \scriptsize {\textcolor{blue}{$\alpha$}: switching activity. \hspace{15 mm} \textcolor{blue}{$CL$}: load capacitance [F].\\ + \textcolor{blue}{$V$}: the supply voltage [V]. \hspace{8 mm} \textcolor{blue}{$F$}: operational frequency [Hz].} \begin{equation} \label{eq:ps} \small \textcolor{red}{P_s} = \textcolor{blue}{V \cdot N_{trans} \cdot K_{design} \cdot I_{Leak}} \end{equation} \underline{Where}:\\ - \scriptsize{ \textcolor{blue}{$V$}: the supply voltage. \hspace{28 mm} \textcolor{blue}{$N_{trans}$}: number of transistors. \\ - \textcolor{blue}{$K_{design}$}: design dependent parameter. \hspace{8 mm} \textcolor{blue}{$I_{leak}$}: technology dependent - parameter.} + \scriptsize{ \textcolor{blue}{$V$}: the supply voltage [V]. \hspace{19 mm} \textcolor{blue}{$N_{trans}$}: number of transistors. \\ + \textcolor{blue}{$K_{design}$}: design dependent parameter. \hspace{3 mm} \textcolor{blue}{$I_{leak}$}: technology dependent + parameter [A].} + - The frequency scaling factor is the ratio between the maximum and the new frequency, \textcolor{blue}{$S = \frac{F_{max}}{F_{new}}$}. \end{frame} + + %%%%%%%%%%%%%%%%%%%% %% SLIDE 12 %% %%%%%%%%%%%%%%%%%%%% \begin{frame}{Energy model for a homogeneous platform} - \vspace{-0.77cm} + \vspace{-0.77cm} \begin{figure} \animategraphics[autopause,controls,scale=0.3,buttonsize=0.2cm]{10}{homo-model/a-}{0}{441} %\includegraphics[width=0.6\textwidth]{homo-model/a-356} @@ -362,26 +392,6 @@ for a warehouse-sized computer. \end{frame} - - -%%%%%%%%%%%%%%%%%%%% -%% SLIDE 13 %% -%%%%%%%%%%%%%%%%%%%% -\begin{frame}{Performance evaluation of MPI programs} - \begin{femtoBlock}{} - \vspace{-5 mm} - \begin{block}{\small Execution time prediction model} - \centering{ $ \textcolor{red}{T_{new}} = \textcolor{blue}{T_{Max Comp Old} \cdot S + T_{{Min Comm Old}}}$} - \end{block} - \vspace{10 mm} - \centering{\includegraphics[width=.4\textwidth]{c1/cg_per} - \quad% - \includegraphics[width=.4\textwidth]{c1/lu_pre}} - \vspace{5 mm} - - \small The maximum normalized error for CG=0.0073 \textbf{(the smallest)} and LU=0.031 \textbf{(the worst)}. - \end{femtoBlock} -\end{frame} @@ -443,7 +453,7 @@ for a warehouse-sized computer. %%%%%%%%%%%%%%%%%%%% %% SLIDE 17 %% %%%%%%%%%%%%%%%%%%%% -\begin{frame}{Experimental results } +\begin{frame}{Experiment over SimGrid } \begin{femtoBlock}{} \begin{itemize} \small @@ -478,20 +488,21 @@ for a warehouse-sized computer. %% SLIDE 19 %% %%%%%%%%%%%%%%%%%%%% \begin{frame}{Results comparison} - \begin{block}{\small Rauber and Rünger's optimal scaling factor} - $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{block} - - - \centering { - %\includegraphics[width=.33\textwidth]{c1/c1.pdf} - %\qquad - %\includegraphics[width=.33\textwidth]{c1/c2.pdf}} - + \small \textcolor{blue}{Rauber and Rünger's scaling factor \textcolor{black}{ \tiny \textsuperscript{2}}} - \includegraphics[width=.55\textwidth]{c1/compare-c.pdf}} + \vspace{2 mm} + + $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) } $ + + \begin{center} + \includegraphics[width=.55\textwidth]{c1/compare-c.pdf} + \end{center} + + +\vspace{-2 mm} + \tiny \textsuperscript{2} Thomas Rauber and Gudula Rünger. Analytical modeling and simulation of the energy consumption of independent tasks. In Proceedings of the Winter Simulation Conference, 2012. \end{frame} @@ -567,7 +578,7 @@ for a warehouse-sized computer. \item Studying the effect of the scaling factor $S$ on both the \textcolor{blue}{energy consumption and the performance} of message passing iterative applications. \medskip - \item Computing the vector of scaling factors ($S_1, S_2, ..., S_n$) producing \textcolor{blue} {the optimal trade-off} between + \item Computing the vector of scaling factors ($S_1, S_2, ..., S_n$) producing \textcolor{blue} {the good trade-off} between the energy consumption and the performance. \end{itemize} @@ -889,7 +900,7 @@ for a warehouse-sized computer. %%%%%%%%%%%%%%%%%%%% \begin{frame}{Comparing the objective function to EDP} - EDP is the products between the energy consumption and the delay. + EDP is the product between the energy consumption and the delay \tiny\textsuperscript{3}. \vspace{-5 mm} \begin{figure}[!t] \centering @@ -897,6 +908,8 @@ for a warehouse-sized computer. \end{figure} + + \tiny \textsuperscript{3} Spiliopoulos et al, Green governors: A framework for continuously adaptive dvfs, in International Green Computing Conference and Workshops (IGCC), 2011. \end{frame} %\begin{frame}{Summary} %\begin{itemize} @@ -1039,11 +1052,11 @@ for a warehouse-sized computer. %%%%%%%%%%%%%%%%%%%% %% SLIDE 46 %% %%%%%%%%%%%%%%%%%%%% -\begin{frame}{The scaling algorithm for Asynch. applications} -\vspace{-0.1 mm} -\centering -\includegraphics[width=0.55\textwidth]{algo-hybrid.pdf} -\end{frame} +%\begin{frame}{The scaling algorithm for Asynch. applications} +%\vspace{-0.1 mm} +%\centering +%\includegraphics[width=0.55\textwidth]{algo-hybrid.pdf} +%\end{frame} @@ -1169,7 +1182,7 @@ Multi-splitting} method. Science}, 2016. \item Ahmed Fanfakh, Jean-Claude Charr, Raphaël Couturier, Arnaud Giersch. Energy Consumption Reduction for - Asynchronous Message Passing Applications. \textit{Journal of Supercomputing}, 2016, (Submitted) + Asynchronous Message Passing Applications. \textit{Journal of Supercomputing}, 2016, (Accepted with minor revisions) \end{enumerate} \end{block} @@ -1212,6 +1225,9 @@ Multi-splitting} method. \small \barrow The proposed algorithms for heterogeneous platforms should be applied to heterogeneous platforms composed of \textcolor{blue}{CPUs and GPUs}. \small \barrow Comparing the results returned by the energy models to the values given by \textcolor{blue}{real instruments that measure the energy consumptions} of CPUs during the execution time. +\small \barrow Considering the power consumed by the other devices in the node such as +\textcolor{blue}{the memory and the hard drive} in the energy consumption model. + \end{itemize} \end{frame}