X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy2.git/blobdiff_plain/eac9d615d9ae026613914cc0aac04335d39cff5c..71a2ec18276dbbb8ee0dc07e9a390d558eda81d7:/mpi-energy2-extension/Heter_paper.tex diff --git a/mpi-energy2-extension/Heter_paper.tex b/mpi-energy2-extension/Heter_paper.tex index 82c4e24..b6839ce 100644 --- a/mpi-energy2-extension/Heter_paper.tex +++ b/mpi-energy2-extension/Heter_paper.tex @@ -1,4 +1,41 @@ -\documentclass[conference]{IEEEtran} +\documentclass[review]{elsarticle} + +\usepackage{lineno,hyperref} +\modulolinenumbers[5] + +\journal{Journal of Computational Science} + +%%%%%%%%%%%%%%%%%%%%%%% +%% Elsevier bibliography styles +%%%%%%%%%%%%%%%%%%%%%%% +%% To change the style, put a % in front of the second line of the current style and +%% remove the % from the second line of the style you would like to use. +%%%%%%%%%%%%%%%%%%%%%%% + +%% Numbered +%\bibliographystyle{model1-num-names} + +%% Numbered without titles +%\bibliographystyle{model1a-num-names} + +%% Harvard +%\bibliographystyle{model2-names.bst}\biboptions{authoryear} + +%% Vancouver numbered +%\usepackage{numcompress}\bibliographystyle{model3-num-names} + +%% Vancouver name/year +%\usepackage{numcompress}\bibliographystyle{model4-names}\biboptions{authoryear} + +%% APA style +%\bibliographystyle{model5-names}\biboptions{authoryear} + +%% AMA style +%\usepackage{numcompress}\bibliographystyle{model6-num-names} + +%% `Elsevier LaTeX' style +\bibliographystyle{elsarticle-num} +%%%%%%%%%%%%%%%%%%%%%%% \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} @@ -6,6 +43,7 @@ \usepackage{algpseudocode} \usepackage{graphicx} \usepackage{algorithm} +\usepackage{setspace} \usepackage{subfig} \usepackage{amsmath} \usepackage{url} @@ -60,34 +98,81 @@ \newcommand{\Tnew}{\Xsub{T}{New}} \newcommand{\Told}{\Xsub{T}{Old}} + + + \begin{document} -\title{Energy Consumption Reduction with DVFS for \\ - Message Passing Iterative Applications on \\ - Heterogeneous Architectures} - -\author{% - \IEEEauthorblockN{% - Jean-Claude Charr, - Raphaël Couturier, - Ahmed Fanfakh and - Arnaud Giersch - } - \IEEEauthorblockA{% - FEMTO-ST Institute, University of Franche-Comté\\ +\begin{frontmatter} + + + +\title{Energy Consumption Reduction with DVFS for Message \\ + Passing Iterative Applications on \\ + Grid Architecture} + + + + +\author{Ahmed Fanfakh, + Jean-Claude Charr, + Raphaël Couturier, + and Arnaud Giersch} + +\address{FEMTO-ST Institute, University of Franche-Comté\\ IUT de Belfort-Montbéliard, 19 avenue du Maréchal Juin, BP 527, 90016 Belfort cedex, France\\ % Telephone: \mbox{+33 3 84 58 77 86}, % Raphaël % Fax: \mbox{+33 3 84 58 77 81}\\ % Dept Info - Email: \email{{jean-claude.charr,raphael.couturier,ahmed.fanfakh_badri_muslim,arnaud.giersch}@univ-fcomte.fr} + Email: \email{{ahmed.fanfakh_badri_muslim,jean-claude.charr,raphael.couturier,arnaud.giersch}@univ-fcomte.fr} } - } -\maketitle +\begin{abstract} + + In recent years, green computing has become an important topic + in the supercomputing research domain. However, the + computing platforms are still consuming more and +more energy due to the increasing number of nodes composing +them. To minimize the operating costs of these platforms many +techniques have been used. Dynamic voltage and frequency +scaling (DVFS) is one of them. It can be used to reduce the power consumption of the CPU + while computing, by lowering its frequency. However, lowering the frequency of + a CPU may increase the execution time of an application running on that + processor. Therefore, the frequency that gives the best trade-off between + the energy consumption and the performance of an application must be selected. + In this paper, a new online frequency selecting algorithm for grids, composed of heterogeneous clusters, is presented. + It selects the frequencies and tries to give the best + trade-off between energy saving and performance degradation, for each node + computing the message passing iterative application. + The algorithm has a small + overhead and works without training or profiling. It uses a new energy model + for message passing iterative applications running on a grid. + 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[\%]{3.2}. 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} + + +\begin{keyword} + +Dynamic voltage and frequency scaling \sep Grid computing\sep Green computing and frequency scaling online algorithm. + +%% keywords here, in the form: keyword \sep keyword + +%% MSC codes here, in the form: \MSC code \sep code +%% or \MSC[2008] code \sep code (2000 is the default) + +\end{keyword} + +\end{frontmatter} + + \section{Introduction} \label{sec.intro} -\textcolor{blue}{ The need for more computing power is continually increasing. To partially satisfy this need, most supercomputers constructors just put more computing nodes in their platform. The resulting platforms may achieve higher floating @@ -105,9 +190,7 @@ of FLOPS per watt possible, such as the Shoubu-ExaScaler from RIKEN which became the top of the Green500 list in June 2015 \cite{Green500_List}. This heterogeneous platform executes more than 7 GFLOPS per watt while consuming 50.32 kilowatts. -} -\textcolor{blue}{ Besides platform improvements, there are many software and hardware techniques to lower the energy consumption of these platforms, such as scheduling, DVFS, \dots{} DVFS is a widely used process to reduce the energy consumption of a @@ -120,33 +203,30 @@ trade-off between the energy reduction and performance degradation ratio. In \cite{Our_first_paper} and \cite{pdsec2015} , a frequencies selecting algorithm was proposed to reduce the energy consumption of message passing iterative applications running over homogeneous and heterogeneous clusters respectively. -The results of the experiments show significant energy +The results of the experiments showed significant energy consumption reductions. All the experimental results were conducted over -Simgrid simulator \cite{SimGrid}, which offers easy tools to create a homogeneous and heterogeneous platforms. In this paper, a new frequencies selecting algorithm -adapted for heterogeneous grid platform is presented and executed over real testbed, -the grid'5000 platform \cite{grid5000}. It selects the vector of -frequencies, for a heterogeneous grid platform running a message passing iterative -application, that simultaneously tries to offer the maximum energy reduction and -minimum performance degradation ratio. The algorithm has a very small overhead, -works online and does not need any training or profiling.} - -\textcolor{blue}{ +Simgrid simulator \cite{SimGrid}, which offers easy tools to create a homogeneous and heterogeneous platforms and run message passing parallel applications over them. In this paper, a new frequencies selecting algorithm, +adapted to grid platforms composed of heterogeneous clusters, is presented. It is applied to the NAS parallel benchmarks and evaluated over a real testbed, +the grid'5000 platform \cite{grid5000}. It selects for a grid platform running a message passing iterative +application the vector of +frequencies that simultaneously tries to offer the maximum energy reduction and +minimum performance degradation ratios. The algorithm has a very small overhead, +works online and does not need any training or profiling. + + This paper is organized as follows: Section~\ref{sec.relwork} presents some related works from other authors. Section~\ref{sec.exe} describes how the execution time of message passing programs can be predicted. It also presents an energy model that predicts the energy consumption of an application running -over a heterogeneous grid. Section~\ref{sec.compet} presents the +over a grid platform. Section~\ref{sec.compet} presents the energy-performance objective function that maximizes the reduction of energy consumption while minimizing the degradation of the program's performance. Section~\ref{sec.optim} details the proposed frequencies selecting algorithm. Section~\ref{sec.expe} presents the results of applying the algorithm on the -NAS parallel benchmarks and executing them on a grid'5000 testbed. -It shows the results of running different scenarios using multi-cores and one core per node -and comparing them. It also shows the results of running -three different power scenarios and comparing them. Moreover, it shows the +NAS parallel benchmarks and executing them on the grid'5000 testbed. +It also evaluates the algorithm over multi-cores per node architectures and over three different power scenarios. Moreover, it shows the comparison results between the proposed method and an existing method. Finally, -in Section~\ref{sec.concl} the paper ends with a summary and some future works.} - +in Section~\ref{sec.concl} the paper ends with a summary and some future works. \section{Related works} \label{sec.relwork} @@ -423,6 +503,7 @@ static energies for $M$ processors in $N$ clusters. It is computed as follows: +\mathop{\min_{j=1,\dots M}} (\Tcm[hj]) )) \end{multline} + Reducing the frequencies of the processors according to the vector of scaling factors $(S_{11}, S_{12},\dots, S_{NM})$ may degrade the performance of the application and thus, increase the static energy because the execution time is @@ -446,13 +527,15 @@ appropriate frequency scaling factor for each processor while considering the characteristics of each processor (computation power, range of frequencies, dynamic and static powers) and the task executed (computation/communication ratio). The aim being to reduce the overall energy consumption and to avoid -increasing significantly the execution time. In our previous -works~\cite{Our_first_paper} and \cite{pdsec2015}, we proposed a methods that select the optimal -frequency scaling factors for a homogeneous and a heterogeneous clusters respectively. -Both of the two methods executing a message passing -iterative synchronous application while giving the best trade-off between the -energy consumption and the performance for such applications. In this work we -are interested in heterogeneous grid as described above. Due to the +increasing significantly the execution time. +In our previous +works, \cite{Our_first_paper} and \cite{pdsec2015}, two methods that select the optimal +frequency scaling factors for a homogeneous and a heterogeneous cluster respectively, were proposed. +Both methods selects the frequencies that gives the best tradeoff between +energy consumption reduction and performance for message passing +iterative synchronous applications. In this work we +are interested in grids that are composed of heterogeneous clusters were the nodes have different characteristics such as dynamic power, static power, computation power, frequencies range, network latency and bandwidth. +Due to the heterogeneity of the processors, a vector of scaling factors should be selected and it must give the best trade-off between energy consumption and performance. @@ -511,13 +594,12 @@ equation, as follows: \Pnorm = \frac{\Told}{\Tnew} \end{equation} -\begin{figure}[!t] +\begin{figure} \centering \subfloat[Homogeneous cluster]{% - \includegraphics[width=.33\textwidth]{fig/homo}\label{fig:r1}}% - + \includegraphics[width=.4\textwidth]{fig/homo}\label{fig:r1}} \hspace{2cm}% \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} @@ -547,11 +629,13 @@ in~\cite{Zhuo_Energy.efficient.Dynamic.Task.Scheduling,Rauber_Analytical.Modelin \label{sec.optim} \begin{algorithm} +\setstretch{1} \begin{algorithmic}[1] % \footnotesize + \Require ~ \begin{description} - \item [{$N$}] number of clusters in the grid. + \item [{$N$}] number of clusters in the grid. \item [{$M$}] number of nodes in each cluster. \item[{$\Tcp[ij]$}] array of all computation times for all nodes during one iteration and with the highest frequency. \item[{$\Tcm[ij]$}] array of all communication times for all nodes during one iteration and with the highest frequency. @@ -579,8 +663,7 @@ in~\cite{Zhuo_Energy.efficient.Dynamic.Task.Scheduling,Rauber_Analytical.Modelin \EndIf \State $\Tnew \gets $ computed as in equations (\ref{eq:perf}). \State $\Ereduced \gets $ computed as in equations (\ref{eq:energy}). - \State $\Pnorm \gets \frac{\Told}{\Tnew}$ - \State $\Enorm\gets \frac{\Ereduced}{\Eoriginal}$ + \State $\Pnorm \gets \frac{\Told}{\Tnew}$, $\Enorm\gets \frac{\Ereduced}{\Eoriginal}$ \If{$(\Pnorm - \Enorm > \Dist)$} \State $\Sopt[ij] \gets S_{ij},~i=1,\dots,N,~j=1,\dots,M_i. $ \State $\Dist \gets \Pnorm - \Enorm$ @@ -613,7 +696,8 @@ in~\cite{Zhuo_Energy.efficient.Dynamic.Task.Scheduling,Rauber_Analytical.Modelin \end{algorithm} -In this section, the scaling factors selection algorithm for grids, algorithm~\ref{HSA}, is presented. It selects the vector of the frequency +In this section, the scaling factors selection algorithm for grids, algorithm~\ref{HSA}, +is presented. It selects the vector of the frequency scaling factors that gives the best trade-off between minimizing the energy consumption and maximizing the performance of a message passing synchronous iterative application executed on a grid. It works @@ -629,7 +713,7 @@ scaling algorithm is called in the iterative MPI program. \begin{figure}[!t] \centering - \includegraphics[scale=0.45]{fig/init_freq} + \includegraphics[scale=0.6]{fig/init_freq} \caption{Selecting the initial frequencies} \label{fig:st_freq} \end{figure} @@ -751,22 +835,18 @@ selected clusters and are presented in table \ref{table:grid5000}. \caption{The selected two sites of grid'5000} \label{fig:grid5000} \end{figure} - -The energy model and the scaling factors selection algorithm were applied to the NAS parallel benchmarks v3.3 \cite{NAS.Parallel.Benchmarks} and evaluated over grid'5000. -The benchmark suite contains seven applications: CG, MG, EP, LU, BT, SP and FT. These applications have different computations and communications ratios and strategies which make them good testbed applications to evaluate the proposed algorithm and energy model. -The benchmarks have seven different classes, S, W, A, B, C, D and E, that represent the size of the problem that the method solves. In this work, the class D was used for all benchmarks in all the experiments presented in the next sections. - - - - \begin{figure}[!t] \centering \includegraphics[scale=0.6]{fig/power_consumption.pdf} - \caption{The power consumption by one core from Taurus cluster} + \caption{The power consumption by one core from the Taurus cluster} \label{fig:power_cons} \end{figure} +The energy model and the scaling factors selection algorithm were applied to the NAS parallel benchmarks v3.3 \cite{NAS.Parallel.Benchmarks} and evaluated over grid'5000. +The benchmark suite contains seven applications: CG, MG, EP, LU, BT, SP and FT. These applications have different computations and communications ratios and strategies which make them good testbed applications to evaluate the proposed algorithm and energy model. +The benchmarks have seven different classes, S, W, A, B, C, D and E, that represent the size of the problem that the method solves. In this work, the class D was used for all benchmarks in all the experiments presented in the next sections. + \begin{table}[!t] @@ -847,28 +927,15 @@ Table \ref{tab:sc} shows the number of nodes used from each cluster for each sce & Griffon & Nancy & 6 \\ \hline \multirow{3}{*}{One site / 32 nodes} & Graphite & Nancy & 4 \\ \cline{2-4} - & Graphene & Nancy & 12 \\ \cline{2-4} - & Griffon & Nancy & 12 \\ + & Graphene & Nancy & 14 \\ \cline{2-4} + & Griffon & Nancy & 14 \\ \hline \end{tabular} \label{tab:sc} \end{table} -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/eng_con_scenarios.eps} - \caption{The energy consumptions of NAS benchmarks over different scenarios } - \label{fig:eng_sen} -\end{figure} - -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/time_scenarios.eps} - \caption{The execution times of NAS benchmarks over different scenarios } - \label{fig:time_sen} -\end{figure} The NAS parallel benchmarks are executed over these two platforms with different number of nodes, as in Table \ref{tab:sc}. @@ -893,29 +960,8 @@ scenario. Moreover, most of the benchmarks running over the one site scenario th However, the execution times and the energy consumptions of EP and MG benchmarks, which have no or small communications, are not significantly affected 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 - \includegraphics[scale=0.5]{fig/eng_s.eps} - \caption{The energy saving of NAS benchmarks over different scenarios } - \label{fig:eng_s} -\end{figure} - - -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/per_d.eps} - \caption{The performance degradation of NAS benchmarks over different scenarios } - \label{fig:per_d} -\end{figure} -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/dist.eps} - \caption{The tradeoff distance of NAS benchmarks over different scenarios } - \label{fig:dist} -\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, equation (\ref{eq:eorginal}), for all benchmarks as in figure \ref{fig:eng_s}. @@ -928,6 +974,18 @@ 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. +\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 energy saving percentage is reduced for all the benchmarks because of the long distance communications in the two sites @@ -943,12 +1001,23 @@ algorithm select smaller frequencies for the powerful nodes which produces less energy consumption and thus more energy saving. The best energy saving percentage was obtained in the one site scenario with 16 nodes, the energy consumption was on average reduced up to 30\%. - +\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} 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 -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. @@ -960,155 +1029,104 @@ 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 -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. - Finally, the best energy and performance tradeoff depends on all of the following: 1) the computations to communications ratio when there are communications and slack times, 2) the heterogeneity of the computing powers of the nodes and 3) the heterogeneity of the consumed static and dynamic powers of the nodes. -\subsection{The experimental results of multi-cores clusters} +\subsection{The experimental results over multi-cores clusters} \label{sec.res-mc} + The clusters of grid'5000 have different number of cores embedded in their nodes -as shown in Table \ref{table:grid5000}. The cores of each node can exchange -data via the shared memory \cite{rauber_book}. In -this section, the proposed scaling algorithm is evaluated over the grid'5000 grid while using multi-core nodes -selected according to the two platform scenarios described in the section \ref{sec.res}. -The two platform scenarios, the two sites and one site scenarios, use 32 -cores from multi-cores nodes instead of 32 distinct nodes. For example if -the participating number of cores from a certain cluster is equal to 12, -in the multi-core scenario the selected nodes is equal to 3 nodes while using -4 cores from each node. The platforms with one +as shown in Table \ref{table:grid5000}. In +this section, the proposed scaling algorithm is evaluated over the grid'5000 platform while using multi-cores nodes selected according to the one site scenario described in the section \ref{sec.res}. +The one site scenario uses 32 cores from multi-cores nodes instead of 32 distinct nodes. For example if +the participating number of cores from a certain cluster is equal to 14, +in the multi-core scenario the selected nodes is equal to 4 nodes while using +3 or 4 cores from each node. The platforms with one core per node and multi-cores nodes are shown in Table \ref{table:sen-mc}. -The energy consumptions and execution times of running the NAS parallel -benchmarks, class D, over these four different scenarios are presented +The energy consumptions and execution times of running the class D of the NAS parallel +benchmarks over these four different scenarios are presented in the figures \ref{fig:eng-cons-mc} and \ref{fig:time-mc} respectively. -The execution times for most of the NAS benchmarks are higher over the one site multi-cores per node scenario - than the execution time of those running over one site single core per node scenario. Indeed, - the communication times are higher in the one site multi-cores scenario than in the latter scenario because all the cores of a node share the same node network link which can be saturated when running communication bound applications. - - \textcolor{blue}{On the other hand, the execution times for most of the NAS benchmarks are lower over -the two sites multi-cores scenario than those over the two sites one core scenario. ??????? -} - -The experiments showed that for most of the NAS benchmarks and between the four scenarios, -the one site one core scenario gives the best execution times because the communication times are the lowest. -Indeed, in this scenario each core has a dedicated network link and all the communications are local. -Moreover, the energy consumptions of the NAS benchmarks are lower over the -one site one core scenario than over the one site multi-cores scenario because -the first scenario had less execution time than the latter which results in less static energy being consumed. - -The computations to communications ratios of the NAS benchmarks are higher over -the one site one core scenario when compared to the ratios of the other scenarios. -More energy reduction was achieved when this ratio is increased because the proposed scaling algorithm selects smaller frequencies that decrease the dynamic power consumption. - - \textcolor{blue}{ Whereas, the energy consumption in the two sites one core scenario is higher than the energy consumption of the two sites multi-core scenario. This is according to the increase in the execution time of the two sites one core scenario. } - - -These experiments also showed that the energy -consumption and the execution times of the EP and MG benchmarks do not change significantly over these four -scenarios because there are no or small communications, -which could increase or decrease the static power consumptions. Contrary to EP and MG, the energy consumptions -and the execution times of the rest of the benchmarks vary according to the communication times that are different from one scenario to the other. - - -The energy saving percentages of all NAS benchmarks running over these four scenarios are presented in the figure \ref{fig:eng-s-mc}. It shows that the energy saving percentages over the two sites multi-cores scenario -and over the two sites one core scenario are on average equal to 22\% and 18\% -respectively. The energy saving percentages are higher in the former scenario because its computations to communications ratio is higher than the ratio of the latter scenario as mentioned previously. - -In contrast, in the one site one -core and one site multi-cores scenarios the energy saving percentages -are approximately equivalent, on average they are up to 25\%. In both scenarios there -are a small difference in the computations to communications ratios, which leads -the proposed scaling algorithm to select similar frequencies for both scenarios. - -The performance degradation percentages of the NAS benchmarks are presented in -figure \ref{fig:per-d-mc}. It shows that the performance degradation percentages for the NAS benchmarks are higher over the two sites -multi-cores scenario than over the two sites one core scenario, equal on average to 7\% and 4\% respectively. -Moreover, using the two sites multi-cores scenario increased -the computations to communications ratio, which may increase -the overall execution time when the proposed scaling algorithm is applied and the frequencies scaled down. - - -When the benchmarks are executed over the one -site one core scenario, their performance degradation percentages are equal on average -to 10\% and are higher than those executed over the one site multi-cores scenario, -which on average is equal to 7\%. - -\textcolor{blue}{ -The performance degradation percentages over one site multi-cores is lower because the computations to communications ratio is decreased. Therefore, selecting small -frequencies by the scaling algorithm are proportional to this ratio, and thus the execution time do not increase significantly.} - - -The tradeoff distance percentages of the NAS -benchmarks over all scenarios are presented in the figure \ref{fig:dist-mc}. -These tradeoff distance percentages are used to verify which scenario is the best in terms of energy reduction and performance. The figure shows that using muti-cores in both of the one site and two sites scenarios gives bigger tradeoff distance percentages, on overage equal to 17.6\% and 15.3\% respectively, than using one core per node in both of one site and two sites scenarios, on average equal to 14.7\% and 13.3\% respectively. - \begin{table}[] \centering \caption{The multicores scenarios} - \begin{tabular}{|*{4}{c|}} \hline Scenario name & Cluster name & \begin{tabular}[c]{@{}c@{}}No. of nodes\\ in each cluster\end{tabular} & \begin{tabular}[c]{@{}c@{}}No. of cores\\ for each node\end{tabular} \\ \hline -\multirow{3}{*}{Two sites/ one core} & Taurus & 10 & 1 \\ \cline{2-4} - & Graphene & 10 & 1 \\ \cline{2-4} - & Griffon & 12 & 1 \\ \hline -\multirow{3}{*}{Two sites/ multicores} & Taurus & 3 & 3 or 4 \\ \cline{2-4} - & Graphene & 3 & 3 or 4 \\ \cline{2-4} - & Griffon & 3 & 4 \\ \hline -\multirow{3}{*}{One site/ one core} & Graphite & 4 & 1 \\ \cline{2-4} - & Graphene & 12 & 1 \\ \cline{2-4} - & Griffon & 12 & 1 \\ \hline -\multirow{3}{*}{One site/ multicores} & Graphite & 3 & 3 or 4 \\ \cline{2-4} - & Graphene & 3 & 3 or 4 \\ \cline{2-4} - & Griffon & 3 & 4 \\ \hline +\multirow{3}{*}{One core per node} & Graphite & 4 & 1 \\ \cline{2-4} + & Graphene & 14 & 1 \\ \cline{2-4} + & Griffon & 14 & 1 \\ \hline +\multirow{3}{*}{Multi-cores per node} & Graphite & 1 & 4 \\ \cline{2-4} + & Graphene & 4 & 3 or 4 \\ \cline{2-4} + & Griffon & 4 & 3 or 4 \\ \hline \end{tabular} \label{table:sen-mc} \end{table} + \begin{figure} \centering - \includegraphics[scale=0.5]{fig/eng_con.eps} - \caption{Comparing the energy consumptions of running NAS benchmarks over one core and multicores scenarios } - \label{fig:eng-cons-mc} + \subfloat[Comparing the execution times of running NAS benchmarks over one core and multicores scenarios]{% + \includegraphics[width=.4\textwidth]{fig/time.eps}\label{fig:time-mc}} \hspace{1cm}% + \subfloat[Comparing the energy consumptions of running NAS benchmarks over one core and multi-cores scenarios]{% + \includegraphics[width=.4\textwidth]{fig/eng_con.eps}\label{fig:eng-cons-mc}} + \label{fig:eng-cons} + \caption{The energy consumptions and execution times of NAS benchmarks over one core and multi-cores per node architectures} \end{figure} - \begin{figure} - \centering - \includegraphics[scale=0.5]{fig/time.eps} - \caption{Comparing the execution times of running NAS benchmarks over one core and multicores scenarios } - \label{fig:time-mc} -\end{figure} - \begin{figure} - \centering - \includegraphics[scale=0.5]{fig/eng_s_mc.eps} - \caption{The energy saving of running NAS benchmarks over one core and multicores scenarios } - \label{fig:eng-s-mc} -\end{figure} +The execution times for most of the NAS benchmarks are higher over the multi-cores per node scenario +than over single core per node scenario. Indeed, + the communication times are higher in the one site multi-cores scenario than in the latter scenario because all the cores of a node share the same node network link which can be saturated when running communication bound applications. Moreover, the cores of a node share the memory bus which can be also saturated and become a bottleneck. +Moreover, the energy consumptions of the NAS benchmarks are lower over the + one core scenario than over the multi-cores scenario because +the first scenario had less execution time than the latter which results in less static energy being consumed. +The computations to communications ratios of the NAS benchmarks are higher over +the one site one core scenario when compared to the ratio of the multi-cores scenario. +More energy reduction can be gained when this ratio is big because it pushes the proposed scaling algorithm to select smaller frequencies that decrease the dynamic power consumption. These experiments also showed that the energy +consumption and the execution times of the EP and MG benchmarks do not change significantly over these two +scenarios because there are no or small communications. Contrary to EP and MG, the energy consumptions and the execution times of the rest of the benchmarks vary according to the communication times that are different from one scenario to the other. + + +The energy saving percentages of all NAS benchmarks running over these two scenarios are presented in the figure \ref{fig:eng-s-mc}. +The figure shows that the energy saving percentages in the one +core and the multi-cores scenarios +are approximately equivalent, on average they are equal to 25.9\% and 25.1\% respectively. +The energy consumption is reduced at the same rate in the two scenarios when compared to the energy consumption of the executions without DVFS. + + +The performance degradation percentages of the NAS benchmarks are presented in +figure \ref{fig:per-d-mc}. It shows that the performance degradation percentages is higher for the NAS benchmarks over the one core per node scenario (on average equal to 10.6\%) than over the multi-cores scenario (on average equal to 7.5\%). The performance degradation percentages over the multi-cores scenario is lower because the computations to communications ratio is smaller than the ratio of the other scenario. + +The tradeoff distance percentages of the NAS benchmarks over the two scenarios are presented +in the figure \ref{fig:dist-mc}. These tradeoff distance between energy consumption reduction and performance are used to verify which scenario is the best in both terms at the same time. The figure shows that the tradeoff distance percentages are on average bigger over the multi-cores scenario (17.6\%) than over the one core per node scenario (15.3\%). + -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/per_d_mc.eps} - \caption{The performance degradation of running NAS benchmarks over one core and multicores scenarios } - \label{fig:per-d-mc} -\end{figure} \begin{figure} \centering - \includegraphics[scale=0.5]{fig/dist_mc.eps} - \caption{The tradeoff distance of running NAS benchmarks over one core and multicores scenarios } - \label{fig:dist-mc} + \subfloat[The energy saving of running NAS benchmarks over one core and multicores scenarios]{% + \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 + ]{% + \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]{% + \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} + + \subsection{Experiments with different static and dynamic powers consumption scenarios} \label{sec.pow_sen} @@ -1116,176 +1134,137 @@ In section \ref{sec.grid5000}, since it was not possible to measure the static p The aim of this section is to evaluate the scaling algorithm while assuming different values of static powers. In addition to the previously used percentage of static power, two new static power ratios, 10\% and 30\% of the measured dynamic power of the core, are used in this section. -The experiments have been executed with these two new static power scenarios and over the one site one core per node scenario. -In these experiments, the class D of the NAS parallel benchmarks are executed over Nancy's site. 16 computing nodes from the three sites, Graphite, Graphene and Griffon, where used in this experiment. +The experiments have been executed with these two new static power scenarios over the one site one core per node scenario. +In these experiments, the class D of the NAS parallel benchmarks are executed over Nancy's site. 16 computing nodes from the three clusters, Graphite, Graphene and Griffon, where used in this experiment. - \begin{figure} - \centering - \includegraphics[scale=0.5]{fig/eng_pow.eps} - \caption{The energy saving percentages for NAS benchmarks of the three power scenario} - \label{fig:eng-pow} -\end{figure} \begin{figure} \centering - \includegraphics[scale=0.5]{fig/per_pow.eps} - \caption{The performance degradation percentages for NAS benchmarks of the three power scenario} - \label{fig:per-pow} + \subfloat[The energy saving percentages for the nodes executing the NAS benchmarks over the three power scenarios]{% + \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]{% + \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]{% + + \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} -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/dist_pow.eps} - \caption{The tradeoff distance for NAS benchmarks of the three power scenario} - \label{fig:dist-pow} -\end{figure} \begin{figure} \centering - \includegraphics[scale=0.47]{fig/three_scenarios.pdf} - \caption{Comparing the selected frequency scaling factors of MG benchmark for three static power scenarios} + \includegraphics[scale=0.5]{fig/three_scenarios.pdf} + \caption{Comparing the selected frequency scaling factors for the MG benchmark over the three static power scenarios} \label{fig:fre-pow} \end{figure} - The energy saving percentages of the NAS benchmarks with the three static power scenarios are presented in figure \ref{fig:eng_sen}. This figure shows that the 10\% of static power scenario -gives the biggest energy saving percentage in comparison to the 20\% and 30\% static power -scenarios. The small value of static power consumption makes the proposed +gives the biggest energy saving percentages in comparison to the 20\% and 30\% static power +scenarios. The small value of the static power consumption makes the proposed scaling algorithm select smaller frequencies for the CPUs. These smaller frequencies reduce the dynamic energy consumption more than increasing the consumed static energy which gives less overall energy consumption. The energy saving percentages of the 30\% static power scenario is the smallest between the other scenarios, because the scaling algorithm selects bigger frequencies for the CPUs which increases the energy consumption. Figure \ref{fig:fre-pow} demonstrates that the proposed scaling algorithm selects the best frequency scaling factors according to the static power consumption ratio being used. -\textcolor{blue}{ -The performance degradation percentages are presented in the figure \ref{fig:per-pow}, -the 30\% of static power scenario had less performance degradation percentage. This because -bigger frequencies are selected for the CPUs by the scaling algorithm. While, -the inverse happens in the 20\% and 30\% scenarios, because the scaling algorithm selects bigger -frequencies. -The tradeoff distance percentage for the NAS benchmarks with these three static power scenarios -are presented in the figure \ref{fig:dist}. It shows that the tradeoff -distance percentage is the best when the 10\% of static power scenario is used, and this percentage -is decreased for the other two scenarios because of different frequencies have being selected by the scaling algorithm. -In EP benchmark, the results of energy saving, performance degradation and tradeoff -distance are showed small differences when the these static power scenarios are used. -In this benchmark there are no communications which leads the proposed scaling algorithm to select similar frequencies even if the static power values are different. While, the -inverse has been shown for the rest of the benchmarks, which have different communication times. -This makes the scaling algorithm proportionally selects big or small frequencies for each benchmark, -because the communication times proportionally increase or decrease the static energy consumption. } +The performance degradation percentages are presented in the figure \ref{fig:per-pow}. +The 30\% static power scenario had less performance degradation percentage because the scaling algorithm +had selected big frequencies for the CPUs. While, +the inverse happens in the 10\% and 20\% scenarios because the scaling algorithm had selected CPUs' frequencies smaller than those of the 30\% scenario. The tradeoff distance percentage for the NAS benchmarks with these three static power scenarios +are presented in the figure \ref{fig:dist}. +It shows that the best tradeoff +distance percentage is obtained with the 10\% static power scenario and this percentage +is decreased for the other two scenarios because the scaling algorithm had selected different frequencies according to the static power values. + +In the EP benchmark, the energy saving, performance degradation and tradeoff +distance percentages for the these static power scenarios are not significantly different because there is no communication in this benchmark. Therefore, the static power is only consumed during computation and the proposed scaling algorithm selects similar frequencies for the three scenarios. On the other hand, for the rest of the benchmarks, the scaling algorithm selects the values of the frequencies according to the communication times of each benchmark because the static energy consumption increases proportionally to the communication times. + \subsection{The comparison of the proposed frequencies selecting algorithm } \label{sec.compare_EDP} -\textcolor{blue}{ -The tradeoff between the energy consumption and the performance of the parallel -applications had significant importance in the domain of the research. -Many researchers, \cite{EDP_for_multi_processors,Energy_aware_application_scheduling,Exploring_Energy_Performance_TradeOffs}, -have optimized the tradeoff between the energy and the performance using the well known energy and delay product, $EDP=energy \times delay$. -This model is also used by Spiliopoulos et al. algorithm \cite{Spiliopoulos_Green.governors.Adaptive.DVFS}, -the objective is to select the frequencies that minimized EDP product for the multi-cores -architecture when DVFS is used. Moreover, their algorithm is applied online, which synchronously optimized the energy consumption -and the execution time. Both energy consumption and execution time of a processor are predicted by the their algorithm. -In this section the proposed frequencies selection algorithm, called Maxdist is compared with Spiliopoulos et al. algorithm, called EDP. -To make both of the algorithms follow the same direction and fairly comparing them, the same energy model, equation \ref{eq:energy} and -the execution time model, equation \ref{eq:perf}, are used in the prediction process to select the best vector of the frequencies. -In contrast, the proposed algorithm starts the search space from the lower bound computed as in equation the \ref{eq:Fint}. Also, the algorithm -stops the search process when it is reached to the lower bound as mentioned before. In the same way, the EDP algorithm is developed to start from the -same upper bound used in Maxdist algorithm, and it stops the search process when a minimum available frequencies is reached. -Finally, the resulting EDP algorithm is an exhaustive search algorithm that test all possible frequencies, starting from the initial frequencies, -and selecting those minimized the EDP product. -Both algorithms were applied to NAS benchmarks, class D, over 16 nodes selected from grid'5000 clusters. -The participating computing nodes are distributed between two sites and one site to have two different scenarios that used in the section \ref{sec.res}. -The experimental results: the energy saving, performance degradation and tradeoff distance percentages are -presented in the figures \ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-dist} respectively. -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/edp_eng} - \caption{Comparing of the energy saving for the proposed method with EDP method} - \label{fig:edp-eng} -\end{figure} -\begin{figure} - \centering - \includegraphics[scale=0.5]{fig/edp_per} - \caption{Comparing of the performance degradation for the proposed method with EDP method} - \label{fig:edp-perf} -\end{figure} + +Finding the frequencies that gives the best tradeoff between the energy consumption and the performance for a parallel +application is not a trivial task. Many algorithms have been proposed to tackle this problem. +In this section, the proposed frequencies selecting algorithm is compared to a method that uses the well known energy and delay product objective function, $EDP=energy \times delay$, that has been used by many researchers \cite{EDP_for_multi_processors,Energy_aware_application_scheduling,Exploring_Energy_Performance_TradeOffs}. +This objective function was also used by Spiliopoulos et al. algorithm \cite{Spiliopoulos_Green.governors.Adaptive.DVFS} where they select the frequencies that minimize the EDP product and apply them with DVFS operations to the multi-cores +architecture. Their online algorithm predicts the energy consumption and execution time of a processor before using the EDP method. + +To fairly compare the proposed frequencies scaling algorithm to Spiliopoulos et al. algorithm, called Maxdist and EDP respectively, both algorithms use the same energy model, equation \ref{eq:energy} and +execution time model, equation \ref{eq:perf}, to predict the energy consumption and the execution time for each computing node. +Moreover, both algorithms start the search space from the upper bound computed as in equation \ref{eq:Fint}. +Finally, the resulting EDP algorithm is an exhaustive search algorithm that tests all the possible frequencies, starting from the initial frequencies (upper bound), +and selects the vector of frequencies that minimize the EDP product. + +Both algorithms were applied to the class D of the NAS benchmarks over 16 nodes. +The participating computing nodes are distributed according to the two scenarios described in section \ref{sec.res}. +The experimental results, the energy saving, performance degradation and tradeoff distance percentages, are +presented in the figures \ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-dist} respectively. + + \begin{figure} \centering - \includegraphics[scale=0.5]{fig/edp_dist} - \caption{Comparing of the tradeoff distance for the proposed method with EDP method} - \label{fig:edp-dist} + \subfloat[The energy reduction induced by the Maxdist method and the EDP method]{% + \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]{% + \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]{% + \includegraphics[width=.4\textwidth]{fig/edp_dist}\label{fig:edp-dist}} + \label{fig:edp-comparison} + \caption{The comparison results} \end{figure} -As shown form these figures, the proposed frequencies selection algorithm, Maxdist, outperform the EDP algorithm in term of energy and performance for all of the benchmarks executed over the two scenarios. -Generally, the proposed algorithm gives better results for all benchmarks because it is -optimized the distance between the energy saving and the performance degradation in the same time. + +As shown in these figures, the proposed frequencies selection algorithm, Maxdist, outperforms the EDP algorithm in terms of energy consumption reduction and performance for all of the benchmarks executed over the two scenarios. +The proposed algorithm gives better results than EDP because it +maximizes the energy saving and the performance at the same time. Moreover, the proposed scaling algorithm gives the same weight for these two metrics. -Whereas, the EDP algorithm gives some times negative tradeoff values for some benchmarks in the two sites scenarios. +Whereas, the EDP algorithm gives sometimes negative tradeoff values for some benchmarks in the two sites scenarios. These negative tradeoff values mean that the performance degradation percentage is higher than energy saving percentage. -The higher positive value of the tradeoff distance percentage mean that the energy saving percentage is much higher than the performance degradation percentage. +The high positive values of the tradeoff distance percentage mean that the energy saving percentage is much higher than the performance degradation percentage. The time complexity of both Maxdist and EDP algorithms are $O(N \cdot M \cdot F)$ and -$O(N \cdot M \cdot F^2)$ respectively. Where $N$ is the number of the clusters, $M$ is the number of nodes and $F$ is the -maximum number of available frequencies. The proposed algorithm, Maxdist, has selected the best frequencies in a small execution time, -on average is equal to 0.01 $ms$, when it is executed over 32 nodes distributed between Nancy and Lyon sites. -While the EDP algorithm was slower than Maxdist algorithm by ten times over the same number of nodes and same distribution, its execution time on average -is equal to 0.1 $ms$. -} +$O(N \cdot M \cdot F^2)$ respectively, where $N$ is the number of the clusters, $M$ is the number of nodes and $F$ is the +maximum number of available frequencies. When Maxdist is applied to a benchmark that is being executed over 32 nodes distributed between Nancy and Lyon sites, it takes on average $0.01 ms$ to compute the best frequencies while EDP is on average ten times slower over the same architecture. \section{Conclusion} \label{sec.concl} -\textcolor{blue}{ -This paper has been presented a new online frequencies selection algorithm. -It works based on objective function that maximized the tradeoff distance +This paper has presented a new online frequencies selection algorithm. + The algorithm selects the best vector of +frequencies that maximizes the tradeoff distance between the predicted energy consumption and the predicted execution time of the distributed -iterative applications running over heterogeneous grid. The algorithm selects the best vector of the -frequencies which maximized the objective function has been used. A new energy model -used by the proposed algorithm for measuring and predicting the energy consumption -of the distributed iterative message passing application running over grid architecture. +iterative applications running over a heterogeneous grid. A new energy model +is used by the proposed algorithm to predict the energy consumption +of the distributed iterative message passing application running over a grid architecture. To evaluate the proposed method on a real heterogeneous grid platform, it was applied on the -NAS parallel benchmarks class D instance and executed over grid'5000 testbed platform. -The experimental results showed that the algorithm saves the energy consumptions on average -for all NAS benchmarks up to 30\% while gives only 3\% percentage on average for the performance -degradation for the same instance. The algorithm also selecting different frequencies according to the -computations and communication times ratio, and according to the values of the static and measured dynamic power of the CPUs. The computations to communications ratio was varied between different scenarios have been used, concerning to the distribution of the computing nodes between different clusters' sites and using one core or multi-cores per node. -Finally, the proposed algorithm was compared to other algorithm which it -used the will known energy and delay product as an objective function. The comparison results showed -that the proposed algorithm outperform the other one in term of energy-time tradeoff. + 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 3.2\% 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 use multi-cores per node architecture or consume different static power values. 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 well known energy and delay product as an objective function. The comparison results showed +that the proposed algorithm outperforms the latter by selecting a vector of frequencies that gives a better tradeoff between energy consumption reduction and performance. + In the near future, we would like to develop a similar method that is adapted to -asynchronous iterative applications where each task does not -wait for other tasks to finish their works. The development of +asynchronous iterative applications where iterations are not synchronized and communications are overlapped with computations. + The development of such a method might require a new energy model because the number of iterations is not known in advance and depends on the global convergence of the iterative system. -} + \section*{Acknowledgment} This work has been partially supported by the Labex ACTION project (contract -``ANR-11-LABX-01-01''). Computations have been performed on the supercomputer -facilities of the Mésocentre de calcul de Franche-Comté. As a PhD student, +``ANR-11-LABX-01-01''). Computations have been performed on the Grid'5000 platform. As a PhD student, Mr. Ahmed Fanfakh, would like to thank the University of Babylon (Iraq) for supporting his work. -% trigger a \newpage just before the given reference -% number - used to balance the columns on the last page -% adjust value as needed - may need to be readjusted if -% the document is modified later -%\IEEEtriggeratref{15} +\section*{References} +\bibliography{my_reference} -\bibliographystyle{IEEEtran} -\bibliography{IEEEabrv,my_reference} \end{document} -%%% Local Variables: -%%% mode: latex -%%% TeX-master: t -%%% fill-column: 80 -%%% ispell-local-dictionary: "american" -%%% End: - -% LocalWords: Fanfakh Charr FIXME Tianhe DVFS HPC NAS NPB SMPI Rauber's Rauber -% LocalWords: CMOS EPSA Franche Comté Tflop Rünger IUT Maréchal Juin cedex GPU -% LocalWords: de badri muslim MPI SimGrid GFlops Xeon EP BT GPUs CPUs AMD -% LocalWords: Spiliopoulos scalability +