From: afanfakh Date: Wed, 25 May 2016 09:36:06 +0000 (+0200) Subject: adding reviewers remarks X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy2.git/commitdiff_plain/726291de7fb06ef88f7cda08fa69ba2a075a554a adding reviewers remarks --- diff --git a/mpi-energy2-extension/Heter_paper.tex b/mpi-energy2-extension/Heter_paper.tex index 6754e6f..29d06ab 100644 --- a/mpi-energy2-extension/Heter_paper.tex +++ b/mpi-energy2-extension/Heter_paper.tex @@ -108,7 +108,7 @@ \title{Optimizing Energy Consumption with DVFS for Message \\ - Passing Iterative Applications on \\ + Passing Applications \textcolor{blue}{with iterations} on \\ Grid Architectures} @@ -143,10 +143,10 @@ scaling (DVFS) is one of them. It can be used to reduce the power consumption of 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. + computing the message passing application \textcolor{blue}{with iterations}. 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. + for message passing applications \textcolor{blue}{with iterations} 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 on 16 nodes, distributed on three clusters, show that it reduces on average the energy consumption by \np[\%]{30} while the performance is on average only degraded @@ -192,8 +192,8 @@ This heterogeneous platform executes more than 7 GFlops per watt while consuming 50.32 kilowatts. 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 +to lower the energy consumption of these platforms, such as DVFS, scheduling \textcolor{blue}{and other techniques}. + DVFS is a widely used process to reduce the energy consumption of a processor by lowering its frequency \cite{Rizvandi_Some.Observations.on.Optimal.Frequency}. However, it also reduces the number of FLOPS executed by the processor which may increase the execution @@ -201,8 +201,8 @@ time of the application running over that processor. Therefore, researchers use different optimization strategies to select the frequency that gives the best trade-off between the energy reduction and performance degradation ratio. In \cite{Our_first_paper} and \cite{pdsec2015}, a frequency selecting algorithm -was proposed to reduce the energy consumption of message passing iterative -applications running over homogeneous and heterogeneous clusters respectively. +was proposed to reduce the energy consumption of message passing +applications \textcolor{blue}{with iterations} running over homogeneous and heterogeneous clusters respectively. The results of the experiments showed significant energy consumption reductions. All the experimental results were conducted over the SimGrid simulator \cite{SimGrid}, which offers easy tools to describe homogeneous and heterogeneous platforms, and to simulate the execution of message passing parallel @@ -212,7 +212,7 @@ In this paper, a new frequency 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 + application \textcolor{blue}{with iterations} 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. @@ -228,7 +228,7 @@ 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 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 +It also evaluates the algorithm over multi-core 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. @@ -253,10 +253,10 @@ The methods could be heuristics, exact or brute force methods that satisfy varied objectives such as energy reduction or performance. They also could be adapted to the execution's environment and the type of the application such as sequential, parallel or distributed architecture, homogeneous or heterogeneous -platform, synchronous or asynchronous application, \dots{} +platform, synchronous or asynchronous application. In this paper, we are interested in reducing energy for message passing -iterative synchronous applications running over heterogeneous grid platforms. Some + synchronous applications \textcolor{blue}{with iterations} running over heterogeneous grid platforms. Some works have already been done for such platforms and they can be classified into two types of heterogeneous platforms: \begin{itemize} @@ -303,8 +303,8 @@ while respecting given time constraints. This approach had considerable overhead. In contrast to the above described papers, this paper presents the following contributions : \begin{enumerate} -\item two new energy and performance models for message passing iterative - synchronous applications running over a heterogeneous grid platform. Both models +\item two new energy and performance models for message passing + synchronous applications \textcolor{blue}{with iterations} running over a heterogeneous grid platform. Both models take into account communication and slack times. The models can predict the required energy and the execution time of the application. @@ -312,7 +312,7 @@ following contributions : platforms. The algorithm has a very small overhead and does not need any training nor profiling. It uses a new optimization function which simultaneously maximizes the performance and minimizes the energy consumption - of a message passing iterative synchronous application. + of a message passing synchronous application \textcolor{blue}{with iterations}. \end{enumerate} @@ -321,23 +321,26 @@ following contributions : \section{The performance and energy consumption measurements on heterogeneous grid architecture} \label{sec.exe} -\subsection{The execution time of message passing distributed iterative - applications on a heterogeneous platform} +\subsection{The execution time of message passing distributed + applications \textcolor{blue}{with iterations} on a heterogeneous platform} In this paper, we are interested in reducing the energy consumption of message -passing distributed iterative synchronous applications running over +passing distributed synchronous applications \textcolor{blue}{with iterations} running over heterogeneous grid platforms. A heterogeneous grid platform could be defined as a collection of heterogeneous computing clusters interconnected via a long distance network which has lower bandwidth and higher latency than the local networks of the clusters. Each computing cluster in the grid is composed of homogeneous nodes that are connected together via high speed network. Therefore, each cluster has different characteristics such as computing power (FLOPS), energy consumption, CPU's frequency range, network bandwidth and latency. -The overall execution time of a distributed iterative synchronous application +The overall execution time of a distributed synchronous application \textcolor{blue}{with iterations} over a heterogeneous grid consists of the sum of the computation time and -the communication time for every iteration on a node. However, due to the -heterogeneous computation power of the computing clusters, slack times may occur -when fast nodes have to wait, during synchronous communications, for the slower -nodes to finish their computations (see Figure~\ref{fig:heter}). Therefore, the +the communication time for every iteration on a node. +\textcolor{blue}{However, nodes from distinct clusters in a grid have different computing powers, thus +while executing message passing \textcolor{blue}{with iterations} synchronous applications, fast nodes +have to wait for the slower ones to finish their computations before being able +to synchronously communicate with them as in Figure~\ref{fig:heter}. These +periods are called idle or slack times. } +Therefore, the overall execution time of the program is the execution time of the slowest task -which has the highest computation time and no slack time. +which has the highest computation time and no slack time. \textcolor{blue}{For example, in Figure \ref{fig:heter} the task 1 is the slower task which has no slack time (not waits for the other nodes) and it is only has the communication times.} \begin{figure}[!t] \centering @@ -358,6 +361,7 @@ as in (\ref{eq:s}). \label{eq:s} S = \frac{\Fmax}{\Fnew} \end{equation} +\textcolor{blue}{Where $\Fmax$ is the maximum frequency before applying DVFS and $\Fnew$ is the new frequency after applying DVFS.} The execution time of a compute bound sequential program is linearly proportional to the frequency scaling factor $S$. On the other hand, message passing distributed applications consist of two parts: computation and @@ -372,36 +376,35 @@ synchronously sent or received. Since in a heterogeneous grid each cluster has different characteristics, especially different frequency gears, when applying DVFS operations on the nodes of these clusters, they may get different scaling factors represented by a scaling vector: -$(S_{11}, S_{12},\dots, S_{NM})$ where $S_{ij}$ is the scaling factor of processor $j$ in cluster $i$ . To -be able to predict the execution time of message passing synchronous iterative -applications running over a heterogeneous grid, for different vectors of +$(S_{11}, S_{12},\dots, S_{NM_i})$ where $S_{ij}$ is the scaling factor of processor $j$ in cluster $i$ . To +be able to predict the execution time of message passing synchronous +applications \textcolor{blue}{with iterations} running over a heterogeneous grid, for different vectors of scaling factors, the communication time and the computation time for all the tasks must be measured during the first iteration before applying any DVFS operation. Then the execution time for one iteration of the application with any -vector of scaling factors can be predicted using (\ref{eq:perf}). +vector of scaling factors can be predicted using Equation (\ref{eq:perf}). % \begin{equation} \label{eq:perf} - \Tnew = \mathop{\max_{i=1,\dots N}}_{j=1,\dots,M}({\TcpOld[ij]} \cdot S_{ij}) - +\mathop{\min_{j=1,\dots,M}} (\Tcm[hj]) + \Tnew = \mathop{\max_{i=1,\dots N}}_{j=1,\dots,M_i}({\TcpOld[ij]} \cdot S_{ij}) + +\mathop{\min_{j=1,\dots,M_i}} (\Tcm[hj]) \end{equation} % -where $N$ is the number of clusters in the grid, $M$ is the number of nodes in -each cluster, $\TcpOld[ij]$ is the computation time of processor $j$ in the cluster $i$ +where $N$ is the number of clusters in the grid, $M_i$ is the number of nodes in + cluster $i$, $\TcpOld[ij]$ is the computation time of processor $j$ in the cluster $i$ and $\Tcm[hj]$ is the communication time of processor $j$ in the cluster $h$ during the first iteration. The execution time for one iteration is equal to the sum of the maximum computation time for all nodes with the new scaling factors -and the slowest communication time without slack time during one iteration. -The latter is equal to the communication time of the slowest node in the slowest cluster $h$. +and \textcolor{blue}{the communication time of the slower node without slack time during one iteration. +The slower node $h$ is the node that gives maximum execution time in all clusters befor scaling its frequency.} It means that only the communication time without any slack time is taken into account. -Therefore, the execution time of the iterative application is equal to -the execution time of one iteration as in (\ref{eq:perf}) multiplied by the +Therefore, the execution time of the application \textcolor{blue}{with iterations} is equal to +the execution time of one iteration as in Equation (\ref{eq:perf}) multiplied by the number of iterations of that application. This prediction model is developed from the model to predict the execution time of message passing distributed applications for homogeneous and heterogeneous clusters -~\cite{Our_first_paper,pdsec2015}. The execution time prediction model is -used in the method to optimize both the energy consumption and the performance -of iterative methods, which is presented in the following sections. +~\cite{Our_first_paper,pdsec2015}. \textcolor{blue}{where the homogeneous cluster predication model was used one scaling factor denoted as $S$, because all the nodes in the cluster have the same computing powers. Whereas, in heterogeneous cluster prediction model all the nodes have different scales and the scaling factors have denoted as one dimensional vector $(S_1, S_2, \dots, S_N)$. The execution time prediction model for a grid Equation \ref{eq:perf} defines a two dimensional array of scales +$(S_{11}, S_{12},\dots, S_{NM_i})$}. This model is used in the method to optimize both the energy consumption and the performance of iterative methods, which is presented in the following sections. \subsection{Energy model for heterogeneous grid platform} @@ -472,7 +475,7 @@ by the new time of computation and is given by the following equation: \end{equation} The static power is related to the power leakage of the CPU and is consumed during computation and even when idle. As -in~\cite{Rauber_Analytical.Modeling.for.Energy,Zhuo_Energy.efficient.Dynamic.Task.Scheduling}, +in~\cite{Rauber_Analytical.Modeling.for.Energy, Zhuo_Energy.efficient.Dynamic.Task.Scheduling}, the static power of a processor is considered as constant during idle and computation periods, and for all its available frequencies. The static energy is the static power multiplied by the execution time of the program. According @@ -488,9 +491,9 @@ processor after scaling its frequency is computed as follows: In the considered heterogeneous grid platform, each node $j$ in cluster $i$ may have different dynamic and static powers from the nodes of the other clusters, -noted as $\Pd[ij]$ and $\Ps[ij]$ respectively. Therefore, even if the distributed -message passing iterative application is load balanced, the computation time of each CPU $j$ -in cluster $i$ noted $\Tcp[ij]$ may be slightly different due to the delay caused by the scheduler of the operating system. Therefore, different frequency scaling factors may be +noted as $\Pd[ij]$ and $\Ps[ij]$ respectively. \textcolor{blue}{Therefore, even if the distributed +message passing application \textcolor{blue}{with iterations} is load balanced, the computation time of each CPU $j$ +in cluster $i$ noted $\Tcp[ij]$ may be slightly different due to the delay caused by the scheduler of the operating system}. Therefore, different frequency scaling factors may be computed in order to decrease the overall energy consumption of the application and reduce the slack times. The communication time of a processor $j$ in cluster $i$ is noted as $\Tcm[ij]$ and could contain slack times when communicating with slower nodes, @@ -498,24 +501,26 @@ see Figure~\ref{fig:heter}. Therefore, all nodes do not have equal communication times. While the dynamic energy is computed according to the frequency scaling factor and the dynamic power of each node as in (\ref{eq:Edyn}), the static energy is computed as the sum of the execution time -of one iteration multiplied by the static power of each processor. The overall -energy consumption of a message passing distributed application executed over a +of one iteration multiplied by the static power of each processor. +\textcolor{blue}{ The CPU during the communication times consumes only the static power. While +in the computation times, it consumes both the dynamic and the static power refer to \cite{Freeh_Exploring.the.Energy.Time.Tradeoff}.} +The overall energy consumption of a message passing distributed application executed over a heterogeneous grid platform during one iteration is the summation of all dynamic and -static energies for $M$ processors in $N$ clusters. It is computed as follows: +static energies for $M_i$ processors in $N$ clusters. It is computed as follows: \begin{multline} \label{eq:energy} - E = \sum_{i=1}^{N} \sum_{i=1}^{M} {(S_{ij}^{-2} \cdot \Pd[ij] \cdot \Tcp[ij])} + - \sum_{i=1}^{N} \sum_{j=1}^{M} (\Ps[ij] \cdot {} \\ - (\mathop{\max_{i=1,\dots N}}_{j=1,\dots,M}({\Tcp[ij]} \cdot S_{ij}) - +\mathop{\min_{j=1,\dots M}} (\Tcm[hj]) )) + E = \sum_{i=1}^{N} \sum_{i=1}^{M_i} {(S_{ij}^{-2} \cdot \Pd[ij] \cdot \Tcp[ij])} + + \sum_{i=1}^{N} \sum_{j=1}^{M_i} (\Ps[ij] \cdot {} \\ + (\mathop{\max_{i=1,\dots N}}_{j=1,\dots,M_i}({\Tcp[ij]} \cdot S_{ij}) + +\mathop{\min_{j=1,\dots M_i}} (\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 +factors $(S_{11}, S_{12},\dots, S_{NM_i})$ may degrade the performance of the application and thus, increase the static energy because the execution time is increased~\cite{Kim_Leakage.Current.Moore.Law}. The overall energy consumption -for the iterative application can be measured by measuring the energy +for the application \textcolor{blue}{with iterations} can be measured by measuring the energy consumption for one iteration as in (\ref{eq:energy}) multiplied by the number of iterations of that application. @@ -540,8 +545,8 @@ works, \cite{Our_first_paper} and \cite{pdsec2015}, two methods that select the frequency scaling factors for a homogeneous and a heterogeneous cluster respectively, were proposed. Both methods selects the frequencies that gives the best trade-off 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 + synchronous applications \textcolor{blue}{with iterations}. In this work we +are interested in grids that are composed of heterogeneous clusters, \textcolor{blue}{where} 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 @@ -563,12 +568,13 @@ maximum frequency for all nodes) as follows: \end{equation} % where $Tnew$ is computed as in (\ref{eq:perf}) and $Told$ is computed as in (\ref{eq:told}). -% +\textcolor{blue}{ \begin{equation} \label{eq:told} - \Told = \mathop{\max_{i=1,2,\dots,N}}_{j=1,2,\dots,M} (\Tcp[ij]+\Tcm[ij]) + \Told = \mathop{\max_{i=1,\dots N}}_{j=1,\dots,M_i}({\TcpOld[ij]} ) + +\mathop{\min_{j=1,\dots,M_i}} (\Tcm[hj]) \end{equation} -% +} In the same way, the energy is normalized by computing the ratio between the consumed energy while scaling down the frequency and the consumed energy with maximum frequency for all nodes: @@ -583,8 +589,8 @@ computed as in (\ref{eq:eorginal}). % \begin{equation} \label{eq:eorginal} - \Eoriginal = \sum_{i=1}^{N} \sum_{j=1}^{M} ( \Pd[ij] \cdot \Tcp[ij]) + - \mathop{\sum_{i=1}^{N}} \sum_{j=1}^{M} (\Ps[ij] \cdot \Told) + \Eoriginal = \sum_{i=1}^{N} \sum_{j=1}^{M_i} ( \Pd[ij] \cdot \Tcp[ij]) + + \mathop{\sum_{i=1}^{N}} \sum_{j=1}^{M_i} (\Ps[ij] \cdot \Told) \end{equation} While the main goal is to optimize the energy and execution time at the same @@ -623,12 +629,12 @@ Figure~\ref{fig:r2}. Then the objective function has the following form: \begin{equation} \label{eq:max} \MaxDist = -\mathop{ \mathop{\max_{i=1,\dots N}}_{j=1,\dots,M}}_{k=1,\dots,F} +\mathop{ \mathop{\max_{i=1,\dots N}}_{j=1,\dots,M_i}}_{k=1,\dots,F_j} (\overbrace{\Pnorm(S_{ijk})}^{\text{Maximize}} - \overbrace{\Enorm(S_{ijk})}^{\text{Minimize}} ) \end{equation} -where $N$ is the number of clusters, $M$ is the number of nodes in each cluster and -$F$ is the number of available frequencies for each node. Then, the optimal set +where $N$ is the number of clusters, $M_i$ is the number of nodes in the cluster $i$ and +$F_j$ is the number of available frequencies in the node $j$. Then, the optimal set of scaling factors that satisfies (\ref{eq:max}) can be selected. The objective function can work with any energy model or any power values for each node (static and dynamic powers). However, the most important @@ -709,8 +715,8 @@ In this section, the scaling factors selection algorithm for grids, Algorithm~\ 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 -online during the execution time of the iterative message passing program. It +synchronous application \textcolor{blue}{with iterations} executed on a grid. It works +online during the execution time of the message passing program \textcolor{blue}{with iterations}. It uses information gathered during the first iteration such as the computation time and the communication time in one iteration for each node. The algorithm is executed after the first iteration and returns a vector of optimal frequency @@ -718,20 +724,18 @@ scaling factors that satisfies the objective function (\ref{eq:max}). The program applies DVFS operations to change the frequencies of the CPUs according to the computed scaling factors. This algorithm is called just once during the execution of the program. Algorithm~\ref{dvfs} shows where and when the proposed -scaling algorithm is called in the iterative MPI program. +scaling algorithm is called in the MPI program \textcolor{blue}{with iterations}. \begin{figure}[!t] \centering \includegraphics[scale=0.6]{fig/init_freq} - \caption{Selecting the initial frequencies} + \caption{Selecting the initial frequencies in a grid platform} \label{fig:st_freq} \end{figure} -Nodes from distinct clusters in a grid have different computing powers, thus -while executing message passing iterative synchronous applications, fast nodes -have to wait for the slower ones to finish their computations before being able -to synchronously communicate with them as in Figure~\ref{fig:heter}. These -periods are called idle or slack times. The algorithm takes into account this + + +The algorithm takes into account this problem and tries to reduce these slack times when selecting the vector of the frequency scaling factors. At first, it selects initial frequency scaling factors that increase the execution times of fast nodes and minimize the differences @@ -805,7 +809,7 @@ the clusters and their nodes are connected via high speed local area networks. Two types of local networks are used, Ethernet or Infiniband networks which have different characteristics in terms of bandwidth and latency. Since Grid'5000 is dedicated to testing, contrary to production grids it allows a user to deploy its own customized operating system on all the booked nodes. The user could have root rights and thus apply DVFS operations while executing a distributed application. Moreover, the Grid'5000 testbed provides at some sites a power measurement tool to capture -the power consumption for each node in those sites. The measured power is the overall consumed power by all the components of a node at a given instant, such as CPU, hard drive, main-board, memory, \dots{} For more details refer to +the power consumption for each node in those sites. The measured power is the overall consumed power by all the components of a node at a given instant, such as CPU, hard drive, main-board and memory. For more details refer to \cite{Energy_measurement}. In order to correctly measure the CPU power of one core in a node $j$, firstly, the power consumed by the node while being idle at instant $y$, noted as $\Pidle[jy]$, was measured. Then, the power was measured while running a single thread benchmark with no communication (no idle time) over the same node with its CPU scaled to the maximum available frequency. The latter power measured at time $x$ with maximum frequency for one core of node $j$ is noted $\Pmax[jx]$. The difference between the two measured power consumptions represents the dynamic power consumption of that core with the maximum frequency, see Figure~\ref{fig:power_cons}. @@ -850,13 +854,16 @@ selected clusters and are presented in Table~\ref{table:grid5000}. 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 benchmark suite contains seven applications: CG, MG, EP, LU, BT, SP and FT. \textcolor{blue}{These benchmarks are message passing applications with iterations compute +the same block of operations several times, starting from the initial solution until reaching +the acceptable approximation of the exact solution.} + 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, class D was used for all benchmarks in all the experiments presented in the next sections. \begin{table}[!t] - \caption{CPUs characteristics of the selected clusters} + \caption{The characteristics of the CPUs in the selected clusters} % title of Table \centering \begin{tabular}{|*{7}{c|}} @@ -890,7 +897,7 @@ The benchmarks have seven different classes, S, W, A, B, C, D and E, that repres \subsection{The experimental results of the scaling algorithm} \label{sec.res} In this section, the results of the application of the scaling factors selection algorithm \ref{HSA} -to the NAS parallel benchmarks are presented. +to the NAS parallel benchmarks are presented. \textcolor{blue}{Each experiment of this section and next sections has been executed many times and the results presented in the figures are the average values of many execution.} As mentioned previously, the experiments were conducted over two sites of Grid'5000, Lyon and Nancy sites. @@ -913,7 +920,7 @@ Table~\ref{tab:sc} shows the number of nodes used from each cluster for each sce \begin{table}[h] -\caption{The different clusters scenarios} +\caption{The different grid scenarios} \centering \begin{tabular}{|*{4}{c|}} \hline @@ -940,8 +947,16 @@ Table~\ref{tab:sc} shows the number of nodes used from each cluster for each sce \label{tab:sc} \end{table} - - +\begin{figure} + \centering + \subfloat[The energy consumption by the nodes wile executing the NAS benchmarks over different scenarios + ]{% + \includegraphics[width=.48\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{0.4cm}% + \subfloat[The execution times of the NAS benchmarks over different scenarios]{% + \includegraphics[width=.48\textwidth]{fig/time_scenarios.eps}\label{fig:time_sen}} + \label{fig:exp-time-energy} + \caption{The energy consumption and execution time of NAS Benchmarks over different scenarios} +\end{figure} The NAS parallel benchmarks are executed over these two platforms with different number of nodes, as in Table~\ref{tab:sc}. @@ -949,7 +964,7 @@ The overall energy consumption of all the benchmarks solving the class D instanc using the proposed frequency selection algorithm is measured using the equation of the reduced energy consumption, Equation~\ref{eq:energy}. This model uses the measured dynamic power showed in Table~\ref{table:grid5000} and the static -power is assumed to be equal to 20\% of the dynamic power. The execution +power is assumed to be equal to 20\% of the dynamic power \textcolor{blue}{as in \cite{Rauber_Analytical.Modeling.for.Energy}}. The execution time is measured for all the benchmarks over these different scenarios. The energy consumptions and the execution times for all the benchmarks are @@ -960,14 +975,14 @@ for 16 and 32 nodes is lower than the energy consumed while using two sites. The long distance communications between the two distributed sites increase the idle time, which leads to more static energy consumption. The execution times of these benchmarks -over one site with 16 and 32 nodes are also lower when compared to those of the two sites -scenario. Moreover, most of the benchmarks running over the one site scenario have their execution times approximately divided by two when the number of computing nodes is doubled from 16 to 32 nodes (linear speed up according to the number of the nodes). +over one site with 16 and 32 nodes are also lower than those of the two sites +scenario. Moreover, most of the benchmarks running over the one site scenario have their execution times approximately halved when the number of computing nodes is doubled from 16 to 32 nodes (linear speed up according to the number of the nodes). -However, the execution times and the energy consumptions of EP and MG +However, the execution times and the energy consumptions of the 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 communication times of the rest of the benchmarks increases when -using long distance communications between two sites or increasing the number of +other hand, the communication times of the rest of the benchmarks increase when +using long distance communications between two sites or when increasing the number of computing nodes. @@ -982,18 +997,20 @@ results in a lower energy consumption. Indeed, the dynamic consumed power is exponentially related to the CPU's frequency value. On the other hand, the increase in the number of computing nodes can increase the communication times and thus produces less energy saving depending on the benchmarks being executed. The results of 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=.48\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{0.4cm}% - \subfloat[The execution times of the NAS benchmarks over different scenarios]{% - \includegraphics[width=.48\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} +energy saving percentage in the one site scenario when executed over 16 nodes than over 32 nodes. 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*}[!h] + \centering + \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{% + \includegraphics[width=.48\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{0.4cm}% + \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{% + \includegraphics[width=.48\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{0.4cm}% + \subfloat[The trade-off distance between the energy reduction and the performance of the NAS benchmarks + over different scenarios]{% + \includegraphics[width=.48\textwidth]{fig/dist.eps}\label{fig:dist}} + \label{fig:exp-res} + \caption{The experimental results of different scenarios} +\end{figure*} @@ -1010,30 +1027,19 @@ 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*}[t] - \centering - \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{% - \includegraphics[width=.48\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{0.4cm}% - \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{% - \includegraphics[width=.48\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{0.4cm}% - \subfloat[The trade-off distance between the energy reduction and the performance of the NAS benchmarks - over different scenarios]{% - \includegraphics[width=.48\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 8.3\% 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 3.2\% or 10.6\% respectively. In contrary 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\% and 10.6\% respectively. In contrary 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. The performance degradation percentage of the EP benchmark after applying the scaling factors selection algorithm is the highest in comparison to the other benchmarks. Indeed, in the EP benchmark, there are no communication and slack times and its performance degradation percentage only depends on the frequencies values selected by the algorithm for the computing nodes. -The rest of the benchmarks showed different performance degradation percentages, which decrease +The rest of the benchmarks showed different performance degradation percentages which decrease 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 trade-off distance percentage can be @@ -1048,25 +1054,25 @@ which increase the computations to communications ratio and the latter uses lon -\subsection{The experimental results over multi-cores clusters} +\subsection{The experimental results over multi-core 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}. 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 Section~\ref{sec.res}. -The one site scenario uses 32 cores from multi-cores nodes instead of 32 distinct nodes. For example if +The one site scenario uses 32 cores from multi-core 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 class D of the NAS parallel -benchmarks over these two different scenarios are presented +in the multi-core scenario 4 nodes are selected and +3 or 4 cores from each node are used. The platforms with one +core per node and multi-core nodes are shown in Table~\ref{table:sen-mc}. +The energy consumptions and execution times of running the class D of the NAS parallel +benchmarks over these two different platforms are presented in Figures \ref{fig:eng-cons-mc} and \ref{fig:time-mc} respectively. -\begin{table}[] +\begin{table}[!h] \centering -\caption{The multicores scenarios} +\caption{The multi-core scenarios} \begin{tabular}{|*{4}{c|}} \hline Scenario name & Cluster name & Nodes per cluster & @@ -1074,7 +1080,7 @@ Scenario name & Cluster name & Nodes per cluster & \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} +\multirow{3}{*}{Multi-core per node} & Graphite & 1 & 4 \\ \cline{2-4} & Graphene & 4 & 3 or 4 \\ \cline{2-4} & Griffon & 4 & 3 or 4 \\ \hline \end{tabular} @@ -1082,54 +1088,54 @@ Scenario name & Cluster name & Nodes per cluster & \end{table} -\begin{figure} +\begin{figure}[!h] \centering - \subfloat[Comparing the execution times of running NAS benchmarks over one core and multicores scenarios]{% + \subfloat[Comparing the execution times of running the NAS benchmarks over one core and multi-core scenarios]{% \includegraphics[width=.48\textwidth]{fig/time.eps}\label{fig:time-mc}} \hspace{0.4cm}% - \subfloat[Comparing the energy consumptions of running NAS benchmarks over one core and multi-cores scenarios]{% + \subfloat[Comparing the energy consumptions of running the NAS benchmarks over one core and multi-core scenarios]{% \includegraphics[width=.48\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} + \caption{The energy consumptions and execution times of the NAS benchmarks running over one core and multi-core per node architectures} \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. +The execution times for most of the NAS benchmarks are higher over the multi-core per node scenario +than over the single core per node scenario. Indeed, + the communication times are higher in the one site multi-core 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 + one core scenario than over the multi-core 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. +the one site one core scenario when compared to the ratio of the multi-core 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. \begin{figure*}[t] \centering - \subfloat[The energy saving of running NAS benchmarks over one core and multicores scenarios]{% + \subfloat[The energy saving of running NAS benchmarks over one core and multicore scenarios]{% \includegraphics[width=.48\textwidth]{fig/eng_s_mc.eps}\label{fig:eng-s-mc}} \hspace{0.4cm}% - \subfloat[The performance degradation of running NAS benchmarks over one core and multicores scenarios + \subfloat[The performance degradation of running NAS benchmarks over one core and multi-core scenarios ]{% \includegraphics[width=.48\textwidth]{fig/per_d_mc.eps}\label{fig:per-d-mc}}\hspace{0.4cm}% - \subfloat[The trade-off distance of running NAS benchmarks over one core and multicores scenarios]{% + \subfloat[The trade-off distance of running NAS benchmarks over one core and multicore scenarios]{% \includegraphics[width=.48\textwidth]{fig/dist_mc.eps}\label{fig:dist-mc}} \label{fig:exp-res2} - \caption{The experimental results of one core and multi-cores scenarios} + \caption{The experimental results of one core and multi-core scenarios} \end{figure*} -The energy saving percentages of all NAS benchmarks running over these two scenarios are presented in Figure~\ref{fig:eng-s-mc}. +The energy saving percentages of all the NAS benchmarks running over these two scenarios are presented in Figure~\ref{fig:eng-s-mc}. The figure shows that the energy saving percentages in the one -core and the multi-cores scenarios +core and the multi-core 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 are 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 are lower because the computations to communications ratios are smaller than the ratios of the other scenario. +Figure~\ref{fig:per-d-mc}. It shows that the performance degradation percentages are higher for the NAS benchmarks executed over the one core per node scenario (on average equal to 10.6\%) than over the multi-core scenario (on average equal to 7.5\%). The performance degradation percentages over the multi-core scenario are lower because the computations to communications ratios are smaller than the ratios of the other scenario. -The trade-off distances percentages of the NAS benchmarks over the two scenarios are presented -in ~Figure~\ref{fig:dist-mc}. These trade-off distances 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 trade-off distance percentages are on average bigger over the multi-cores scenario (17.6\%) than over the one core per node scenario (15.3\%). +The trade-off distances percentages of the NAS benchmarks over both scenarios are presented +in ~Figure~\ref{fig:dist-mc}. These trade-off distances 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 trade-off distance percentages are on average bigger over the multi-core scenario (17.6\%) than over the one core per node scenario (15.3\%). @@ -1145,7 +1151,7 @@ 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 over the one site one core per node scenario. -In these experiments, class D of the NAS parallel benchmarks are executed over the Nancy site. 16 computing nodes from the three clusters, Graphite, Graphene and Griffon, where used in this experiment. +In these experiments, the class D of the NAS parallel benchmarks were executed over the Nancy site. 16 computing nodes from the three clusters, Graphite, Graphene and Griffon, were used in this experiment. \begin{figure*}[t] @@ -1171,18 +1177,18 @@ In these experiments, class D of the NAS parallel benchmarks are executed over t \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 +in Figure~\ref{fig:eng-pow}. This figure shows that the 10\% of static power scenario 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. +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. The performance degradation percentages are presented in 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 trade-off distance percentage for the NAS benchmarks with these three static power scenarios -are presented in Figure~\ref{fig:dist}. +are presented in Figure~\ref{fig:dist-pow}. It shows that the best trade-off 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. @@ -1198,21 +1204,8 @@ distance percentages for these static power scenarios are not significantly diff Finding the frequencies that give the best trade-off 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 +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-core 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 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 trade-off distance percentages, are -presented in Figures~\ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-dist} respectively. - - \begin{figure*}[t] \centering \subfloat[The energy reduction induced by the Maxdist method and the EDP method]{% @@ -1224,17 +1217,27 @@ presented in Figures~\ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-dis \label{fig:edp-comparison} \caption{The comparison results} \end{figure*} +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 running 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 trade-off distance percentages, are +presented in Figures~\ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp-dist} respectively. 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 +The proposed algorithm gives better results than the EDP method 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 sometimes negative trade-off values for some benchmarks in the two sites scenarios. These negative trade-off values mean that the performance degradation percentage is higher than the energy saving percentage. The high positive values of the trade-off 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. 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. +The complexity of both algorithms, Maxdist and EDP, are of order $O(N \cdot M_i \cdot F_j)$ and +$O(N \cdot M_i \cdot F_j^2)$ respectively, where $N$ is the number of the clusters, $M_i$ is the number of nodes and $F_j$ 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 the EDP method is on average ten times slower over the same architecture. \section{Conclusion} @@ -1243,21 +1246,22 @@ This paper presents a new online frequencies selection algorithm. The algorithm selects the best vector of frequencies that maximizes the trade-off distance between the predicted energy consumption and the predicted execution time of the distributed -iterative applications running over a heterogeneous grid. A new energy model + applications \textcolor{blue}{with iterations} 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. +of the distributed message passing application \textcolor{blue}{with iterations} running over a grid architecture. To evaluate the proposed method on a real heterogeneous grid platform, it was applied on the - NAS parallel benchmarks and the class D instance was executed over the Grid'5000 testbed platform. - The experiments on 16 nodes, distributed over three clusters, showed that the algorithm on average reduces by 30\% the energy consumption +NAS parallel benchmarks and the class D instance was executed over the Grid'5000 testbed platform. +The experiments executed on 16 nodes, distributed over three clusters, showed that the algorithm on average reduces by 30\% the energy consumption for all the NAS benchmarks while on average only degrading by 3.2\% 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 vectors of frequencies according to the +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-core per node architecture or consume different static power values. The algorithm selects different vectors 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 trade-off 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 iterations are not synchronized and communications are overlapped with computations. +In the near future, \textcolor{blue}{we will adapt the proposed algorithm to take the variability between some iterations in two steps. In the first step, the algorithm selects the best frequencies at the end of the first iterations and apply them to the system. In the second step, after some iterations (e.g. 5 iterations) the algorithm recomputes the frequencies depending on the average of the communication and computation times for all previous iterations. It will change the frequency of each node if the new frequency is different from the old one. Otherwise, it keeps the old frequency.} +Also, we would like to develop a similar method that is adapted to +asynchronous applications \textcolor{blue}{with iterations} 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. diff --git a/mpi-energy2-extension/fig/commtasks.pdf b/mpi-energy2-extension/fig/commtasks.pdf index 1b1498c..0e39a6d 100644 Binary files a/mpi-energy2-extension/fig/commtasks.pdf and b/mpi-energy2-extension/fig/commtasks.pdf differ diff --git a/mpi-energy2-extension/fig/eng_con.eps b/mpi-energy2-extension/fig/eng_con.eps index 814faa1..6600740 100644 --- a/mpi-energy2-extension/fig/eng_con.eps +++ b/mpi-energy2-extension/fig/eng_con.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 17:46:42 2015 +%%CreationDate: Tue May 24 10:35:14 2016 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 17:46:42 2015) + /CreationDate (Tue May 24 10:35:14 2016) /DOCINFO pdfmark end } ifelse @@ -534,294 +534,246 @@ stroke ] -50.0 MRshow 1.000 UL LTb -803 414 M +803 427 M 31 0 V 4007 0 R -31 0 V -803 477 M +803 502 M 31 0 V 4007 0 R -31 0 V -803 539 M +803 576 M 31 0 V 4007 0 R -31 0 V -803 601 M +803 651 M 31 0 V 4007 0 R -31 0 V -803 664 M +803 726 M 63 0 V 3975 0 R -63 0 V stroke -737 664 M +737 726 M [ [(Helvetica) 150.0 0.0 true true 0 ( 300000)] ] -50.0 MRshow 1.000 UL LTb -803 726 M +803 801 M 31 0 V 4007 0 R -31 0 V -803 788 M +803 875 M 31 0 V 4007 0 R -31 0 V -803 851 M +803 950 M 31 0 V 4007 0 R -31 0 V -803 913 M +803 1025 M 31 0 V 4007 0 R -31 0 V -803 975 M +803 1100 M 63 0 V 3975 0 R -63 0 V stroke -737 975 M +737 1100 M [ [(Helvetica) 150.0 0.0 true true 0 ( 600000)] ] -50.0 MRshow 1.000 UL LTb -803 1038 M +803 1175 M 31 0 V 4007 0 R -31 0 V -803 1100 M +803 1249 M 31 0 V 4007 0 R -31 0 V -803 1162 M +803 1324 M 31 0 V 4007 0 R -31 0 V -803 1224 M +803 1399 M 31 0 V 4007 0 R -31 0 V -803 1287 M +803 1474 M 63 0 V 3975 0 R -63 0 V stroke -737 1287 M +737 1474 M [ [(Helvetica) 150.0 0.0 true true 0 ( 900000)] ] -50.0 MRshow 1.000 UL LTb -803 1349 M +803 1549 M 31 0 V 4007 0 R -31 0 V -803 1411 M +803 1623 M 31 0 V 4007 0 R -31 0 V -803 1474 M +803 1698 M 31 0 V 4007 0 R -31 0 V -803 1536 M +803 1773 M 31 0 V 4007 0 R -31 0 V -803 1598 M +803 1848 M 63 0 V 3975 0 R -63 0 V stroke -737 1598 M +737 1848 M [ [(Helvetica) 150.0 0.0 true true 0 ( 1.2e+06)] ] -50.0 MRshow 1.000 UL LTb -803 1661 M +803 1922 M 31 0 V 4007 0 R -31 0 V -803 1723 M +803 1997 M 31 0 V 4007 0 R -31 0 V -803 1785 M +803 2072 M 31 0 V 4007 0 R -31 0 V -803 1848 M +803 2147 M 31 0 V 4007 0 R -31 0 V -803 1910 M +803 2222 M 63 0 V 3975 0 R -63 0 V stroke -737 1910 M +737 2222 M [ [(Helvetica) 150.0 0.0 true true 0 ( 1.5e+06)] ] -50.0 MRshow 1.000 UL LTb -803 1972 M +803 2296 M 31 0 V 4007 0 R -31 0 V -803 2035 M +803 2371 M 31 0 V 4007 0 R -31 0 V -803 2097 M +803 2446 M 31 0 V 4007 0 R -31 0 V -803 2159 M +803 2521 M 31 0 V 4007 0 R -31 0 V -803 2222 M +803 2596 M 63 0 V 3975 0 R -63 0 V stroke -737 2222 M +737 2596 M [ [(Helvetica) 150.0 0.0 true true 0 ( 1.8e+06)] ] -50.0 MRshow 1.000 UL LTb -803 2284 M +803 2670 M 31 0 V 4007 0 R -31 0 V -803 2346 M +803 2745 M 31 0 V 4007 0 R -31 0 V -803 2409 M +803 2820 M 31 0 V 4007 0 R -31 0 V -803 2471 M +803 2895 M 31 0 V 4007 0 R -31 0 V -803 2533 M +803 2969 M 63 0 V 3975 0 R -63 0 V stroke -737 2533 M +737 2969 M [ [(Helvetica) 150.0 0.0 true true 0 ( 2.1e+06)] ] -50.0 MRshow 1.000 UL LTb -803 2596 M +803 3044 M 31 0 V 4007 0 R -31 0 V -803 2658 M +803 3119 M 31 0 V 4007 0 R -31 0 V -803 2720 M +803 3194 M 31 0 V 4007 0 R -31 0 V -803 2782 M +803 3269 M 31 0 V 4007 0 R -31 0 V -803 2845 M +803 3343 M 63 0 V 3975 0 R -63 0 V stroke -737 2845 M +737 3343 M [ [(Helvetica) 150.0 0.0 true true 0 ( 2.4e+06)] ] -50.0 MRshow 1.000 UL LTb -803 2907 M +803 3418 M 31 0 V 4007 0 R -31 0 V -803 2969 M -31 0 V -4007 0 R --31 0 V -803 3032 M -31 0 V -4007 0 R --31 0 V -803 3094 M -31 0 V -4007 0 R --31 0 V -803 3156 M -63 0 V -3975 0 R --63 0 V -stroke -737 3156 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 2.7e+06)] -] -50.0 MRshow -1.000 UL -LTb -803 3219 M -31 0 V -4007 0 R --31 0 V -803 3281 M -31 0 V -4007 0 R --31 0 V -803 3343 M -31 0 V -4007 0 R --31 0 V -803 3406 M -31 0 V -4007 0 R --31 0 V -803 3468 M -63 0 V -3975 0 R --63 0 V -stroke -737 3468 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 3e+06)] -] -50.0 MRshow -1.000 UL -LTb -803 352 M +1308 352 M 0 63 V 0 3053 R 0 -63 V stroke -803 242 M +1466 242 M [ [(Helvetica) 150.0 0.0 true true 0 (CG)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -1476 352 M +1813 352 M 0 63 V 0 3053 R 0 -63 V stroke -1476 242 M +1971 242 M [ [(Helvetica) 150.0 0.0 true true 0 (MG)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -2149 352 M +2317 352 M 0 63 V 0 3053 R 0 -63 V stroke -2149 242 M +2475 242 M [ [(Helvetica) 150.0 0.0 true true 0 (EP)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb 2822 352 M @@ -829,39 +781,39 @@ LTb 0 3053 R 0 -63 V stroke -2822 242 M +2980 242 M [ [(Helvetica) 150.0 0.0 true true 0 (LU)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -3495 352 M +3327 352 M 0 63 V 0 3053 R 0 -63 V stroke -3495 242 M +3485 242 M [ [(Helvetica) 150.0 0.0 true true 0 (BT)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -4168 352 M +3832 352 M 0 63 V 0 3053 R 0 -63 V stroke -4168 242 M +3990 242 M [ [(Helvetica) 150.0 0.0 true true 0 (SP)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -4841 352 M +4336 352 M 0 63 V 0 3053 R 0 -63 V stroke -4841 242 M +4494 242 M [ [(Helvetica) 150.0 0.0 true true 0 (FT)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb 1.000 UL @@ -888,58 +840,38 @@ LTb 1.000 UL LTb % Begin plot #1 -1.000 UP 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2767 3298 M +2666 3277 M [ [(Helvetica) 140.0 0.0 true true 0 (One core per node scenario)] ] -46.7 MRshow LT0 -0.10 0.10 0.44 C 2833 3298 M -327 0 V -803 768 M -1476 427 L -673 92 V -673 625 V -3495 610 L -673 1288 V -4841 705 L -803 768 Pls -1476 427 Pls -2149 519 Pls -2822 1144 Pls -3495 610 Pls -4168 1898 Pls -4841 705 Pls -2996 3298 Pls +0.10 0.10 0.44 C 1.000 2732 3244 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 1257 352 102 500 BoxColFill +0.10 0.10 0.44 C 1.000 1762 352 102 91 BoxColFill +0.10 0.10 0.44 C 1.000 2267 352 102 202 BoxColFill +0.10 0.10 0.44 C 1.000 2772 352 101 952 BoxColFill +0.10 0.10 0.44 C 1.000 3276 352 102 310 BoxColFill +0.10 0.10 0.44 C 1.000 3781 352 102 1856 BoxColFill +0.10 0.10 0.44 C 1.000 4286 352 102 425 BoxColFill % End plot #1 % Begin plot #2 -1.000 UP 1.000 UL LT1 -1.00 0.00 0.00 C LCb setrgbcolor -2767 3166 M +0.94 0.50 0.50 C LCb setrgbcolor +2666 3145 M [ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2833 3166 M -327 0 V -803 1231 M -1476 494 L -673 48 V -673 355 V -3495 718 L -673 2118 V -4841 631 L -803 1231 Crs -1476 494 Crs -2149 542 Crs -2822 897 Crs -3495 718 Crs -4168 2836 Crs -4841 631 Crs -2996 3166 Crs +0.94 0.50 0.50 C 1.000 2732 3112 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 1383 352 102 1056 BoxColFill +0.94 0.50 0.50 C 1.000 1888 352 102 172 BoxColFill +0.94 0.50 0.50 C 1.000 2393 352 102 229 BoxColFill +0.94 0.50 0.50 C 1.000 2898 352 102 654 BoxColFill +0.94 0.50 0.50 C 1.000 3402 352 102 440 BoxColFill +0.94 0.50 0.50 C 1.000 3907 352 102 2982 BoxColFill +0.94 0.50 0.50 C 1.000 4412 352 102 336 BoxColFill % End plot #2 1.000 UL LTb diff --git a/mpi-energy2-extension/fig/eng_con_scenarios-eps-converted-to.pdf b/mpi-energy2-extension/fig/eng_con_scenarios-eps-converted-to.pdf index 82cb5fd..04deeb3 100644 Binary files a/mpi-energy2-extension/fig/eng_con_scenarios-eps-converted-to.pdf and b/mpi-energy2-extension/fig/eng_con_scenarios-eps-converted-to.pdf differ diff --git a/mpi-energy2-extension/fig/eng_con_scenarios.eps b/mpi-energy2-extension/fig/eng_con_scenarios.eps index 7feac40..346571b 100644 --- a/mpi-energy2-extension/fig/eng_con_scenarios.eps +++ b/mpi-energy2-extension/fig/eng_con_scenarios.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 12:39:18 2015 +%%CreationDate: Tue May 24 10:13:23 2016 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 12:39:18 2015) + /CreationDate (Tue May 24 10:13:23 2016) /DOCINFO pdfmark end } ifelse @@ -746,32 +746,32 @@ LTb 31 0 V 4007 0 R -31 0 V -803 352 M +1308 352 M 0 63 V 0 3053 R 0 -63 V stroke -803 242 M +1308 242 M [ [(Helvetica) 150.0 0.0 true true 0 (CG)] ] -50.0 MCshow 1.000 UL LTb -1476 352 M +1813 352 M 0 63 V 0 3053 R 0 -63 V stroke -1476 242 M +1813 242 M [ [(Helvetica) 150.0 0.0 true true 0 (MG)] ] -50.0 MCshow 1.000 UL LTb -2149 352 M +2317 352 M 0 63 V 0 3053 R 0 -63 V stroke -2149 242 M +2317 242 M [ [(Helvetica) 150.0 0.0 true true 0 (EP)] ] -50.0 MCshow 1.000 UL @@ -786,32 +786,32 @@ stroke ] -50.0 MCshow 1.000 UL LTb -3495 352 M +3327 352 M 0 63 V 0 3053 R 0 -63 V stroke -3495 242 M +3327 242 M [ [(Helvetica) 150.0 0.0 true true 0 (BT)] ] -50.0 MCshow 1.000 UL LTb -4168 352 M +3832 352 M 0 63 V 0 3053 R 0 -63 V stroke -4168 242 M +3832 242 M [ [(Helvetica) 150.0 0.0 true true 0 (SP)] ] -50.0 MCshow 1.000 UL LTb -4841 352 M +4336 352 M 0 63 V 0 3053 R 0 -63 V stroke -4841 242 M +4336 242 M [ [(Helvetica) 150.0 0.0 true true 0 (FT)] ] -50.0 MCshow 1.000 UL @@ -840,112 +840,72 @@ LTb 1.000 UL LTb % Begin plot #1 -1.000 UP 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2228 3277 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ 16 nodes)] +2262 3277 M +[ [(Helvetica) 140.0 0.0 true true 0 (One site / 16 nodes)] ] -46.7 MRshow LT0 -0.10 0.10 0.44 C 2294 3277 M -327 0 V -803 804 M -1476 430 L -673 152 V -673 1594 V -673 -817 V -673 683 V -4841 731 L -803 804 Pls -1476 430 Pls -2149 582 Pls -2822 2176 Pls -3495 1359 Pls -4168 2042 Pls -4841 731 Pls -2457 3277 Pls +0.10 0.10 0.44 C 2328 3244 327 66 40 45 2 PatternFill +0.10 0.10 0.44 C 1190 352 68 453 40 45 2 PatternFill +0.10 0.10 0.44 C 1695 352 68 79 40 45 2 PatternFill +0.10 0.10 0.44 C 2199 352 69 231 40 45 2 PatternFill +0.10 0.10 0.44 C 2704 352 69 1825 40 45 2 PatternFill +0.10 0.10 0.44 C 3209 352 68 1008 40 45 2 PatternFill +0.10 0.10 0.44 C 3714 352 68 1691 40 45 2 PatternFill +0.10 0.10 0.44 C 4218 352 69 380 40 45 2 PatternFill % End plot #1 % Begin plot #2 -1.000 UP 1.000 UL LT1 -1.00 0.00 0.00 C LCb setrgbcolor -2228 3145 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ 32 nodes)] +0.10 0.10 0.44 C LCb setrgbcolor +2262 3145 M +[ [(Helvetica) 140.0 0.0 true true 0 (One site / 32 nodes)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2294 3145 M -327 0 V -803 851 M -1476 442 L -673 111 V -673 750 V -3495 661 L -673 1546 V -4841 776 L -803 851 Crs -1476 442 Crs -2149 553 Crs -2822 1303 Crs -3495 661 Crs -4168 2207 Crs -4841 776 Crs -2457 3145 Crs +0.10 0.10 0.44 C 1.000 2328 3112 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 1274 352 68 500 BoxColFill +0.10 0.10 0.44 C 1.000 1779 352 68 91 BoxColFill +0.10 0.10 0.44 C 1.000 2284 352 68 202 BoxColFill +0.10 0.10 0.44 C 1.000 2788 352 69 952 BoxColFill +0.10 0.10 0.44 C 1.000 3293 352 68 310 BoxColFill +0.10 0.10 0.44 C 1.000 3798 352 68 1856 BoxColFill +0.10 0.10 0.44 C 1.000 4303 352 68 425 BoxColFill % End plot #2 % Begin plot #3 -1.000 UP 1.000 UL -LT2 +LT0 0.00 0.39 0.00 C LCb setrgbcolor -2228 3013 M -[ [(Helvetica) 140.0 0.0 true true 0 (Two sites/ 16 nodes)] +2262 3013 M +[ [(Helvetica) 140.0 0.0 true true 0 (Two sites / 16 nodes)] ] -46.7 MRshow -LT2 -0.00 0.39 0.00 C 2294 3013 M -327 0 V -803 1202 M -1476 475 L -673 78 V -673 1763 V -673 -909 V -673 1111 V -4841 1228 L -803 1202 Star -1476 475 Star -2149 553 Star -2822 2316 Star -3495 1407 Star -4168 2518 Star -4841 1228 Star -2457 3013 Star +LT0 +0.00 0.39 0.00 C 2328 2980 327 66 80 -45 1 PatternFill +0.00 0.39 0.00 C 1358 352 69 851 80 -45 1 PatternFill +0.00 0.39 0.00 C 1863 352 68 124 80 -45 1 PatternFill +0.00 0.39 0.00 C 2368 352 68 202 80 -45 1 PatternFill +0.00 0.39 0.00 C 2872 352 69 1965 80 -45 1 PatternFill +0.00 0.39 0.00 C 3377 352 69 1056 80 -45 1 PatternFill +0.00 0.39 0.00 C 3882 352 68 2167 80 -45 1 PatternFill +0.00 0.39 0.00 C 4387 352 68 877 80 -45 1 PatternFill % End plot #3 % Begin plot #4 -1.000 UP 1.000 UL LT3 -0.72 0.53 0.04 C LCb setrgbcolor -2228 2881 M -[ [(Helvetica) 140.0 0.0 true true 0 (Two sites/ 32 nodes)] +0.94 0.50 0.50 C LCb setrgbcolor +2262 2881 M +[ [(Helvetica) 140.0 0.0 true true 0 (Two sites / 32 nodes)] ] -46.7 MRshow LT3 -0.72 0.53 0.04 C 2294 2881 M -327 0 V -803 1704 M -1476 504 L -673 45 V -673 1278 V -673 -69 V -673 1532 V -4841 1258 L -803 1704 Box -1476 504 Box -2149 549 Box -2822 1827 Box -3495 1758 Box -4168 3290 Box -4841 1258 Box -2457 2881 Box +0.94 0.50 0.50 C 1.000 2328 2848 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 1442 352 69 1353 BoxColFill +0.94 0.50 0.50 C 1.000 1947 352 68 153 BoxColFill +0.94 0.50 0.50 C 1.000 2452 352 68 198 BoxColFill +0.94 0.50 0.50 C 1.000 2957 352 68 1476 BoxColFill +0.94 0.50 0.50 C 1.000 3461 352 69 1407 BoxColFill +0.94 0.50 0.50 C 1.000 3966 352 68 2939 BoxColFill +0.94 0.50 0.50 C 1.000 4471 352 68 907 BoxColFill % End plot #4 1.000 UL LTb diff --git a/mpi-energy2-extension/fig/heter-eps-converted-to.pdf b/mpi-energy2-extension/fig/heter-eps-converted-to.pdf index 1d953eb..4c19c36 100644 Binary files a/mpi-energy2-extension/fig/heter-eps-converted-to.pdf and b/mpi-energy2-extension/fig/heter-eps-converted-to.pdf differ diff --git a/mpi-energy2-extension/fig/heter.eps b/mpi-energy2-extension/fig/heter.eps index e012be1..08e648a 100644 --- a/mpi-energy2-extension/fig/heter.eps +++ b/mpi-energy2-extension/fig/heter.eps @@ -1,9 +1,9 @@ %!PS-Adobe-2.0 EPSF-2.0 %%Title: heter2.eps -%%Creator: gnuplot 4.6 patchlevel 0 -%%CreationDate: Fri May 15 14:32:08 2015 +%%Creator: gnuplot 4.6 patchlevel 6 +%%CreationDate: Tue May 24 14:17:58 2016 %%DocumentFonts: (atend) -%%BoundingBox: 50 50 320 239 +%%BoundingBox: 50 50 338 251 %%EndComments %%BeginProlog /gnudict 256 dict def @@ -42,12 +42,12 @@ gnudict begin /vpt vpt_ def /doclip { ClipToBoundingBox { - newpath 50 50 moveto 320 50 lineto 320 239 lineto 50 239 lineto closepath + newpath 50 50 moveto 338 50 lineto 338 251 lineto 50 251 lineto closepath clip } if } def % -% Gnuplot Prolog Version 4.4 (August 2010) +% Gnuplot Prolog Version 4.6 (September 2012) % %/SuppressPDFMark true def % @@ -314,7 +314,8 @@ gnudict begin /PatternFill {gsave /PFa [ 9 2 roll ] def PFa 0 get PFa 2 get 2 div add PFa 1 get PFa 3 get 2 div add translate PFa 2 get -2 div PFa 3 get -2 div PFa 2 get PFa 3 get Rec - gsave 1 setgray fill grestore clip + TransparentPatterns {} {gsave 1 setgray fill grestore} ifelse + clip currentlinewidth 0.5 mul setlinewidth /PFs PFa 2 get dup mul PFa 3 get dup mul add sqrt def 0 0 M PFa 5 get rotate PFs -2 div dup translate @@ -428,11 +429,11 @@ systemdict /pdfmark known not { SDict begin [ /Title (heter2.eps) /Subject (gnuplot plot) - /Creator (gnuplot 4.6 patchlevel 0) + /Creator (gnuplot 4.6 patchlevel 6) /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Fri May 15 14:32:08 2015) + /CreationDate (Tue May 24 14:17:58 2016) /DOCINFO pdfmark end } ifelse @@ -447,154 +448,252 @@ doclip 0 setgray newpath (Helvetica) findfont 140 scalefont setfont -BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {BackgroundColor C 1.000 0 0 5400.00 3780.00 BoxColFill} if +BackgroundColor 0 lt 3 1 roll 0 lt exch 0 lt or or not {BackgroundColor C 1.000 0 0 5760.00 4032.00 BoxColFill} if 1.000 UL LTb -686 737 M +686 966 M 63 0 V -4398 0 R +4758 0 R -63 0 V /Helvetica findfont 220 scalefont setfont -602 737 M +/vshift -73 def +602 966 M ( 0.4) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb -686 1456 M +686 1690 M 63 0 V -4398 0 R +4758 0 R -63 0 V /Helvetica findfont 220 scalefont setfont --4482 0 R +/vshift -73 def +-4842 0 R ( 0.6) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb -686 2174 M +686 2415 M 63 0 V -4398 0 R +4758 0 R -63 0 V /Helvetica findfont 220 scalefont setfont --4482 0 R +/vshift -73 def +-4842 0 R ( 0.8) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb -686 2893 M +686 3139 M 63 0 V -4398 0 R +4758 0 R -63 0 V /Helvetica findfont 220 scalefont setfont --4482 0 R +/vshift -73 def +-4842 0 R ( 1) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb -686 3611 M +686 3863 M 63 0 V -4398 0 R +4758 0 R -63 0 V /Helvetica findfont 220 scalefont setfont --4482 0 R +/vshift -73 def +-4842 0 R ( 1.2) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb 1.000 UL LTb -686 3611 N -686 378 L -4461 0 V -0 3233 V --4461 0 V +686 3863 N +686 604 L +4821 0 V +0 3259 V +-4821 0 V Z stroke LCb setrgbcolor /Helvetica findfont 220 scalefont setfont -112 1994 M +/vshift -73 def +112 2233 M currentpoint gsave translate -270 rotate 0 0 M (Normalized energy and performance) Cshow grestore /Helvetica findfont 140 scalefont setfont +/vshift -46 def LTb LCb setrgbcolor /Helvetica findfont 220 scalefont setfont -3016 98 M -(Vectors of frequency scaling factors) Cshow +/vshift -73 def +3196 324 M +() Cshow +3196 104 M +( Vectors of frequency scaling factors) Cshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def LTb 1.000 UP /Helvetica findfont 220 scalefont setfont -1435 558 M +/vshift -73 def +1496 857 M (Optimal vector of scaling factors) Lshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def /Helvetica findfont 220 scalefont setfont -4255 1497 M +/vshift -73 def +4543 1732 M () Lshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def /Helvetica findfont 190 scalefont setfont -793 3277 M +/vshift -63 def +802 3526 M ( Upper bound) Lshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def /Helvetica findfont 190 scalefont setfont -3541 1887 M +/vshift -63 def +3771 2125 M ( Lower bound) Lshow /Helvetica findfont 140 scalefont setfont -1384 2246 M +/vshift -46 def +1440 2487 M ( Max.) Lshow -1384 2102 M +1440 2342 M ( distance) Lshow +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +686 459 M +(V1) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +1419 459 M +(V2) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +2229 459 M +(V3) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +3000 459 M +(V4) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +3771 459 M +(V5) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +4543 459 M +(V6) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 190 scalefont setfont +/vshift -63 def +5411 459 M +(Vn) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +4928 459 M +( . . .) Lshow +/Helvetica findfont 110 scalefont setfont +/vshift -36 def +2287 658 M +(|) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 110 scalefont setfont +/vshift -36 def +3058 658 M +(|) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 110 scalefont setfont +/vshift -36 def +3829 658 M +(|) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 110 scalefont setfont +/vshift -36 def +1419 658 M +(|) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def +/Helvetica findfont 110 scalefont setfont +/vshift -36 def +4601 658 M +(|) Lshow +/Helvetica findfont 140 scalefont setfont +/vshift -46 def 1.000 UL LTb -1378 2821 M -0 -1153 V +1434 3066 M +0 -1162 V stroke LT2 -1346 517 M +1402 743 M 32 -121 V 32 121 V --32 2304 R -0 -2425 V +-32 2323 R +0 -2444 V stroke gsave [] 0 setdash -1346 517 M +1402 743 M 32 -121 V 32 121 V stroke grestore 1.000 UL LT2 -1217 2976 M +1262 3222 M 22 -83 V 22 83 V --22 204 R -0 -287 V +-22 206 R +0 -289 V stroke gsave [] 0 setdash -1217 2976 M +1262 3222 M 22 -83 V 22 83 V stroke grestore 1.000 UL LT2 -4011 1534 M -30 -114 V -30 114 V --30 281 R -0 -395 V +4281 1769 M +30 -115 V +30 115 V +-30 283 R +0 -398 V stroke gsave [] 0 setdash -4011 1534 M -30 -114 V -30 114 V +4281 1769 M +30 -115 V +30 115 V stroke grestore 1.000 UL LT0 -1311 2821 M -142 0 V -1311 1668 M -142 0 V +1361 3066 M +154 0 V +1361 1904 M +154 0 V stroke LTb % Begin plot #1 @@ -603,32 +702,34 @@ LT2 LC2 setrgbcolor LCb setrgbcolor /Helvetica findfont 220 scalefont setfont -4496 3443 M +/vshift -73 def +4856 3695 M (Normalized performance) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def LT2 LC2 setrgbcolor -4580 3443 M +4940 3695 M 399 0 V -686 2893 M -74 0 V -81 0 V +686 3139 M +80 0 V 88 0 V -97 0 V -106 0 V -117 0 V -131 -72 V -146 -142 V -164 -135 V -186 -171 V -212 -164 V -245 -148 V -286 -164 V -338 -170 V -406 -135 V -495 -135 V -620 -135 V -312 -63 V +95 0 V +104 0 V +115 0 V +127 0 V +141 -73 V +157 -142 V +178 -136 V +201 -172 V +229 -166 V +265 -150 V +309 -165 V +365 -172 V +439 -135 V +535 -136 V +670 -136 V +337 -64 V % End plot #1 % Begin plot #2 stroke @@ -636,45 +737,42 @@ stroke LT0 1.00 0.00 0.00 C LCb setrgbcolor /Helvetica findfont 220 scalefont setfont -4496 3233 M +/vshift -73 def +4856 3485 M (Normalized energy) Rshow /Helvetica findfont 140 scalefont setfont +/vshift -46 def LT0 -1.00 0.00 0.00 C 4580 3233 M +1.00 0.00 0.00 C 4940 3485 M 399 0 V -686 2893 M -74 -248 V -81 -193 V -88 -182 V -97 -170 V -106 -156 V -117 -144 V -131 -129 V -146 -115 V -164 -100 V -186 -82 V -212 -64 V -245 -43 V -286 -20 V -338 7 V -406 39 V -495 80 V -620 131 V -312 59 V +686 3139 M +80 -250 V +88 -195 V +95 -183 V +104 -171 V +115 -158 V +127 -144 V +141 -131 V +157 -116 V +178 -100 V +201 -83 V +229 -64 V +265 -44 V +309 -20 V +365 7 V +439 40 V +535 80 V +670 133 V +337 59 V % End plot #2 -% Begin plot #3 stroke 1.000 UL -LT0 -1.00 1.00 1.00 C 5147 641 M -% End plot #3 -stroke LTb -686 3611 N -686 378 L -4461 0 V -0 3233 V --4461 0 V +686 3863 N +686 604 L +4821 0 V +0 3259 V +-4821 0 V Z stroke 1.000 UP 1.000 UL @@ -685,5 +783,3 @@ end showpage %%Trailer %%DocumentFonts: Helvetica -%%Trailer -%%DocumentFonts: Helvetica diff --git a/mpi-energy2-extension/fig/time.eps b/mpi-energy2-extension/fig/time.eps index 99cea89..4a2c77a 100644 --- a/mpi-energy2-extension/fig/time.eps +++ b/mpi-energy2-extension/fig/time.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 17:45:34 2015 +%%CreationDate: Tue May 24 10:34:34 2016 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 17:45:34 2015) + /CreationDate (Tue May 24 10:34:34 2016) /DOCINFO pdfmark end } ifelse @@ -534,227 +534,175 @@ stroke ] -50.0 MRshow 1.000 UL LTb -605 421 M +605 441 M 31 0 V 4205 0 R -31 0 V -605 490 M +605 530 M 31 0 V 4205 0 R -31 0 V -605 560 M +605 619 M 31 0 V 4205 0 R -31 0 V -605 629 M +605 708 M 31 0 V 4205 0 R -31 0 V -605 698 M +605 797 M 63 0 V 4173 0 R -63 0 V stroke -539 698 M +539 797 M [ [(Helvetica) 150.0 0.0 true true 0 ( 500)] ] -50.0 MRshow 1.000 UL LTb -605 767 M +605 886 M 31 0 V 4205 0 R -31 0 V -605 837 M +605 975 M 31 0 V 4205 0 R -31 0 V -605 906 M +605 1064 M 31 0 V 4205 0 R -31 0 V -605 975 M +605 1153 M 31 0 V 4205 0 R -31 0 V -605 1044 M +605 1242 M 63 0 V 4173 0 R -63 0 V stroke -539 1044 M +539 1242 M [ [(Helvetica) 150.0 0.0 true true 0 ( 1000)] ] -50.0 MRshow 1.000 UL LTb -605 1114 M +605 1331 M 31 0 V 4205 0 R -31 0 V -605 1183 M +605 1420 M 31 0 V 4205 0 R -31 0 V -605 1252 M +605 1509 M 31 0 V 4205 0 R -31 0 V -605 1321 M +605 1598 M 31 0 V 4205 0 R -31 0 V -605 1391 M +605 1687 M 63 0 V 4173 0 R -63 0 V stroke -539 1391 M +539 1687 M [ [(Helvetica) 150.0 0.0 true true 0 ( 1500)] ] -50.0 MRshow 1.000 UL LTb -605 1460 M +605 1776 M 31 0 V 4205 0 R -31 0 V -605 1529 M +605 1865 M 31 0 V 4205 0 R -31 0 V -605 1598 M +605 1955 M 31 0 V 4205 0 R -31 0 V -605 1668 M +605 2044 M 31 0 V 4205 0 R -31 0 V -605 1737 M +605 2133 M 63 0 V 4173 0 R -63 0 V stroke -539 1737 M +539 2133 M [ [(Helvetica) 150.0 0.0 true true 0 ( 2000)] ] -50.0 MRshow 1.000 UL LTb -605 1806 M +605 2222 M 31 0 V 4205 0 R -31 0 V -605 1875 M +605 2311 M 31 0 V 4205 0 R -31 0 V -605 1945 M +605 2400 M 31 0 V 4205 0 R -31 0 V -605 2014 M +605 2489 M 31 0 V 4205 0 R -31 0 V -605 2083 M +605 2578 M 63 0 V 4173 0 R -63 0 V stroke -539 2083 M +539 2578 M [ [(Helvetica) 150.0 0.0 true true 0 ( 2500)] ] -50.0 MRshow 1.000 UL LTb -605 2152 M -31 0 V -4205 0 R --31 0 V -605 2222 M -31 0 V -4205 0 R --31 0 V -605 2291 M -31 0 V -4205 0 R --31 0 V -605 2360 M -31 0 V -4205 0 R --31 0 V -605 2429 M -63 0 V -4173 0 R --63 0 V -stroke -539 2429 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 3000)] -] -50.0 MRshow -1.000 UL -LTb -605 2499 M -31 0 V -4205 0 R --31 0 V -605 2568 M +605 2667 M 31 0 V 4205 0 R -31 0 V -605 2637 M +605 2756 M 31 0 V 4205 0 R -31 0 V -605 2706 M -31 0 V -4205 0 R --31 0 V -605 2776 M -63 0 V -4173 0 R --63 0 V -stroke -539 2776 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 3500)] -] -50.0 MRshow -1.000 UL -LTb 605 2845 M 31 0 V 4205 0 R -31 0 V -605 2914 M +605 2934 M 31 0 V 4205 0 R -31 0 V -605 2983 M -31 0 V -4205 0 R --31 0 V -605 3053 M -31 0 V -4205 0 R --31 0 V -605 3122 M +605 3023 M 63 0 V 4173 0 R -63 0 V stroke -539 3122 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 4000)] +539 3023 M +[ [(Helvetica) 150.0 0.0 true true 0 ( 3000)] ] -50.0 MRshow 1.000 UL LTb -605 3191 M +605 3112 M 31 0 V 4205 0 R -31 0 V -605 3260 M +605 3201 M 31 0 V 4205 0 R -31 0 V -605 3330 M +605 3290 M 31 0 V 4205 0 R -31 0 V -605 3399 M +605 3379 M 31 0 V 4205 0 R -31 0 V @@ -764,38 +712,38 @@ LTb -63 0 V stroke 539 3468 M -[ [(Helvetica) 150.0 0.0 true true 0 ( 4500)] +[ [(Helvetica) 150.0 0.0 true true 0 ( 3500)] ] -50.0 MRshow 1.000 UL LTb -605 352 M +1135 352 M 0 63 V 0 3053 R 0 -63 V stroke -605 242 M +1293 242 M [ [(Helvetica) 150.0 0.0 true true 0 (CG)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -1311 352 M +1664 352 M 0 63 V 0 3053 R 0 -63 V stroke -1311 242 M +1822 242 M [ [(Helvetica) 150.0 0.0 true true 0 (MG)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -2017 352 M +2194 352 M 0 63 V 0 3053 R 0 -63 V stroke -2017 242 M +2352 242 M [ [(Helvetica) 150.0 0.0 true true 0 (EP)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb 2723 352 M @@ -803,39 +751,39 @@ LTb 0 3053 R 0 -63 V stroke -2723 242 M +2881 242 M [ [(Helvetica) 150.0 0.0 true true 0 (LU)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -3429 352 M +3253 352 M 0 63 V 0 3053 R 0 -63 V stroke -3429 242 M +3411 242 M [ [(Helvetica) 150.0 0.0 true true 0 (BT)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -4135 352 M +3782 352 M 0 63 V 0 3053 R 0 -63 V stroke -4135 242 M +3940 242 M [ [(Helvetica) 150.0 0.0 true true 0 (SP)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb -4841 352 M +4312 352 M 0 63 V 0 3053 R 0 -63 V stroke -4841 242 M +4470 242 M [ [(Helvetica) 150.0 0.0 true true 0 (FT)] -] -50.0 MCshow +] -50.0 MRshow 1.000 UL LTb 1.000 UL @@ -862,58 +810,38 @@ LTb 1.000 UL LTb % Begin plot #1 -1.000 UP 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2546 3264 M +2476 3313 M [ [(Helvetica) 140.0 0.0 true true 0 (One core per node scenario)] ] -46.7 MRshow LT0 -0.10 0.10 0.44 C 2612 3264 M -327 0 V -605 1208 M -1311 445 L -706 78 V -706 595 V -3429 907 L -706 930 V -706 52 V -605 1208 Pls -1311 445 Pls -2017 523 Pls -2723 1118 Pls -3429 907 Pls -4135 1837 Pls -4841 1889 Pls -2775 3264 Pls +0.10 0.10 0.44 C 1.000 2542 3280 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 1082 352 106 1102 BoxColFill +0.10 0.10 0.44 C 1.000 1611 352 107 121 BoxColFill +0.10 0.10 0.44 C 1.000 2141 352 106 221 BoxColFill +0.10 0.10 0.44 C 1.000 2670 352 107 986 BoxColFill +0.10 0.10 0.44 C 1.000 3200 352 106 715 BoxColFill +0.10 0.10 0.44 C 1.000 3729 352 107 1911 BoxColFill +0.10 0.10 0.44 C 1.000 4259 352 106 1978 BoxColFill % End plot #1 % Begin plot #2 -1.000 UP 1.000 UL LT1 -1.00 0.00 0.00 C LCb setrgbcolor -2546 3132 M +0.94 0.50 0.50 C LCb setrgbcolor +2476 3181 M [ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2612 3132 M -327 0 V -605 2089 M -1311 592 L -706 30 V -706 951 V -706 -482 V -706 1385 V -706 -120 V -605 2089 Crs -1311 592 Crs -2017 622 Crs -2723 1573 Crs -3429 1091 Crs -4135 2476 Crs -4841 2356 Crs -2775 3132 Crs +0.94 0.50 0.50 C 1.000 2542 3148 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 1214 352 107 2235 BoxColFill +0.94 0.50 0.50 C 1.000 1743 352 107 310 BoxColFill +0.94 0.50 0.50 C 1.000 2273 352 107 349 BoxColFill +0.94 0.50 0.50 C 1.000 2802 352 107 1570 BoxColFill +0.94 0.50 0.50 C 1.000 3332 352 107 952 BoxColFill +0.94 0.50 0.50 C 1.000 3861 352 107 2732 BoxColFill +0.94 0.50 0.50 C 1.000 4391 352 107 2578 BoxColFill % End plot #2 1.000 UL LTb diff --git a/mpi-energy2-extension/fig/time_scenarios-eps-converted-to.pdf b/mpi-energy2-extension/fig/time_scenarios-eps-converted-to.pdf index 09b6734..20b5e11 100644 Binary files a/mpi-energy2-extension/fig/time_scenarios-eps-converted-to.pdf and b/mpi-energy2-extension/fig/time_scenarios-eps-converted-to.pdf differ diff --git a/mpi-energy2-extension/fig/time_scenarios.eps b/mpi-energy2-extension/fig/time_scenarios.eps index a9b8da9..7db1743 100644 --- a/mpi-energy2-extension/fig/time_scenarios.eps +++ b/mpi-energy2-extension/fig/time_scenarios.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 12:39:30 2015 +%%CreationDate: Tue May 24 10:16:31 2016 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 12:39:30 2015) + /CreationDate (Tue May 24 10:16:31 2016) /DOCINFO pdfmark end } ifelse @@ -716,32 +716,32 @@ stroke ] -50.0 MRshow 1.000 UL LTb -605 352 M +1135 352 M 0 63 V 0 3053 R 0 -63 V stroke -605 242 M +1135 242 M [ [(Helvetica) 150.0 0.0 true true 0 (CG)] ] -50.0 MCshow 1.000 UL LTb -1311 352 M +1664 352 M 0 63 V 0 3053 R 0 -63 V stroke -1311 242 M +1664 242 M [ [(Helvetica) 150.0 0.0 true true 0 (MG)] ] -50.0 MCshow 1.000 UL LTb -2017 352 M +2194 352 M 0 63 V 0 3053 R 0 -63 V stroke -2017 242 M +2194 242 M [ [(Helvetica) 150.0 0.0 true true 0 (EP)] ] -50.0 MCshow 1.000 UL @@ -756,32 +756,32 @@ stroke ] -50.0 MCshow 1.000 UL LTb -3429 352 M +3253 352 M 0 63 V 0 3053 R 0 -63 V stroke -3429 242 M +3253 242 M [ [(Helvetica) 150.0 0.0 true true 0 (BT)] ] -50.0 MCshow 1.000 UL LTb -4135 352 M +3782 352 M 0 63 V 0 3053 R 0 -63 V stroke -4135 242 M +3782 242 M [ [(Helvetica) 150.0 0.0 true true 0 (SP)] ] -50.0 MCshow 1.000 UL LTb -4841 352 M +4312 352 M 0 63 V 0 3053 R 0 -63 V stroke -4841 242 M +4312 242 M [ [(Helvetica) 150.0 0.0 true true 0 (FT)] ] -50.0 MCshow 1.000 UL @@ -810,112 +810,72 @@ LTb 1.000 UL LTb % Begin plot #1 -1.000 UP 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2123 3268 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ 16 nodes)] +2158 3268 M +[ [(Helvetica) 140.0 0.0 true true 0 (One site / 16 nodes)] ] -46.7 MRshow LT0 -0.10 0.10 0.44 C 2189 3268 M -327 0 V -605 1101 M -1311 464 L -706 162 V -706 975 V -706 -161 V -706 672 V -706 79 V -605 1101 Pls -1311 464 Pls -2017 626 Pls -2723 1601 Pls -3429 1440 Pls -4135 2112 Pls -4841 2191 Pls -2352 3268 Pls +0.10 0.10 0.44 C 2224 3235 327 66 40 45 2 PatternFill +0.10 0.10 0.44 C 1011 352 72 750 40 45 2 PatternFill +0.10 0.10 0.44 C 1540 352 72 113 40 45 2 PatternFill +0.10 0.10 0.44 C 2070 352 72 275 40 45 2 PatternFill +0.10 0.10 0.44 C 2599 352 72 1250 40 45 2 PatternFill +0.10 0.10 0.44 C 3129 352 72 1089 40 45 2 PatternFill +0.10 0.10 0.44 C 3658 352 72 1761 40 45 2 PatternFill +0.10 0.10 0.44 C 4188 352 72 1840 40 45 2 PatternFill % End plot #1 % Begin plot #2 -1.000 UP 1.000 UL LT1 -1.00 0.00 0.00 C LCb setrgbcolor -2123 3136 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ 32 nodes)] +0.10 0.10 0.44 C LCb setrgbcolor +2158 3136 M +[ [(Helvetica) 140.0 0.0 true true 0 (One site / 32 nodes)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2189 3136 M -327 0 V -605 902 M -1311 412 L -706 50 V -706 383 V -3429 709 L -706 598 V -706 33 V -605 902 Crs -1311 412 Crs -2017 462 Crs -2723 845 Crs -3429 709 Crs -4135 1307 Crs -4841 1340 Crs -2352 3136 Crs +0.10 0.10 0.44 C 1.000 2224 3103 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 1099 352 72 551 BoxColFill +0.10 0.10 0.44 C 1.000 1629 352 71 61 BoxColFill +0.10 0.10 0.44 C 1.000 2158 352 72 111 BoxColFill +0.10 0.10 0.44 C 1.000 2688 352 71 494 BoxColFill +0.10 0.10 0.44 C 1.000 3217 352 72 358 BoxColFill +0.10 0.10 0.44 C 1.000 3747 352 71 956 BoxColFill +0.10 0.10 0.44 C 1.000 4276 352 72 989 BoxColFill % End plot #2 % Begin plot #3 -1.000 UP 1.000 UL -LT2 +LT0 0.00 0.39 0.00 C LCb setrgbcolor -2123 3004 M -[ [(Helvetica) 140.0 0.0 true true 0 (Two sites/ 16 nodes)] +2158 3004 M +[ [(Helvetica) 140.0 0.0 true true 0 (Two sites / 16 nodes)] ] -46.7 MRshow -LT2 -0.00 0.39 0.00 C 2189 3004 M -327 0 V -605 2263 M -1311 584 L -706 25 V -706 1112 V -706 613 V -706 291 V -706 343 V -605 2263 Star -1311 584 Star -2017 609 Star -2723 1721 Star -3429 2334 Star -4135 2625 Star -4841 2968 Star -2352 3004 Star +LT0 +0.00 0.39 0.00 C 2224 2971 327 66 80 -45 1 PatternFill +0.00 0.39 0.00 C 1187 352 72 1912 80 -45 1 PatternFill +0.00 0.39 0.00 C 1717 352 72 233 80 -45 1 PatternFill +0.00 0.39 0.00 C 2246 352 72 258 80 -45 1 PatternFill +0.00 0.39 0.00 C 2776 352 72 1370 80 -45 1 PatternFill +0.00 0.39 0.00 C 3305 352 72 1983 80 -45 1 PatternFill +0.00 0.39 0.00 C 3835 352 72 2274 80 -45 1 PatternFill +0.00 0.39 0.00 C 4364 352 72 2617 80 -45 1 PatternFill % End plot #3 % Begin plot #4 -1.000 UP 1.000 UL LT3 -0.72 0.53 0.04 C LCb setrgbcolor -2123 2872 M -[ [(Helvetica) 140.0 0.0 true true 0 (Two sites/ 32 nodes)] +0.94 0.50 0.50 C LCb setrgbcolor +2158 2872 M +[ [(Helvetica) 140.0 0.0 true true 0 (Two sites / 32 nodes)] ] -46.7 MRshow LT3 -0.72 0.53 0.04 C 2189 2872 M -327 0 V -605 2203 M -1311 512 L -706 -41 V -706 576 V -706 390 V -706 448 V -706 161 V -605 2203 Box -1311 512 Box -2017 471 Box -2723 1047 Box -3429 1437 Box -4135 1885 Box -4841 2046 Box -2352 2872 Box +0.94 0.50 0.50 C 1.000 2224 2839 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 1276 352 71 1852 BoxColFill +0.94 0.50 0.50 C 1.000 1805 352 72 161 BoxColFill +0.94 0.50 0.50 C 1.000 2335 352 71 120 BoxColFill +0.94 0.50 0.50 C 1.000 2864 352 72 696 BoxColFill +0.94 0.50 0.50 C 1.000 3394 352 71 1086 BoxColFill +0.94 0.50 0.50 C 1.000 3923 352 72 1534 BoxColFill +0.94 0.50 0.50 C 1.000 4453 352 71 1695 BoxColFill % End plot #4 1.000 UL LTb diff --git a/mpi-energy2-extension/my_reference.bib b/mpi-energy2-extension/my_reference.bib index 2ef90d0..71e9cbe 100644 --- a/mpi-energy2-extension/my_reference.bib +++ b/mpi-energy2-extension/my_reference.bib @@ -23,20 +23,7 @@ } -@inproceedings{Rauber_Analytical.Modeling.for.Energy, - author = {Rauber, Thomas and R\"{u}nger, Gudula}, - title = {Analytical Modeling and Simulation of the Energy Consumption of Independent Tasks}, - booktitle = {Proceedings of the Winter Simulation Conference}, - series = {WSC '12}, - year = {2012}, - location = {Berlin, Germany}, - pages = {245:1--245:13}, - articleno = {245}, - numpages = {13}, - acmid = {2430090}, - publisher = {Winter Simulation Conference}, - doi={10.1109/WSC.2012.6465151} -} + @inproceedings{4, author = {Jejurikar, Ravindra and Pereira, Cristiano and Gupta, Rajesh}, @@ -887,3 +874,17 @@ publisher={Springer Berlin Heidelberg}, author={Nagpal, Rahul and Srikant, Y.N.}, pages={497-508} } + +@inproceedings{Rauber_Analytical.Modeling.for.Energy, + author = {Rauber, Thomas and R\"{u}nger, Gudula}, + title = {Analytical Modeling and Simulation of the Energy Consumption of Independent Tasks}, + booktitle = {Proceedings of the Winter Simulation Conference}, + series = {WSC '12}, + year = {2012}, + location = {Berlin, Germany}, + pages = {245:1--245:13}, + articleno = {245}, + numpages = {13}, + acmid = {2430090}, + publisher = {Winter Simulation Conference} +} \ No newline at end of file