From: afanfakh Date: Mon, 28 Sep 2015 12:23:07 +0000 (+0200) Subject: adding new section X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy2.git/commitdiff_plain/26cbe1ae1953d2db886af547cac5067e697ac555?ds=sidebyside;hp=ec0705e8f0a3472c0bdd894bf3348ece04a9bea3 adding new section --- diff --git a/mpi-energy2-extension/Heter_paper.tex b/mpi-energy2-extension/Heter_paper.tex index 7252e44..e30d62c 100644 --- a/mpi-energy2-extension/Heter_paper.tex +++ b/mpi-energy2-extension/Heter_paper.tex @@ -54,7 +54,7 @@ \newcommand{\Sopt}[1][]{\Xsub{S}{opt}_{#1}} \newcommand{\Tcm}[1][]{\Xsub{T}{cm}_{\fxheight{#1}}} \newcommand{\Tcp}[1][]{\Xsub{T}{cp}_{#1}} -\newcommand{\Ppeak}[1][]{\Xsub{P}{peak}_{#1}} +\newcommand{\Pmax}[1][]{\Xsub{P}{max}_{#1}} \newcommand{\Pidle}[1][]{\Xsub{P}{idle}_{\fxheight{#1}}} \newcommand{\TcpOld}[1][]{\Xsub{T}{cpOld}_{#1}} \newcommand{\Tnew}{\Xsub{T}{New}} @@ -350,9 +350,9 @@ maximum frequency for all nodes: \end{equation} Where $\Ereduced$ is computed using (\ref{eq:energy}) and $\Eoriginal$ is -computed as in (). +computed as in (\ref{eq:eorginal}). + -\textcolor{red}{A reference is missing} \begin{equation} \label{eq:eorginal} \Eoriginal = \sum_{i=1}^{N} \sum_{j=1}^{M} ( \Pd[ij] \cdot \Tcp[ij]) + @@ -477,9 +477,7 @@ in~\cite{Zhuo_Energy.efficient.Dynamic.Task.Scheduling,Rauber_Analytical.Modelin \label{dvfs} \end{algorithm} -\subsection{The algorithm details} -\textcolor{red}{Delete the subsection if there's only one.} In this section, the scaling factors selection algorithm for grids, algorithm~\ref{HSA}, is presented. It selects the vector of the frequency scaling factors that gives the best trade-off between minimizing the @@ -578,29 +576,28 @@ Grid'5000~\cite{grid5000} is a large-scale testbed that consists of ten sites di which is the French National Telecommunication Network for Technology. Each site of the grid is composed of few heterogeneous computing clusters and each cluster contains many homogeneous nodes. In total, - grid'5000 has about one thousand heterogeneous nodes and eight thousand cores. In each site, +grid'5000 has about one thousand heterogeneous nodes and eight thousand cores. In each site, 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 for 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 by all the components of a node at a given instant, such as CPU, hard drive, main-board, memory, ... For more details refer to \cite{Energy_measurement}. To just 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 $P\max[jx]$. The difference between the two measured power consumption represents the + 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 consumption represents the dynamic power consumption of that core with the maximum frequency, see figure(\ref{fig:power_cons}). -\textcolor{red}{why maximum and minimum, change peak in the equation and the figure} The dynamic power $\Pd[j]$ is computed as in equation (\ref{eq:pdyn}) \begin{equation} \label{eq:pdyn} - \Pd[j] = \max_{x=\beta_1,\dots \beta_2} (P\max[jx]) - \min_{y=\Theta_1,\dots \Theta_2} (\Pidle[jy]) + \Pd[j] = \max_{x=\beta_1,\dots \beta_2} (Pmax[jx]) - \min_{y=\Theta_1,\dots \Theta_2} (\Pidle[jy]) \end{equation} where $\Pd[j]$ is the dynamic power consumption for one core of node $j$, -$\lbrace \beta_1,\beta_2 \rbrace$ is the time interval for the measured peak power values, +$\lbrace \beta_1,\beta_2 \rbrace$ is the time interval for the measured maximum power values, $\lbrace\Theta_1,\Theta_2\rbrace$ is the time interval for the measured idle power values. Therefore, the dynamic power of one core is computed as the difference between the maximum -measured value in peak powers vector and the minimum measured value in the idle powers vector. +measured value in maximum powers vector and the minimum measured value in the idle powers vector. On the other hand, the static power consumption by one core is a part of the measured idle power consumption of the node. Since in grid'5000 there is no way to measure precisely the consumed static power and in~\cite{Our_first_paper,pdsec2015,Rauber_Analytical.Modeling.for.Energy} it was assumed that the static power represents a ratio of the dynamic power, the value of the static power is assumed as np[\%]{20} of dynamic power consumption of the core. @@ -743,7 +740,7 @@ Table \ref{tab:sc} shows the number of nodes used from each cluster for each sce \label{fig:time_sen} \end{figure} -The NAS parallel benchmarks are executed over these two platform +The NAS parallel benchmarks are executed over these two platforms with different number of nodes, as in Table \ref{tab:sc}. The overall energy consumption of all the benchmarks solving the class D instance and using the proposed frequency selection algorithm is measured @@ -762,8 +759,6 @@ The long distance communications between the two distributed sites increase the over one site with 16 and 32 nodes are also lower when compared to those of the two sites scenario. - - However, the execution times and the energy consumptions of EP and MG benchmarks, which have no or small communications, are not significantly affected in both scenarios. Even when the number of nodes is doubled. On the other hand, the communications of the rest of the benchmarks increases when using long distance communications between two sites or increasing the number of computing nodes. @@ -846,8 +841,159 @@ percentage. Finally, the best energy and performance tradeoff depends on the inc 1) the computations to communications ratio, 2) the differences in computing powers between the computing nodes and 3) the differences in static and the dynamic powers of the nodes. -\subsection{The experimental results of multi-cores clusters} -\label{sec.res} +\subsection{The experimental results of multicores clusters} +\label{sec.res-mc} +The grid'5000 clusters have different number of cores embedded in their nodes +as in the Table \ref{table:grid5000}. Moreover, the cores of each node are +connected via shared memory model, the data transfer between cores' local +memories achieved via the global memory \cite{rauber_book}. Therefore, in +this section the proposed scaling algorithm is implemented over the grid'5000 +clusters which are included multicores in the selected nodes as same as the +two previous platform scenarios that mentioned in the section \ref{sec.res}. +The two platform scenarios, the two sites and one site scenarios, with 32 +nodes are reconfigured to used multicores for each node. For example if +the participating number of nodes from a certain cluster is equal to 12 nodes, +in the multicores scenario the selected nodes is equal to 3 nodes with using +4 cores for each of them to produced 12 cores. These scenarios with one +core and multicores are demonstrated in Table \ref{table:sen-mc}. +The energy consumptions and execution times of running the NAS parallel +benchmarks, class D, over these four different scenarios are represented +in the figures \ref{fig:eng-cons-mc} and \ref{fig:time-mc} respectively. +The execution times of NAS benchmarks over the one site multicores scenario +is higher than the execution time of those running over one site multicores scenario. +This because in the one site multicores scenario the communication is increased significantly, +and all node's cores share the same node network link which increased +the communication times. While, the execution times of the NAS benchmarks over +the two site multicores scenario is less than those executed over the two +sites one core scenario. This because using multicores decrease the communications, +while the cores shared same nodes' link but the communications between the cores +are less than the communication times between the nodes over the long distance +networks, and thus the over all execution time decreased. Generally, executing +the NAS benchmarks over the one site one core gives smaller execution times +comparing to other scenarios. This because each node in this scenario has it's +dedicated network link that used independently by one core, while in the other +scenarios the communication times are higher when using long distance communication +link or using the shared link communications between cores of each node. +On the other hand, the energy consumptions of the NAS benchmarks over the +one site one cores is less than the one site multicores scenario because +this scenario had less execution time as mentioned before. Also, in the +one site one core scenario the computations to communications ratio is +higher, then the new scaled frequencies are decreased the dynamic energy +consumption, because the dynamic power consumption are decreased exponentially +with the new frequency scaling factors. These experiments also showed, the energy +consumption and the execution times of EP and MG benchmarks over these four +scenarios are not change a lot, because there are no or small communications + which are increase or decrease the static power consumptions. +The other benchmarks were showed that their energy consumptions and execution times +are changed according to the decreasing or increasing in the communication +times that are different from scenario to other or due to the amount of +communications in each of them. + +The energy saving percentages of all NAS benchmarks, as in figure +\ref{fig:eng-s-mc}, running over these four scenarios are presented. The figure +showed the energy saving percentages of NAS benchmarks over two sites multicores scenario is higher +than two sites once core scenario, this because the the computation +times in the two sites multicores scenario is higher than the computation times +of the two sites one core scenario, then the more reduction in the +dynamic energy can be obtained as mentioned previously. In contrast, in the one site one +core and one site multicores scenarios the energy saving percentages +are approximately equivalent, on average they are up to 25\%. This +because in the both scenarios there are a small difference in the +computations to communications ratio, leading the proposed scaling algorithm +to selects the frequencies proportionally to these ratios and keeping +as much as possible the energy saving percentages the same. The +performance degradation percentages of NAS benchmarks are presented in +figure \ref{fig:per-d-mc}. This figure indicates that performance +degradation percentages of running NAS benchmarks over two sites +multocores, on average is equal to 7\%, gives more performance degradation percentage +than two sites one core scenario, which on average is equal to 4\%. +This because when using the two sites multicores scenario increased +the computations to communications ratio, which may be increased the effect +on the overall execution time when the proposed scaling algorithm is applied and scaling down the frequencies. +The inverse was happened when the benchmarks are executed over one +site one core scenario their performance degradation percentages, on average +is equal to 10\%, are higher than those executed over one sit one core, +which on average is equal to 7\%. This because in one site +multicores scenario the computations to communications ratio is decreased +as mentioned before, thus selecting new frequencies are less effect +on the overall execution time. The tradeoff distances of all NAS +benchmarks over all scenarios are presented in the figure \ref{fig:dist-mc}. +These tradeoff distances are used to verified which scenario is the best in term of +energy and performance ratio. The one sites multicores scenario is the best scenario in term of +energy and performance tradeoff, on average is equal to 17.6\%, when comparing to the one site one core +scenario, one average is equal to 15.3\%. This because the one site multicores scenario +has the same energy saving percentages of the one site one core scenario but +with less performance degradation. The two sites multicores scenario is gives better +energy and performance tradeoff, one average is equal to 14.7\%, than the two sites +one core, on average is equal to 13.3\%. +Finally, using multicore in both scenarios increased the energy and performance tradeoff +distance. This is because using multicores are increased the computations to communications +ratio in two sites scenario and thus the energy saving increased over the performance degradation, whereas decreased this ratio +in one site scenario causing the performance degradation decreased over the energy saving. + + + + + +\begin{table}[] +\centering +\caption{The multicores scenarios} + +\begin{tabular}{|*{4}{c|}} +\hline +Scenario name & Cluster name & \begin{tabular}[c]{@{}c@{}}No. of nodes\\ in each cluster\end{tabular} & + \begin{tabular}[c]{@{}c@{}}No. of cores\\ for each node\end{tabular} \\ \hline +\multirow{3}{*}{Two sites/ one core} & Taurus & 10 & 1 \\ \cline{2-4} + & Graphene & 10 & 1 \\ \cline{2-4} + & Griffon & 12 & 1 \\ \hline +\multirow{3}{*}{Two sites/ multicores} & Taurus & 3 & 3 or 4 \\ \cline{2-4} + & Graphene & 3 & 3 or 4 \\ \cline{2-4} + & Griffon & 3 & 4 \\ \hline +\multirow{3}{*}{One site/ one core} & Graphite & 4 & 1 \\ \cline{2-4} + & Graphene & 12 & 1 \\ \cline{2-4} + & Griffon & 12 & 1 \\ \hline +\multirow{3}{*}{One site/ multicores} & Graphite & 3 & 3 or 4 \\ \cline{2-4} + & Graphene & 3 & 3 or 4 \\ \cline{2-4} + & Griffon & 3 & 4 \\ \hline +\end{tabular} +\label{table:sen-mc} +\end{table} + +\begin{figure} + \centering + \includegraphics[scale=0.5]{fig/eng_con.eps} + \caption{Comparing the energy consumptions of running NAS benchmarks over one core and multicores scenarios } + \label{fig:eng-cons-mc} +\end{figure} + + + \begin{figure} + \centering + \includegraphics[scale=0.5]{fig/time.eps} + \caption{Comparing the execution times of running NAS benchmarks over one core and multicores scenarios } + \label{fig:time-mc} +\end{figure} + + \begin{figure} + \centering + \includegraphics[scale=0.5]{fig/eng_s_mc.eps} + \caption{The energy saving of running NAS benchmarks over one core and multicores scenarios } + \label{fig:eng-s-mc} +\end{figure} + +\begin{figure} + \centering + \includegraphics[scale=0.5]{fig/per_d_mc.eps} + \caption{The performance degradation of running NAS benchmarks over one core and multicores scenarios } + \label{fig:per-d-mc} +\end{figure} + +\begin{figure} + \centering + \includegraphics[scale=0.5]{fig/dist_mc.eps} + \caption{The tradeoff distance of running NAS benchmarks over one core and multicores scenarios } + \label{fig:dist-mc} +\end{figure} \subsection{The results for different power consumption scenarios} \label{sec.compare} diff --git a/mpi-energy2-extension/fig/eng_con.eps b/mpi-energy2-extension/fig/eng_con.eps index 3076d23..4b9eb26 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: Fri Sep 11 14:21:34 2015 +%%CreationDate: Fri Sep 25 09:46:14 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Fri Sep 11 14:21:34 2015) + /CreationDate (Fri Sep 25 09:46:14 2015) /DOCINFO pdfmark end } ifelse @@ -875,7 +875,7 @@ Z stroke LCb setrgbcolor 88 1910 M currentpoint gsave translate -270 rotate 0 0 moveto -[ [(Helvetica) 160.0 0.0 true true 0 (Energy consumption)] +[ [(Helvetica) 160.0 0.0 true true 0 (Energy consumption [J])] ] -53.3 MCshow grestore LTb @@ -892,11 +892,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2094 3205 M +2094 3309 M [ [(Helvetica) 130.0 0.0 true true 0 (One site/ one core)] ] -43.3 MRshow LT0 -0.10 0.10 0.44 C 2160 3205 M +0.10 0.10 0.44 C 2160 3309 M 327 0 V 803 768 M 1476 427 L @@ -912,18 +912,18 @@ LT0 3495 610 Pls 4168 1898 Pls 4841 705 Pls -2323 3205 Pls +2323 3309 Pls % End plot #1 % Begin plot #2 1.000 UP 1.000 UL LT1 1.00 0.00 0.00 C LCb setrgbcolor -2094 3095 M +2094 3199 M [ [(Helvetica) 130.0 0.0 true true 0 (One site/ multicores)] ] -43.3 MRshow LT1 -1.00 0.00 0.00 C 2160 3095 M +1.00 0.00 0.00 C 2160 3199 M 327 0 V 803 1231 M 1476 494 L @@ -939,18 +939,18 @@ LT1 3495 718 Crs 4168 2836 Crs 4841 631 Crs -2323 3095 Crs +2323 3199 Crs % End plot #2 % Begin plot #3 1.000 UP 1.000 UL LT2 0.00 0.39 0.00 C LCb setrgbcolor -2094 2985 M +2094 3089 M [ [(Helvetica) 130.0 0.0 true true 0 (Two sites/ one core)] ] -43.3 MRshow LT2 -0.00 0.39 0.00 C 2160 2985 M +0.00 0.39 0.00 C 2160 3089 M 327 0 V 803 1478 M 1476 479 L @@ -966,18 +966,18 @@ LT2 3495 1524 Star 4168 2800 Star 4841 1107 Star -2323 2985 Star +2323 3089 Star % End plot #3 % Begin plot #4 1.000 UP 1.000 UL LT3 -0.85 0.65 0.13 C LCb setrgbcolor -2094 2875 M +0.72 0.53 0.04 C LCb setrgbcolor +2094 2979 M [ [(Helvetica) 130.0 0.0 true true 0 (Two sites/ multicores)] ] -43.3 MRshow LT3 -0.85 0.65 0.13 C 2160 2875 M +0.72 0.53 0.04 C 2160 2979 M 327 0 V 803 993 M 1476 469 L @@ -993,7 +993,7 @@ LT3 3495 745 Box 4168 3046 Box 4841 913 Box -2323 2875 Box +2323 2979 Box % End plot #4 1.000 UL LTb diff --git a/mpi-energy2-extension/fig/power_consumption.pdf b/mpi-energy2-extension/fig/power_consumption.pdf index aea4b86..6405813 100644 Binary files a/mpi-energy2-extension/fig/power_consumption.pdf and b/mpi-energy2-extension/fig/power_consumption.pdf differ diff --git a/mpi-energy2-extension/fig/time.eps b/mpi-energy2-extension/fig/time.eps index f066918..7e71b2e 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: Fri Sep 11 14:28:07 2015 +%%CreationDate: Fri Sep 25 09:43:46 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Fri Sep 11 14:28:07 2015) + /CreationDate (Fri Sep 25 09:43:46 2015) /DOCINFO pdfmark end } ifelse @@ -849,7 +849,7 @@ Z stroke LCb setrgbcolor 88 1910 M currentpoint gsave translate -270 rotate 0 0 moveto -[ [(Helvetica) 160.0 0.0 true true 0 (Execution time)] +[ [(Helvetica) 160.0 0.0 true true 0 (Execution time [s])] ] -53.3 MCshow grestore LTb @@ -901,14 +901,14 @@ LT1 327 0 V 605 2089 M 1311 592 L -706 187 V -706 794 V +706 30 V +706 951 V 706 -482 V 706 1385 V 706 -120 V 605 2089 Crs 1311 592 Crs -2017 779 Crs +2017 622 Crs 2723 1573 Crs 3429 1091 Crs 4135 2476 Crs @@ -946,12 +946,12 @@ LT2 1.000 UP 1.000 UL LT3 -0.85 0.65 0.13 C LCb setrgbcolor +0.72 0.53 0.04 C LCb setrgbcolor 1982 2945 M [ [(Helvetica) 130.0 0.0 true true 0 (Two sites/ multicores)] ] -43.3 MRshow LT3 -0.85 0.65 0.13 C 2048 2945 M +0.72 0.53 0.04 C 2048 2945 M 327 0 V 605 1685 M 1311 551 L diff --git a/mpi-energy2-extension/my_reference.bib b/mpi-energy2-extension/my_reference.bib index ae351be..81d1c9f 100644 --- a/mpi-energy2-extension/my_reference.bib +++ b/mpi-energy2-extension/my_reference.bib @@ -587,7 +587,7 @@ ISSN={0278-0070} url = {http://www.top500.org} } -@MISC{SimGrid.org, +@MISC{SimGrid, title = {{SimGrid: Versatile Simulation of Distributed Systems}}, url = {http://simgrid.org} } @@ -826,4 +826,11 @@ pages={1451-1476} @MISC{grid5000, title = {grid5000}, url = {http://www.grid5000.fr/} -} \ No newline at end of file +} + +@book{rauber_book, + title={Parallel programming: For multicore and cluster systems}, + author={Rauber, Thomas and R{\"u}nger, Gudula}, + year={2013}, + publisher={Springer Science \& Business Media} +}