From: afanfakh Date: Fri, 23 Oct 2015 09:52:30 +0000 (+0200) Subject: adding some changes X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy2.git/commitdiff_plain/c9efa3aa1b816cbed779a8f68048dca4759ed1b1?ds=sidebyside;hp=--cc adding some changes --- c9efa3aa1b816cbed779a8f68048dca4759ed1b1 diff --git a/mpi-energy2-extension/Heter_paper.tex b/mpi-energy2-extension/Heter_paper.tex index 8c6061c..5dc876c 100644 --- a/mpi-energy2-extension/Heter_paper.tex +++ b/mpi-energy2-extension/Heter_paper.tex @@ -213,7 +213,7 @@ scaling (DVFS) is one of them. It can be used to reduce the power consumption of The proposed algorithm is evaluated on a real grid, the grid'5000 platform, while running the NAS parallel benchmarks. The experiments show that it reduces the energy consumption on average by \np[\%]{30} while the performance is only degraded - on average by \np[\%]{3}. Finally, the algorithm is + on average by \np[\%]{3.2}. Finally, the algorithm is compared to an existing method. The comparison results show that it outperforms the latter in terms of energy consumption reduction and performance. \end{abstract} @@ -661,9 +661,9 @@ equation, as follows: \begin{figure} \centering \subfloat[Homogeneous cluster]{% - \includegraphics[width=.33\textwidth]{fig/homo}\label{fig:r1}} \hspace{2cm}% + \includegraphics[width=.4\textwidth]{fig/homo}\label{fig:r1}} \hspace{2cm}% \subfloat[Heterogeneous grid]{% - \includegraphics[width=.33\textwidth]{fig/heter}\label{fig:r2}} + \includegraphics[width=.4\textwidth]{fig/heter}\label{fig:r2}} \label{fig:rel} \caption{The energy and performance relation} \end{figure} @@ -998,16 +998,7 @@ Table \ref{tab:sc} shows the number of nodes used from each cluster for each sce \end{table} -\begin{figure} - \centering - \subfloat[The energy consumption by the nodes wile executing the NAS benchmarks over different scenarios - ]{% - \includegraphics[width=.4\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{1cm}% - \subfloat[The execution times of the NAS benchmarks over different scenarios]{% - \includegraphics[width=.4\textwidth]{fig/time_scenarios.eps}\label{fig:time_sen}} - \label{fig:exp-time-energy} - \caption{The energy consumption and execution time of NAS Benchmarks over different scenarios} -\end{figure} + The NAS parallel benchmarks are executed over these two platforms with different number of nodes, as in Table \ref{tab:sc}. @@ -1033,18 +1024,6 @@ However, the execution times and the energy consumptions of EP and MG benchmark in both scenarios. Even when the number of nodes is doubled. On the other hand, the communications of the rest of the benchmarks increases when using long distance communications between two sites or increasing the number of computing nodes. -\begin{figure} - \centering - \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{% - \includegraphics[width=.33\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{0.08cm}% - \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{% - \includegraphics[width=.33\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{0.08cm}% - \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks - over different scenarios]{% - \includegraphics[width=.33\textwidth]{fig/dist.eps}\label{fig:dist}} - \label{fig:exp-res} - \caption{The experimental results of different scenarios} -\end{figure} The energy saving percentage is computed as the ratio between the reduced energy consumption, equation (\ref{eq:energy}), and the original energy consumption, @@ -1058,8 +1037,31 @@ is exponentially related to the CPU's frequency value. On the other side, the in increase the communication times and thus produces less energy saving depending on the benchmarks being executed. The results of the benchmarks CG, MG, BT and FT show more energy saving percentage in one site scenario when executed over 16 nodes comparing to 32 nodes. While, LU and SP consume more energy with 16 nodes than 32 in one site because their computations to communications ratio is not affected by the increase of the number of local communications. +\begin{figure} + \centering + \subfloat[The energy consumption by the nodes wile executing the NAS benchmarks over different scenarios + ]{% + \includegraphics[width=.4\textwidth]{fig/eng_con_scenarios.eps}\label{fig:eng_sen}} \hspace{1cm}% + \subfloat[The execution times of the NAS benchmarks over different scenarios]{% + \includegraphics[width=.4\textwidth]{fig/time_scenarios.eps}\label{fig:time_sen}} + \label{fig:exp-time-energy} + \caption{The energy consumption and execution time of NAS Benchmarks over different scenarios} +\end{figure} +\begin{figure} + \centering + \subfloat[The energy reduction while executing the NAS benchmarks over different scenarios ]{% + \includegraphics[width=.4\textwidth]{fig/eng_s.eps}\label{fig:eng_s}} \hspace{2cm}% + \subfloat[The performance degradation of the NAS benchmarks over different scenarios]{% + \includegraphics[width=.4\textwidth]{fig/per_d.eps}\label{fig:per_d}}\hspace{2cm}% + \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks + over different scenarios]{% + \includegraphics[width=.4\textwidth]{fig/dist.eps}\label{fig:dist}} + \label{fig:exp-res} + \caption{The experimental results of different scenarios} +\end{figure} + The energy saving percentage is reduced for all the benchmarks because of the long distance communications in the two sites scenario, except for the EP benchmark which has no communications. Therefore, the energy saving percentage of this benchmark is dependent on the maximum difference between the computing powers of the heterogeneous computing nodes, for example @@ -1076,9 +1078,9 @@ The best energy saving percentage was obtained in the one site scenario with 16 Figure \ref{fig:per_d} presents the performance degradation percentages for all benchmarks over the two scenarios. The performance degradation percentage for the benchmarks running on two sites with -16 or 32 nodes is on average equal to 8\% or 4\% respectively. +16 or 32 nodes is on average equal to 8.3\% or 4.7\% respectively. For this scenario, the proposed scaling algorithm selects smaller frequencies for the executions with 32 nodes without significantly degrading their performance because the communication times are higher with 32 nodes which results in smaller computations to communications ratio. On the other hand, the performance degradation percentage for the benchmarks running on one site with -16 or 32 nodes is on average equal to 3\% or 10\% respectively. In opposition to the two sites scenario, when the number of computing nodes is increased in the one site scenario, the performance degradation percentage is increased. Therefore, doubling the number of computing +16 or 32 nodes is on average equal to 3.2\% or 10.6\% respectively. In opposition to the two sites scenario, when the number of computing nodes is increased in the one site scenario, the performance degradation percentage is increased. Therefore, doubling the number of computing nodes when the communications occur in high speed network does not decrease the computations to communication ratio. @@ -1090,7 +1092,7 @@ when the communication times increase and vice versa. Figure \ref{fig:dist} presents the distance percentage between the energy saving and the performance degradation for each benchmark over both scenarios. The tradeoff distance percentage can be computed as in equation \ref{eq:max}. The one site scenario with 16 nodes gives the best energy and performance -tradeoff, on average it is equal to 26\%. The one site scenario using both 16 and 32 nodes had better energy and performance +tradeoff, on average it is equal to 26.8\%. The one site scenario using both 16 and 32 nodes had better energy and performance tradeoff comparing to the two sites scenario because the former has high speed local communications which increase the computations to communications ratio and the latter uses long distance communications which decrease this ratio. @@ -1179,12 +1181,12 @@ These tradeoff distance percentages are used to verify which scenario is the be \begin{figure} \centering \subfloat[The energy saving of running NAS benchmarks over one core and multicores scenarios]{% - \includegraphics[width=.33\textwidth]{fig/eng_s_mc.eps}\label{fig:eng-s-mc}} \hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/eng_s_mc.eps}\label{fig:eng-s-mc}} \hspace{2cm}% \subfloat[The performance degradation of running NAS benchmarks over one core and multicores scenarios ]{% - \includegraphics[width=.33\textwidth]{fig/per_d_mc.eps}\label{fig:per-d-mc}}\hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/per_d_mc.eps}\label{fig:per-d-mc}}\hspace{2cm}% \subfloat[The tradeoff distance of running NAS benchmarks over one core and multicores scenarios]{% - \includegraphics[width=.33\textwidth]{fig/dist_mc.eps}\label{fig:dist-mc}} + \includegraphics[width=.4\textwidth]{fig/dist_mc.eps}\label{fig:dist-mc}} \label{fig:exp-res} \caption{The experimental results of one core and multi-cores scenarios} \end{figure} @@ -1205,11 +1207,12 @@ In these experiments, the class D of the NAS parallel benchmarks are executed ov \begin{figure} \centering \subfloat[The energy saving percentages for the nodes executing the NAS benchmarks over the three power scenarios]{% - \includegraphics[width=.33\textwidth]{fig/eng_pow.eps}\label{fig:eng-pow}} \hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/eng_pow.eps}\label{fig:eng-pow}} \hspace{2cm}% \subfloat[The performance degradation percentages for the NAS benchmarks over the three power scenarios]{% - \includegraphics[width=.33\textwidth]{fig/per_pow.eps}\label{fig:per-pow}}\hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/per_pow.eps}\label{fig:per-pow}}\hspace{2cm}% \subfloat[The tradeoff distance between the energy reduction and the performance of the NAS benchmarks over the three power scenarios]{% - \includegraphics[width=.33\textwidth]{fig/dist_pow.eps}\label{fig:dist-pow}} + + \includegraphics[width=.4\textwidth]{fig/dist_pow.eps}\label{fig:dist-pow}} \label{fig:exp-pow} \caption{The experimental results of different static power scenarios} \end{figure} @@ -1269,11 +1272,11 @@ presented in the figures \ref{fig:edp-eng}, \ref{fig:edp-perf} and \ref{fig:edp- \begin{figure} \centering \subfloat[The energy reduction induced by the Maxdist method and the EDP method]{% - \includegraphics[width=.33\textwidth]{fig/edp_eng}\label{fig:edp-eng}} \hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/edp_eng}\label{fig:edp-eng}} \hspace{2cm}% \subfloat[The performance degradation induced by the Maxdist method and the EDP method]{% - \includegraphics[width=.33\textwidth]{fig/edp_per}\label{fig:edp-perf}}\hspace{0.08cm}% + \includegraphics[width=.4\textwidth]{fig/edp_per}\label{fig:edp-perf}}\hspace{2cm}% \subfloat[The tradeoff distance between the energy consumption reduction and the performance for the Maxdist method and the EDP method]{% - \includegraphics[width=.33\textwidth]{fig/edp_dist}\label{fig:edp-dist}} + \includegraphics[width=.4\textwidth]{fig/edp_dist}\label{fig:edp-dist}} \label{fig:edp-comparison} \caption{The comparison results} \end{figure} @@ -1302,7 +1305,7 @@ of the distributed iterative message passing application running over a grid arc 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 experimental results showed that the algorithm reduces on average 30\% of the energy consumption -for all the NAS benchmarks while only degrading by 3\% on average the performance. +for all the NAS benchmarks while only degrading by 3.2\% on average the performance. The Maxdist algorithm was also evaluated in different scenarios that vary in the distribution of the computing nodes between different clusters' sites or \textcolor{blue}{between using one core and multi-cores per node} or in the values of the consumed static power. The algorithm selects different vector of frequencies according to the computations and communication times ratios, and the values of the static and measured dynamic powers of the CPUs. Finally, the proposed algorithm was compared to another method that uses diff --git a/mpi-energy2-extension/fig/dist_mc.eps b/mpi-energy2-extension/fig/dist_mc.eps index 059db72..240fa99 100644 --- a/mpi-energy2-extension/fig/dist_mc.eps +++ b/mpi-energy2-extension/fig/dist_mc.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 13:24:19 2015 +%%CreationDate: Thu Oct 22 17:45:05 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 13:24:19 2015) + /CreationDate (Thu Oct 22 17:45:05 2015) /DOCINFO pdfmark end } ifelse @@ -839,11 +839,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -1980 3246 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ one core)] +2362 3246 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 1.000 2046 3213 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 2428 3213 327 66 BoxColFill 0.10 0.10 0.44 C 1.000 964 352 111 568 BoxColFill 0.10 0.10 0.44 C 1.000 1510 352 111 919 BoxColFill 0.10 0.10 0.44 C 1.000 2056 352 111 755 BoxColFill @@ -856,11 +856,11 @@ LT0 1.000 UL LT1 0.94 0.50 0.50 C LCb setrgbcolor -1980 3114 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ multicores)] +2362 3114 M +[ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -0.94 0.50 0.50 C 1.000 2046 3081 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 2428 3081 327 66 BoxColFill 0.94 0.50 0.50 C 1.000 1101 352 110 1106 BoxColFill 0.94 0.50 0.50 C 1.000 1647 352 110 1256 BoxColFill 0.94 0.50 0.50 C 1.000 2193 352 110 85 BoxColFill diff --git a/mpi-energy2-extension/fig/eng_con.eps b/mpi-energy2-extension/fig/eng_con.eps index c55888a..814faa1 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 13:28:11 2015 +%%CreationDate: Thu Oct 22 17:46:42 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 13:28:11 2015) + /CreationDate (Thu Oct 22 17:46:42 2015) /DOCINFO pdfmark end } ifelse @@ -892,11 +892,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2296 3298 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ one core)] +2767 3298 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 2362 3298 M +0.10 0.10 0.44 C 2833 3298 M 327 0 V 803 768 M 1476 427 L @@ -912,18 +912,18 @@ LT0 3495 610 Pls 4168 1898 Pls 4841 705 Pls -2525 3298 Pls +2996 3298 Pls % End plot #1 % Begin plot #2 1.000 UP 1.000 UL LT1 1.00 0.00 0.00 C LCb setrgbcolor -2296 3166 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ multicores)] +2767 3166 M +[ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2362 3166 M +1.00 0.00 0.00 C 2833 3166 M 327 0 V 803 1231 M 1476 494 L @@ -939,7 +939,7 @@ LT1 3495 718 Crs 4168 2836 Crs 4841 631 Crs -2525 3166 Crs +2996 3166 Crs % End plot #2 1.000 UL LTb diff --git a/mpi-energy2-extension/fig/eng_s_mc.eps b/mpi-energy2-extension/fig/eng_s_mc.eps index 3de05f5..aa7c105 100644 --- a/mpi-energy2-extension/fig/eng_s_mc.eps +++ b/mpi-energy2-extension/fig/eng_s_mc.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 13:21:43 2015 +%%CreationDate: Thu Oct 22 17:39:34 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 13:21:43 2015) + /CreationDate (Thu Oct 22 17:39:34 2015) /DOCINFO pdfmark end } ifelse @@ -839,11 +839,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -1980 3246 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ one core)] +2362 3246 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 1.000 2046 3213 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 2428 3213 327 66 BoxColFill 0.10 0.10 0.44 C 1.000 964 352 111 1656 BoxColFill 0.10 0.10 0.44 C 1.000 1510 352 111 1506 BoxColFill 0.10 0.10 0.44 C 1.000 2056 352 111 2190 BoxColFill @@ -856,11 +856,11 @@ LT0 1.000 UL LT1 0.94 0.50 0.50 C LCb setrgbcolor -1980 3114 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ multicores)] +2362 3114 M +[ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -0.94 0.50 0.50 C 1.000 2046 3081 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 2428 3081 327 66 BoxColFill 0.94 0.50 0.50 C 1.000 1101 352 110 1453 BoxColFill 0.94 0.50 0.50 C 1.000 1647 352 110 1873 BoxColFill 0.94 0.50 0.50 C 1.000 2193 352 110 2153 BoxColFill diff --git a/mpi-energy2-extension/fig/per_d_mc.eps b/mpi-energy2-extension/fig/per_d_mc.eps index e64ad0e..19d87f1 100644 --- a/mpi-energy2-extension/fig/per_d_mc.eps +++ b/mpi-energy2-extension/fig/per_d_mc.eps @@ -1,6 +1,6 @@ %!PS-Adobe-2.0 %%Creator: gnuplot 4.6 patchlevel 6 -%%CreationDate: Thu Oct 22 13:20:07 2015 +%%CreationDate: Thu Oct 22 17:36:36 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 13:20:07 2015) + /CreationDate (Thu Oct 22 17:36:36 2015) /DOCINFO pdfmark end } ifelse @@ -795,11 +795,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -1980 3305 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ one core)] +2362 3305 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 1.000 2046 3272 327 66 BoxColFill +0.10 0.10 0.44 C 1.000 2428 3272 327 66 BoxColFill 0.10 0.10 0.44 C 1.000 964 352 111 1359 BoxColFill 0.10 0.10 0.44 C 1.000 1510 352 111 734 BoxColFill 0.10 0.10 0.44 C 1.000 2056 352 111 1794 BoxColFill @@ -812,11 +812,11 @@ LT0 1.000 UL LT1 0.94 0.50 0.50 C LCb setrgbcolor -1980 3173 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ multicores)] +2362 3173 M +[ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -0.94 0.50 0.50 C 1.000 2046 3140 327 66 BoxColFill +0.94 0.50 0.50 C 1.000 2428 3140 327 66 BoxColFill 0.94 0.50 0.50 C 1.000 1101 352 110 434 BoxColFill 0.94 0.50 0.50 C 1.000 1647 352 110 771 BoxColFill 0.94 0.50 0.50 C 1.000 2193 352 110 2586 BoxColFill diff --git a/mpi-energy2-extension/fig/time.eps b/mpi-energy2-extension/fig/time.eps index 72eb22b..99cea89 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 13:29:00 2015 +%%CreationDate: Thu Oct 22 17:45:34 2015 %%DocumentFonts: (atend) %%BoundingBox: 50 50 554 410 %%Orientation: Portrait @@ -506,7 +506,7 @@ SDict begin [ /Author (afanfakh) % /Producer (gnuplot) % /Keywords () - /CreationDate (Thu Oct 22 13:29:00 2015) + /CreationDate (Thu Oct 22 17:45:34 2015) /DOCINFO pdfmark end } ifelse @@ -866,11 +866,11 @@ LTb 1.000 UL LT0 0.10 0.10 0.44 C LCb setrgbcolor -2123 3264 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ one core)] +2546 3264 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 2189 3264 M +0.10 0.10 0.44 C 2612 3264 M 327 0 V 605 1208 M 1311 445 L @@ -886,18 +886,18 @@ LT0 3429 907 Pls 4135 1837 Pls 4841 1889 Pls -2352 3264 Pls +2775 3264 Pls % End plot #1 % Begin plot #2 1.000 UP 1.000 UL LT1 1.00 0.00 0.00 C LCb setrgbcolor -2123 3132 M -[ [(Helvetica) 140.0 0.0 true true 0 (One site/ multicores)] +2546 3132 M +[ [(Helvetica) 140.0 0.0 true true 0 (Multicores per node scenario)] ] -46.7 MRshow LT1 -1.00 0.00 0.00 C 2189 3132 M +1.00 0.00 0.00 C 2612 3132 M 327 0 V 605 2089 M 1311 592 L @@ -913,7 +913,7 @@ LT1 3429 1091 Crs 4135 2476 Crs 4841 2356 Crs -2352 3132 Crs +2775 3132 Crs % End plot #2 1.000 UL LTb diff --git a/mpi-energy2-extension/my_reference.bib b/mpi-energy2-extension/my_reference.bib index 2c7e80f..26a1858 100644 --- a/mpi-energy2-extension/my_reference.bib +++ b/mpi-energy2-extension/my_reference.bib @@ -7,7 +7,6 @@ isbn = {0-7695-2700-0}, location = {Tampa, Florida}, articleno = {107}, - doi = {10.1145/1188455.1188567}, acmid = {1188567}, publisher = {ACM}, address = {New York, NY, USA} @@ -15,11 +14,11 @@ @article{2, author = {Peraza , J. and Tiwari , A. and Laurenzano , M. and Carrington L. and Snavely}, - title = {{PMaC}'s green queue: a framework for selecting energy optimal {DVFS} configurations in large scale {MPI} applications}, - journal = {Concurrency Computat.: Pract. Exper.DOI: 10.1002/cpe}, + title = {PMaC's green queue: a framework for selecting energy optimal DVFS configurations in large scale MPI applications}, + journal = {Concurrency and Computation: Practice and Experience}, pages = {1-20}, year = {2012} - + } } @@ -47,7 +46,6 @@ location = {San Diego, CA, USA}, pages = {275--280}, numpages = {6}, - doi = {10.1145/996566.996650}, acmid = {996650}, publisher = {ACM}, address = {New York, NY, USA}, @@ -90,19 +88,17 @@ title={Bounding energy consumption in large-scale {MPI} programs}, year={2007}, month=nov, pages={1-9}, -keywords={Clustering algorithms;Delay effects;Dynamic voltage scaling;Energy consumption;Frequency;Government;Laboratories;Large-scale systems;Linear programming;Processor scheduling}, -doi={10.1145/1362622.1362688} +keywords={Clustering algorithms;Delay effects;Dynamic voltage scaling;Energy consumption;Frequency;Government;Laboratories;Large-scale systems;Linear programming;Processor scheduling} } @phdthesis {Malkowski_energy.efficient.high.performance.computing, - author = "Malkowski, Konrad", - title = "Co-adapting scientific applications and architectures toward energy-efficient high performance computing", - school = "The Pennsylvania State University", - address = "USA", - year = "2009", - pages = "227", + author = {Malkowski, Konrad}, + title = {Co-adapting scientific applications and architectures toward energy-efficient high performance computing}, + school = {The Pennsylvania State University}, + address = {USA}, + year = {2009}, + pages = {227} - } @INPROCEEDINGS{10, @@ -112,8 +108,7 @@ title={Crown scheduling: Energy-efficient resource allocation, mapping and discr year={2013}, month=sep, pages={215-222}, -keywords={cores;microprocessor chips;optimisation;power consumption;resource allocation;scaling circuits;scheduling;ILP;crown scheduling;data flows;discrete voltage-frequency scaling;dynamic discrete frequency scaling;dynamic rescaling;energy-efficient resource allocation;energy-optimal code;integer linear programming;malleable streaming tasks;many-core processor;mapping;optimization;pipelined task graph;power consumption;processor cores;streaming task collections;Dynamic scheduling;Optimization;Processor scheduling;Radio spectrum management;Resource management;Schedules}, -doi={10.1109/PATMOS.2013.6662176} +keywords={cores;microprocessor chips;optimisation;power consumption;resource allocation;scaling circuits;scheduling;ILP;crown scheduling;data flows;discrete voltage-frequency scaling;dynamic discrete frequency scaling;dynamic rescaling;energy-efficient resource allocation;energy-optimal code;integer linear programming;malleable streaming tasks;many-core processor;mapping;optimization;pipelined task graph;power consumption;processor cores;streaming task collections;Dynamic scheduling;Optimization;Processor scheduling;Radio spectrum management;Resource management;Schedules} } @INPROCEEDINGS{11, @@ -124,7 +119,6 @@ year={2006}, month=sep, pages={1-10}, keywords={directed graphs;parallel programming;power aware computing;AMD Turion;PC clusters;PowerWatch;Transmeta Crusoe;control library;directed acyclic task graph;dynamic voltage scaling;energy consumption;energy reduction;frequency scaling;high performance computing;microprocessors;parallel programs;power consumption;power monitoring tools;slack reclamation;Clustering algorithms;Concurrent computing;Dynamic voltage scaling;Energy consumption;Energy efficiency;Frequency synchronization;Gears;Libraries;Microprocessors;Monitoring}, -doi={10.1109/CLUSTR.2006.311839}, ISSN={1552-5244} } @@ -140,7 +134,6 @@ ISSN={1552-5244} issn = {1094-3420}, pages = {342--350}, numpages = {9}, - doi = {10.1177/1094342011414749}, acmid = {2020813}, publisher = {Sage Publications, Inc.}, address = {Thousand Oaks, CA, USA}, @@ -148,7 +141,7 @@ ISSN={1552-5244} } @ARTICLE{13, - author = {Lizhe Wang a,b, Samee U. Khan c , Dan Chen a , Joanna Kołodziej d , Rajiv Ranjan e , Cheng-zhong Xu f ,Albert Zomaya}, + author = {Lizhe Wang a,b, Samee U. Khan c, Dan Chen a, Joanna Kołodziej d, Rajiv Ranjan e, Cheng-zhong Xu f,Albert Zomaya}, title = {Energy-aware parallel task scheduling in a cluster}, journal = {Future Generation Computer Systems}, volume = {29}, @@ -165,8 +158,7 @@ title={Energy-Efficient Cluster Computing via Accurate Workload Characterization year={2009}, month=may, pages={68-75}, -keywords={parallel processing;power aware computing;workstation clusters;cluster computer;eco-friendly daemon;energy consumption reduction;energy-efficient cluster computing;power consumption reduction;processor stall cycles;workload characterization;Application software;Clustering algorithms;Energy consumption;Energy efficiency;Frequency;Grid computing;Hardware;High performance computing;Runtime;Voltage}, -doi={10.1109/CCGRID.2009.88} +keywords={parallel processing;power aware computing;workstation clusters;cluster computer;eco-friendly daemon;energy consumption reduction;energy-efficient cluster computing;power consumption reduction;processor stall cycles;workload characterization;Application software;Clustering algorithms;Energy consumption;Energy efficiency;Frequency;Grid computing;Hardware;High performance computing;Runtime;Voltage} } @article{Zhuo_Energy.efficient.Dynamic.Task.Scheduling, @@ -182,7 +174,6 @@ doi={10.1109/CCGRID.2009.88} pages = {17:1--17:25}, articleno = {17}, numpages = {25}, - doi = {10.1145/1331331.1331341}, acmid = {1331341}, publisher = {ACM}, address = {New York, NY, USA}, @@ -197,7 +188,6 @@ doi={10.1109/CCGRID.2009.88} year = {2007}, isbn = {0-7695-2933-X}, pages = {19--}, - doi = {10.1109/ICPP.2007.39}, acmid = {1306033}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -211,7 +201,6 @@ doi={10.1109/CCGRID.2009.88} year = {2005}, isbn = {0-7695-2312-9}, pages = {4a-4a}, - doi = {10.1109/IPDPS.2005.214}, acmid = {1054466}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -225,7 +214,6 @@ year={2010}, month=apr, pages={1-12}, keywords={message passing;parallel algorithms;power aware computing;HPC environment;dynamic concurrency throttling;dynamic voltage-and-frequency scaling;high performance computing;hybrid MPI-OpenMP computing;hybrid programming models;large-scale distributed systems;message passing interface;parallel programs;power-aware computing;power-aware performance prediction model;Concurrent computing;Discrete cosine transforms;Dynamic programming;Dynamic voltage scaling;Frequency;Heuristic algorithms;Large-scale systems;Multicore processing;Power system modeling;Predictive models;MPI;OpenMP;performance modeling;power-aware high -performance computing}, -doi={10.1109/IPDPS.2010.5470463}, ISSN={1530-2075} } @@ -238,10 +226,8 @@ ISSN={1530-2075} and energy management}, booktitle = {ISQED}, year = {2012}, - pages = {747-754}, - ee = {http://dx.doi.org/10.1109/ISQED.2012.6187575}, - CCcrossref = {DBLP:conf/isqed/2012}, - CCbibsource = {DBLP, http://dblp.uni-trier.de} + pages = {747-754} + } @@ -255,7 +241,6 @@ ISSN={1530-2075} location = {New York, New York, USA}, pages = {230--238}, numpages = {9}, - doi = {10.1145/1122971.1123006}, acmid = {1123006}, publisher = {ACM}, address = {New York, NY, USA}, @@ -275,7 +260,7 @@ ISSN={1530-2075} pages = {11-18}, publisher = {SCS/ACM}, timestamp = {2011-12-01T00:00:00.000+0100}, - title = {Modeling the energy consumption for concurrent executions of parallel tasks.}, + title = {Modeling the energy consumption for concurrent executions of parallel tasks}, year = {2011} } @@ -287,7 +272,6 @@ ISSN={1530-2075} year = {2005}, isbn = {1-59593-061-2}, pages = {34--}, - doi = {10.1109/SC.2005.57}, acmid = {1105799}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -302,7 +286,6 @@ ISSN={1530-2075} year = {2005}, isbn = {0-7695-2312-9}, pages = {34--}, - doi = {10.1109/IPDPS.2005.346}, acmid = {1054376}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -316,7 +299,6 @@ ISSN={1530-2075} date = {2009-11-27}, description = {dblp}, editor = {Mueller, Peter and Cao, Jian-Nong and Wang, Cho-Li}, - ee = {http://dx.doi.org/10.1007/978-3-642-10485-5_8}, interhash = {d191ac30e6c4bd27288ffdf9e6d0e815}, intrahash = {4601b8a777bdf956bb48fa611b7556f5}, isbn = {978-3-642-10484-8}, @@ -358,7 +340,6 @@ ISSN={1530-2075} issn = {0743-7315}, pages = {1154--1164}, numpages = {11}, - doi = {10.1016/j.jpdc.2011.01.004}, acmid = {1998949}, publisher = {Academic Press, Inc.}, address = {Orlando, FL, USA}, @@ -377,7 +358,6 @@ ISSN={1530-2075} issn = {0278-0070}, pages = {676--689}, numpages = {14}, - doi = {10.1109/TCAD.2009.2015740}, acmid = {1656937}, publisher = {IEEE Press}, address = {Piscataway, NJ, USA}, @@ -391,8 +371,7 @@ title={Thermal vs Energy Optimization for {DVFS}-Enabled Processors in Embedded year={2007}, month=mar, pages={204-209}, -keywords={circuit optimisation;embedded systems;integrated circuit design;low-power electronics;microprocessor chips;nonlinear programming;thermal management (packaging);DVFS-enabled processors;application peak temperature;cooling costs;dynamic voltage voltage;embedded systems;energy consumption;frequency scaling;nonlinear programming;power optimization;run-time thermal emergencies;system thermal profile;thermal optimization;thermal-constrained energy optimization;Cooling;Cost function;Design optimization;Dynamic voltage scaling;Embedded system;Energy consumption;Frequency;Power system planning;Runtime;Temperature}, -doi={10.1109/ISQED.2007.158} +keywords={circuit optimisation;embedded systems;integrated circuit design;low-power electronics;microprocessor chips;nonlinear programming;thermal management (packaging);DVFS-enabled processors;application peak temperature;cooling costs;dynamic voltage voltage;embedded systems;energy consumption;frequency scaling;nonlinear programming;power optimization;run-time thermal emergencies;system thermal profile;thermal optimization;thermal-constrained energy optimization;Cooling;Cost function;Design optimization;Dynamic voltage scaling;Embedded system;Energy consumption;Frequency;Power system planning;Runtime;Temperature} } @INPROCEEDINGS{29, @@ -402,8 +381,7 @@ title={Bounds on power savings using runtime dynamic voltage scaling: an exact a year={2005}, month=aug, pages={287-292}, -keywords={approximation theory;energy conservation;low-power electronics;power consumption;power supply circuits;DVFS policy;discrete voltage/frequency voltage level;dynamic voltage scaling;dynamic voltage/frequency scaling;energy reduction technique;exponential algorithm;linear-time heuristic approximation;power reduction technique;switching cost;Approximation algorithms;Costs;Dynamic voltage scaling;Energy consumption;Frequency;Linear approximation;Power system modeling;Runtime;Semiconductor device modeling;Upper bound}, -doi={10.1109/LPE.2005.195529} +keywords={approximation theory;energy conservation;low-power electronics;power consumption;power supply circuits;DVFS policy;discrete voltage/frequency voltage level;dynamic voltage scaling;dynamic voltage/frequency scaling;energy reduction technique;exponential algorithm;linear-time heuristic approximation;power reduction technique;switching cost;Approximation algorithms;Costs;Dynamic voltage scaling;Energy consumption;Frequency;Linear approximation;Power system modeling;Runtime;Semiconductor device modeling;Upper bound} } @INPROCEEDINGS{30, @@ -413,8 +391,7 @@ title={Towards Energy Aware Scheduling for Precedence Constrained Parallel Tasks year={2010}, month=may, pages={368-377}, -keywords={environmental factors;parallel processing;power aware computing;scheduling;workstation clusters;dynamic voltage frequency scaling technique;energy aware scheduling heuristics;green service level agreement;high end computing;precedence constrained parallel tasks;Computational modeling;Concurrent computing;Costs;Dynamic voltage scaling;Energy consumption;Frequency;Grid computing;High performance computing;Power engineering computing;Processor scheduling;Cluster Computing;Green Computing;Task Scheduling}, -doi={10.1109/CCGRID.2010.19} +keywords={environmental factors;parallel processing;power aware computing;scheduling;workstation clusters;dynamic voltage frequency scaling technique;energy aware scheduling heuristics;green service level agreement;high end computing;precedence constrained parallel tasks;Computational modeling;Concurrent computing;Costs;Dynamic voltage scaling;Energy consumption;Frequency;Grid computing;High performance computing;Power engineering computing;Processor scheduling;Cluster Computing;Green Computing;Task Scheduling} } @article{31, @@ -426,7 +403,6 @@ number = {RapidPosts}, issn = {1556-6056}, year = {2013}, pages = {1}, -doi = {http://doi.ieeecomputersociety.org/10.1109/L-CA.2013.1}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA} } @@ -440,7 +416,6 @@ pages = "76 - 91", year = "2013", note = "S.I.Energy efficiency in grids and clouds ", issn = "1569-190X", -doi = "http://dx.doi.org/10.1016/j.simpat.2013.04.007", author = {Tom Guérout and Thierry Monteil and Georges Da Costa and Rodrigo Neves Calheiros and Rajkumar Buyya and Mihai Alexandru} } @@ -452,8 +427,7 @@ title={Just In Time Dynamic Voltage Scaling: Exploiting Inter-Node Slack to Save year={2005}, month=nov, pages={33-33}, -keywords={Computer science;Dynamic voltage scaling;Energy consumption;Energy efficiency;Frequency;Gears;Jitter;Microprocessors;Performance loss;Permission}, -doi={10.1109/SC.2005.39} +keywords={Computer science;Dynamic voltage scaling;Energy consumption;Energy efficiency;Frequency;Gears;Jitter;Microprocessors;Performance loss;Permission} } @inproceedings{34, @@ -480,7 +454,6 @@ pages = " - ", year = "2013", note = "", issn = "1084-8045", -doi = "http://dx.doi.org/10.1016/j.jnca.2013.10.009", author = {Wei Liu and Wei Du and Jing Chen and Wei Wang and GuoSun Zeng} } @@ -497,7 +470,6 @@ author = {Wei Liu and Wei Du and Jing Chen and Wei Wang and GuoSun Zeng} issn = {0018-9162}, pages = {68--75}, numpages = {8}, - doi = {10.1109/MC.2003.1250885}, acmid = {957974}, publisher = {IEEE Computer Society Press}, address = {Los Alamitos, CA, USA} @@ -522,7 +494,6 @@ author = {Wei Liu and Wei Du and Jing Chen and Wei Wang and GuoSun Zeng} location = {Porto Alegre, Brazil}, pages = {175--185}, numpages = {11}, - doi = {10.1145/2155620.2155641}, acmid = {2155641}, publisher = {ACM}, address = {NY, USA} @@ -535,8 +506,8 @@ title={Dynamic voltage frequency scaling for multi-tasking systems using online year={2007}, month=aug, pages={207-212}, -keywords={Linux;computer aided instruction;multiprogramming;power aware computing;program compilers;system monitoring;Intel PXA27x;Linux 2.6.9;dynamic voltage frequency scaling;multitasking systems;online learning;processors runtime statistics;Batteries;Computer applications;Delay;Dynamic voltage scaling;Embedded system;Energy consumption;Frequency estimation;Linux;Power engineering computing;Statistics;dynamic voltage frequency scaling;online learning}, -doi={10.1145/1283780.1283825} +keywords={Linux;computer aided instruction;multiprogramming;power aware computing;program compilers;system monitoring;Intel PXA27x;Linux 2.6.9;dynamic voltage frequency scaling;multitasking systems;online learning;processors runtime statistics;Batteries;Computer applications;Delay;Dynamic voltage scaling;Embedded system;Energy consumption;Frequency estimation;Linux;Power engineering computing;Statistics;dynamic voltage frequency scaling;online learning} + } @inproceedings{40, @@ -562,7 +533,6 @@ doi={10.1145/1283780.1283825} location = {Vancouver, B.C., CANADA}, pages = {155--165}, numpages = {11}, - doi = {10.1109/MICRO.2012.23}, acmid = {2457493}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -578,7 +548,6 @@ volume={28}, number={5}, pages={676-689}, keywords={power aware computing;DPM policies;Intel PXA27x core;device leakage characteristics;dynamic power management;dynamic voltage-frequency scaling problems;hard disk drive;online learning;system-level power management;workload characterization;Dynamic voltage frequency scaling;energy-performance trade-off;online learning;power management}, -doi={10.1109/TCAD.2009.2015740}, ISSN={0278-0070} } @@ -629,7 +598,6 @@ ISSN={0278-0070} isbn = {978-0-7695-3114-4}, pages = {126--131}, numpages = {6}, - doi = {10.1109/UKSIM.2008.28}, acmid = {1398183}, publisher = {IEEE Computer Society}, address = {Washington, DC, USA} @@ -647,7 +615,6 @@ ISSN={0278-0070} pages = {2899--2917}, year = 2014, month = oct, - doi = {10.1016/j.jpdc.2014.06.008}, pdf = {http://hal.inria.fr/docs/01/05/75/41/PDF/simgrid3-journal.pdf} } @@ -675,7 +642,6 @@ year={2012}, month=sep, pages={48-57}, keywords={energy consumption;graphics processing units;parallel architectures;AMD Phenom II CPU;CUDA framework;GPU-CPU heterogeneous architectures;GreenGPU;Nvidia GeForce GPU;energy consumption;energy efficiency;high performance computing;holistic approach;Algorithm design and analysis;Computer architecture;Frequency conversion;Graphics processing unit;Green products;Heuristic algorithms;Time frequency analysis;GPU;dynamic frequency scaling;energy efficiency;workload division}, -doi={10.1109/ICPP.2012.31}, ISSN={0190-3918} } @@ -689,7 +655,6 @@ year={2013}, month=oct, pages={826-833}, keywords={energy conservation;graphics processing units;parallel processing;power aware computing;power consumption;DVFS schedulers;GPU computing;K20 GPU;Nvidia K20c Kepler GPU;application performance;compute-bound high-performance workloads;dual Intel Sandy Bridge CPU;dynamic voltage and frequency scaling;energy efficiency;high-throughput workloads;power consumption;power-aware heterogeneous system;Benchmark testing;Computer architecture;Energy consumption;Graphics processing units;Market research;Measurement;Power demand;DVFS in GPU Computing;Dynamic Voltage and Frequency Scaling;Energy-Efficient Computing}, -doi={10.1109/ICPP.2013.98}, ISSN={0190-3918} } @@ -700,7 +665,7 @@ ISSN={0190-3918} urldate = {2014-10-16}, institution = {{DTIC} Document}, author = {Luley, Ryan and Usmail, Courtney and Barnell, Mark}, - year = {2011}, + year = {2011} } @@ -721,7 +686,6 @@ number = "7", pages = "1661 - 1670", year = "2013", issn = "0167-739X", -doi = "http://dx.doi.org/10.1016/j.future.2013.02.010", author = {Lizhe Wang and Samee U. Khan and Dan Chen and Joanna Kołodziej and Rajiv Ranjan and Cheng-zhong Xu and Albert Zomaya} @@ -747,8 +711,7 @@ booktitle={International Green Computing Conference and Workshops (IGCC)}, title={Green governors: A framework for Continuously Adaptive DVFS}, year={2011}, month=jul, -pages={1-8}, -doi={10.1109/IGCC.2011.6008552} +pages={1-8} } @@ -772,7 +735,6 @@ volume={PP}, number={99}, pages={1-1}, keywords={Energy consumption;Optimization;Partitioning algorithms;Processor scheduling;Program processors;Runtime;Time-frequency analysis}, -doi={10.1109/TPDS.2014.2313338}, ISSN={1045-9219},} } @@ -818,7 +780,6 @@ issn={0920-8542}, journal={The Journal of Supercomputing}, volume={70}, number={3}, -doi={10.1007/s11227-014-1236-4}, title={Energy measurement, modeling, and prediction for processors with frequency scaling}, publisher={Springer US}, keywords={Dynamic voltage–frequency scaling; DVFS; SPEC CPU2006 benchmarks; Energy measurement; Energy models}, @@ -845,9 +806,7 @@ journal={Human-centric Computing and Information Sciences}, eid={28}, volume={5}, number={1}, -doi={10.1186/s13673-015-0046-x}, title={An energy-delay product study on chip multi-processors for variable stage pipelining}, -url={http://dx.doi.org/10.1186/s13673-015-0046-x}, publisher={Springer Berlin Heidelberg}, keywords={Chip multi-processors (CMP); Variable stage pipelining (VSP); Power-performance; Optimal pipeline}, author={Saravanan, Vijayalakshmi and Anpalagan, Alagan and Woungang, Isaac} @@ -861,7 +820,6 @@ title={Energy-aware application scheduling on a heterogeneous multi-core system} year={2008}, pages={5-13}, keywords={fuzzy logic;power aware computing;processor scheduling;resource allocation;branch transition rate;energy-aware application scheduling mechanism;fuzzy logic;heterogeneous multicore processor;instruction dependency distance;power efficient computing;program execution;random scheduling approach;resource requirement;suitability-guided program scheduling mechanism;workload balancing;Algorithm design and analysis;Application software;Energy consumption;Fuzzy logic;Hardware;Multicore processing;Power engineering and energy;Power engineering computing;Processor scheduling;Scheduling algorithm}, -doi={10.1109/IISWC.2008.4636086}, month={Sept} } @@ -878,9 +836,7 @@ isbn={978-3-540-68039-0}, booktitle={High Performance Computing - HiPC 2006}, volume={4297}, editor={Robert, Yves and Parashar, Manish and Badrinath, Ramamurthy and Prasanna, ViktorK.}, -doi={10.1007/11945918_48}, title={Exploring Energy-Performance Trade-Offs for Heterogeneous Interconnect Clustered VLIW Processors}, -url={http://dx.doi.org/10.1007/11945918_48}, publisher={Springer Berlin Heidelberg}, author={Nagpal, Rahul and Srikant, Y.N.}, pages={497-508}