From 0d6c7fbfb35dbfc041886ff260a29ce8da9017d0 Mon Sep 17 00:00:00 2001 From: Arnaud Giersch Date: Wed, 7 May 2014 17:48:26 +0200 Subject: [PATCH 1/1] Add some words on validity of SimGrid's models. --- hpcc.tex | 24 +++++++++++++++++------- hpccBib.bib | 31 ++++++++++++++++++++++++++++--- 2 files changed, 45 insertions(+), 10 deletions(-) diff --git a/hpcc.tex b/hpcc.tex index 6e262b1..b9e6bf3 100644 --- a/hpcc.tex +++ b/hpcc.tex @@ -261,24 +261,26 @@ run real applications written in MPI~\cite{MPI}. Apart from the native C interface, SimGrid provides bindings for the C++, Java, Lua and Ruby programming languages. SMPI is the interface that has been used for the work exposed in this paper. The SMPI interface implements about \np[\%]{80} of the MPI 2.0 -standard~\cite{bedaride:hal-00919507}, and supports applications written in C or -Fortran, with little or no modifications. +standard~\cite{bedaride+degomme+genaud+al.2013.toward}, and supports +applications written in C or Fortran, with little or no modifications. -Within SimGrid, the execution of a distributed application is simulated on a -single machine. The application code is really executed, but some operations +Within SimGrid, the execution of a distributed application is simulated by a +single process. The application code is really executed, but some operations like the communications are intercepted, and their running time is computed according to the characteristics of the simulated execution platform. The description of this target platform is given as an input for the execution, by the mean of an XML file. It describes the properties of the platform, such as the computing nodes with their computing power, the interconnection links with -their bandwidth and latency, and the routing strategy. The simulated running -time of the application is computed according to these properties. +their bandwidth and latency, and the routing strategy. The scheduling of the +simulated processes, as well as the simulated running time of the application is +computed according to these properties. To compute the durations of the operations in the simulated world, and to take into account resource sharing (e.g. bandwidth sharing between competing communications), SimGrid uses a fluid model. This allows to run relatively fast simulations, while still keeping accurate -results~\cite{bedaride:hal-00919507,tomacs13}. Moreover, depending on the +results~\cite{bedaride+degomme+genaud+al.2013.toward, + velho+schnorr+casanova+al.2013.validity}. Moreover, depending on the simulated application, SimGrid/SMPI allows to skip long lasting computations and to only take their duration into account. When the real computations cannot be skipped, but the results have no importance for the simulation results, there is @@ -286,6 +288,14 @@ also the possibility to share dynamically allocated data structures between several simulated processes, and thus to reduce the whole memory consumption. These two techniques can help to run simulations at a very large scale. +The validity of simulations with SimGrid has been asserted by several studies. +See, for example, \cite{velho+schnorr+casanova+al.2013.validity} and articles +referenced therein for the validity of the network models. Comparisons between +real execution of MPI applications on the one hand, and their simulation with +SMPI on the other hand, are presented in~\cite{guermouche+renard.2010.first, + clauss+stillwell+genaud+al.2011.single, + bedaride+degomme+genaud+al.2013.toward}. + %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% \section{Simulation of the multisplitting method} diff --git a/hpccBib.bib b/hpccBib.bib index 8c38292..735bc37 100644 --- a/hpccBib.bib +++ b/hpccBib.bib @@ -35,7 +35,7 @@ year = {1986} year = 2014, } -@InProceedings{bedaride:hal-00919507, +@InProceedings{bedaride+degomme+genaud+al.2013.toward, title = {{Toward Better Simulation of MPI Applications on Ethernet/TCP Networks}}, author = {Bedaride, Paul and Degomme, Augustin and Genaud, @@ -50,7 +50,7 @@ year = {1986} month = Nov, } -@Article{tomacs13, +@Article{velho+schnorr+casanova+al.2013.validity, author = {Velho, Pedro and Schnorr, Lucas and Casanova, Henri and Legrand, Arnaud}, title = {{On the Validity of Flow-level TCP Network Models @@ -64,6 +64,31 @@ year = {1986} month = Oct } +@InProceedings{guermouche+renard.2010.first, + author = {A. Guermouche and H. Renard}, + title = {{A First Step to the Evaluation of {SimGrid} in the + Context of a Complex Application}}, + booktitle = {19th International Heterogeneity in Computing + Workshop (HCW)}, + publisher = {IEEE}, + month = apr, + year = 2010 +} + +@InProceedings{clauss+stillwell+genaud+al.2011.single, + author = {Clauss, Pierre-Nicolas and Stillwell, Mark and + Genaud, St{\'e}phane and Suter, Fr{\'e}d{\'e}ric and + Casanova, Henri and Quinson, Martin}, + title = {{Single Node On-Line Simulation of MPI Applications + with SMPI}}, + booktitle = {Proc. of the 25th IEEE Intl. Parallel and + Distributed Processing Symp (IPDPS)}, + year = 2011, + pages = {661--672}, + month = may, + publisher = {IEEE} +} + @article{Calheiros:2011:CTM:1951445.1951450, author = {Calheiros, Rodrigo N. and Ranjan, Rajiv and Beloglazov, Anton and De Rose, C\&\#x00e9;sar A. F. and Buyya, Rajkumar}, title = {CloudSim: A Toolkit for Modeling and Simulation of Cloud Computing Environments and Evaluation of Resource Provisioning Algorithms}, @@ -76,7 +101,7 @@ year = {1986} issn = {0038-0644}, pages = {23--50}, numpages = {28}, - url = {http://dx.doi.org/10.1002/spe.995}, + NOurl = {http://dx.doi.org/10.1002/spe.995}, doi = {10.1002/spe.995}, acmid = {1951450}, publisher = {John Wiley \& Sons, Inc.}, -- 2.39.5