Hello All, I am using gem5 for simulation of *alpha architecture* and able to gets stats for sample example. Also able to convert gem5 stats into xml file using m5-mcpat-parse-se.py to the power.xml file which is used as input to McPat. However, power.xml is not generated correctly, not all stats are added in power.xml and also when I tried to provided it as input to McPat I getting following error. *"some value(s) of number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not correct!"* I have tried to look into power.xml file and update it manually but issue is not resolved as suggested in some previous email chains and also followed the steps provided on the link : https://www.cl.cam.ac.uk/~acr31/sicsa/. I have attached the file which are generated by gem5, output.xml file and using the parser from github link : https://github.com/danielpalomino/mcpat-hotspot-parser. Please help how to to resolve this issue. If anybody have working script please share with me. Thanks, Bala

Hi Balasaheb, Did you made a copy/paste error with the Github link ? I don't understand why you are using a mcpat-to-hotspot-parser if you want to do a gem5-to-mcpat-parser. Anyway, you could try with those parser [1,2]. [2] is more up-to-date, last commit was last month. I modified it for my experiments. Remember that McPAT interconnection with gem5 is "user specific". For a better accuracy, you will need to tune the parser to get the exact information that you want. I'm pretty sure that the default version of [2] will not work, or will not provide good results. [1] https://bitbucket.org/dskhudia/gem5tomcpat [2] https://projects.gso.ac.upc.edu/projects/gem5-mcpat On 12/24/2015 07:22 AM, Balasaheb Dabhade wrote: > Hello All, > > I am using gem5 for simulation of *alpha architecture* and able to gets > stats for sample example. Also able to convert gem5 stats into xml file > using m5-mcpat-parse-se.py to the power.xml file which is used as input to > McPat. However, power.xml is not generated correctly, not all stats are > added in power.xml and also when I tried to provided it as input to McPat I > getting following error. > *"some value(s) of > number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not > correct!"* > > I have tried to look into power.xml file and update it manually but issue > is not resolved as suggested in some previous email chains and > also followed the steps provided on the link : > https://www.cl.cam.ac.uk/~acr31/sicsa/. I have attached the file which are > generated by gem5, output.xml file and using the parser from github link : > https://github.com/danielpalomino/mcpat-hotspot-parser. > > Please help how to to resolve this issue. If anybody have working script > please share with me. > > Thanks, > Bala > > > > _______________________________________________ > gem5-users mailing list > gem5-users(a)gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > -- +-------------------------------------------------------------------+ | Pierre-Yves Péneau - PhD student | first.last at umontpellier.fr | | LIRMM / CNRS - SYSMIC team | + 33 4 67 41 85 85 | | Building 4 Office H2.2 | http://walafc0.org | +-------------------------------------------------------------------+

Hello All, I am really sorry, I did copy paste mistake with wrong github link of parser in previous email. Parser suggested by Pierre-Yves Péneau on below link is working perfectly fine for me: [1] https://bitbucket.org/dskhudia/gem5tomcpat Thanks a lot for your help. Thanks, Bala On Thu, Dec 24, 2015 at 2:28 PM, Pierre-Yves Péneau < pierre-yves.peneau(a)lirmm.fr> wrote: > Hi Balasaheb, > > Did you made a copy/paste error with the Github link ? I don't > understand why you are using a mcpat-to-hotspot-parser if you want to do > a gem5-to-mcpat-parser. > > Anyway, you could try with those parser [1,2]. [2] is more up-to-date, > last commit was last month. I modified it for my experiments. Remember > that McPAT interconnection with gem5 is "user specific". For a better > accuracy, you will need to tune the parser to get the exact information > that you want. I'm pretty sure that the default version of [2] will not > work, or will not provide good results. > > > [1] https://bitbucket.org/dskhudia/gem5tomcpat > [2] https://projects.gso.ac.upc.edu/projects/gem5-mcpat > > > On 12/24/2015 07:22 AM, Balasaheb Dabhade wrote: > > Hello All, > > > > I am using gem5 for simulation of *alpha architecture* and able to gets > > stats for sample example. Also able to convert gem5 stats into xml file > > using m5-mcpat-parse-se.py to the power.xml file which is used as input > to > > McPat. However, power.xml is not generated correctly, not all stats are > > added in power.xml and also when I tried to provided it as input to > McPat I > > getting following error. > > *"some value(s) of > > number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not > > correct!"* > > > > I have tried to look into power.xml file and update it manually but issue > > is not resolved as suggested in some previous email chains and > > also followed the steps provided on the link : > > https://www.cl.cam.ac.uk/~acr31/sicsa/. I have attached the file which > are > > generated by gem5, output.xml file and using the parser from github link > : > > https://github.com/danielpalomino/mcpat-hotspot-parser. > > > > Please help how to to resolve this issue. If anybody have working script > > please share with me. > > > > Thanks, > > Bala > > > > > > > > _______________________________________________ > > gem5-users mailing list > > gem5-users(a)gem5.org > > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > > > -- > +-------------------------------------------------------------------+ > | Pierre-Yves Péneau - PhD student | first.last at umontpellier.fr | > | LIRMM / CNRS - SYSMIC team | + 33 4 67 41 85 85 | > | Building 4 Office H2.2 | http://walafc0.org | > +-------------------------------------------------------------------+ > > > _______________________________________________ > gem5-users mailing list > gem5-users(a)gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >

Finally, you may want to take a look at this [1,2]. [1] http://www.samxi.org/papers/xi_hpca2015.pdf [2] http://users.ece.utexas.edu/~gerstl/publications/islped15.PowerTrain.pdf On 12/24/2015 10:06 AM, Balasaheb Dabhade wrote: > Hello All, > > I am really sorry, I did copy paste mistake with wrong github link of > parser in previous email. Parser suggested by Pierre-Yves Péneau on below > link is working perfectly fine for me: > [1] https://bitbucket.org/dskhudia/gem5tomcpat > > Thanks a lot for your help. > > Thanks, > Bala > > On Thu, Dec 24, 2015 at 2:28 PM, Pierre-Yves Péneau < > pierre-yves.peneau(a)lirmm.fr> wrote: > >> Hi Balasaheb, >> >> Did you made a copy/paste error with the Github link ? I don't >> understand why you are using a mcpat-to-hotspot-parser if you want to do >> a gem5-to-mcpat-parser. >> >> Anyway, you could try with those parser [1,2]. [2] is more up-to-date, >> last commit was last month. I modified it for my experiments. Remember >> that McPAT interconnection with gem5 is "user specific". For a better >> accuracy, you will need to tune the parser to get the exact information >> that you want. I'm pretty sure that the default version of [2] will not >> work, or will not provide good results. >> >> >> [1] https://bitbucket.org/dskhudia/gem5tomcpat >> [2] https://projects.gso.ac.upc.edu/projects/gem5-mcpat >> >> >> On 12/24/2015 07:22 AM, Balasaheb Dabhade wrote: >>> Hello All, >>> >>> I am using gem5 for simulation of *alpha architecture* and able to gets >>> stats for sample example. Also able to convert gem5 stats into xml file >>> using m5-mcpat-parse-se.py to the power.xml file which is used as input >> to >>> McPat. However, power.xml is not generated correctly, not all stats are >>> added in power.xml and also when I tried to provided it as input to >> McPat I >>> getting following error. >>> *"some value(s) of >>> number_of_cores/number_of_L2s/number_of_L3s/number_of_NoCs is/are not >>> correct!"* >>> >>> I have tried to look into power.xml file and update it manually but issue >>> is not resolved as suggested in some previous email chains and >>> also followed the steps provided on the link : >>> https://www.cl.cam.ac.uk/~acr31/sicsa/. I have attached the file which >> are >>> generated by gem5, output.xml file and using the parser from github link >> : >>> https://github.com/danielpalomino/mcpat-hotspot-parser. >>> >>> Please help how to to resolve this issue. If anybody have working script >>> please share with me. >>> >>> Thanks, >>> Bala >>> >>> >>> >>> _______________________________________________ >>> gem5-users mailing list >>> gem5-users(a)gem5.org >>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >>> >> >> -- >> +-------------------------------------------------------------------+ >> | Pierre-Yves Péneau - PhD student | first.last at umontpellier.fr | >> | LIRMM / CNRS - SYSMIC team | + 33 4 67 41 85 85 | >> | Building 4 Office H2.2 | http://walafc0.org | >> +-------------------------------------------------------------------+ >> >> >> _______________________________________________ >> gem5-users mailing list >> gem5-users(a)gem5.org >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> > > > > _______________________________________________ > gem5-users mailing list > gem5-users(a)gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > -- +-------------------------------------------------------------------+ | Pierre-Yves Péneau - PhD student | first.last at umontpellier.fr | | LIRMM / CNRS - SYSMIC team | + 33 4 67 41 85 85 | | Building 4 Office H2.2 | http://walafc0.org | +-------------------------------------------------------------------+