Hi Andreas, Thanks for the link. Sounds really interesting. Are the power models extensible to architectures other than Big.little? It seems like the tool targets mobile architectures at this point.
Thanks, Amin On Thu, Apr 21, 2016 at 3:09 AM, Andreas Hansson <[email protected]> wrote: > Hi all, > > McPAT definitely has valid use-cases, but it is also fraught with pitfalls. > > > For anyone wanting reliable and accurate power models I can greatly > recommend: http://www.powmon.ecs.soton.ac.uk/powermodeling/ > > The generated models work very well with recent versions of gem5, as it > now supports power states, and hooks for these equation-based power models. > > Andreas > > On 21/04/2016, 10:50, "gem5-users on behalf of Raul Garcia" > <[email protected] on behalf of [email protected]> > wrote: > > >Hello Marcos, > > > >Does this translator supports inputs using the ARM architecture? If not > >what would it take to enable this support? > > > >Raul. > >________________________________________ > >From: gem5-users [[email protected]] on behalf of Kien > >[[email protected]] > >Sent: Thursday, April 21, 2016 3:03 AM > >To: [email protected] > >Subject: Re: [gem5-users] gem5ToMcPAT v0.1 > > > >Marcos Horro Varela <marcos.horro <at> udc.es> writes: > > > >> > >> Hello all, > >> > >> I would like to make an annoucement: I have been developing a translator > >from gem5 to McPAT in Bison, Flex and > >> C/C++. Basically: parses the configuration file and statistics file from > >gem5 and generates an XML based > >> on a template which fits properly as McPAT input. It seems to work > >properly. All the details and source code > >> can be found here [1]. If you have any problems using it, just tell me. > >> I would like to thank Fernando Endo for his work [2], which was really > >helpful during the process. > >> > >> Best regards, > >> > >> [1] https://github.com/markoshorro/gem5ToMcPAT > >> [2] https://tel.archives-ouvertes.fr/tel-01285964/document > >> > > > > > >Thanks Horro Varela, > > > >This is what I am looking for, but my first try with FS Alpha failed (with > >either provided xml templates or the one from mcpat with some > >modification. > > > >I got alot of warnings like these > > > >Warning: stat system 'total_cycles' may have not been set! > >Warning: stat system 'idle_cycles' may have not been set! > >Warning: stat system 'busy_cycles' may have not been set! > >Warning: param system.core0 'x86' may have not been set! > >Warning: param system.core0 'fetch_width' may have not been set! > >Warning: param system.core0 'decode_width' may have not been set! > >Warning: param system.core0 'issue_width' may have not been set! > >.... <30 + more :)> > > > >I check the template is fine as it works with mcpat, do you have any > >suggestions? > >I am using mcpat1.0 and the latest version of gem5, alpha fs image was the > >one with embedded parsec benchmarks. > > > >Thanks & regards, > >-- > >Kien > > > > > > > >_______________________________________________ > >gem5-users mailing list > >[email protected] > >http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > >_______________________________________________ > >gem5-users mailing list > >[email protected] > >http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > IMPORTANT NOTICE: The contents of this email and any attachments are > confidential and may also be privileged. If you are not the intended > recipient, please notify the sender immediately and do not disclose the > contents to any other person, use it for any purpose, or store or copy the > information in any medium. Thank you. > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
