Hi, Can anyone tell me what the syntax of using checkpoint_aggregator.py is? I find there is little usage information inside the file.
Thanks, Leonard On Tue, Jun 29, 2010 at 4:28 PM, Susie Sally <[email protected]> wrote: > Hi Lisa, > > Thank you very much. I appreciated it! > > Susie > > On Tue, Jun 29, 2010 at 4:15 PM, <[email protected]> wrote: > >> Send m5-users mailing list submissions to >> [email protected] >> >> To subscribe or unsubscribe via the World Wide Web, visit >> >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> or, via email, send a message with subject or body 'help' to >> [email protected] >> >> You can reach the person managing the list at >> [email protected] >> >> When replying, please edit your Subject line so it is more specific >> than "Re: Contents of m5-users digest..." >> >> >> Today's Topics: >> >> 1. Re: m5threads (Lisa Hsu) >> 2. Re: running multi-program workloads with individual >> checkpoints for each program (Lisa Hsu) >> 3. Re: running multi-program workloads with >> individualcheckpoints for each program (Sujay Phadke) >> 4. Re: running multi-program workloads with >> individualcheckpoints for each program (Korey Sewell) >> 5. Re: running multi-program workloads withindividualcheckpoints >> for each program (Sujay Phadke) >> >> >> ---------------------------------------------------------------------- >> >> Message: 1 >> Date: Tue, 29 Jun 2010 09:30:27 -0700 >> From: Lisa Hsu <[email protected]> >> To: M5 users mailing list <[email protected]> >> Subject: Re: [m5-users] m5threads >> Message-ID: >> <[email protected]> >> Content-Type: text/plain; charset="iso-8859-1" >> >> Hi Matt, >> >> As far as I know, no one has touched m5threads in a long time. I don't >> think >> there is any documentation aside from the README either, aside from any >> comments you might find in the code or discussions that might be on the >> mailing list archive. >> >> Lisa >> >> >> On Mon, Jun 28, 2010 at 10:03 AM, Matthew Horsnell < >> [email protected]> wrote: >> >> > Hi >> > >> > I've got a couple of questions about m5threads: >> > >> > Is anyone actively maintaining the m5threads repository? >> > Does anyone know which of the architectures is fully supported (as far >> as I >> > can tell there is partial support for x86 and sparc)? >> > Is there any documentation for using m5threads (supplimentary of the >> README >> > file). >> > >> > Thanks, >> > >> > Matt >> >> > >> > _______________________________________________ >> > m5-users mailing list >> > [email protected] >> > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> > >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: < >> http://m5sim.org/cgi-bin/mailman/private/m5-users/attachments/20100629/3774996e/attachment-0001.html >> > >> >> ------------------------------ >> >> Message: 2 >> Date: Tue, 29 Jun 2010 09:36:52 -0700 >> From: Lisa Hsu <[email protected]> >> To: M5 users mailing list <[email protected]> >> >> Subject: Re: [m5-users] running multi-program workloads with >> individual checkpoints for each program >> Message-ID: >> <[email protected]> >> Content-Type: text/plain; charset="iso-8859-1" >> >> >> Hi Susie, >> >> The code for that has been checked into the development repository. It's >> in >> the util/ directory and is called checkpoint-aggregator.py. >> >> Lisa >> >> On Sun, Jun 20, 2010 at 3:27 PM, Susie Sally <[email protected]> wrote: >> >> > Hi, >> > >> > I would like to run simulations with multiple workloads with restoring >> an >> > individual checkpoint for each program. >> > >> > I read this thread >> > http://www.mail-archive.com/[email protected]/msg02870.html from the >> > archive. >> > >> > I will very much appreciate if you can point me to the mentioned patch >> or >> > give me pointers for the required modifications to do this. >> > >> > thank you very much. >> > >> > regards, >> > >> > Susie >> > >> > _______________________________________________ >> > m5-users mailing list >> > [email protected] >> > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> > >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: < >> http://m5sim.org/cgi-bin/mailman/private/m5-users/attachments/20100629/7815e750/attachment-0001.html >> > >> >> ------------------------------ >> >> Message: 3 >> Date: Tue, 29 Jun 2010 14:14:47 -0400 >> From: "Sujay Phadke" <[email protected]> >> To: "M5 users mailing list" <[email protected]> >> >> Subject: Re: [m5-users] running multi-program workloads with >> individualcheckpoints for each program >> Message-ID: <575C68AB497044E78FCF6DBE68D08375@eecslowpower> >> Content-Type: text/plain; charset="iso-8859-1" >> >> >> For multi-programmed workloads, I have a clean solution now to the problem >> referred to in the thread: >> http://www.mail-archive.com/[email protected]/msg02832.html >> >> We need to ensure each core completes atleast max_insts_all_thread >> instructions. The default implementation exits as soon as any 1 core reaches >> that count. I created a new exit event called which counts the total system >> events and puts an exit event on the main Q only when all cores have >> completed the required instructions. Further, it can dump stats whenever a >> particular core has reached that count, giving the effect of "freezing" >> stats for that core for max_insts instructions. >> >> I can send a patch for this if interested. Has anyone else implemented >> this? >> >> Sujay >> >> >> >> From: Lisa Hsu >> Sent: Tuesday, June 29, 2010 12:36 PM >> >> To: M5 users mailing list >> Subject: Re: [m5-users] running multi-program workloads with >> individualcheckpoints for each program >> >> >> Hi Susie, >> >> >> The code for that has been checked into the development repository. It's >> in the util/ directory and is called checkpoint-aggregator.py. >> >> >> Lisa >> >> >> On Sun, Jun 20, 2010 at 3:27 PM, Susie Sally <[email protected]> wrote: >> >> Hi, >> >> I would like to run simulations with multiple workloads with restoring an >> individual checkpoint for each program. >> >> I read this thread >> http://www.mail-archive.com/[email protected]/msg02870.html from the >> archive. >> >> I will very much appreciate if you can point me to the mentioned patch or >> give me pointers for the required modifications to do this. >> >> thank you very much. >> >> regards, >> >> Susie >> >> _______________________________________________ >> m5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> >> >> >> >> >> >> -------------------------------------------------------------------------------- >> >> >> >> _______________________________________________ >> m5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: < >> http://m5sim.org/cgi-bin/mailman/private/m5-users/attachments/20100629/6c58e740/attachment-0001.html >> > >> >> ------------------------------ >> >> Message: 4 >> Date: Tue, 29 Jun 2010 14:31:35 -0400 >> From: Korey Sewell <[email protected]> >> To: M5 users mailing list <[email protected]> >> >> Subject: Re: [m5-users] running multi-program workloads with >> individualcheckpoints for each program >> Message-ID: >> <[email protected]> >> Content-Type: text/plain; charset="iso-8859-1" >> >> >> > I can send a patch for this if interested. Has anyone else implemented >> > this? >> > >> At some point we had in the tree where when a thread called the exit >> system >> call, the system would check the threadcontexts in the system and only >> called "exitSimLoop" if there was only 1 thread active in the system. >> >> I think Steve (?) removed it on a code update given that it's not >> necessarily clear that counting the number of threads that are active is a >> good indicator of if the workload calling exit should really exit or not. >> I'm not sure about the reason, so maybe Steve could comment or a double >> check of the archives is in order because I do remember a similar >> functionality to this inside of M5 previously. >> >> I dont think there was anything about "freezing" stats though. So with >> regards to that patch, I guess it wouldnt hurt to post it on reviewboard >> though so that people can comment on it and potentially get it into the >> tree. >> -- >> - Korey >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: < >> http://m5sim.org/cgi-bin/mailman/private/m5-users/attachments/20100629/50fc0985/attachment-0001.html >> > >> >> ------------------------------ >> >> Message: 5 >> Date: Tue, 29 Jun 2010 16:15:35 -0400 >> From: "Sujay Phadke" <[email protected]> >> To: "M5 users mailing list" <[email protected]> >> >> Subject: Re: [m5-users] running multi-program workloads >> withindividualcheckpoints for each program >> Message-ID: <625F6966332B495D80252DFC519F9D34@eecslowpower> >> Content-Type: text/plain; charset="iso-8859-1" >> >> >> if we have just 1 thread/core and n cores. how would the current >> functionality be suited for this? In my implementation, the remaining >> workloads keep executing, since we want a multi-workload behaviour. But it >> makes sure that all cores reach the max_insts count. Isnt that the expected >> behaviour? >> >> Sujay >> >> >> From: Korey Sewell >> Sent: Tuesday, June 29, 2010 2:31 PM >> To: M5 users mailing list >> Subject: Re: [m5-users] running multi-program workloads >> withindividualcheckpoints for each program >> >> >> >> >> I can send a patch for this if interested. Has anyone else implemented >> this? >> At some point we had in the tree where when a thread called the exit >> system call, the system would check the threadcontexts in the system and >> only called "exitSimLoop" if there was only 1 thread active in the system. >> >> I think Steve (?) removed it on a code update given that it's not >> necessarily clear that counting the number of threads that are active is a >> good indicator of if the workload calling exit should really exit or not. >> I'm not sure about the reason, so maybe Steve could comment or a double >> check of the archives is in order because I do remember a similar >> functionality to this inside of M5 previously. >> >> I dont think there was anything about "freezing" stats though. So with >> regards to that patch, I guess it wouldnt hurt to post it on reviewboard >> though so that people can comment on it and potentially get it into the >> tree. >> >> -- >> - Korey >> >> >> >> >> -------------------------------------------------------------------------------- >> >> >> _______________________________________________ >> m5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> -------------- next part -------------- >> An HTML attachment was scrubbed... >> URL: < >> http://m5sim.org/cgi-bin/mailman/private/m5-users/attachments/20100629/008d04df/attachment.html >> > >> >> ------------------------------ >> >> >> _______________________________________________ >> m5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> >> End of m5-users Digest, Vol 47, Issue 41 >> **************************************** >> > > > _______________________________________________ > m5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > -- Give our ability to our work, but our genius to our life!
_______________________________________________ m5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
