Re: [Gems-users] how to reproduce the experiment like LogTM or any other TMs


Date: Tue, 2 Jun 2009 15:34:22 +0800
From: ruzhu kao <kaoruzhu@xxxxxxxxx>
Subject: Re: [Gems-users] how to reproduce the experiment like LogTM or any other TMs
Thanks for your reply, these URLs give me a clear guideline. I will
have a try. Thanks again.

2009/6/2 Jayaram Bobba <bobba@xxxxxxxxxxx>:
> Some pointers to help you out once you get an OS checkpoint...
>
> http://pages.cs.wisc.edu/~david/courses/cs758/Fall2007/handouts/hw-logtm.html
> http://pages.cs.wisc.edu/~markhill/cs757/Spring2008/handouts/hw3.html
> http://www.cs.wisc.edu/gems/doc/gems-wiki/moin.cgi/TM_Workload_Setup
>
> ruzhu kao wrote:
>> Hi all:
>>     I am a newbie using GEMS. After I have read some papers about TM,
>> I find it is a very interesting topic that attracted me very much. So
>> I want to reproduce a testbed for me to quickly learn some merits of
>> TM. However, I have met many problems after I start to do some actual
>> work about TM.
>>    My software environment include: CentOS4.7, Simics 3.0.31, GEMS 2.1
>>    1. When I use naked-check-create.sh to create a naked checkpoints
>> as a beginning, it failed again and again.( I have already edited
>> "system.conf" with correct path and OS images. ) I noticed someone has
>> counted the similar problem and post to this list, but when I try to
>> use their advices, I failed again. It really make me dispirited. I
>> hope someone could indicate me a more detail solution.
>>
>> /************ Below is the output in simics console. **************/
>> Capturing output to 'install-log.txt'
>> Warning: Limit larger than the amount of physical memory.
>> Start at : Mon Jun  1 21:39:33 2009
>> [system info] Disabling slave processors.
>> [system info] Enabling slave processors.
>> Segmentation fault (SIGSEGV) in main thread
>> The simulation state has been corrupted. Simulation cannot continue.
>> Please restart Simics.
>> Starting command line. (May have skipped commands in script files.)
>> [cpu36] v:0x0000000001038cd4 p:0x03801c38cd4  sth %o2, [%o1 + %g0]
>> Setting new inspection cpu: cpu36
>> /*****************************************************/
>>
>>    2. Then I use OS setup scripts contained in Simics, then I had done
>> OS setup. When I want to reproduce some TM system such as LogTM, I
>> have no idea about how to do that. I want to repeated just like ISCA05
>> tutorial, but I don't know how to produce a checkpoint which contains
>> some microbenchmarks in it. It seems need a script to do some
>> instructions like workload-check-create.sh. However I failed using
>> nake-check-create.sh, so I have no idea how to use
>> workload-check-create.sh Then I begin to read each README file in
>> GEMS. But I do not find proper solution. Does anybody could tell me
>> how to reproduce a TM system like LogTM, I think I may miss some
>> important steps.
>>
>> I think I need your kindly and patient help to explain how to using
>> GEMS. Much appreciate for your valuable comments.
>> _______________________________________________
>> Gems-users mailing list
>> Gems-users@xxxxxxxxxxx
>> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
>> Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>>
>>
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>
>
[← Prev in Thread] Current Thread [Next in Thread→]