Yes, if you have a spin lock in some code, it's highly likely that a faster core will spin for more instructions on that lock and therefore the number if instructions will increase somewhat proportional to frequency.
Ali On 11.04.2014 10:29, Heba Khdr wrote: > The number of committed instructions was increasing when I increase the > frequency from 0.2 Ghz, 0.4, 0.6 , and so on till 1Ghz. However, after that > it will not increase, but as I mentioned in the first email. #instructions in > 1.2 Ghz will be the same liken #instructions in 0.6 Ghz and so on. > > Best, > Heba > > On Fri, Apr 11, 2014 at 5:15 PM, narayanamoor <narayanam...@wisc.edu> wrote: > > Also, in multi core simulations the number of committed instructions do not > represent work fully as some instructions may be used for synchronization. > > Thanks > Srini > > -------- Original message -------- > From: Andreas Hansson <andreas.hans...@arm.com> > Date: 04/11/2014 9:11 AM (GMT-06:00) > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: Re: [gem5-users] number of committed instructions > > Hi Fernando, > > Something to keep in mind is that if it is a full system run then the number > of committed instructions could very well change. > > Andreas > > From: Fernando Endo <fernando.en...@gmail.com> > Reply-To: gem5 users mailing list <gem5-users@gem5.org> > Date: Friday, 11 April 2014 15:08 > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: Re: [gem5-users] number of committed instructions > > Hello, > > The number of committed instructions should be always the same! Because the > real work done can be represented by committed instruction, and it is the > same if one change the CPU frequency. What may change is the number of > executed instructions (iew stage), because the dynamic behavior, i.e. the > speculation, will be different with different CPU/cache freq ratio. > > Regards, > > -- > Fernando A. Endo, PhD student and researcher > > Universit� de Grenoble, UJF > France > > 2014-04-11 10:42 GMT+02:00 Heba Khdr <heba.k...@informatik.uni-karlsruhe.de>: > > Dear all, > > I have a question: I am running parsec applications using gem5 and for > different freqeuencies in each experiment. When I increase the frequency, the > number of committed instructions (which I got it from stats.txt) increase, > till I exceed the frequency more than 1 Ghz, then the number of instructions > will not increase. It will not saturated, but I will get the following: > #instructions for 1.2 Ghz = #instructions for 0.6 Ghz. #instructions for 1.6 > Ghz = #instructions for 0.8 Ghz. > > So, what do you think the problem is ? > > Thanks in advance. > > _______________________________________________ > gem5-users mailing list > gem5-users@gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users [1] > -- 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. > > ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, > Registered in England & Wales, Company No: 2557590 > ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, > Registered in England & Wales, Company No: 2548782 > > _______________________________________________ > gem5-users mailing list > gem5-users@gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users [1] _______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users [1] Links: ------ [1] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
