Hello! I am sorry for spamming similar mail at both lists. Of course I know about the threads but here at http://gem5.org/Multiprogrammed_workloads I found that SE mode has no thread scheduling. So will it be okay to use pthreads in SE mode to create my application. I can not use FS mode because it invloves Operating System.
On Mon, Jun 25, 2012 at 11:37 AM, <gem5-users-requ...@gem5.org> wrote: > Send gem5-users mailing list submissions to > gem5-users@gem5.org > > To subscribe or unsubscribe via the World Wide Web, visit > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > or, via email, send a message with subject or body 'help' to > gem5-users-requ...@gem5.org > > You can reach the person managing the list at > gem5-users-ow...@gem5.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of gem5-users digest..." > > > Today's Topics: > > 1. Re: Implementation of producer consumer problem (Nilay) > 2. Re: Timing in Ruby (Nilay) > 3. Re: Write Through Cache (Nilay) > 4. Re: Run GEM5 with 256 cores (Hossein Nikoonia) > 5. Re: Run GEM5 with 256 cores (gem5 gem5) > 6. ruby memory system (Hossein Nikoonia) > 7. Re: Run GEM5 with 256 cores (Hossein Nikoonia) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Mon, 25 Jun 2012 00:16:04 -0500 > From: "Nilay" <ni...@cs.wisc.edu> > To: "gem5 users mailing list" <gem5-users@gem5.org> > Cc: vishal rawtiya <vishu.h...@gmail.com> > Subject: Re: [gem5-users] Implementation of producer consumer problem > Message-ID: > <8cedae9a6f4d31f7bf89448f3840de68.squir...@webmail.cs.wisc.edu> > Content-Type: text/plain;charset=iso-8859-1 > > On Sun, June 24, 2012 11:43 pm, vishal rawtiya wrote: > > Hello! > > I guess i was not clear enough in my question last time as i din't > > receive any response so here i am. > > > > 1) I want to modify gem5 so that it can identify shared region among the > > processes. > > 2) I found that arch/x86 may support system calls like shmget, shmctl > etc. > > but currently those system calls are not implemented. > > But, > > I am working with alpha "(SE mode)" so is there any way that i can modify > > gem5 > > i) To support the system calls mentioned above. > > ii) or may be use other IPC methods like message passing or others. > > > > Thank you. > > Vishal > > > > Why do you need to send the same email to two different lists related to > gem5? You did not even bother to read the response that was sent to your > original email on gem5-users list? > > gem5 is a piece of software which can be modified in whatever way you > like. If you need those system calls, you can implement them on your own. > And if you have heard of threads (pthreads, or something similar), you > might want to use it. > > -- > Nilay > > > > ------------------------------ > > Message: 2 > Date: Mon, 25 Jun 2012 00:23:33 -0500 > From: "Nilay" <ni...@cs.wisc.edu> > To: "gem5 users mailing list" <gem5-users@gem5.org> > Cc: Anouk <a.l...@ee.ucl.ac.uk> > Subject: Re: [gem5-users] Timing in Ruby > Message-ID: > <dc8469b49395bc64e448290d7ba917f0.squir...@webmail.cs.wisc.edu> > Content-Type: text/plain;charset=iso-8859-1 > > On Sat, June 23, 2012 10:21 am, Anouk wrote: > > Dear, > > > > I have a question about the relationship between a Ruby cycle and it's > > equivalent in 'real time' seconds. Could somebody please tell me whether > I > > am > > right in what I am thinking? > > > > In the default case, 1 Ruby cycle is equal to 500 ticks, which makes 1 > > Ruby > > cycle equal to 0.5 ns. So is correct to say then when you call the Ruby > > event > > queue to schedule the next event, that that event will take place 0.5 ns > > later, > > in 'real life'? > > The use of the word 'real' seems dubious to me, but you are correct. > > > > > The reason for this question is that I want to write a time division > > multiplexed > > network in which cores can only communicate during certain time slots and > > therefore I need to relate a Ruby cycle to a number of ns. > > > > I don't see why you need to know the length of a cycle in terms of how > much time passed in 'real life'. > > -- > Nilay > > > > ------------------------------ > > Message: 3 > Date: Mon, 25 Jun 2012 00:27:35 -0500 > From: "Nilay" <ni...@cs.wisc.edu> > To: "gem5 users mailing list" <gem5-users@gem5.org> > Cc: Puneet Ginoria <punnu.gino...@gmail.com> > Subject: Re: [gem5-users] Write Through Cache > Message-ID: > <708a05c07eecd3737dd15c7a6565ae52.squir...@webmail.cs.wisc.edu> > Content-Type: text/plain;charset=iso-8859-1 > > On Sat, June 23, 2012 2:36 am, Puneet Ginoria wrote: > > Hi all, > > > > I am doing a power modeling project and i need gem 5 for it. I need to > > know > > if write through cache and write buffer exists in it and how to enable > it. > > > > I think both classic and ruby have only write-back caches as of now. > > -- > Nilay > > > > ------------------------------ > > Message: 4 > Date: Mon, 25 Jun 2012 10:16:44 +0430 > From: Hossein Nikoonia <nikoo...@gmail.com> > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: Re: [gem5-users] Run GEM5 with 256 cores > Message-ID: > < > cap-6s88hjiqhzzm1diwivsgeu5knacvyab5pzlo5fipzcsw...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > are you sure you can run a multi-threaded benchmark (pthread or omp) in x86 > SE mode? > > for FS mode, you need to have a linux kernel compiled with the ability to > handle 256 cores > > On Mon, Jun 25, 2012 at 9:38 AM, gem5 gem5 <gem5.user....@gmail.com> > wrote: > > > Hi all, > > > > I need to run some simulation with about 256 cores. So far I only find > two > > benchmarks from parsec2.1 which can work alright with X86_SE with 256 > > num.cpus. I wonder if someone has benchmarks which work well with gem5 > for > > 256 cores or can tell me a better/right way to run 256 cores with GEM5. I > > really appreciate your help. Thanks! > > > > Best, > > > > Jinzhu > > > > _______________________________________________ > > gem5-users mailing list > > gem5-users@gem5.org > > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20120625/62e34045/attachment-0001.html > > > > ------------------------------ > > Message: 5 > Date: Mon, 25 Jun 2012 01:59:05 -0400 > From: gem5 gem5 <gem5.user....@gmail.com> > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: Re: [gem5-users] Run GEM5 with 256 cores > Message-ID: > <CAFBeb=EpZdZ+wyyR= > ejdqexfx1t699p4_qo_ihqlkywv+ey...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > I checked the output when running 256 threads with X86 SE and its 99% the > same as the standard output. So I guess it's ok. I used gcc-pthread version > of parsec and m5thread library to compile. > > According to the GEM5 website, BigTsunami only suppports up to 64 cores in > FS mode and it's quite slow....Do you have some instructions on how to > compile a linux kernel with the ability to handle 256 cores? > > Thanks! > > Jinzhu > > On Mon, Jun 25, 2012 at 1:46 AM, Hossein Nikoonia <nikoo...@gmail.com > >wrote: > > > are you sure you can run a multi-threaded benchmark (pthread or omp) in > > x86 SE mode? > > > > for FS mode, you need to have a linux kernel compiled with the ability to > > handle 256 cores > > > > On Mon, Jun 25, 2012 at 9:38 AM, gem5 gem5 <gem5.user....@gmail.com > >wrote: > > > >> Hi all, > >> > >> I need to run some simulation with about 256 cores. So far I only find > >> two benchmarks from parsec2.1 which can work alright with X86_SE with > 256 > >> num.cpus. I wonder if someone has benchmarks which work well with gem5 > for > >> 256 cores or can tell me a better/right way to run 256 cores with GEM5. > I > >> really appreciate your help. Thanks! > >> > >> Best, > >> > >> Jinzhu > >> > >> _______________________________________________ > >> gem5-users mailing list > >> gem5-users@gem5.org > >> 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 > > > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20120625/bd24c2ac/attachment-0001.html > > > > ------------------------------ > > Message: 6 > Date: Mon, 25 Jun 2012 10:30:22 +0430 > From: Hossein Nikoonia <nikoo...@gmail.com> > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: [gem5-users] ruby memory system > Message-ID: > <CAP-6s88ieVemA9qq2Q9jPLkRXo= > s5zccamk78q1fte3bpk-...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > List, > > I'm (in the beginning of) going deep into Ruby memory model. However, I > cannot understand the bellow things: > > - Why ruby is a part of 'system'? could it be child of 'root'? so 'root' > have two childs: 'system' (containing cpu and other things) and 'ruby'. is > it logical and/or possible? > - where is the actual physical memory? I found it is attached to pio_bus > (part of 'system'). I guess it should be part of 'ruby' bellow caches or > connected to garnet. am i wrong? > - if the actual memory (as i understand) is connected to pio_bus, how a > memory request from cpu is handled by ruby? > > hit: cpu->sequencer->ruby->sequencer->cpu ? > miss: > > cpu->sequencer->ruby->sequencer->pio_bus->physmem->pio_bus->sequencer->ruby->sequencer->cpu > ? > > I'd appreciate if some one could explain it. we may also update the wiki. > > Best > Seyed Hossein > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20120625/16b40a05/attachment-0001.html > > > > ------------------------------ > > Message: 7 > Date: Mon, 25 Jun 2012 10:38:43 +0430 > From: Hossein Nikoonia <nikoo...@gmail.com> > To: gem5 users mailing list <gem5-users@gem5.org> > Subject: Re: [gem5-users] Run GEM5 with 256 cores > Message-ID: > < > cap-6s8_4coe7kiqxajwkjqk-ub_qfzg2a2zo0cauy0ulo6i...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > you should config the kernel with CONFIG_NR_CPUS options set to 256. see > http://cateee.net/lkddb/web-lkddb/NR_CPUS.html for more details. > see wiki for how to compile a kernel for gem5. there is a .config file for > it. only modify the above option. > > I don't know how well linux kernel can handle 256 cores. > > could you please let us know the instructions you have taken to compile > parsec with pthread? I'd really appreciate it. > > On Mon, Jun 25, 2012 at 10:29 AM, gem5 gem5 <gem5.user....@gmail.com> > wrote: > > > I checked the output when running 256 threads with X86 SE and its 99% the > > same as the standard output. So I guess it's ok. I used gcc-pthread > version > > of parsec and m5thread library to compile. > > > > According to the GEM5 website, BigTsunami only suppports up to 64 cores > > in FS mode and it's quite slow....Do you have some instructions on how to > > compile a linux kernel with the ability to handle 256 cores? > > > > Thanks! > > > > Jinzhu > > > > > > On Mon, Jun 25, 2012 at 1:46 AM, Hossein Nikoonia <nikoo...@gmail.com > >wrote: > > > >> are you sure you can run a multi-threaded benchmark (pthread or omp) in > >> x86 SE mode? > >> > >> for FS mode, you need to have a linux kernel compiled with the ability > to > >> handle 256 cores > >> > >> On Mon, Jun 25, 2012 at 9:38 AM, gem5 gem5 <gem5.user....@gmail.com > >wrote: > >> > >>> Hi all, > >>> > >>> I need to run some simulation with about 256 cores. So far I only find > >>> two benchmarks from parsec2.1 which can work alright with X86_SE with > 256 > >>> num.cpus. I wonder if someone has benchmarks which work well with gem5 > for > >>> 256 cores or can tell me a better/right way to run 256 cores with > GEM5. I > >>> really appreciate your help. Thanks! > >>> > >>> Best, > >>> > >>> Jinzhu > >>> > >>> _______________________________________________ > >>> gem5-users mailing list > >>> gem5-users@gem5.org > >>> 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 > >> > > > > > > _______________________________________________ > > gem5-users mailing list > > gem5-users@gem5.org > > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://m5sim.org/cgi-bin/mailman/private/gem5-users/attachments/20120625/ebe8497a/attachment.html > > > > ------------------------------ > > _______________________________________________ > gem5-users mailing list > gem5-users@gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > > End of gem5-users Digest, Vol 71, Issue 83 > ****************************************** >
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
