Re: [Gems-users] Naked checkpoints creation on 64-bit machines

[Stamatis Kavadias <kavadias@xxxxxxxxxxxx>]

Hello Xiongfei,

    I have not used GEMS scripts for checkpointing booted Solaris on Serengeti
(is that what naked checkpoints are?), but I am using Solaris (10) on Serengeti
and have taken checkpoints using some of the scripts provided in an earlier
Simics version (2.2.19) and later a script I found in Simics mailing list
(https://www.simics.net/mwf/topic_show.pl?tid=9375) for large
configurations (>24 processors) of the Serengeti target. So I assume that
yes, using gcc-3.4.6 to compile GEMS you will be able to take checkpoints.
I have created checkpoints on both Intel core2 and ADM (Opteron I think)
64-bit CPU hosts.

Regards,

Stamatis

PS: I have used GEMS versions 2.0 and 2.1 for the above.

Subject:

Re: [Gems-users] Simics 4.0 for GEMS?

From:

Xiongfei Liao <xiongfei.liao@xxxxxxxxx>

Date:

Wed, 4 Feb 2009 10:11:24 +0800

To:

Gems Users <gems-users@xxxxxxxxxxx>

To:

Gems Users <gems-users@xxxxxxxxxxx>

Hi, Stamatis,

Does your configuration work well with the creation of naked checkpoints?

I failed with gcc3.4.1 with both Intel and AMD 64-bit processors.

Regards,
Xiongfei

On Wed, Feb 4, 2009 at 9:02 AM, Stamatis Kavadias <kavadias@xxxxxxxxxxxx> wrote:

Hello all,

    If it's any help to anyone, I have been using GEMS with simics 3 on both Intel and AMD 64-bit
processors, compiling GEMS with gcc 3.4.6.
    This solved the problem of instantiating opal (tested on AMD) and I never had problems with
memory allocation and Ruby in general. (Note: I have not used Opal thereafter so no guaranties...).


Regards,

Stamatis

Subject:

Re: [Gems-users] Simics 4.0 for GEMS?

From:

Dan Gibson <degibson@xxxxxxxx>

Date:

Mon, 2 Feb 2009 11:52:27 -0600

To:

Gems Users <gems-users@xxxxxxxxxxx>

To:

Gems Users <gems-users@xxxxxxxxxxx>

On Mon, Feb 2, 2009 at 11:48 AM, Greg Byrd <gbyrd@xxxxxxxx> wrote:

I spoke up this time because I didn't want the GEMS
community to think that everyone is using Simics 3.x at this
point.

I also will mention that we at Wisconsin are all still using Simics 2.x internally.
 

...Greg

Dan Gibson wrote:
> Greg (+list),
> The compiler version issue is a really, really difficult problem. We
> have seen this problem at various times, on the list and internally, and
> we invariably get the same response from Virtutech: Upgrade.
>
> My current theory on this is that Simics 2.x (or 3.x) is compiled
> against ABI x, GEMS is compiled to ABI y according to the setup of the
> host machine, and both GEMS and Simics end up /using/ ABI z at runtime,
> where in general x!=z and y!=z (though usually y==z). Hence, (at least)
> two flavors of libc interact, and eventually the heap gets smashed.
> Unfortunately, I don't know why it works for some folks and not for
> others -- memory corruption is a pretty subtle problem as you know.
>
> So why not upgrade? There is no short answer, so here's the long one.
> 1) GEMS-users (including ourselves) have a lot of scripts that are not
> forward compatible (though checkpoints ARE from 2.x to 3.x).
> 2) We have had some indication that GEMS+Simics2 is faster than
> GEMS+Simics3 for some workloads
> 3) Upgrading is a big pain and we don't have a lot of free graduate
> students available to make the change
> 4) Changing Simics version has the nasty side effect of changing
> results... and no one wants to admit mid-thesis that results are
> sensitive to something like that.
>
> However, as I said in my earlier post, we are looking into Simics 4.0
> compatibility for GEMS right now. It will not be available for use in
> classes this semester. In fact, from my 'experience' in porting GEMS to
> 3.0, I won't guarantee it'll /ever/ be available. But, we're looking
> into it and we request and appreciate patience from our user community.
>
> Regards,
> Dan
>

> On Mon, Feb 2, 2009 at 11:18 AM, Greg Byrd <gbyrd@xxxxxxxx

> <mailto:gbyrd@xxxxxxxx>> wrote:
>

>     For the record, I have not been able to get GEMS to work
>     "just fine" with Simics 3.x.  The main issue is the versions
>     of compilers used to compile and link GEMS vs. what's used
>     for Simics.
>
>     I know others have had success, but my experience has not
>     been good.  I was hoping to make the move to 3.0 for my
>     class this semester, but I ended up sticking with 2.x.
>
>     So I'm unhappy to see 2.x go away, but I understand why and
>     hopefully will figure out a way to work around it.
>
>     ...Greg
>
>     PS.  I found the right mix of compilers to get everything to
>     link, but then ruby0.init crashes immediately with a bad
>     address passed to free().  If anyone has seen similar
>     behavior and figured out a fix, let me know.  I'm somewhat
>     constrained by a university computing environment that's
>     largely out of my control, so please don't send me fixes
>     like "reinstall Linux with this patch."
>
>
>
>     Abdullah Kayi wrote:
>      > Hi Dan,
>      >
>      > FYI, Virtutech already suspended new Simics 2.x licenses. However, as
>      > you mentioned Simics 3.x works fine with GEMS, the only problem
>     would be
>      > the checkpoint scripts.
>      >
>      > Regards,
>      >
>      > AK
>      >
>      > On 2/2/09 11:52 AM, "Dan Gibson" <degibson@xxxxxxxx

>     <mailto:degibson@xxxxxxxx>> wrote:
>      >
>      >     Hi,
>      >
>      >     We're working internally on Simics 4.0 compatibility and testing
>      >     right now. As with a lot of these graduate-student driven
>      >     projects... its a slow process.
>      >
>      >     The good news is that there is no real rush for current GEMS
>     users
>      >     to upgrade from Simics 3.0 to 4.0 on their own. There is some
>      >     concern that Virtutech may be considering suspending
>     availability of
>      >     new Simics 2.x licenses, but GEMS works with Simics 3.x already.
>      >
>      >     Regards,
>      >     Dan
>      >
>      >     On Mon, Feb 2, 2009 at 10:46 AM, Yangchun Luo

>     <yluo@xxxxxxxxxx <mailto:yluo@xxxxxxxxxx>> wrote:
>      >
>      >         Hi,
>      >
>      >         Since Simics 4.0 is released by Virtutech, I wonder if it is
>      >         also compatible with GEMS 2.1?
>      >         And how urgent is it for GEMS users to upgrade from
>     Simics 3.0.x
>      >         to 4.0?
>      >
>      >         Thanks!
>      >
>      >         _______________________________________________

>      >         Gems-users mailing list

>      >         Gems-users@xxxxxxxxxxx <mailto: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 <mailto: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 <mailto: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.
>
>
>
>

> --
> http://www.cs.wisc.edu/~gibson [esc]:wq!
>
>

> ------------------------------------------------------------------------

>
> _______________________________________________

> 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.

--

http://www.cs.wisc.edu/~gibson [esc]:wq!

_______________________________________________
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.

---

Subject:

[Gems-users] Naked checkpoints creation on 64-bit machines

From:

Xiongfei Liao <xiongfei.liao@xxxxxxxxx>

Date:

Thu, 5 Feb 2009 21:55:07 +0800

To:

Gems Users <gems-users@xxxxxxxxxxx>

To:

Gems Users <gems-users@xxxxxxxxxxx>

Hi, GEMS users,

Did anyone even create the naked checkpoints successfully on Intel or AMD 64 CPUs? If yes, what kind of configuration was used?

Thanks a lot.

Best regards,
Xiongfei

---