4) Be careful to only simulate the important regions of code -- do not
include thread creation / destruction, process forking, etc.
BTW, does this mean GEMS can't simulate multiprogramed or multithreaded
programs? Thanks!
Best regards,
Xuan Qi
On Mon, 3 Mar 2008, Dan Gibson wrote:
> Have a look at the various headers that come in the LogTM codebase, in
> transactions/common/ (GEMS 2.0+) in particular. There should be some
> handy macros there intended for this purpose.
>
> Regards,
> Dan
>
> Philip Garcia wrote:
> Look in the simics reference manual about using the special
> magic instructions. Using magic breakpoints in the code
> (combined with having set magic-break-enable before running
> the code) will have simics stop execution at that
> instruction. Just make sure you do a "c 1" after the magic
> instruction before saving the processor's state. If you
> don't do this, the state will be saved at the magic
> instruction, and telling it to execute again will just cause
> it to break again.
> Phil
> On Mar 3, 2008, at 1:13 AM, Jim Leek wrote:
>
> The wiki FAQ
> (http://www.cs.wisc.edu/gems/doc/wiki/moin.cgi/Frequently_Asked_Questions)
> recommends the following:
>
> 4) Be careful to only simulate the important regions of code -- do not
>
> include thread creation / destruction, process forking, etc.
>
> That sounds like a good idea. What is the standard way
> to do this? It seems like you would have to throw an
> instruction into the benchmark code to halt the
> simulation and drop back to the simics CLI. Is there
> an instruction to do this? I guess I could use
> getchar() to do that. What did the logTM guys do?
>
> Jim
> _______________________________________________
> 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!
>
>
|