Re: [Gems-users] x86 simics stall mode

[Byn Choi <bynchoi1@xxxxxxxxxxxx>]

Niranjan,

I've encountered this problem and temporarily fixed it by putting the  
following in
ruby_operate(...) in $GEMS/ruby/module/ruby.c

if (!g->may_stall) { return 0; }

In simics for x86, it seems that instruction fetches are unstallable.  
Some discussion on how to correctly model instruction fetch delay can  
be found here.
https://www.simics.net/mwf/topic_show.pl?pid=84629

Byn


On Oct 6, 2009, at 10:38 PM, niranjan soundararajan wrote:

> Hello,
>
> I am using GEMS 2.1 with simics 3.0.31. When I use the -stall mode  
> to run, I get the following error.
> failed assertion 'mem_trans->s.may_stall' at fn  
> MemoryTransactionResult SimicsProcessor::makeRequest 
> (memory_transaction_t*) in simics/SimicsProcessor.C:326
> There was an earlier post related to this : https://lists.cs.wisc.edu/archive/gems-users/2008-February/msg00041.shtml
>
> While I tried to remove the 'instruction-fetch-mode instruction- 
> fetch-trace' option, it didn't work. I have not tried the other  
> option but wanted to check if someone had tried it before and if so  
> wanted to check if it worked.
> Any other way to run x86 workloads with GEMS, let me know.
>
> Thank you,
> Niranjan
> _______________________________________________
> 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.