Re: [Gems-users] SIMICS_translate_address

[Kevin Moore <kmoore@xxxxxxxxxxx>]

Dave,
	This is more a simics question than a gems issue, but I 
think that translate_address accesses the TLB, which is 
different for each processor.  I believe it will fail if the 
page is not mapped in the processor's TLB.  If anyone else 
has experience with SIM_logical_to_physical please chime in. 
 Thanks,
Kevin


Dave Z. wrote:
> Hello,
>
> I have a question regarding SIMICS_translate_address
> function. I'm simulating a multithreaded program,
> where each thread is bound to a processor. Using magic
> calls, I pass some data addresses from the program to
> GEMS. I use SIMICS_translate_address to get physical
> addresses so that I can do some operations on the
> data. When I do SIMICS_translate_address(0,
> Address(X)), everything is fine, but I get no
> traslation when procID is 1. I don't understand what
> is going on, because the threads are bound to
> processors and each processor should have the same
> virtual address, right? 
>
> Thanks,
>
> Dave
>
>
>  
> ____________________________________________________________________________________
> The fish are biting. 
> Get more visitors on your site using Yahoo! Search Marketing.
> http://searchmarketing.yahoo.com/arp/sponsoredsearch_v2.php
> _______________________________________________
> 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.