I am trying to compare performance of walking without a tick as well as walking 
with ticks, but SE does not do the latter.



> On Dec 9, 2015, at 9:34 AM, Nizamudheen Ahmed <[email protected]> wrote:
> 
> I thought you wanted the walk without a tick... Which is what the SE seems to 
> do, per your claim. I am sure I am missing something..
> From: Arman Shan <mailto:[email protected]>
> Sent: ‎09-‎12-‎2015 21:01
> To: gem5 users mailing list <mailto:[email protected]>
> Subject: Re: [gem5-users] TranslateFunctional
> 
> It turns out that in SE mode, there is no latency for page table walk. The 
> page table is internally a hash table, and it returns immediately, without 
> simulating memory accesses. I find this ridiculous, don’t you?
> 
> 
>> On Dec 9, 2015, at 9:27 AM, Nizamudheen Ahmed <[email protected] 
>> <mailto:[email protected]>> wrote:
>> 
>> Translate atomic should help you do the translation without tick. Isn't it?
>> From: Arman Shan <mailto:[email protected]>
>> Sent: ‎08-‎12-‎2015 23:56
>> To: [email protected] <mailto:[email protected]>
>> Subject: [gem5-users]  TranslateFunctional
>> 
>> Hi,
>> 
>> I was wondering if someone has already implemented translate functional for 
>> the TLB. Otherwise, does anyone know how to do a page table walk without 
>> using any ticks?
>> 
>> Thank you,
>> Arman
>> _______________________________________________
>> gem5-users mailing list
>> [email protected] <mailto:[email protected]>
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>> _______________________________________________
>> gem5-users mailing list
>> [email protected] <mailto:[email protected]>
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
> 
> _______________________________________________
> gem5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to