Re: [Gems-users] L1 cache latency

["Abhishek Ranjan" <absk82@xxxxxxxxx>]

Is the process similar for changing size, asociativity etc, L2 latency, size etc?

If I use opal without ruby, then are these parameters configurable through the config file?

 

On 5/29/06, Mike Marty <mikem@xxxxxxxxxxx> wrote:

The L1_RESPONSE_LATENCY, like most of the specified latencies, are specific to an individual protocol.  Adjusting the L1 hit latency is unfortunately not at all straightforward.  By default, he L1 hit latency is always 1 cycle.  This can be changed by turning off "fast path hits", controlled by the REMOVE_SINGLE_CYCLE_DCACHE_FAST_PATH flag.  A fast path hit is where the Ruby sequencer (ruby/sequencer.C) directly checks the permissions in the L1 caches before actually issuing a request to Ruby.  If you turn this off, the L1 hit latency can be controlled by the SEQUENCER_TO_CONTROLLER_LATENCY parameter.

 

Sorry this is confusing...hopefully we can clean this up in the future.   

 

--Mike

 

-----Original Message-----
From: gems-users-bounces@xxxxxxxxxxx [mailto:gems-users-bounces@xxxxxxxxxxx] On Behalf Of Abhishek Ranjan
Sent: Monday, May 29, 2006 4:53 PM
To: Gems Users
Subject: [Gems-users] L1 cache latency

Hi,

I am simulating a simple program on ruby with simics. If I vary the L1_RESPONSE_LATENCY from 3 cycles to 20 cycles, I was hoping that the Rubycycles will increase a lot but they remain constant and I am not sure why this is so. Can anyone help me in that?

thanks,

Abhishek

_______________________________________________
Gems-users mailing list
Gems-users@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/gems-users