Thanks for the reply.
I was also trying to ungroup power dissipation in various components i.e.
buffers, arbiters and crossbar as well. I declared different functions in
the NetwrokPower.C , which did the same stuff as they were doing in the main
but now only calculating the individual powers.
But the results came out to be strange:
Router power : now in KW (earlier in 1-2 W)
Buffer power : in KW
Arbiter : ~0.01W (normal)
Crossbar : 2W
What can be the possible reason , why even the Router power shoots up even
though I didn't make any change in the calculate_offline _power function.
Regards
Muhammad Shoaib
--------------------------------------------------
From: <niketa@xxxxxxxxxxxxx>
Sent: Tuesday, April 28, 2009 3:15 PM
To: "Gems Users" <gems-users@xxxxxxxxxxx>
Subject: Re: [Gems-users] Static & dynamic power distribution
If you take a look at Router_d:calculate_offline_power function,
everything that is being calculated using the activity numbers is dynamic
power. Leakage power is also labeled in the function. The dynamic power
would be total power - leakage power.
Cheers,
Niket
----- Original Message -----
From: Shoaib Altaf <shoaibbinalt@xxxxxxxx>
Date: Tuesday, April 28, 2009 1:37 pm
Subject: [Gems-users] Static & dynamic power distribution
To: Gems <gems-users@xxxxxxxxxxx>
Hi All,
I am trying to figure out the dissipated power in terms of static &
dynamic power. Now I believe the function calculate_offline_power()
in NetworkPower.C gives the total power( static & dynamic).
The leakage power defined in the same function is the static power
I think so is the rest the dynamic power?. If not then how to
calculate the dynamic power???
Regards
Muhammad Shoaib
_______________________________________________
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.
|