Hi,

peak power refers to the peak dynamic + total leakage. Peak dynamic is
kinda like a TDP value, meaning that it is what a fully active circuit
would give you (let's call the scenario a power virus, not an actual
working code). When you execute a specific code on your simulator and use
the different statistics, McPAT computes the runtime dynamic power, which
is dependent on the actual code enabling or using different parts of the
circuit. Total leakage is the subthreshold leakage and gate leakage. These
are not actually dependent on the code you are executing but rather on your
device being powered on (that is why it is called static power). In the
end, the power consumed for a specific program is the dynamic power + total
leakage.

Best,
Andreas

On Sun, Aug 16, 2020 at 11:23 PM FARIDEH ZIAEE via gem5-users <
gem5-users@gem5.org> wrote:

> Hi,
>
>   According to the mcpat paper, it  calculates power with this Equation:
>
> total power= dynamic power + short-circuit power + leakage power
>
> when I ran mcpat , I couldn't understand which of paramets  are dynamic ,
> short-circuit and static(leakage) power in output-imcpat  .
>  Could someone guide me which parameters are static and short-circuit  and
> dynamic power ?
>
> Best Regards.
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
> *McPAT (version 1.3 of Feb, 2015) results  (current print level is
> 5)*****************************************************************************************
> Technology 65 nm  Interconnect metal projection= aggressive interconnect
> technology projection  Core clock Rate(MHz)
> 2000*****************************************************************************************Processor:
>   Area = 391.232 mm^2  Peak Power = 778.824 W  Total Leakage = 179.53 W
> Peak Dynamic = 599.294 W  Subthreshold Leakage = 163.458 W  Subthreshold
> Leakage with power gating = 66.6128 W  Gate Leakage = 16.0724 W  Runtime
> Dynamic = 547.762 W*
>
> _______________________________________________
> gem5-users mailing list -- gem5-users@gem5.org
> To unsubscribe send an email to gem5-users-le...@gem5.org
> %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
_______________________________________________
gem5-users mailing list -- gem5-users@gem5.org
To unsubscribe send an email to gem5-users-le...@gem5.org
%(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s

Reply via email to