[Libre-soc-sim] NLnet grant request, draft

[lkcl]

On August 9, 2021 5:16:33 PM UTC, Peter Hsu <peter.hsu at bsc.es> wrote:

>I’ve used resource counting for many years to estimate chip power in my
>designs.  I found that while not very accurate for short runs, it is
>quite good for trillions of instruction versus extrapolating from
>detailed power simulation of small benchmarks.

fascinating.

now of course that has me wondering if there is a close statistical correlation between that and hardware-level stat counters (i temporarily forget the industry-standard name for them)

l.