Messages in this thread | | | Date | Mon, 3 Jul 2023 16:30:13 +0100 | Subject | Re: [PATCH v2 12/17] PM: EM: Add argument to get_cost() for runtime modification | From | Lukasz Luba <> |
| |
On 5/30/23 10:53, Dietmar Eggemann wrote: > On 12/05/2023 11:57, Lukasz Luba wrote: >> The Energy Model (EM) supports runtime modifications. Let also the >> artificial EM use this new feature and allow to update the 'cost' values >> at runtime. When the artificial EM is used there is a need to provide >> two callbacks: get_cost() and update_power(), not only the last one. >> >> Update also CPPC driver code, since the new argument is needed there >> to compile properly and register EM. > > Is there a real use case behind this? It can't be mobile which IMHO > drivers the rest of the 'Runtime modifiable EM' feature.
Correct, CPPC+EM is not for mobile phones, but notebooks. For now the notebooks are not tested with that feature and were not in requirement scope.
> > Do we know of any machine using the artificial EM. And do they care > about EM matching workload or static power? > > [...]
For now we don't know about such notebook which uses CPPC + EM and if it's a candidate for this feature.
I thought, since it's just one patch w/ small change, it would be consistent to not 'forget' about that notebooks angle. I know that there are some folks who 'run'/'are willing to run' Arm laptop with CPPC w/ artificial EM. They might pick that feature as well.
| |