lkml.org 
[lkml]   [2024]   [Feb]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH v7 15/23] PM: EM: Optimize em_cpu_energy() and remove division
From
On 17/01/2024 09:57, Lukasz Luba wrote:
> The Energy Model (EM) can be modified at runtime which brings new
> possibilities. The em_cpu_energy() is called by the Energy Aware Scheduler
> (EAS) in its hot path. The energy calculation uses power value for
> a given performance state (ps) and the CPU busy time as percentage for that
> given frequency.
>
> It is possible to avoid the division by 'scale_cpu' at runtime, because
> EM is updated whenever new max capacity CPU is set in the system.
>
> Use that feature and do the needed division during the calculation of the
> coefficient 'ps->cost'. That enhanced 'ps->cost' value can be then just
> multiplied simply by utilization:
>
> pd_nrg = ps->cost * \Sum cpu_util
>
> to get the needed energy for whole Performance Domain (PD).
>
> With this optimization and earlier removal of map_util_freq(), the
> em_cpu_energy() should run faster on the Big CPU by 1.43x and on the Little
> CPU by 1.69x (RockPi 4B board).
>
> Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
> ---
> include/linux/energy_model.h | 54 ++++++++++--------------------------
> kernel/power/energy_model.c | 7 ++---
> 2 files changed, 17 insertions(+), 44 deletions(-)
>
> diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
> index 689d71f6b56f..aabfc26fcd31 100644
> --- a/include/linux/energy_model.h
> +++ b/include/linux/energy_model.h
> [...]
> @@ -208,8 +206,9 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table,
> return -EINVAL;
> }
> } else {
> - power_res = table[i].power;
> - cost = div64_u64(fmax * power_res, table[i].frequency);
> + /* increase resolution of 'cost' precision */
> + power_res = table[i].power * 10;

NIT: Does this have to be 10, or something simple like << 3 (* 8) also
does the job?

Although compiler these days often are clever enough to convert x * 10
into (x << 3) + (x << 1), and this is not on the hot path anyway, so
just a NIT.

> + cost = power_res / table[i].performance;
> }
>
> table[i].cost = cost;

Reviewed-by: Hongyan Xia <hongyan.xia2@arm.com>

\
 
 \ /
  Last update: 2024-05-27 14:53    [W:0.047 / U:0.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site