diff options
author | Lukasz Luba <lukasz.luba@arm.com> | 2024-02-08 14:55:49 +0300 |
---|---|---|
committer | Rafael J. Wysocki <rafael.j.wysocki@intel.com> | 2024-02-08 17:00:31 +0300 |
commit | 1b600da510735a0f92c8b4140a7e2cb037a6a6c3 (patch) | |
tree | ea67df6e89321d69a5ae51acbbc6cc183dc15562 /kernel/power/energy_model.c | |
parent | e3f1164fc9ee8430b3a51e400abfa1b67664f538 (diff) | |
download | linux-1b600da510735a0f92c8b4140a7e2cb037a6a6c3.tar.xz |
PM: EM: Optimize em_cpu_energy() and remove division
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).
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'kernel/power/energy_model.c')
-rw-r--r-- | kernel/power/energy_model.c | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index b192b0ac8c6e..a631d7d52c40 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -192,11 +192,9 @@ static int em_compute_costs(struct device *dev, struct em_perf_state *table, unsigned long flags) { unsigned long prev_cost = ULONG_MAX; - u64 fmax; int i, ret; /* Compute the cost of each performance state. */ - fmax = (u64) table[nr_states - 1].frequency; for (i = nr_states - 1; i >= 0; i--) { unsigned long power_res, cost; @@ -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; + cost = power_res / table[i].performance; } table[i].cost = cost; |