tuned-amdgpu/roles/tuned_amdgpu/templates/amdgpu-profile.sh.j2

130 lines
5.6 KiB
Django/Jinja

#!/bin/bash
{{ ansible_managed | comment }}
# This is the script for 'amdgpu' profiles, (re)setting clock/power/voltage tunables
#
# AMDGPU driver/sysfs references:
# https://01.org/linuxgraphics/gfx-docs/drm/gpu/amdgpu.html
# https://docs.kernel.org/gpu/amdgpu/thermal.html
#
# Variables shown below named '$TUNED_...' are given values by '/etc/tuned/amdgpu-profile-vars.conf'
#
# determine the connected GPU using the DRM subsystem. FIXME: assumes one card, make configurable
CARD=$(/usr/bin/grep -ls ^connected /sys/class/drm/*/status | /usr/bin/grep -o 'card[0-9]' | /usr/bin/sort | /usr/bin/uniq | /usr/bin/sort -h | /usr/bin/tail -1)
function get_hwmon_dir() {
CARD_DIR="/sys/class/drm/${1}/device/"
for CANDIDATE in "${CARD_DIR}"/hwmon/hwmon*; do
if [[ -f "${CANDIDATE}"/power1_cap ]]; then
# found a valid hwmon dir
echo "${CANDIDATE}"
fi
done
}
# determine the hwmon directory
HWMON_DIR=$(get_hwmon_dir "${CARD}")
# read all of the power profiles, used to get the IDs for assignment later
PROFILE_MODES=$(< /sys/class/drm/"${CARD}"/device/pp_power_profile_mode)
# get power capability; later used determine limits
read -r -d '' POWER_CAP < "$HWMON_DIR"/power1_cap_max
function amdgpu_profile_reset() {
# set control mode back to auto
# attempts to dynamically set optimal power profile for (load) conditions
echo 'auto' | tee /sys/class/drm/"${CARD}"/device/power_dpm_force_performance_level
# reset any existing profile clock changes
echo 'r' | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
# adjust power limit using multiplier against board capability
POWER_LIM_DEFAULT=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_tuned_amdgpu_power_multi_def}" 'BEGIN {printf "%.0f", (m*n)}')
echo "$POWER_LIM_DEFAULT" | tee "${HWMON_DIR}/power1_cap"
# extract the power-saving profile ID number
PROF_DEFAULT_NUM=$(/usr/bin/awk '$0 ~ /BOOTUP_DEFAULT.*:/ {print $1}' <<< "$PROFILE_MODES")
# reset power/clock heuristics to power-saving
echo "${PROF_DEFAULT_NUM}" | tee /sys/class/drm/"${CARD}"/device/pp_power_profile_mode
# delay before returning - have mercy, may be followed with other profile function calls
sleep 0.5
}
function amdgpu_profile_overclock() {
echo "s 0 ${TUNED_tuned_amdgpu_clock_min}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
echo "s 1 ${TUNED_tuned_amdgpu_clock_max}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
echo "m 1 ${TUNED_tuned_amdgpu_memclock_static}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
# under/over-voltage is considered optional or less likely to be defined, checked before use
if [[ -n ${TUNED_tuned_amdgpu_mv_offset} ]]; then
echo "vo ${TUNED_tuned_amdgpu_mv_offset}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
fi
# commit the changes
echo 'c' | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
# force GPU core and memory into highest clocks (fix flickering and poor power management)
# set manual control mode
# allows control via 'pp_dpm_mclk', 'pp_dpm_sclk', 'pp_dpm_pcie', 'pp_dpm_fclk', and 'pp_power_profile_mode' files
echo 'manual' | tee /sys/class/drm/"${CARD}"/device/power_dpm_force_performance_level
# adjust power limit using multiplier against board capability
POWER_LIM_OC=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_tuned_amdgpu_power_multi_oc}" 'BEGIN {printf "%.0f", (m*n)}')
echo "$POWER_LIM_OC" | tee "${HWMON_DIR}/power1_cap"
# avoid display flickering, force OC'd memory to highest clock
echo '3' | tee /sys/class/drm/"${CARD}"/device/pp_dpm_mclk
# extract the VR power profile ID number
PROF_VR_NUM=$(/usr/bin/awk '$0 ~ /VR.*:/ {print $1}' <<< "$PROFILE_MODES")
# force 'overclocked' profile to 'VR' power/clock heuristics
# latency/frame timing seemed favorable with relatively-close minimum clocks
echo "${PROF_VR_NUM}" | tee /sys/class/drm/"${CARD}"/device/pp_power_profile_mode
# delay before returning - have mercy, may be followed with other profile function calls
sleep 0.5
}
function amdgpu_profile_help() {
echo "Usage: $0 {reset|overclock|peak}"
exit 1
}
# Check if an argument was provided
if [ -z "$1" ]; then
amdgpu_profile_help
fi
# 'tuned' has trouble running scripts with args - treats '/path/to/script.sh arg1' as one complete item
# so, based on the active profile - run the right function
read -r -d '' TUNED_PROFILE < /etc/tuned/active_profile
case "$TUNED_PROFILE" in
*-amdgpu-default)
amdgpu_profile_reset
;;
*-amdgpu-overclock)
amdgpu_profile_reset
amdgpu_profile_overclock
;;
*-amdgpu-peak)
# do everything the other profiles do... then set each clock table to their peak
amdgpu_profile_reset
amdgpu_profile_overclock
echo '1' | tee /sys/class/drm/"${CARD}"/device/pp_dpm_sclk
echo '3' | tee /sys/class/drm/"${CARD}"/device/pp_dpm_mclk
echo '2' | tee /sys/class/drm/"${CARD}"/device/pp_dpm_fclk
echo '2' | tee /sys/class/drm/"${CARD}"/device/pp_dpm_socclk
# if I understand correctly, 'power_dpm_force_performance_level' at 'profile_peak' achieves similar... but precludes some control
;;
*)
amdgpu_profile_help
;;
esac