I have installed most of the nvidia l4t tools in a docker container (see Installing nvidia-l4t-core package in a docker layer).
I can see the nvpmodel tool exists but there is no default configuration file present.
Any ideas what I might be missing?
NOTE: I have NOT used Jetpack to flash the board in this situtation (I have a custom image).
hello jonathan.kehler,
please refer to Supported Modes and Power Efficiency session,
you may define a custom power mode since you’re using your customization image,
thanks
I created the following in /etc/nvpmodel.conf
< POWER_MODEL ID=3 NAME=MODE_30W >
CPU_ONLINE CORE_0 1
CPU_ONLINE CORE_1 1
CPU_ONLINE CORE_2 1
CPU_ONLINE CORE_3 1
CPU_ONLINE CORE_4 1
CPU_ONLINE CORE_5 1
CPU_ONLINE CORE_6 1
CPU_ONLINE CORE_7 1
CPU_DENVER_0 MIN_FREQ 1200000
CPU_DENVER_0 MAX_FREQ 1200000
CPU_DENVER_1 MIN_FREQ 1200000
CPU_DENVER_1 MAX_FREQ 1200000
CPU_DENVER_2 MIN_FREQ 1200000
CPU_DENVER_2 MAX_FREQ 1200000
CPU_DENVER_3 MIN_FREQ 1200000
CPU_DENVER_3 MAX_FREQ 1200000
CPU_DENVER_4 MIN_FREQ 1200000
CPU_DENVER_4 MAX_FREQ 1200000
CPU_DENVER_5 MIN_FREQ 1200000
CPU_DENVER_5 MAX_FREQ 1200000
CPU_DENVER_6 MIN_FREQ 1200000
CPU_DENVER_6 MAX_FREQ 1200000
CPU_DENVER_7 MIN_FREQ 1200000
CPU_DENVER_7 MAX_FREQ 1200000
GPU MIN_FREQ 0
GPU MAX_FREQ 900000000
EMC MAX_FREQ 1600000000
DLA_CORE MAX_FREQ 1050000000
DLA_FALCON MAX_FREQ 450000000
PVA_VPS MAX_FREQ 760000000
PVA_CORE MAX_FREQ 385000000
But I get:
# sudo /usr/sbin/nvpmodel -m 3
NVPM ERROR: undefined PARAM CPU_ONLINE
NVPM ERROR: failed to add param CPU_ONLINE: arg CORE_0 for POWER_MODEL 3
NVPM ERROR: Failed to parse /etc/nvpmodel.conf
(Also wasn’t sure what to set DLA_FALCON and PVA_CORE to)
hello jonathan.kehler,
please refer to NVIDIA Tools TBZ2, had you include this archive into your customize image?
I guess my syntax was insufficient (despite copying from Tegra Linux Driver.
Using the existing nvpmodel_t194.conf worked well.
nvpmodel -m 3 -d cool -f /etc/nvpmodel/nvpmodel_t194.conf
Thanks!