I want to know about 3 contents.
Is there a most efficient clock mode such as MAX-Q at TX2?
#of course I understand there are 7 mode by setting nvpmodel
VDD_CV includes DLA power and PVA power?
If so, when calculating power consumption at deep learning by GPU and DLA,
I should measure VDD_GPU+VDD_CPU+VDD_CV?
I measured power consumption at VGG16, VDD_CPU is higher than GPU.
What is the reason for this?
clock mode : MAXN
weights : FP32
GPU : yes
Framework : tensorRT
VDD_GPU(MAX) : 2162 mW
VDD_CPU(MAX) : 4474 mW
VDD_SoC(MAX) : 3860 mW
VDD_CV(MAX) : 0
VDD_VDDQ(MAX) : 926 mW
VDD_SYS5V(MAX) : 3577
#Both peak and avg CPU is higher than GPU