SPRADC9 july   2023 AM62A3 , AM62A7

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
    1. 1.1 Defect Detection Demo Summary
    2. 1.2 AM62A Processor
    3. 1.3 Defect Detection Systems
    4. 1.4 Conventional Machine Vision vs Deep Learning
  5. 2Data Set Preparation
    1. 2.1 Test Samples
    2. 2.2 Data Collection
    3. 2.3 Data Annotation
    4. 2.4 Data Augmentation
  6. 3Model Selection and Training
    1. 3.1 Model Selection
    2. 3.2 Model Training and Compilation
  7. 4Application Development
    1. 4.1 System Flow
    2. 4.2 Object Tracker
    3. 4.3 Dashboard and Bounding Boxes Drawing
    4. 4.4 Physical Demo Setup
  8. 5Performance Analysis
    1. 5.1 System Accuracy
    2. 5.2 Frame Rate
    3. 5.3 Cores Utilization
    4. 5.4 Power Consumption
  9. 6Summary
  10. 7References

5.4 Power Consumption

The power consumption of the AM62A SoC while running the defect detection demo can be estimated using the Power Estimation Tool (PET). This tool is built based on measured and simulated data. Most of the measured data are collected from bare-metal tests with no operating system. The tool estimates power based on clock frequency and utilization of the various components of the AM62A in addition to other factors such as the expected temperature. The cores utilization data presented in the previous section is used to estimate the power consumption of the entire system.

Table 5-2 lists the estimated power for the AM62A running defect detection demo with a summary of the important core utilization used for the power estimation. The PET estimates a total of 1.43 W consumed by the AM62A based on the core utilization for the defect detection application.

Table 5-2 Cores Loading Utilization and Power Estimation of AM62A While Running the Defect Detection Application
Main IP Core Loading Utilization/Power
ARM A-53 39 [%] at 1.25 [GHz]
Deep Learning C7x/MMA 22 [%] at 850 [MHz]
DDR BW 22 [%]
VPAC (ISP) 20 [%]
Power Consumption Est using PET at 85°C
Core Voltage at 0.75 V		 1435 [mW]