SPRAD74 March   2023 AM62A3 , AM62A3-Q1 , AM62A7 , AM62A7-Q1

 

  1.   Abstract
  2.   Trademarks
  3. 1Smarter Cameras at the Edge
  4. 2AM6xA Scalable Portfolio and the AM62A
  5. 3Smart Camera Use Cases
    1. 3.1 Security Camera Example
  6. 4Deep Learning on the AM62A
    1. 4.1 Deep Learning Accelerator
    2. 4.2 Edge AI Software
  7. 5VPAC Vision Accelerator and ISP
  8. 6Low-Power Performance
  9. 7Call to Action
  10. 8References

6 Low-Power Performance

The AM62A processor is designed to meet the demanding computational requirements of deep learning algorithms while providing high energy efficiency. The device operates at a unique low-core voltage of 0.75 V, which enables the processor to achieve a high level of power efficiency, thus making it suitable for battery-powered and thermal-sensitive applications.

The AM62A can run deep learning processing with a 5 MP 60 fps camera within a power consumption range of 2 W under typical operating conditions, such as room temperature and nominal silicon, which is ideal for battery-powered edge devices that require real-time image recognition and object detection. The device also supports low-power modes, reducing its overall power consumption and extending the battery life in portable applications or relaxing thermal design requirements.

TI provides a power estimation tool to help engineers and designers estimate the power consumption of the AM62A processor in their specific application, taking into account factors such as operating voltage, frequency, junction temperature, and silicon characteristics. This information can be used to optimize power consumption, extend battery life, thermal design and ensure that the device meets the required power budget.