SPRY344A January   2022  – March 2023 AM67 , AM67A , AM68 , AM68A , AM69 , AM69A , TDA4AEN-Q1 , TDA4AH-Q1 , TDA4AL-Q1 , TDA4AP-Q1 , TDA4APE-Q1 , TDA4VE-Q1 , TDA4VEN-Q1 , TDA4VH-Q1 , TDA4VL-Q1 , TDA4VM , TDA4VM-Q1 , TDA4VP-Q1 , TDA4VPE-Q1

 

  1.   At a glance
  2.   Authors
  3.   Introduction
  4.   Defining AI at the edge
  5.   What is an efficient edge AI system?
    1.     Selecting an SoC architecture
    2.     Programmable core types and accelerators
  6.   Designing edge AI systems with TI vision processors
    1.     Deep learning accelerator
    2.     Imaging and computer vision hardware accelerators
    3.     Smart internal bus and memory architecture
    4.     Optimized system BOM
    5.     Easy-to-use software development environment
  7.   Conclusion

Optimized system BOM

Let’s review the advanced integrated system components and features in TI vision SoCs that can reduce system BOM cost savings for several types of edge AI applications:

  • ISP. The integrated ISP core eliminates the need for an external ISP or FPGA design. All single and multicamera AI applications such as machine vision, smart shopping carts, robotics and ADASs can benefit from this integration.
  • Safety. The integrated Automotive Safety Integrity Level (ASIL) D and SIL 3-compliant safety microcontroller (MCU), with Cortex-R5 cores, helps achieve safety goals without an external safety MCU. With the rest of the processing also ASIL B/SIL 2-compliant, such an architecture enables ADAS, robotics, construction and agriculture electronic control unit applications.
  • Ethernet and PCIe switches. Integrated Ethernet and PCIe switches eliminate the need for external switch components.
  • Security. Integrated security accelerators offer state-of-the-art security support.
  • DDR memory. Inline error-correcting code protection and fewer DDR memory instances (through smart memory) compared to typical memory architectures can result in cost savings.