SPRY344 January   2022 TDA4VM , TDA4VM-Q1

 

  1. 1At a glance
  2. 2Introduction
  3. 3Defining AI at the edge
  4. 4What is an efficient edge AI system?
    1. 4.1 Selecting an SoC architecture
    2. 4.2 Programmable core types and accelerators
  5. 5Designing edge AI systems with the Jacinto 7 TDA4 SoC
    1. 5.1 Deep learning accelerator
    2. 5.2 Imaging and computer vision hardware accelerators
    3. 5.3 Smart internal bus and memory architecture
    4. 5.4 Optimized system BOM
    5. 5.5 Easy-to-use software development environment
  6. 6Conclusion
  7. 7Important Notice
The expansion of automation is increasing from the factory floor to the front door.

At a glance

At a glance This white paper explains the requirements for building an efficient edge artificial intelligence (AI) system and how the TI TDA4 processor family can help optimize performance due to a heterogenous architecture.

    Section 3 Defining artificial intelligence at the edge. Many different kinds of systems can benefit from edge AI processing.
    Section 4 What is a practical edge AI system? Consider which architecture and cores will best complete the tasks required of a system.
    Section 5 Designing edge AI systems with the Jacinto™ 7 TDA4 system on chip. The TDA4 processor family, is designed to achieve high-throughput, high-performance computing at low power and with lower system BOM costs.