SPRACZ2 August   2022 TDA4VM , TDA4VM-Q1

ADVANCE INFORMATION  

  1.   Abstract
  2. 1Introduction
    1. 1.1 Vision Analytics
    2. 1.2 End Equipments
    3. 1.3 Deep learning: State-of-the-art
  3. 2Embedded edge AI system: Design considerations
    1. 2.1 Processors for edge AI: Technology landscape
    2. 2.2 Edge AI with TI: Energy-efficient and Practical AI
      1. 2.2.1 TDA4VM processor architecture
        1. 2.2.1.1 Development platform
    3. 2.3 Software programming
  4. 3Industry standard performance and power benchmarking
    1. 3.1 MLPerf models
    2. 3.2 Performance and efficiency benchmarking
    3. 3.3 Comparison against other SoC Architectures
      1. 3.3.1 Benchmarking against GPU-based architectures
      2. 3.3.2 Benchmarking against FPGA based SoCs
      3. 3.3.3 Summary of competitive benchmarking
  5. 4Conclusion
  6.   Revision History
  7. 5References

4 Conclusion

AI inferencing technology is a key enabler for broader deployment of edge AI devices across from home to factories with the potential to impact every aspect of our lives. Performance and power benchmarking different edge AI SoC processors is a complex task and having an apples-to-apples comparison is critical for developers to pick up the right device for applications that are cost, size, and power sensitive. In this application note, we discussed industry standard performance and power benchmarking used to compare the TDA4x architecture with GPU-based and FPGA-based architectures.

TI Edge AI tools are bringing state-of-the-art process and technology leadership with the TDA4VM SoC devices. Developers can now achieve more than60% better energy efficiency compared to GPU based devices resulting in greener edge devices. Edge AI devices can also include greater levels of sophistication with more than six times higher performance compared to FPGA based solutions.

TDA4x processor family also comes with easy to use, no-cost to low-cost development platforms making it easier for developers to innovate with AI without any prior experience. Developers can also take advantage of an extensive collection of embedded AI projects from TI and also from our third-party ecosystem for faster time to market [20].