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

Abstract

AI is revolutionizing our lifestyles with constant innovation in deep learning and machine learning driving new use cases across home, retail, and factories. AI at the edge is instrumental for continued success of AI delivering low latency, privacy, and better user experience. The key AI function that happens in an embedded edge device is inference. This is where Texas Instruments (TI) is innovating with TDA4x processor family specially designed to make greener, smarter, and safer edgeAI devices possible.

With industry-leading vision and AI accelerators, TDA4x processors achieve more than 60% higher deep learning performance and energy efficiency compared to leading GPU based architectures. With process and technology leadership, developers can achieve more than six times better deep learning performance compared to leading FPGA based architectures that exist today.

This application note uses the industry standard performance and power benchmarking used to compare the TDA4x system-on-chip (SoC) with other architectures. 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 even without any prior experience.