SDAA476 July   2026 AM13E23019 , AM13E232N9

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
    1. 1.1 TI AM13E230x Introduction
    2. 1.2 AI Toolchain for TI MCU Introduction
  5. 2Detailed Description
    1. 2.1 Sysconfig Settings for EPI
      1. 2.1.1 Refresh Count
      2. 2.1.2 EPI Clock Divider
    2. 2.2 AI Model Library Deployment for External SRAM Execution
      1. 2.2.1 Step 1: Add the AI “.a” File to the CCS Project
      2. 2.2.2 Step 2: Linker Script Change (`linker_m33_ti_arm_clang.cmd`)
      3. 2.2.3 'main.c' Changes
        1. 2.2.3.1 Include Headers
        2. 2.2.3.2 Declare Linker-Generated Symbols
        3. 2.2.3.3 memcpy Function
        4. 2.2.3.4 Place the Entry Function in the SDRAM Section
        5. 2.2.3.5 main() Boot Sequence
      4. 2.2.4 Step 4: CSS Project Validation
    3. 2.3 H/W Design Best Practices
  6. 3Summary
  7. 4References

AI Toolchain for TI MCU Introduction

TI provides strong toolchain support for EdgeAI for MCUs. Customers with different experience levels can leverage TI Toolchain to build and deploy AI models on MCUs. Right from data acquisition to data labeling to training the AI model and compiling and deployment, the TI toolchain manages the entire process.

The user's guides for different tools are attached to the References section:

  • tinyml-lensorlab release in git hub [1] and edge AI studio GUI release in TI.com official website [2] contains the models and the whole toolchain for AI model compiling validated by TI. Users can directly integrate these models into applications.. In git hub release, users can read the .py file directly to know how the toolchain works. Those models are all developed for speed, and no need for external SRAM, users can directly train and validate the model with TI’s launchpad. The MCU deployment example for those models are included in the individual MCU device SDKs.
  • If users want to do some DIY AI model with the commonly used AI model developer such as PyTorch, TI Neural Network Compiler for MCUs [3] can support compiling the .onnx file into MCU .a library file. In this case, if the MCU on chip NPU must be used as accelerator, the model must be built with the NPU supported operation [4], and the TI-NPU QAT [5] must be applied to .onnx file, to make the model fit into NPU. If the model needs to be executed in CPU core, then the DQD is good enough for quantization. Users must validate the model carefully by themselves. The compiler also outputs the lib.c file for users to debug the input and output of each layer. Those highly customized models with different AI training structures can easily occupy large amounts of memories. One case is AI models using transformer structures, in which case users need external SDRAM for memory extending.

With both approaches, the final generated AI model that needs to be embedded into MCU project is a “.a” file (code and weights library file), and a “.h” header file to provide the interface of the library.