SDAA476 July   2026 AM13E23019

 

  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

Abstract

Texas Instruments supports Edge AI applications with a wide range of tool chains and MCU microcontrollers for a variety of end-equipment. In the world of fast-moving Edge AI, memory must not be the challenge when users try to deploy the relatively “complex” edge AI model in MCU. This application note leverages the AM13x external peripheral interface (EPI), offloading the AI model in external SDRAM, to help users achieve the balance between performance, cost, and power consumption at a system level. The approaches and step-by-step guidance are presented in this application note. The demo project is available in AM13E230x MCU_SDK at "am13e230x_sdk_26_01_00_00/examples/driverlib/epi/epi_sdram_read_write," supported by SDK version 26.01.00, and tested with SDRAM AS4C32M16S [14].