• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 366 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: Two difference ways to use this device for AI model

Josel Go
Expert 7355 points

Part Number: TDA4VM

Hi Experts,
Our customer with the above information(Please see notes) is asking below.

From the quick search I did about the device, I have the following assumption:

On this edge device, an AI model can be executed using two different approaches:
  1. Executed using DSP-C71/MMA running FreeRTOS independently from Cortex (A72) which runs the Linux, but only if my AI model is fully supported by the TIDL accelerator operators (TIDL-Runtime).
  2. Executed using A72 running Linux, with some operations potentially delegated to the DSP-C71/MMA (without FreeRTOS). This approach uses the OSRT.
Are the two approaches valid or am I wrong?
Regards,

Josel