• State Resolved
  • Locked Locked
  • Replies 3 replies
  • Subscribers 97 subscribers
  • Views 247 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.

TDA4VH-Q1: IPC Latency

Lucas
Prodigy 40 points

Part Number: TDA4VH-Q1

Tool/software:

Hi,

We want to optimize IPC latency between C7x cores. We measured around 30 μs for a RPMessage, which is way too much for our application, and 2 μs for a Mailbox message, which is still too much.

Could you provide us with the following information?

  1. Your measurements for RPMessage and Mailbox latency
  2. The path of an interrupt sent by a mailbox to a C7x core (software and hardware)
  3. Your measurements for the time it takes for an interrupt to reach a C7x core

Also, do you have some advice on this subject? Is triggering an interruption from the CLEC an option?

Note: in the IPC section of the SDK RTOS developer’s notes, there is a Latency section: https://software-dl.ti.com/jacinto7/esd/processor-sdk-rtos-j784s4/latest/exports/docs/psdk_rtos/docs/user_guide/developer_notes_ipc.html#latency. It links to https://software-dl.ti.com/jacinto7/esd/processor-sdk-rtos-j784s4/latest/exports/docs/pdk_j784s4_10_01_00_25/docs/datasheet/j784s4/datasheet_j784s4.html#ipc for IPC performance measurements, but there is nothing about IPCs on this page.

Best regards,

Lucas