Is it possible/performant to run TI-RTOS on the CortexM4 and have the necessary computing power for an Ethercat Slave at 1khz with DC, while using RT-Linux on the A15 cores, doing IPC between them?
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.
So I've been looking a bit into this. The interconnect make it so that the M4 can access the PRU. If I install Linux RTOS on the A15, then I can launch a firmware ecat slave built for M4 on the IPU, then we can IPC stuff from the IPU to the A15.
Any idea of the latencies involved? Latency between M4 and PRU, I would guess it is 100us for the ecat slave stack and latency of IPC between M4 and A15, I am not sure.
Hi,
We want the feature rich environment of linuxrt to do vision with opencl. And we want hard realtime with rtos ti. So the idea is to use the slave on rtos without having to code the driver in linux, and also to keep it realtime.
Thus, the m4 looks like a nice alternative, the porting job looks easier.
Also, I am familiar with the ethercat slave, we have one that runs on the AM3359 (another product) and it's perfect, so this is not new to me. What is new, is the am5728 and linux. Unless you tell me you have a ecat slave driver that communicates directly with the PRU in realtime with DC on linux, I'm all in!