STM32H7 DMA Speed

[AlexSmart]

How fast is DMA on STM32H7 mcus? I didnt find any description on how many ticks takes one transaction.

I linked DMA to a timer, transfer from memory to port. With system clock 480 MHz and timer DMA request frequency 40 MHz it doesnt seem to work fast enough. 20 MHz DMA requests works fine...

Memory buffer located in SRAM1, DMA1 is used, D-cache disabled.

[TDK]

It depends on many things including where the data is going and how busy the rest of the system is with the relevant buses. Generally, in the tens of MBps, which is consistent with your observations.

Access to GPIO pin registers is generally slower than other things as they're in the D3 domain.

[AlexSmart]

I see. So if want to reduce latency I need to put My memory buffer in SRAM4, and use BDMA instead of DMA1?

[TDK]

As far as I understand, yes, that should help considerably. Please report results if you check.

[Tesla DeLorean]

Quick hack on the H723 with a simple Mem-to-Mem transfer from SRAM4 to GPIOB->BSRR, looked to be 10 MHz (5 MHz square wave from pattern buffer)

[waclawek.jan]

Generally, AN2548 applies to BDMA and AN4031 to DMA.

The devil is of course in the details, of which in the 'H7 are just too many.

JW

[AlexSmart]

AN4031 is pretty good document for STM32F mcus, pitty there is no such document on H7.

BTW, it seems like STM32F4 would be faster for my case than H7 :>

[Pavel A.]

>  it seems like STM32F4 would be faster for my case than H7

Or not. If your H7's are already in stock and F4 would take a year to arrive...

[waclawek.jan]

> AN4031 is pretty good document for STM32F mcus, pitty there is no such document on H7.

AN4031 does apply to DMA1 and DMA2 in H7, except that the overcomplicated bus/matrices structure has to be taken into consideration when talking about timing.

> BTW, it seems like STM32F4 would be faster for my case than H7

It might quite well be the case.

JW

[AlexSmart]

Thanks everyone, Ill keep trying and see what will work good enough for me