# PYNQ on Ultra96v2 running on Cortex R5

**URL:** <https://discuss.pynq.io/t/pynq-on-ultra96v2-running-on-cortex-r5/5151>\
**Category:** Support\
**Created:** [January 27, 2023, 7:12am UTC](https://discuss.pynq.io/t/pynq-on-ultra96v2-running-on-cortex-r5/5151 "2023-01-27T07:12:22Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![julianop99](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/julianop99/32/4201_2.png) [@julianop99](https://discuss.pynq.io/u/julianop99)\
**Post date:** [January 27, 2023, 7:12am UTC](https://discuss.pynq.io/t/pynq-on-ultra96v2-running-on-cortex-r5/5151/1 "2023-01-27T07:12:23Z")

</div>

Hi,  
I’m using Ultra96v2 with PYNQ 3.0  
I want to run the same python models on both Cortex A53 and R5 processors.  
Does anyone have knowledge/experience how do I run from the R5 in the first place?  
I have not seen anything related in the forum.  
Thanks!

---

<div class="post-metadata">

**Author:** ![pynqzen](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/pynqzen/32/97_2.png) [@pynqzen](https://discuss.pynq.io/u/pynqzen)\
**Post date:** [January 28, 2023, 2:42am UTC](https://discuss.pynq.io/t/pynq-on-ultra96v2-running-on-cortex-r5/5151/2 "2023-01-28T02:42:22Z")

</div>

Hi,

You could maybe start with MicroPython and the FreeRTOS port for R5. You would then have to figure out too how you want to do inter process communications between the APUs and the R5s. All of this will be a lot of work. Also, MicroPython is not full Python. Whether you can run the “same python models” is going to depend on what you are doing.

> **[FreeRTOS - ARM Cortex-R5 demo on Xilinx UltraScale+ MPSoC](https://www.freertos.org/RTOS-ARM-Cortex-R5-Xilinx-UltraScale_MPSoC.html)**
>
> Running FreeRTOS on a Xilinx UltraScale MPSoC ARM Cortex-R5 RPU (real-time processing unit)

> **[MicroPython - Python for microcontrollers](https://micropython.org/)**
>
> MicroPython is a lean and efficient
> implementation of the Python 3 programming language
> that includes a small subset of the Python standard library and is
> optimised to run on microcontrollers and in constrained environments.

That’s the best advice I can give on this at this time. Maybe someone else can offer some alternatives?

---

<div class="post-metadata">

**Author:** ![julianop99](https://sea1.discourse-cdn.com/flex019/user_avatar/discuss.pynq.io/julianop99/32/4201_2.png) [@julianop99](https://discuss.pynq.io/u/julianop99)\
**Post date:** [January 28, 2023, 8:57am UTC](https://discuss.pynq.io/t/pynq-on-ultra96v2-running-on-cortex-r5/5151/3 "2023-01-28T08:57:36Z")

</div>

Thanks for sharing the alternatives with me @pynqzen. I should have been more clear: I want to run the sameML models on both processors, one at a time for comparison sake - especially that R5 is safety related and my applications are intended for safety critical operations.  
Thanks!