# Customization of DPU to program it using DOCA for FEC and AI programs?

**URL:** <https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162>\
**Category:** Infrastructure Management\
**Created:** [March 6, 2024, 3:37pm UTC](https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162 "2024-03-06T15:37:34Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![aiatlasinc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@aiatlasinc](https://forums.developer.nvidia.com/u/aiatlasinc)\
**Post date:** [March 6, 2024, 3:37pm UTC](https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162/1 "2024-03-06T15:37:34Z")

</div>

Hello  
My question is can we customize DPU using DOCA programming to put our own FEC&AI algorithms there for optical transceivers hasn’t inbuilt FECs ?

We want to use our algorithms developed by us, but we aren’t sure if product like this :[ConnectX7](https://nvidiaproduction.getoutreach.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)  
Has this capabilities, so we asked here.  
Thanks

---

<div class="post-metadata">

**Author:** ![xiaofengl](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/xiaofengl/32/367020_2.png) [@xiaofengl](https://forums.developer.nvidia.com/u/xiaofengl)\
**Post date:** [March 7, 2024, 12:41am UTC](https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162/2 "2024-03-07T00:41:33Z")

</div>

DOCA has no this kind of API.

---

<div class="post-metadata">

**Author:** ![aiatlasinc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@aiatlasinc](https://forums.developer.nvidia.com/u/aiatlasinc)\
**Post date:** [March 7, 2024, 1:19am UTC](https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162/3 "2024-03-07T01:19:33Z")

</div>

Thanks for replying, any kind of network card producing by Nvidia, does have API capabilities in other ways than DOCA?

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [March 21, 2024, 1:20am UTC](https://forums.developer.nvidia.com/t/customization-of-dpu-to-program-it-using-doca-for-fec-and-ai-programs/285162/4 "2024-03-21T01:20:30Z")

</div>

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.