# How to use the PVA DLA and the other co-processor

**URL:** <https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619>\
**Category:** Jetson Xavier NX\
**Tags:** camera, cuda\
**Created:** [December 1, 2023, 1:07am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619 "2023-12-01T01:07:37Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![legendflying](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@legendflying](https://forums.developer.nvidia.com/u/legendflying)\
**Post date:** [December 1, 2023, 1:07am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619/1 "2023-12-01T01:07:37Z")

</div>

hello, i do power performance test, using the yolov8 model(the video is a USB UVC camera), now the model can run and i can get the results. But the GPU take the main heavy task, and the DLA PVA are off, they are not working.  
my env:  
 ![image](https://global.discourse-cdn.com/nvidia/original/4X/f/2/6/f265079f2b67989c2fb1efe46b0c58a72630a4fc.png)  
the GPU loading chart:

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/d/2/6/d26100aba2dc7ae4a15c14e9e57c23e48e9ce256.png)  
the jetson stats:  
 ![image](https://global.discourse-cdn.com/nvidia/original/4X/4/9/4/4940edf30c26e9541eaadbd1bae89a504f244a9c.png)  
the DLA and PVA is OFF  
 ![image](https://global.discourse-cdn.com/nvidia/original/4X/f/d/8/fd8903e4ef1156771431e5d406034735a9a1f43e.png)

my Devkit is Xavier NX, but I do the same test in AGX xavier devkit，the result is the same.

my question is how to use the DLAx PVAx to accelerate the performance? and let the DLA/PVA do more, offload the GPU task?  
now we use one usb camera, if we use more cameras, the GPU’s ability is not enough.  
thanks

---

<div class="post-metadata">

**Author:** ![legendflying](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@legendflying](https://forums.developer.nvidia.com/u/legendflying)\
**Post date:** [December 1, 2023, 1:13am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619/2 "2023-12-01T01:13:48Z")

</div>

Among the computing power provided by NVIDIA, DLA PVA provides the majority of the computing power.  
take the spec of orin nx as example:

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/5/5/9/5595d404e1d5287e51759754c4ee9e17347dd525.png)

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [December 1, 2023, 3:09am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619/4 "2023-12-01T03:09:41Z")

</div>

Hi,

PVA is designed for vision tasks and you can deploy jobs on it with VPI:  
[https://docs.nvidia.com/vpi/architecture.html#autotoc\_md11](https://docs.nvidia.com/vpi/architecture.html#autotoc_md11)

DLA can be used via TensorRT. For more information, please check below doc:

> **[Developer Guide :: NVIDIA Deep Learning TensorRT Documentation](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla_topic)**
>
> This is the revision history of the NVIDIA TensorRT 8.6 Developer Guide.

Thanks.

---

<div class="post-metadata">

**Author:** ![legendflying](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@legendflying](https://forums.developer.nvidia.com/u/legendflying)\
**Post date:** [December 1, 2023, 5:22am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619/5 "2023-12-01T05:22:44Z")

</div>

copy that and thanks  
use the correct parameter to enable the DLA function.  
./trtexec --onnx=data/resnet50/ResNet50.onnx --useDLACore=0 --fp16 --allowGPUFallback  
about PVA, we will go on learning it and the VPI.

---

<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:** [December 15, 2023, 5:22am UTC](https://forums.developer.nvidia.com/t/how-to-use-the-pva-dla-and-the-other-co-processor/274619/6 "2023-12-15T05:22:55Z")

</div>

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