Xavier NX GPU Code Latency

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX
1

Hi,

I have a GPU code of mine working on the MX450 GPU (laptop) at maximum 20 milliseconds. For 100 features, it gives 15 milliseconds.

When I compile and run the same code for Jetson Xavier NX, I get about 25 milliseconds latency at maximum but most of the cases the code runs about 5-6 milliseconds even if the feature count is large (about 20 features). Sometimes, with the same feature count, it can give about 25 milliseconds latency (for 20 features) .

On Jetson side, the code takes the real time camera images and runs the algorithm parallel on GPU.

Is the variation of the latency normal?
Any suggestions?

Thanks.

Best regards,
Mert

2

What kidnd of GPU code? Based on CUDA or ?

Did you boost the system by nvpmodel and jetson_clocks?
sudo nvpmodel -m 0
sudo jeston_clocks

4

Hi,
Pease try kayccc’ ssuggestion and you can also execute sudo tegrastats to get loading of GPU.

5

The code is based on cuda, yes.

I tried with sudo nvpmodel -m2 and sudo jetson_clocks --fan.

6

Hi kayccc,

I tried your suggestion, it worked better. Thanks.

8

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