Performance doesn't increase when tops increase

[gowtham2]

Please provide complete information as applicable to your setup.

• Hardware Platform DGPU
• DeepStream Version 6.0.1
• NVIDIA GPU Driver Version 510.85.02
• Issue Type( questions, new requirements, bugs)

performance is not increasing when tops increases

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

my pipeline
streammux->tee->
display_queue->inference->nvvideoconvert->capsfilter->tiler->fakesink
recording_queue->demux->queue->nvvideoconvert->>nv4l2h264enc->h264parse->splitmuxsink

also I added motion detection code in probe function. get frame in probe and using opencv, wrote motion detection code.

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I am running deepstream python code with 4 rtsp streams, one inference(yolov7-tiny) and video storage. video only stores when motion detected. I wrote motion detection code in probe function.

In jetson nano I am able to achieve maximum 4 rtsp streams, but in xavier nx only 8 rtsp stream. jetson nano has 0.5 tops and xavier nx has 20 tops, will get minimum 10x performance in xavier nx compare with nano, but i am not getting it.

could you please explain and resolve this issue?

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

The TOPS of a Jetson device is the overall compute capacities, in your case it seems some component (maybe encoder/decoder/gpu) has reached the limit, you may use jtop or tegrastats to analyze the usage of different components.