Deepstream VRAM Scaling?

[dan.mccormack]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) 1 X RX8000
• DeepStream Version v5.0.1
• JetPack Version (valid for Jetson only) N/A
• TensorRT Version N/A
• NVIDIA GPU Driver Version (valid for GPU only) 470.57.02
• Issue Type( questions, new requirements, bugs) Question
• 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) N/A
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description) N/A

I’m processing multiple RTSP streams at edge at 1080@15fps. I’m trying to compute scaling requirements for adding additional streams, and wanted to understand GStreamer’s impact on VRAM. Right now I’m seeing 12GB / 48 GB of FB VRAM in use for 60 streams. My question is can I roughly assume 12 GB / 60 streams requires .2 GB VRAM per stream to process?

My pipeline is currently uridecode (nvdec) → nvmstreamux → nvvideoconvert → capsfilter → nvmultistreamtiler.

From what I understand all but the capsfilter would be leveraging the VRAM.

[yuweiw]

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

Hi @dan.mccormack , You can roughly calculate how much storage you need with the video raw data. Like 1080P 8bit RGB video, the number is (1920x1080x8x3) bit.