Multi concurrency primary gie to increase fps

[hieuhv]

I have pipeline as below figure:
(src1, src2, …, srcN )—> streammux —> pgie ----> tracker —> sink
It’s ok if i have some 8 cameras, but when i run with 100 or more cameras, i have to use greater batch size as 64 or 128 so inference time of pgie is very slow and FPS is decreased.
So, I have a question. Can i run multi pgie (with batch size 8) concurrently to increase FPS, and how to do that?
Pipeline in my imagination:
(src1, src2,…,srcN) —> streammux —> load_balancer —>( pgie1, pgie2, …pgieN ) —> tracker —> sink

• Hardware Platform (Jetson / GPU) : GTX 2080
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.0.3.1
• NVIDIA GPU Driver Version (valid for GPU only) 470
• Issue Type( questions, new requirements, bugs)
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

[kayccc]

Please provide complete information as applicable to your setup.

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

[hieuhv]

I updated information about my environment

[kesong]

Please check if there any bottle neck in your system, such as GPU/CPU.

Performance — DeepStream 6.0.1 Release documentation (nvidia.com)