Increase GPU utilization for more FPS and streams

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

For the reference application, how can I increase the gpu utilization and streams?, I see the performance reported by Nvidia on T4 is around 35 streams and ~35% of gpu utilization, but what is the bottleneck preventing to have a maximum gpu utilization and therefore improving throughput performance?

https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream%2520Development%2520Guide%2Fdeepstream_performance.html%23wwpID0E0BB0HA

**• NVIDIA T4
**• DeepStream Version:5.0

Thanks,

3

The performance data such as GPU utilization will change with different pipelines, models and configurations. The performance data in https://docs.nvidia.com/metropolis/deepstream/dev-guide/index.html#page/DeepStream_Development_Guide/deepstream_performance.html# is to show deepstream capabilities on different Nvidia platforms. It is not to show the limitations of the platform. For example, on T4, even with the same configuration and model in the test case, more than 35 streams can be supported.
The performance data means nothing if no precondition is identified.
Deepstream will use various accelerators such as VIC, GPU, DLA, NVDEC and NVENC in the Nvidia platform, any of the resources and CPU can be bottleneck for different application, different models and different configurations.