intel_gpu_top & showing impact of deep learning

[AvatarRokuAsking]

When using OpenVino models how should I see their impact in `intel_gpu_top`? Asking since when I'm calling my model repeatedly on the same static image I'm seeing the Render/3D engine % go down, so I assume I'm using the tool incorrectly.

[Iffa_Intel]

Hi,

Generally, the measurement of performance OpenVINO on GPU has to be looked at its latency(measures the synchronous execution of inference requests and is reported in milliseconds) and throughput( measures the number of inferences delivered within a latency threshold ,for example, number of Frames Per Second - FPS).

You may refer to:

1. OpenVINO Performance Benchmark

2. OpenVINO performance comparison on CPU and GPU

It is expected to see GPU performs better than CPU. Perhaps the percentage that you mentioned goes down because the processing/rendering of image had completed at that time.

Cordially,

Iffa

[Iffa_Intel]

Hi,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question. 

Cordially,

Iffa