Please provide the following info (check/uncheck the boxes after creating this topic):
Software Version
DRIVE OS Linux 5.2.6
DRIVE OS Linux 5.2.6 and DriveWorks 4.0
DRIVE OS Linux 5.2.0
DRIVE OS Linux 5.2.0 and DriveWorks 3.5
NVIDIA DRIVE™ Software 10.0 (Linux)
NVIDIA DRIVE™ Software 9.0 (Linux)
other DRIVE OS version
other
Target Operating System
Linux
QNX
other
Hardware Platform
NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
NVIDIA DRIVE™ AGX Pegasus DevKit (E3550)
other
SDK Manager Version
1.9.1.10844
other
Host Machine Version
native Ubuntu 18.04
other
Hello team,
We are using NVIDIA AGX Xavier and wanted to check the iGPU core utilization (how many cores out of 512 are in use) while we inference from our machine learning model.
We tried using tegrastats but it gives only % utilization relative to current running frequency.
We tried using Nsight systems 2019.3 also to monitor CUDA trace for AGX. However, even that doesn’t give comprehensible output that will identify how many cores are used.
We have generated a graph from Nsight system report but we are not sure how to interpret it.
We went through many threads in the forum but did not find any concrete solution.
Can you help us monitor below performance metrics for AGX
- iGPU no. of cores used during inferencing
- % utilization of iGPU cores during inferencing
- How to interpret Nsight system report graph.
