Nsight compute CLI commands for remote profiling on Jetson TX2

Hi,

I am trying to get profiling information from Jetson to host using Nsignt Compute. I don’t want to use GUI for variety of reasons. I saw CLI has only “–hostname” option to the already launched process on a remote host but didn’t find options that reflect the GUI remote profiling feature in the CLI. Please let me know if I am missing anything here.

Thanks,
MRK

Hi,

The tool is located in the same folder.
For example:

$ cd /opt/nvidia/nsight-compute/2019.5.3
$ ./nv-nsight-cu-cli -h
usage: nv-nsight-cu-cli [options] [program] [program-arguments]

General Options:
  -h [ --help ]                         Print this help message.
  -v [ --version ]                      Print the version number.
  --mode arg (=launch-and-attach)       Select the mode of interaction with the target application:
                                          launch-and-attach
                                          (launch and attach for profiling)
                                          launch
                                          (launch and suspend for later attach)
                                          attach
                                          (attach to launched application)
  -p [ --port ] arg (=49152)            Base port for connecting to target application
  --max-connections arg (=64)           Maximum number of ports for connecting to target application
...

Thanks.

Hi AastaLLL,

Thanks for the response. In the remote profiling GUI, I can provide the username, password and executable but in this CLI I didn’t find the options for the similar behavior. If you can provide me with a basic example to profile on Jetson from CLI that would be great.

Thanks,
Ramakrishna

Hi,

Below is the document for your reference:

Thanks.

1 Like

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.