L20 is supported in nsight compute?

I have attempted to profile a CUDA kernel on an L20 GPU using Nsight Compute, but it failed.

ncu -o vecAdd_profile ./Samples/0_Introduction/vectorAdd/vectorAdd

[Vector addition of 50000 elements]
==PROF== Connected to process 42863 (/data/shuren/code/cuda-samples/Samples/0_Introduction/vectorAdd/vectorAdd)
Copy input data from the host memory to the CUDA device
CUDA kernel launch with 196 blocks of 256 threads
==ERROR== Failed to prepare kernel for profiling

==ERROR== Unknown Error on device 0.
==ERROR== Failed to profile “vectorAdd” in process 42863
==PROF== Trying to shutdown target application
==ERROR== The application returned an error code (9).
==ERROR== An error occurred while trying to profile.
==WARNING== No kernels were profiled.

My cuda toolkit and driver are latest:

and the kernel can run correctly without ncu.
Does the nsight compute support the L20 gpu or is there something wrong on my env?

Hi, @274962485

Sorry for the issue you met. L20 is supported by nsight compute.
Have you checked if it works after reboot ? There are similar ask before and resolved after reboot.

It doesn’t work after reboot for my case.


  1. Are you using nsight compute installed from cuda package ? What is the version ?
  2. Can you rebuild the sample and check ?
  3. Please check if other sample have the same issue.

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.