How to enable GPU at runtime in jetson nano development board

Hello NVIDIA Team,
i am working on jetson nano development board(B01).

i have installed cuda to enable GPU.Running below command to check GPU status on the board.

#cat /sys/devices/gpu.0/gpu_powered_on

it gives me output β€œ1” that means it is powered on.

and when run below command

#cat /sys/devices/gpu.0/devfreq/57000000.gpu/power/runtime_enabled

it gives me output "disabled "

so my question is how can i enable this on runtime?

Thank you.

Hi,

You don’t need to enable the GPU manually.
If an application is implemented on CUDA, it will be launched on the GPU.

For example, here is a sample of our CUDA toolkit.

$ cd /usr/local/cuda/samples/0_Simple/vectorAdd
$ sudo make
$ ./vectorAdd
[Vector addition of 50000 elements]
Copy input data from the host memory to the CUDA device
CUDA kernel launch with 196 blocks of 256 threads
Copy output data from the CUDA device to the host memory
Test PASSED
Done

Thanks.

1 Like

Hi AastaLLL,

Thank you for quick response.

I have another question after installing cuda components from the SDKManager on the board i just have perform the above test and if it passed successfully that means GPU is running successfully?