Let's look at the steps, as follows:

1. With the first instruction, we import the Python driver (that is, pycuda.driver) to the CUDA library installed on our PC:

import pycuda.driver as drv

2. Initialize CUDA. Note also that the following instruction must be called before any other instruction in the pycuda.driver module:

drv.init()

3. Enumerate the number of GPU cards on the PC:

print ("%d device(s) found." % drv.Device.count())

4. For each of the GPU cards present, print the model name, the computing capability, and the total amount of memory on the device in kilobytes:

for ordinal i n range(drv.Device.count()): 
       dev = drv.Device(ordinal) 
       print ("Device #%d: %s" % (ordinal, dev.name()) 
       print ("Compute Capability: %d.%d"% dev.compute_capability()) 
       print ("Total Memory: %s KB" % (dev.total_memory()//(1024)))