As wmf said, what NVidia calls a "core" isn't something that can issue it's own instructions so it isn't really something you'd normally consider a core, though it does have a PC and can compare its PC against the PC of broadcast instructions to decide if it should execute or not so it's a bit more sophisticated than a simple SIMD vector lane. Maybe on par with an execution port?

What's more equivalent to a CPU core would be what NVidia calls an SM and AMD calls a compute unit. These decide which instructions to issue next and broadcast them to the various lanes. You'll have dozens of them in a typical GPU, about the same as the number of CPU cores in the same silicon area.

They don't; GPUs have <72 real cores and thousands of marketing cores. And they can disable defective cores so their massive dies are still usable.