I have the following conceptual questions to ask you:
When use Hyper-Q, probably we can have kernels (more than ONE) to be executed at the same moment. Right?
And without the Hyper-Q technology we can only have ONE kernel launching at a moment-----however maybe overlapped with data transfer (GPU-CPU). Right?
For making use of Hyper-Q, are there some settings of procedures we should do before?
If we employ
“Dynamic Parallelism”, can the sub-kernels and their parent kernel run at the same moment? (Providing GPU resource is enough)
I will highly appreciate your helps !