-
|
Dynamic Parallelism (DP) seems to me a very exotic feature of CUDA and I've seen it used rarely in some papers. Do I understand it right that PDL and persistent kernels are possible due to Dynamic Parallelism of CUDA? Does it really the case that one kernel call some other one or do I misunderstand something really bad? |
Beta Was this translation helpful? Give feedback.
Answered by
thakkarV
Nov 21, 2024
Replies: 1 comment
-
|
No, we don't call other kernels from a kernel anywhere |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
dukallis
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
No, we don't call other kernels from a kernel anywhere