Reputation: 11
Is it possible, to generate some kind of data on GPU, store it in the local memory and use this data over more than one kernel?
It would be nice to see a simple example, if it's possible.
Thank you!
Upvotes: 1
Views: 1268
Reputation: 56347
Sure, just create a buffer in global memory and write into it from your first kernel, and then just read the buffer in your second kernel execution.
Upvotes: 1