Dear Expert
As we know, __syncthreads() synchronizes threads in the block.
How can we synchronize all the threads generated by a kernel function?
I want to loop inside the kernel in which all the threads are synchronized at the end of each iteration.
Thank you for any advice :)
You can see past posts for answers.
No, we can’t.
So we should use parallel methods, pls refer to some links to great references in past posts.