What are the 4 parameters inside Kernel<<< >>> ()?

Accelerated Computing CUDA CUDA Programming and Performance
1

My understanding is we have two options:

kernel<<<numBlocks, numThreadsPerBlock>>>( arguments, ...);

Or:

kernel<<<numBlocks, numThreadsPerBlock, ???, stream>>>( arguments, ...);

I have been searching for hours but can’t find anything useful on what the ??? is except that most people seem to set it to zero.

Any help? In basic terms? Where is this documented?

2

The third parameter specifies the size of dynamic shared memory per thread block.

1 Like
3

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.