Function tma_group_wait_read

pub fn tma_group_wait_read(_max_pending: u32)

Wait TMA copy operations have finished reading from shared memory, with at most max_pending operations being unfinished.

Example

I believe you may use max_pending like this.

copy_data(smem1);
copy_data(smem2);
copy_data(smem3);
copy_data(smem4);
tma_wait_read(2);
// reuse smem1 & smem2 while 3 and 4 are still pending