// Producers:
// A producer operation can can be any enqueue operation, such as a kernel or a memory fill.
clEnqueueXXX(producer_queue, ...);
// There can be more than one independent producer operations.
clEnqueueXXX(producer_queue, ...);

// This barrier requires all producer operations to be complete:
clEnqueueBarrierWithWaitList(producer_queue); 

// The semaphore cannot be signaled until the barrier is complete:
clEnqueueSignalSemaphore(producer_queue, semaphore);

// Note: the consumer_queue can be a separate queue or the same as the producer_queue!
// If the consumer_queue and the producer_queue are the same then there needs to be
// an explicit dependency between the semaphore signal and the semaphore wait, which
// could be an event dependency or another barrier.

// Consumers:
// Wait for the producers to signal completion via the semaphore:
clEnqueueWaitSemaphore(consumer_queue, semaphore);

// This barrier ensures all consumers cannot start until the semaphore wait is complete:
clEnqueueBarrierWithWaitList(consumer_queue);

// Now consumers can execute, and should see the producer results.
clEnqueueXXX(consumer_queue, ...);
clEnqueueXXX(consumer_queue, ...);