What is the correct way to GPU execution before reclaiming data?

[l3utterfly]

Following the launch_kernel example, it launches a kernel then uses "sync reclaim" to copy the results back to the CPU.

Do I need to call the synchronise method after calling the kernel? Because in C, this is required. None of the examples have this, just making sure.

[Corey Lowman]

Nope!

All the device to host copy methods are synchronize (they call synchronize internally). I attempted to make this clear by including sync in all the method names that are inherently synchronous.

There are the following ways of copying data back to host:

1. CudaDevice::sync_reclaim, which deallocates the device memory and returns the vec
2. CudaDevice::dtoh_sync_copy, which synchronously copies into a newly allocated vec
3. CudaDevice::dtoh_sync_copy_into which synchronously copies into an existing slice

[Corey Lowman]

I will note that if you are using a separate CudaStream to launch kernels, you will need to explicitly synchronize the stream with CudaDevice::wait_for, which is shown in the examples/04-stream.rs

[l3utterfly]

Thanks, got it!