[DOC]: DeviceSelect::If upper limit of temp_storage_bytes?

[isovic]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this bug and that I agree to the Code of Conduct

Is this for new documentation, or an update to existing docs?

Update

Describe the incorrect/future/missing documentation

The DeviceSelect module documentation lacks information on an estimated (or better yet, upper bound) memory required for the temporary storage. Which parameters does it scale with (e.g the length of the input, number of threads, or is it fixed size)?

For example, the DeviceRadixSort docs provide information as the following:

This operation requires an allocation of temporary device storage that is O(N+P), where N is the length of the input and P is the number of streaming multiprocessors on the device. For sorting using only O(P) temporary storage, see the sorting interface using DoubleBuffer wrappers below.

However, for DeviceSelect::If I cannot tell if the temp_storage_bytes will even fit my memory for giant inputs or not, and I cannot batch my array beforehand because I don't know how temp storage scales.

Before the docs are officially updated, can you please provide some information about the estimate here?

Thank you,
Best regards,
Ivan.

If this is a correction, please provide a link to the incorrect documentation. If this is a new documentation request, please link to where you have looked.

No response

[github-actions]

Hi @isovic!

Thanks for submitting this issue - the CCCL team has been notified and we'll get back to you as soon as we can!
In the mean time, feel free to add any relevant information to this issue.

[jrhemstad]

At present, we don't document anything other than the temporary memory required is implementation defined. We've had similar requests recently, so we will likely try to do something more.

The problem is that providing an exact number or even robust estimate ties our hands on ever changing or improving the implementation in the future.