[FEA]: Provide a host/device CRC implementation

[fbusato]

Is this a duplicate?

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

Area

CUDA Experimental (cudax)

Is your feature request related to a problem? Please describe.

CRC is an extremely popular utility and other vendors offer it as part of their library.
On the other hand, CUDA doesn't directly provide such functionality. Many CUDA libraries, internally and externally, reimplement the same functionalities, creating redundancy and duplicating the effort.

Describe the solution you'd like

Provide <cudax/crc> to compute the CRC of a buffer of data both on the host and on the device (single function/device)

Describe alternatives you've considered

No response

Additional context

No response

[leofang]

What's CRC?

[fbusato]

Cyclic Redundancy Check https://en.wikipedia.org/wiki/Cyclic_redundancy_check
It is the most popular algorithm for computing checksum