[ENHANCEMENT]: Enable `packed_cas` codepath using 16B CAS on sm_90+ architectures

[sleeepyjack]

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

The packed_cas update routine shows better performance compared to back_to_back_cas and cas_dependent_write.

On sm_90 and higher we have hardware support for 16B atomic CAS which we currently don't make use of.

Describe the solution you'd like

16B atomicCAS was introduced with CUDA 12.3 (see docs).

Idea: Add a dedicated codepath for sm_90+ by adding something like

NV_IF_TARGET(some_target_that_means_sm_90_or_higher,
             atomicCAS(...) // 16B CAS,
             // pre-sm_90 code path);

Describe alternatives you've considered

Convince CCCL to expose cuda::atomic_ref::compare_exchange_* for 16B types ;)

Additional context

No response

[PointKernel]

Convince CCCL to expose cuda::atomic_ref::compare_exchange_* for 16B types

+1

[sleeepyjack]

Convince CCCL to expose cuda::atomic_ref::compare_exchange_* for 16B types

Discussion thread (NVIDIA internal): https://nvidia.slack.com/archives/CCP05T27R/p1721095033011529