Michael Schellenberger Costa

We want this as a wrapper around a plain memory allocation, that takes care of alignment proper size calculations as well as deallocation of the memory Importantly we also need...

[FEA]: `cuda::span<T, Properties...>` a safe view over - heterogeneous - memory

1

We want to extent the property based design for safe heterogeneous memory accesses to view types. This will most likely require us to implement an iterator type that does the...

### Is this a duplicate? - [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md) ### Area...

We need to implement higher level data structures that take a `cuda::mr::resource_ref` as an type erased way of allocating memory. The goal is that the user is not required to...

Memory access in heterogeneous systems is notoriously difficult and error prone. With the property design we can use the type system to safeguard memory accesses across memory systems. Consequently we...

Stream ordered memory allocations are non trivial and we need to provide users with a simple but effective way of using stream ordered allocations. This will require two different data...

We want to extent the property based design for safe heterogeneous memory accesses to view types. With `cuda::std::mdspan` we might need to work with the accessor to ensure that we...

Update patches for CCCL 2.6

1

This adopts the patches to thrust to apply with CCCL 2.6. Should only be merged when updating the CCCL version, but I am opening them now to not forget it...

Cleanup the semaphore headers

1

This cleanes up our semaphore implementation and moves all respective features into their own headers

Do not pass integral constants to ptx

11

Rather than passing the instance of integral_constant we should pass the value Fixes #2225