Michael Schellenberger Costa

icon indicating an email [email protected]

icon company @NVIDIA icon location Germany icon location Member of the CUDA C++ Core Libraries team at Nvidia.

Results 319 comments of Michael Schellenberger Costa

Added some wording for the init function.

@griwes would you mind pushing this over the finishing line?

[BUG] atomic is not trivially copyable when used inside template class

@wmaxey @griwes Given that the original bug has been fixed I believe we should close this

`<cuda/pipeline>` is not a part of libcu++

@wmaxey I believe you worked last on pipelines. Can we close this now that the header is available?

Implement `std::array`

`` is now available so closing this

libcu++ atomic fails to compile with address sanitizer (ASAN) enabled

This has been fixed by https://github.com/NVIDIA/libcudacxx/pull/206 AFAIK so closing

Added support for most of <mutex>

@jrhemstad How important is this and should I try to get this rebased?

Added support for most of <mutex>

While everything works fine locally, this PR is incredibly flaky in CI. We need to investigate why that is the case and find a strategy to unflake it

Added support for most of <mutex>

Dropping in favor of https://github.com/NVIDIA/cccl/pull/187

Implement `shift_left` and `shift_right` algorithms

Closing in favor of https://github.com/NVIDIA/cccl/pull/259

windef.h include via windows.h include causes issue with "near" and "far" names

Unfortunately there is nothing we can do here.