Skip to content
This repository has been archived by the owner on Mar 21, 2024. It is now read-only.

Create release 1.6.0. #191

Merged
merged 3 commits into from
Aug 4, 2021
Merged

Create release 1.6.0. #191

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
020b2a6
Create changelog for release 1.6.0
wmaxey Jul 30, 2021
0bf8fb2
Bump libcudacxx API version to 1.6.0
wmaxey Jul 30, 2021
64f88f6
Add clearer notification about ABI break. Fix capitalization.
wmaxey Aug 4, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 29 additions & 1 deletion docs/releases/changelog.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,37 @@ It pulls in the latest version of upstream libc++ and marks the beginning of

!-->

## libcu++ 1.6.0 (CUDA Toolkit 11.5)

libcu++ 1.6.0 is a major release. It adds two new functions to the `cuda::std::barrier` API and
uses `<nv/target>` as the primary dispatch mechanism for `cuda::std::atomic`. This is an ABI breaking release.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Go look up the changelog entry for the last new ABI, and make sure we are using the same wording. I think the summary for the last ABI change explained that the new one was now the default, and that the old one was still supported.


Supported ABI Versions: 4 (default), 3, and 2.

Included in: CUDA Toolkit 11.5.

### New Features

- #111: Adds two APIs to `cuda::std::barrier` for waiting on the parity of the barrier.
- Thanks to Olivier Giroux for this contribution.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Technically speaking we don't need to call out Olivier as he's a core contributor, but it's fine. Always good to thank people.


### Issues fixed
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fixed should be capitalized.


- #179: Refactors the atomic layer to allow for layering the host device/host abstractions.
- #189: Changed pragmas for silencing chrono long double warnings.
- #186: Allows `<nv/target>` to be used under NVRTC.
- #177: Allows `<nv/target>` to build when compiled under C and C++98.
- Thanks to David Olsen for this contribution.
- #172: Introduces ABI version 4.
- Forces `cuda::std::complex` alignment for enhanced performance.
- Sets the internal representation of `cuda::std::chrono` literals to `double`.
- #165: For tests on some older distributions keep using Python 3, but downgrade lit.
- #164: Fixes testing issues related to Python 2/3 switch for lit.
- Thanks to Royil Damer for this contribution.

## libcu++ 1.5.0 (CUDA Toolkit 11.4)

libcu++ 1.5.0 is a major release. It adds `<nv/target>`,
libcu++ 1.5.0 is a major release. It adds `<nv/target>`,
the library support header for the new `if target`
target specialization mechanism.

Expand Down
2 changes: 1 addition & 1 deletion include/cuda/std/detail/__config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@
# define _LIBCUDACXX_ABI_UNSTABLE
#endif

#define _LIBCUDACXX_CUDA_API_VERSION 001005000
#define _LIBCUDACXX_CUDA_API_VERSION 001006000

#define _LIBCUDACXX_CUDA_API_VERSION_MAJOR \
(_LIBCUDACXX_CUDA_API_VERSION / 1000000)
Expand Down