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This repository has been archived by the owner on Mar 21, 2024.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

Commit

Permalink
Debump to 1.4.1
Browse files Browse the repository at this point in the history
  • Loading branch information
wmaxey committed Feb 25, 2021
1 parent 51f5b78 commit 66c034c
Show file tree
Hide file tree
Showing 2 changed files with 25 additions and 7 deletions.
30 changes: 24 additions & 6 deletions docs/releases/changelog.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,5 @@
# Changelog

<!--
## libcu++ 2.0.0
libcu++ 2.0.0 is the first release of libcu++ as a complete standalone Standard
Expand All @@ -11,15 +9,27 @@ It adds `cuda::[std::]atomic_ref`, `<cuda/std/mutex>`, and
It pulls in the latest version of upstream libc++ and marks the beginning of
automatic tracking of upstream.
!-->

## libcu++ 1.4.1 (CUDA Toolkit 11.3)

libcu++ 1.4.1 is a minor bugfix release.

Supported ABI versions: 3 (default) and 2.

### New Features
Included in: CUDA Toolkit 11.3.

### Other Enhancements

- [Documentation](https://nvidia.github.io/libcudacxx): Several enhancements and fixed a few broken links.
- #108: Added `constexpr` to synchronization object constructors.
- Thanks to Olivier Giroux for this contribution.

### Issues Fixed

-->
- #106: Fixed host code atomics on VS 2019 Version 16.5 / MSVC 1925 and above.
- #101: Fixed `cuda::std::complex` for NVRTC.
- #118: Renamed `__is_convertible`, which NVCC treats as a context sensitive keyword.

## libcu++ 1.4.0

Expand Down Expand Up @@ -69,7 +79,7 @@ It also adds [documentation](https://nvidia.github.io/libcudacxx).

Supported ABI versions: 3 (default) and 2.

Included in: CUDA 11.2.
Included in: CUDA Toolkit 11.2.

### New Features

Expand Down Expand Up @@ -101,7 +111,7 @@ This release introduces ABI version 3, which is now the default.

Supported ABI versions: 3 (default) and 2.

Included in: CUDA 11.1.
Included in: CUDA Toolkit 11.1.

### ABI Breaking Changes

Expand Down Expand Up @@ -147,6 +157,10 @@ An extension for managing asynchronous local copies, `cuda::memcpy_async` is
It also adds `<cuda/std/chrono>`, `<cuda/std/ratio>`, and most of
`<cuda/std/functional>`.

Supported ABI versions: 2.

Included in: CUDA Toolkit 11.0.

### ABI Breaking Changes

- ABI version 2 has been introduced and is now the default.
Expand Down Expand Up @@ -200,6 +214,10 @@ It brings C++ atomics to CUDA: `<cuda/[std/]atomic>`.
It also introduces `<cuda/std/type_traits>`, `<cuda/std/cassert>`,
`<cuda/std/cfloat>`, `<cuda/std/cstddef>`, and `<cuda/std/cstdint>`.

Supported ABI versions: 1.

Included in: CUDA Toolkit 10.2.

### New Features

- `<cuda/[std/]atomic>`:
Expand Down
2 changes: 1 addition & 1 deletion include/cuda/std/detail/__config
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@
# define _LIBCUDACXX_ABI_UNSTABLE
#endif

#define _LIBCUDACXX_CUDA_API_VERSION 002000000
#define _LIBCUDACXX_CUDA_API_VERSION 001004001

#define _LIBCUDACXX_CUDA_API_VERSION_MAJOR \
(_LIBCUDACXX_CUDA_API_VERSION / 1000000)
Expand Down

0 comments on commit 66c034c

Please sign in to comment.