Skip to content

Commit

Permalink
Merge pull request LLNL#1641 from LLNL/main
Browse files Browse the repository at this point in the history
Main mergeback to develop after v2024.02.2 release
  • Loading branch information
rhornung67 authored May 9, 2024
2 parents 7ce4f39 + 593f756 commit 5295aee
Show file tree
Hide file tree
Showing 3 changed files with 35 additions and 2 deletions.
2 changes: 1 addition & 1 deletion CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ include(CMakeDependentOption)
# Set version number
set(RAJA_VERSION_MAJOR 2024)
set(RAJA_VERSION_MINOR 02)
set(RAJA_VERSION_PATCHLEVEL 1)
set(RAJA_VERSION_PATCHLEVEL 2)

if (RAJA_LOADED AND (NOT RAJA_LOADED STREQUAL "${RAJA_VERSION_MAJOR}.${RAJA_VERSION_MINOR}.${RAJA_VERSION_PATCHLEVEL}"))
message(FATAL_ERROR "You are mixing RAJA versions. Loaded is ${RAJA_LOADED}, expected ${RAJA_VERSION_MAJOR}.${RAJA_VERSION_MINOR}.${RAJA_VERSION_PATCHLEVEL}")
Expand Down
33 changes: 33 additions & 0 deletions RELEASE_NOTES.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,39 @@ Notable changes include:
* Bug fixes/improvements:


Version 2024.02.2 -- Release date 2024-05-08
============================================

This release contains a bugfix and new execution policies that improve
performance for GPU kernels with reductions.

Notable changes include:

* New features / API changes:
* New GPU execution policies for CUDA and HIP added which provide
improved performance for GPU kernels with reductions. Please see the
RAJA User Guide for more information. Short summary:
* Option added to change max grid size in policies that use the
occupancy calculator.
* Policies added to run with max occupancy, a fraction of of the
max occupancy, and to run with a "concretizer" which allows a
user to determine how to run based on what the occupancy
calculator determines about a kernel.
* Additional options to tune kernels containing reductions, such as
* an option to initialize data on host for reductions that use
atomic operations
* an option to avoid device scope memory fences
* Change ordering of SYCL thread index ordering in RAJA::launch to
follow the SYCL "row-major" convention. Please see RAJA User Guide
for more information.

* Build changes/improvements:
* NONE.

* Bug fixes/improvements:
* Fixed issue in bump-style allocator used internally in RAJA::launch.


Version 2024.02.1 -- Release date 2024-04-03
============================================

Expand Down
2 changes: 1 addition & 1 deletion docs/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@
# The short X.Y version.
version = u'2024.02'
# The full version, including alpha/beta/rc tags.
release = u'2024.02.1'
release = u'2024.02.2'

# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
Expand Down

0 comments on commit 5295aee

Please sign in to comment.