Skip to content

Commit 9385369

Browse files
adayton1adayton1
authored
Merge pull request #279 from LLNL/v0.13.3-RC
v0.13.3 RC
2 parents b25dcd2 + 30adbc6 commit 9385369

File tree

8 files changed

+24
-17
lines changed

8 files changed

+24
-17
lines changed

‎CMakeLists.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ cmake_minimum_required(VERSION 3.23)
1717

1818
project(CARE
1919
LANGUAGES C CXX
20-
VERSION 0.13.2)
20+
VERSION 0.13.3)
2121

2222
include(${PROJECT_SOURCE_DIR}/cmake/Setup.cmake)
2323

‎README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
[comment]: # (SPDX-License-Identifier: BSD-3-Clause)
66
[comment]: # (#################################################################)
77

8-
# CARE v0.13.2
8+
# CARE v0.13.3
99

1010
CARE: CHAI and RAJA Extensions
1111
===============================

‎RELEASE_NOTES.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,12 @@ in this file.
1212

1313
The format of this file is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
1414

15+
## [Version 0.13.3] - Release date 2024-07-31
16+
17+
### Fixed
18+
- Replaced loop\_work alias with seq\_work (loop\_work was removed in RAJA v2024.02.2)
19+
- Fixed CHUNKED loop macro implementations
20+
1521
## [Version 0.13.2] - Release date 2024-07-29
1622

1723
### Changed

‎docs/sphinx/conf.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@
5757
# The short X.Y version.
5858
version = '0.13'
5959
# The full version, including alpha/beta/rc tags.
60-
release = '0.13.2'
60+
release = '0.13.3'
6161

6262
# The language for content autogenerated by Sphinx. Refer to documentation
6363
# for a list of supported languages.

‎scripts/make_release_tarball.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@
88
##############################################################################
99

1010
TAR_CMD=gtar
11-
VERSION=0.13.2
11+
VERSION=0.13.3
1212

1313
git archive --prefix=care-${VERSION}/ -o care-${VERSION}.tar HEAD 2> /dev/null
1414

‎src/care/DefaultMacros.h

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -313,7 +313,7 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
313313
/// @arg[in] CHECK The variable to check that the start and end macros match
314314
///
315315
////////////////////////////////////////////////////////////////////////////////
316-
#define CARE_CHECKED_CHUNKED_GPU_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK) CARE_CHECKED_OPENMP_FOR_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
316+
#define CARE_CHECKED_CHUNKED_GPU_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK) CARE_CHECKED_CHUNKED_OPENMP_FOR_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
317317

318318
#define CARE_CHECKED_CHUNKED_GPU_LOOP_END(CHECK) CARE_CHECKED_CHUNKED_OPENMP_FOR_LOOP_END(CHECK)
319319

@@ -366,12 +366,12 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
366366
/// @arg[in] CHECK The variable to check that the start and end macros match
367367
///
368368
////////////////////////////////////////////////////////////////////////////////
369-
#define CARE_CHECKED_CHUNKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK) CARE_CHECKED_OPENMP_FOR_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
369+
#define CARE_CHECKED_CHUNKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK) CARE_CHECKED_CHUNKED_OPENMP_FOR_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
370370

371-
#define CARE_CHECKED_CHUNKED_PARALLEL_LOOP_END(CHECK) CARE_CHECKED_OPENMP_FOR_LOOP_END(CHECK)
371+
#define CARE_CHECKED_CHUNKED_PARALLEL_LOOP_END(CHECK) CARE_CHECKED_CHUNKED_OPENMP_FOR_LOOP_END(CHECK)
372372

373373
#define CARE_CHECKED_CHUNKED_REDUCE_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK) \
374-
CARE_CHECKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
374+
CARE_CHECKED_CHUNKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, CHECK)
375375

376376
#define CARE_CHECKED_CHUNKED_REDUCE_LOOP_END(CHECK) CARE_CHECKED_CHUNKED_PARALLEL_LOOP_END(CHECK)
377377

@@ -901,9 +901,9 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
901901
/// @arg[in] CHUNK_SIZE Maximum kernel size
902902
///
903903
////////////////////////////////////////////////////////////////////////////////
904-
#define CARE_CHUNKED_LOOP(POLICY, INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_LOOP_START(POLICY, INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_loop_chunked_check)
904+
#define CARE_CHUNKED_LOOP(POLICY, INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_CHUNKED_LOOP_START(POLICY, INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_loop_chunked_check)
905905

906-
#define CARE_CHUNKED_LOOP_END CARE_CHECKED_LOOP_END(care_loop_chunked_check)
906+
#define CARE_CHUNKED_LOOP_END CARE_CHECKED_CHUNKED_LOOP_END(care_loop_chunked_check)
907907

908908
////////////////////////////////////////////////////////////////////////////////
909909
///
@@ -1041,7 +1041,7 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
10411041
/// @arg[in] CHUNK_SIZE Maximum kernel size
10421042
///
10431043
////////////////////////////////////////////////////////////////////////////////
1044-
#define CARE_CHUNKED_GPU_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_GPU_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_gpu_loop_chunked_check)
1044+
#define CARE_CHUNKED_GPU_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_CHUNKED_GPU_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_gpu_loop_chunked_check)
10451045

10461046
#define CARE_CHUNKED_GPU_LOOP_END CARE_CHECKED_CHUNKED_GPU_LOOP_END(care_gpu_loop_chunked_check)
10471047

@@ -1149,7 +1149,7 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
11491149
/// @arg[in] CHUNK_SIZE Maximum kernel size
11501150
///
11511151
////////////////////////////////////////////////////////////////////////////////
1152-
#define CARE_CHUNKED_WORK_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_work_loop_chunked_check)
1152+
#define CARE_CHUNKED_WORK_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_CHUNKED_PARALLEL_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_work_loop_chunked_check)
11531153

11541154
#define CARE_CHUNKED_WORK_LOOP_END CARE_CHECKED_CHUNKED_PARALLEL_LOOP_END(care_work_loop_chunked_check)
11551155

@@ -1223,7 +1223,7 @@ OMP_FOR_BEGIN for (auto INDEX = _care_openmp_for_loop_chunk_begin_ndx; INDEX < _
12231223
/// @arg[in] CHUNK_SIZE Maximum kernel size
12241224
///
12251225
////////////////////////////////////////////////////////////////////////////////
1226-
#define CARE_CHUNKED_REDUCE_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_REDUCE_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_reduce_loop_chunked_check)
1226+
#define CARE_CHUNKED_REDUCE_LOOP(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE) CARE_CHECKED_CHUNKED_REDUCE_LOOP_START(INDEX, START_INDEX, END_INDEX, CHUNK_SIZE, care_reduce_loop_chunked_check)
12271227

12281228
#define CARE_CHUNKED_REDUCE_LOOP_END CARE_CHECKED_CHUNKED_REDUCE_LOOP_END(care_reduce_loop_chunked_check)
12291229

‎src/care/LoopFuser.h

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,8 @@ constexpr double CARE_DEFAULT_PHASE = -FLT_MAX/2.0;
2626

2727
#if CARE_ENABLE_LOOP_FUSER
2828

29+
#include "RAJA/RAJA.hpp"
30+
2931
#include "umpire/Allocator.hpp"
3032
#include "umpire/TypedAllocator.hpp"
3133

@@ -581,11 +583,11 @@ class LoopFuser : public FusedActions {
581583
RAJA::constant_stride_array_of_objects >;
582584
#else
583585
using workgroup_policy = RAJA::WorkGroupPolicy <
584-
RAJA::loop_work,
586+
RAJA::seq_work,
585587
RAJA::ordered,
586588
RAJA::ragged_array_of_objects >;
587589
using workgroup_ordered_policy = RAJA::WorkGroupPolicy <
588-
RAJA::loop_work,
590+
RAJA::seq_work,
589591
RAJA::ordered,
590592
RAJA::ragged_array_of_objects >;
591593
#endif

‎test/TestForall.cpp

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,7 @@ CPU_TEST(forall, chunked_dynamic_policy)
7979
const int length = 10;
8080
care::host_device_ptr<int> temp(length, "temp");
8181

82-
CARE_LOOP(care::Policy::sequential, i, 0, length, batch_size) {
82+
CARE_CHUNKED_LOOP(care::Policy::sequential, i, 0, length, batch_size) {
8383
temp[i] = i;
8484
} CARE_CHUNKED_LOOP_END
8585

@@ -185,6 +185,5 @@ GPU_TEST(forall, chunked_dynamic_policy)
185185
temp.free();
186186
}
187187

188-
189188
#endif // CARE_GPUCC
190189

0 commit comments

Comments
 (0)