Develop stream 2024-09-12

.clang-format

@@ -1,11 +1,11 @@
 # Style file for MLSE Libraries based on the modified rocBLAS style
 
 # Common settings
-BasedOnStyle:  WebKit
-TabWidth:        4
-IndentWidth:     4
+BasedOnStyle:  LLVM
+TabWidth:        2
+IndentWidth:     2
 UseTab:          Never
-ColumnLimit: 100
+ColumnLimit: 120
 
 # Other languages JavaScript, Proto
 
@@ -20,14 +20,14 @@ Language: Cpp
 # void formatted_code_again;
 
 DisableFormat:   false
-Standard: Cpp11
-
-AccessModifierOffset: -4
+Standard: c++14
+AccessModifierOffset: -2
 AlignAfterOpenBracket: true
 AlignConsecutiveAssignments: true
 AlignConsecutiveDeclarations: true
 AlignEscapedNewlinesLeft: true
 AlignOperands:   true
+AllowAllArgumentsOnNextLine: true
 AlignTrailingComments: false
 AllowAllParametersOfDeclarationOnNextLine: true
 AllowShortBlocksOnASingleLine: false
@@ -39,13 +39,26 @@ AlwaysBreakAfterDefinitionReturnType: false
 AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: false
 AlwaysBreakTemplateDeclarations: true
+AttributeMacros: [
+                  'THRUST_DEVICE',
+                  'THRUST_FORCEINLINE',
+                  'THRUST_HOST_DEVICE',
+                  'THRUST_HOST',
+                  '_CCCL_DEVICE',
+                  '_CCCL_FORCEINLINE',
+                  '_CCCL_HOST_DEVICE',
+                  '_CCCL_HOST',
+                  'THRUST_RUNTIME_FUNCTION',
+                  'THRUST_DETAIL_KERNEL_ATTRIBUTES',
+                 ]
 BinPackArguments: false
 BinPackParameters: false
 
 # Configure each individual brace in BraceWrapping
 BreakBeforeBraces: Custom
 # Control of individual brace wrapping cases
 BraceWrapping: {
+    AfterCaseLabel: 'false'
     AfterClass: 'true'
     AfterControlStatement: 'true'
     AfterEnum : 'true'
@@ -56,52 +69,69 @@ BraceWrapping: {
     BeforeCatch : 'true'
     BeforeElse : 'true'
     IndentBraces : 'false'
-#    AfterExternBlock : 'true'
+    SplitEmptyFunction: 'false'
+    SplitEmptyRecord: 'false'
 }
 
-#BreakAfterJavaFieldAnnotations: true
-#BreakBeforeInheritanceComma: false
-#BreakBeforeBinaryOperators: None
-#BreakBeforeTernaryOperators: true
-#BreakConstructorInitializersBeforeComma: true
-#BreakStringLiterals: true
+BreakBeforeConceptDeclarations: true
+BreakBeforeBinaryOperators: NonAssignment
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializers: BeforeComma
+BreakInheritanceList: BeforeComma
+EmptyLineAfterAccessModifier: Never
+EmptyLineBeforeAccessModifier: Always
+
+InsertBraces: true
+InsertNewlineAtEOF: true
+InsertTrailingCommas: Wrapped
+IndentRequires: true
+IndentPPDirectives: AfterHash
+PackConstructorInitializers: Never
+PenaltyBreakAssignment: 30
+PenaltyBreakTemplateDeclaration: 0
+PenaltyIndentedWhitespace: 2
+RemoveSemicolon: false
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeRangeBasedForLoopColon: true
+
 
 CommentPragmas:  '^ IWYU pragma:'
-#CompactNamespaces: false
+CompactNamespaces: false
 ConstructorInitializerAllOnOneLineOrOnePerLine: false
 ConstructorInitializerIndentWidth: 4
-ContinuationIndentWidth: 4
+ContinuationIndentWidth: 2
 Cpp11BracedListStyle: true
-#SpaceBeforeCpp11BracedList: false
-DerivePointerAlignment: false
+SpaceBeforeCpp11BracedList: false
 ExperimentalAutoDetectBinPacking: false
 ForEachMacros:   [ foreach, Q_FOREACH, BOOST_FOREACH ]
-IndentCaseLabels: false
-#FixNamespaceComments: true
+IndentCaseLabels: true
+FixNamespaceComments: true
 IndentWrappedFunctionNames: false
-KeepEmptyLinesAtTheStartOfBlocks: true
+KeepEmptyLinesAtTheStartOfBlocks: false
 MacroBlockBegin: ''
 MacroBlockEnd:   ''
 #JavaScriptQuotes: Double
 MaxEmptyLinesToKeep: 1
-NamespaceIndentation: Inner
+NamespaceIndentation: None
 ObjCBlockIndentWidth: 4
 #ObjCSpaceAfterProperty: true
 #ObjCSpaceBeforeProtocolList: true
-PenaltyBreakBeforeFirstCallParameter: 19
-PenaltyBreakComment: 300
-PenaltyBreakFirstLessLess: 120
-PenaltyBreakString: 1000
-
-PenaltyExcessCharacter: 1000000
-PenaltyReturnTypeOnItsOwnLine: 60
+PenaltyBreakBeforeFirstCallParameter: 50
+PenaltyBreakComment: 0
+PenaltyBreakFirstLessLess: 0
+PenaltyBreakString: 70
+PenaltyExcessCharacter: 100
+PenaltyReturnTypeOnItsOwnLine: 90
 PointerAlignment: Left
-SpaceAfterCStyleCast: false
+SpaceAfterCStyleCast: true
 SpaceBeforeAssignmentOperators: true
-SpaceBeforeParens: Never
+SpaceBeforeParens: ControlStatements
 SpaceInEmptyParentheses: false
 SpacesBeforeTrailingComments: 1
-SpacesInAngles:  false
+SpacesInAngles: Never
 SpacesInContainerLiterals: true
 SpacesInCStyleCastParentheses: false
 SpacesInParentheses: false
@@ -110,11 +140,25 @@ SpacesInSquareBrackets: false
 #SpaceBeforeInheritanceColon: true
 
 #SortUsingDeclarations: true
-SortIncludes: true
+SortIncludes: CaseInsensitive
 
-# Comments are for developers, they should arrange them
-ReflowComments: false
+ReflowComments: true
 
 #IncludeBlocks: Preserve
 #IndentPPDirectives: AfterHash
+
+StatementMacros: [
+  'THRUST_EXEC_CHECK_DISABLE',
+  'THRUST_NAMESPACE_BEGIN',
+  'THRUST_NAMESPACE_END',
+  'THRUST_EXEC_CHECK_DISABLE',
+  'CUB_NAMESPACE_BEGIN',
+  'CUB_NAMESPACE_END',
+  'THRUST_NAMESPACE_BEGIN',
+  'THRUST_NAMESPACE_END',
+  '_LIBCUDACXX_BEGIN_NAMESPACE_STD',
+  '_LIBCUDACXX_END_NAMESPACE_STD',
+]
+TabWidth: 2
+UseTab: Never
 ---

.gitlab-ci.yml

@@ -12,6 +12,7 @@ include:
       - /deps-rocm.yaml
       - /deps-windows.yaml
       - /deps-nvcc.yaml
+      - /deps-compiler-acceleration.yaml
       - /gpus-rocm.yaml
       - /gpus-nvcc.yaml
       - /rules.yaml
@@ -46,17 +47,21 @@ copyright-date:
   extends:
     - .deps:rocm
     - .deps:cmake-latest
+    - .deps:compiler-acceleration
   before_script:
     - !reference [".deps:rocm", before_script]
     - !reference [".deps:cmake-latest", before_script]
+    - !reference [".deps:compiler-acceleration", before_script]
 
 .cmake-minimum:
   extends:
     - .deps:rocm
     - .deps:cmake-minimum
+    - .deps:compiler-acceleration
   before_script:
     - !reference [".deps:rocm", before_script]
     - !reference [".deps:cmake-minimum", before_script]
+    - !reference [".deps:compiler-acceleration", before_script]
 
 .install-rocprim:
   script:
@@ -69,8 +74,11 @@ copyright-date:
       -D CMAKE_CXX_COMPILER=hipcc
       -D CMAKE_BUILD_TYPE=Release
       -D BUILD_TEST=OFF
+      -D BUILD_HIPSTDPAR_TEST=OFF
       -D BUILD_EXAMPLE=OFF
       -D ROCM_DEP_ROCMCORE=OFF
+      -D CMAKE_C_COMPILER_LAUNCHER=phc_sccache_c
+      -D CMAKE_CXX_COMPILER_LAUNCHER=phc_sccache_cxx
       -S $ROCPRIM_DIR
       -B $ROCPRIM_DIR/build
     - cd $ROCPRIM_DIR/build
@@ -91,7 +99,7 @@ copyright-date:
     - !reference [.install-rocprim, script]
     - | # Setup env vars for testing
         rng_seed_count=0; prng_seeds="0";
-        if [[ $CI_COMMIT_BRANCH == "develop_stream" ]]; then 
+        if [[ $CI_COMMIT_BRANCH == "develop_stream" ]]; then
             rng_seed_count=3
             prng_seeds="0, 1000"
         fi
@@ -111,6 +119,9 @@ copyright-date:
       -D AMDGPU_TEST_TARGETS=$GPU_TARGETS
       -D RNG_SEED_COUNT=$rng_seed_count
       -D PRNG_SEEDS=$prng_seeds
+      -D CMAKE_C_COMPILER_LAUNCHER=phc_sccache_c
+      -D CMAKE_CXX_COMPILER_LAUNCHER=phc_sccache_cxx
+      -D CMAKE_CUDA_COMPILER_LAUNCHER=phc_sccache_cuda
       -S $CI_PROJECT_DIR
       -B $CI_PROJECT_DIR/build
     - cmake --build $CI_PROJECT_DIR/build
@@ -198,10 +209,10 @@ build:windows:
       -D CMAKE_INSTALL_PREFIX:PATH="$ROCPRIM_DIR/build/install" *>&1
     - \& cmake --build "$ROCPRIM_DIR/build" --target install *>&1
     # Configure and build rocThrust
-    - \& cmake 
-      -S "$CI_PROJECT_DIR" 
-      -B "$CI_PROJECT_DIR/build" 
-      -G Ninja 
+    - \& cmake
+      -S "$CI_PROJECT_DIR"
+      -B "$CI_PROJECT_DIR/build"
+      -G Ninja
       -D CMAKE_BUILD_TYPE=Release
       -D GPU_TARGETS=$GPU_TARGET
       -D BUILD_TEST=ON
@@ -327,10 +338,12 @@ test:rocm-windows-install:
     - .deps:nvcc
     - .gpus:nvcc-gpus
     - .deps:cmake-latest
+    - .deps:compiler-acceleration
     - .rules:manual
   before_script:
     - !reference [".deps:nvcc", before_script]
     - !reference [".deps:cmake-latest", before_script]
+    - !reference [".deps:compiler-acceleration", before_script]
 
 build:cuda-and-omp:
   stage: build
@@ -340,7 +353,7 @@ build:cuda-and-omp:
   tags:
     - build
   variables:
-    CCCL_GIT_BRANCH: v2.3.2
+    CCCL_GIT_BRANCH: v2.4.0
     CCCL_DIR: ${CI_PROJECT_DIR}/cccl
   needs: []
   script:
@@ -349,16 +362,21 @@ build:cuda-and-omp:
     - rm -R $CCCL_DIR/thrust/thrust
     - cp -r $CI_PROJECT_DIR/thrust $CCCL_DIR/thrust
     # Build tests and examples from CCCL Thrust
+    # CCCL 2.4.0 breaks compilation of tests. Compile examples only until we
+    # match v2.5.0.
     - cmake
       -G Ninja
       -D CMAKE_BUILD_TYPE=Release
       -D CMAKE_CUDA_ARCHITECTURES="$GPU_TARGETS"
-      -D THRUST_ENABLE_TESTING=ON
+      -D THRUST_ENABLE_TESTING=OFF
       -D THRUST_ENABLE_EXAMPLES=ON
       -D THRUST_ENABLE_BENCHMARKS=OFF
       -D THRUST_ENABLE_MULTICONFIG=ON
       -D THRUST_MULTICONFIG_ENABLE_SYSTEM_OMP=ON
       -D THRUST_MULTICONFIG_ENABLE_SYSTEM_CUDA=ON
+      -D CMAKE_C_COMPILER_LAUNCHER=phc_sccache_c
+      -D CMAKE_CXX_COMPILER_LAUNCHER=phc_sccache_cxx
+      -D CMAKE_CUDA_COMPILER_LAUNCHER=phc_sccache_cuda
       -B $CI_PROJECT_DIR/build
       -S $CCCL_DIR/thrust
     - cmake --build $CI_PROJECT_DIR/build

CHANGELOG.md

@@ -3,17 +3,19 @@
 Documentation for rocThrust available at
 [https://rocm.docs.amd.com/projects/rocThrust/en/latest/](https://rocm.docs.amd.com/projects/rocThrust/en/latest/).
 
-## (Unreleased) rocThrust 3.2.0 for ROCm 6.4
+## (Unreleased) rocThrust 3.3.0 for ROCm 6.4
 
 ### Additions
 * Added regression tests to `rtest.py`. Regression tests are a subset of tests that caused hardware problems for past emulation environments.
   * Can be run with `python rtest.py [--emulation|-e|--test|-t]=regression`
 * Added smoke test options, which runs a subset of the unit tests and ensures that less than 2gb of VRAM will be used
   * Smoke tests can be run using `[--emulation|-e|--test|-t]=smoke`
 * Added `--emulation` option for `rtest.py`
+* Merged changes from upstream CCCL/thrust 2.4.0
 
 ### Changes
 * `--test|-t` is no longer a required flag for `rtest.py`. Instead, the user can use either `--emulation|-e` or `--test|-t`, but not both.
+* Split the contents of HIPSTDPAR's forwarding header into several implementation headers.
 
 ## (Unreleased) rocThrust 3.2.0 for ROCm 6.3
 
@@ -39,6 +41,7 @@ Documentation for rocThrust available at
 
 * Merged changes from upstream CCCL/thrust 2.2.0
   * Updated the contents of `system/hip` and `test` with the upstream changes to `system/cuda` and `testing`
+* Added HIPSTDPAR library as part of rocThrust.
 
 ### Changes
 

CMakeLists.txt

@@ -80,6 +80,7 @@ endif()
 # Disable -Werror
 option(DISABLE_WERROR "Disable building with Werror" ON)
 option(BUILD_TEST "Build tests" OFF)
+option(BUILD_HIPSTDPAR_TEST "Build hipstdpar tests" OFF)
 option(BUILD_EXAMPLES "Build examples" OFF)
 option(BUILD_BENCHMARKS "Build benchmarks" OFF)
 option(DOWNLOAD_ROCPRIM "Download rocPRIM and do not search for rocPRIM package" OFF)
@@ -143,14 +144,14 @@ if(BUILD_TEST OR BUILD_BENCHMARKS)
 endif()
 
 # Tests
-if(BUILD_TEST)
+if(BUILD_TEST OR BUILD_HIPSTDPAR_TEST)
   rocm_package_setup_client_component(tests)
   if (ENABLE_UPSTREAM_TESTS)
     enable_testing()
   endif()
   # We still want the testing to be compiled to catch some errors
   #TODO: Get testing folder working with HIP on Windows
-  if (NOT WIN32)
+  if (NOT WIN32 AND BUILD_TEST)
     add_subdirectory(testing)
   endif()
   enable_testing()