Merge pull request #882 from LLNL/v0.12.0-rc

V0.12.0 rc

.gitignore

@@ -3,6 +3,11 @@
 *.a
 *.exe
 *.gch
-build/
-build-*/
+/*.sublime-*
+/build/
+/build_*/
+/build-*/
+/install/
+/install_*/
+/install-*/
 /Debug/

.travis.yml

@@ -29,28 +29,17 @@ matrix:
     env:
     - COMPILER=g++
     - IMG=gcc8
-    - CMAKE_EXTRA_FLAGS="-DENABLE_WARNINGS=On -DENABLE_TBB=On"
+    - CMAKE_EXTRA_FLAGS="-DENABLE_WARNINGS=On -DENABLE_TBB=On -DRAJA_ENABLE_BOUNDS_CHECK=ON"
   - compiler: clang9
     env:
     - COMPILER=clang++-9
     - IMG=clang9
     - CMAKE_EXTRA_FLAGS="-DCMAKE_CXX_FLAGS=-fmodules -DENABLE_TBB=On"
-  - compiler: clang5
-    env:
-    - COMPILER=clang++
-    - IMG=clang5
-    - CMAKE_EXTRA_FLAGS="-DCMAKE_CXX_FLAGS=-fmodules -DENABLE_TBB=On"
   - compiler: intel18
     env:
     - COMPILER=/opt/intel/bin/icpc
     - IMG=icc18
-    - CMAKE_EXTRA_FLAGS="-DENABLE_TBB=On"
-  - compiler: nvcc9
-    env:
-    - COMPILER=g++
-    - IMG=nvcc9
-    - CMAKE_EXTRA_FLAGS="-DENABLE_CUDA=On -DENABLE_TBB=On"
-    - DO_TEST=no
+    - CMAKE_EXTRA_FLAGS="-DENABLE_FORCEINLINE_RECURSIVE=Off -DENABLE_TBB=On"
   - compiler: nvcc10.2
     env:
     - COMPILER=g++
@@ -86,7 +75,7 @@ matrix:
       - COMPILER=g++
       - IMG=hip
       - HCC_AMDGPU_TARGET=gfx900
-      - CMAKE_EXTRA_FLAGS="-DENABLE_HIP=On -DENABLE_OPENMP=Off -DENABLE_CUDA=Off -DENABLE_WARNINGS_AS_ERRORS=Off"
+      - CMAKE_EXTRA_FLAGS="-DENABLE_HIP=On -DENABLE_OPENMP=Off -DENABLE_CUDA=Off -DENABLE_WARNINGS_AS_ERRORS=Off -DHIP_HIPCC_FLAGS=-fPIC"
       - DO_TEST=no
 
 

CMakeLists.txt

@@ -8,9 +8,13 @@
 cmake_policy(SET CMP0042 NEW)
 cmake_policy(SET CMP0048 NEW)
 
+if (APPLE)
+ cmake_policy(SET CMP0025 NEW)
+endif()
+
 # Set version number
 set(RAJA_VERSION_MAJOR 0)
-set(RAJA_VERSION_MINOR 11)
+set(RAJA_VERSION_MINOR 12)
 set(RAJA_VERSION_PATCHLEVEL 0)
 
 if (RAJA_LOADED AND (NOT RAJA_LOADED STREQUAL "${RAJA_VERSION_MAJOR}.${RAJA_VERSION_MINOR}.${RAJA_VERSION_PATCHLEVEL}"))
@@ -47,7 +51,6 @@ set(ENABLE_GTEST_DEATH_TESTS On CACHE BOOL "Enable tests asserting failure.")
 set(RAJA_CXX_STANDARD_FLAG "default" CACHE STRING "Specific c++ standard flag to use, default attempts to autodetect the highest available")
 
 option(ENABLE_TBB "Build TBB support" Off)
-option(ENABLE_CHAI "Build CHAI support" Off)
 option(ENABLE_TARGET_OPENMP "Build OpenMP on target device support" Off)
 option(ENABLE_CLANG_CUDA "Use Clang's native CUDA support" Off)
 option(ENABLE_EXTERNAL_CUB "Use an external cub for scans" Off)
@@ -64,6 +67,7 @@ option(ENABLE_FORCEINLINE_RECURSIVE "Enable Forceinline recursive (only supporte
 option(ENABLE_BENCHMARKS "Build benchmarks" Off)
 option(RAJA_DEPRECATED_TESTS "Test deprecated features" Off)
 option(RAJA_ENABLE_BOUNDS_CHECK "Enable bounds checking in RAJA::Views/Layouts" Off)
+option(RAJA_TEST_EXHAUSTIVE "Build RAJA exhaustive tests" Off)
 
 set(TEST_DRIVER "" CACHE STRING "driver used to wrap test commands")
 
@@ -72,7 +76,7 @@ cmake_minimum_required(VERSION 3.9)
 if (ENABLE_CUDA)
   if (DEFINED CUDA_ARCH)
     if (CUDA_ARCH MATCHES "^sm_*")
-      if ("${CUDA_ARCH}" STRLESS "sm_35") 
+      if ("${CUDA_ARCH}" STRLESS "sm_35")
         message( FATAL_ERROR "RAJA requires minimum CUDA compute architecture of sm_35")
       endif()
     endif()
@@ -85,7 +89,7 @@ if (ENABLE_CUDA)
     message(STATUS "CUDA compute architecture set to RAJA default sm_35 since it was not specified")
     set(CUDA_ARCH "sm_35" CACHE STRING "Set CUDA_ARCH to RAJA minimum supported" FORCE)
   endif()
-  if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
+  if ( (CMAKE_CXX_COMPILER_ID MATCHES GNU) AND (CMAKE_SYSTEM_PROCESSOR MATCHES ppc64le) )
     if (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER 8.0)
       set (CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler -mno-float128")
     endif ()
@@ -157,7 +161,9 @@ set (raja_sources
   src/LockFreeIndexSetBuilders.cpp
   src/MemUtils_CUDA.cpp
   src/MemUtils_HIP.cpp
-  src/PluginStrategy.cpp)
+  src/PluginStrategy.cpp
+  src/RuntimePluginLoader.cpp
+  src/KokkosPluginLoader.cpp)
 
 set (raja_depends)
 
@@ -182,7 +188,7 @@ if (ENABLE_CUDA)
     if (CUB_FOUND)
       blt_register_library(
         NAME cub
-        INCLUDES ${CUB_INCLUDE_DIRS})
+        INCLUDES $<BUILD_INTERFACE:${CUB_INCLUDE_DIRS}>)
       set(raja_depends
         ${raja_depends}
         cub)
@@ -216,38 +222,34 @@ if (ENABLE_HIP)
   endif ()
 endif ()
 
-if (ENABLE_CHAI)
-  set (raja_depends
-    ${raja_depends}
-    chai)
-endif ()
-
 if (ENABLE_TBB)
   set(raja_depends
     ${raja_depends}
     tbb)
 endif ()
 
-set(EXTERNAL_CAMP_SOURCE_DIR "" CACHE FILEPATH "build with a specific external
+if (NOT TARGET camp)
+  set(EXTERNAL_CAMP_SOURCE_DIR "" CACHE FILEPATH "build with a specific external
 camp source repository")
-if (EXTERNAL_CAMP_SOURCE_DIR)
-  message(STATUS "Using external source CAMP from: " ${EXTERNAL_CAMP_SOURCE_DIR})
-  add_subdirectory(${EXTERNAL_CAMP_SOURCE_DIR}
-    ${CMAKE_CURRENT_BINARY_DIR}/tpl/camp)
-else (EXTERNAL_CAMP_SOURCE_DIR)
-  find_package(camp QUIET)
-  if (NOT camp_FOUND)
-    message(STATUS "Using RAJA CAMP submodule.")
-    add_subdirectory(tpl/camp)
-  else (NOT camp_FOUND)
-    message(STATUS "Using installed CAMP from:  ${camp_INSTALL_PREFIX}")
-  endif(NOT camp_FOUND)
-endif (EXTERNAL_CAMP_SOURCE_DIR)
+  if (EXTERNAL_CAMP_SOURCE_DIR)
+    message(STATUS "Using external source CAMP from: " ${EXTERNAL_CAMP_SOURCE_DIR})
+    add_subdirectory(${EXTERNAL_CAMP_SOURCE_DIR}
+                     ${CMAKE_CURRENT_BINARY_DIR}/tpl/camp)
+  else (EXTERNAL_CAMP_SOURCE_DIR)
+    find_package(camp QUIET)
+    if (NOT camp_FOUND)
+      message(STATUS "Using RAJA CAMP submodule.")
+      add_subdirectory(tpl/camp)
+    else (NOT camp_FOUND)
+      message(STATUS "Using installed CAMP from:  ${camp_INSTALL_PREFIX}")
+    endif(NOT camp_FOUND)
+  endif (EXTERNAL_CAMP_SOURCE_DIR)
+endif (NOT TARGET camp)
 
 blt_add_library(
   NAME RAJA
   SOURCES ${raja_sources}
-  DEPENDS_ON ${raja_depends} camp)
+  DEPENDS_ON ${raja_depends} camp ${CMAKE_DL_LIBS})
 
 install(TARGETS RAJA
   EXPORT RAJA
@@ -262,9 +264,11 @@ target_include_directories(RAJA
   PUBLIC
   $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
   $<BUILD_INTERFACE:${PROJECT_BINARY_DIR}/include>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/tpl/cub>
-  $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/tpl/rocPRIM/rocprim/include>
   $<INSTALL_INTERFACE:include>)
+target_include_directories(RAJA SYSTEM
+  PUBLIC
+  $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/tpl/cub>
+  $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/tpl/rocPRIM/rocprim/include>)
 
 install(DIRECTORY include/ DESTINATION include FILES_MATCHING PATTERN *.hpp)
 if(NOT ENABLE_EXTERNAL_CUB)

README.md

@@ -71,14 +71,14 @@ submodule or as an installed library.
 User Documentation
 -------------------
 
-The [**RAJA User Guide and Tutorial**](http://raja.readthedocs.io/en/master/) 
+The [**RAJA User Guide and Tutorial**](http://raja.readthedocs.io/en/main/) 
 is the best place to start learning about RAJA and how to use it.
 
 To cite RAJA, please use the following references:
 
 * RAJA Performance Portability Layer. https://github.com/LLNL/RAJA
 
-* D. A. Beckingsale, J. Burmark, R. Hornung, H. Jones, W. Killian, A. J. Kunen, O. Pearce, P. Robinson, B. S. Ryujin, T. R. W. Scogland, "RAJA: Porrtable Performance for Large-Scale Scientific Applications", 2019 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC). [Download here](https://conferences.computer.org/sc19w/2019/#!/toc/14)
+* D. A. Beckingsale, J. Burmark, R. Hornung, H. Jones, W. Killian, A. J. Kunen, O. Pearce, P. Robinson, B. S. Ryujin, T. R. W. Scogland, "RAJA: Portable Performance for Large-Scale Scientific Applications", 2019 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC). [Download here](https://conferences.computer.org/sc19w/2019/#!/toc/14)
 
 Related Software
 --------------------
@@ -114,7 +114,7 @@ The RAJA team follows the [GitFlow](http://nvie.com/posts/a-successful-git-branc
 include their work in a feature branch created from the RAJA `develop` branch.
 Then, create a pull request with the `develop` branch as the destination. That
 branch contains the latest work in RAJA. Periodically, we will merge the 
-develop branch into the `master` branch and tag a new release.
+develop branch into the `main` branch and tag a new release.
 
 Authors
 -----------

RELEASE_NOTES.md

@@ -10,6 +10,110 @@
 Version vxx.yy.zz -- Release date 20yy-mm-dd
 ============================================
 
+Version v0.12.0 -- Release date 2020-09-03
+============================================
+
+This release contains new features, notable changes, and bug fixes. Please
+see the RAJA user guide for more information about items in this release.
+
+Notable changes include:
+
+  * Notable repository change:
+      * The 'master' branch in the RAJA git repo has been renamed to 'main'.
+
+  * New features:
+      * New RAJA "work group" capability added. This allows multiple GPU
+        kernels to be fused into one kernel launch, greatly reducing the
+        run time overhead of launching CUDA kernels.
+      * Added support for dynamic plug-ins in RAJA, which enable the use of
+        things like Kokkos Performance Profiline Tools to be used with RAJA
+        (https://github.com/kokkos/kokkos-tools)
+      * Added ability to pass a resource object to RAJA::forall methods to
+        enable asynchronous execution for CUDA and HIP back-ends.
+      * Added "Multi-view" that works like a regular view, except that it
+        can wrap multiple arrays so their accesses can share index arithmetic.
+      * Multiple sort algorithms added. This provides portable parallel sort 
+        operations, which are basic parallel algorithm building blocks.
+      * Introduced RAJA "Teams" concept as an experimental feature. This
+        enables hierarchical parallelism and additional nested loop patterns
+        beyond what RAJA::kernel supports. Please note that this is very much
+        a work-in-progress and is not yet documented in the user guide.
+      * Added initial support for dynamic loop tiling.
+      * New OpenMP execution policies added to support static, dynamic, and 
+        guided scheduling.
+      * Added support for const iterators to be used with RAJA scans.
+      * Support for bitwise and and or reductions have been added.
+      * The RAJA::kernel interface has been expanded to allow only segment 
+        index arguments used in a lambda to be passed to the lambda. In 
+        previous versions of RAJA, every lambda invoked in a kernel had to 
+        accept an index argument for every segment in the segment tuple passed 
+        to RAJA::kernel execution templates, even if not all segment indices 
+        were used in a lambda. This release still allows that usage pattern.
+        The new capability requires an additional template parameter to be 
+        passed to the RAJA::statement::Lambda type, which identify the segment 
+        indices that will be passed and in which order.
+
+  * API Changes:
+      * The RAJA 'VarOps' namespace has been removed. All entities previously
+        in that namespace are now in the 'RAJA' namespace.
+      * RAJA span is now public for users to access and has been made more like
+        std::span.
+      * RAJA::statement::tile_fixed has been moved to RAJA::tile_fixed
+        (namespace change).
+      * RAJA::statement::{Segs, Offsets, Params, ValuesT} have been moved to
+        RAJA::{Segs, Offsets, Params, ValuesT} (namespace change).
+      * RAJA ListSegment constructors have been expanded to accept a camp
+        Resource object. This enables run time specification of the memory
+        space where the data for list segment indices will live. In earlier
+        RAJA versions, the space in which list segment index data lived was a 
+        compile-time choice based on whether CUDA or HIP was enabled and the 
+        data resided in unified memory for either case. This is still supported
+        in this release, but is marked as a DEPRECATED FEATURE. In the next RAJA
+        release, ListSegment construction will require a camp Resource object.
+        When compiling RAJA with your application, you will see deprecation
+        warnings if you are using the deprecated ListSegment constructor. 
+      * A reset method was added to OpenMP target offload reduction classes
+        so they contain the same functionality as reductions for all other 
+        back-ends.
+
+  * Build changes/improvements:
+      * The BLT, camp, CUB, and rocPRIM submodules have all been updated to 
+        more recent versions. Please note that RAJA now requires rocm version 
+        3.5 or newer to use the HIP back-end.
+      * Build for clang9 on macosx has been fixed.
+      * Build for Intel19 on Windows has been fixed.
+      * Host/device annotations have been added to reduction operations to
+        eliminate compiler warnings for certain use cases.
+      * Several warnings generated by the MSVC compiler have been eliminated.
+      * A couple of PGI compiler warnings have been removed.
+      * CMake improvements to make it is easier to use an external camp or 
+        CUB library with RAJA. 
+      * Note that the RAJA tests are undergoing a substantial overhaul. Users,
+        who chose to build and run RAJA tests, should know that many tests
+        are now being generated in the build space directory structure which
+        mimics the RAJA source directory structure. As a result, only some
+        test executables appear in the top-level 'test' subdirectory of the 
+        build directory; others can be found in lower-level directories. The
+        reason for this change is to reduce test build times for certain 
+        compilers.
+
+  * Bug fixes:
+      * An issue with SIMD privatization with the Intel compiler, required
+        to generate correct code, has been fixed.
+      * An issue with the atomicExchange() operation for the RAJA HIP back-end
+        has been fixed.
+      * A type issue in the RAJA::kernel implementation involving RAJA span
+        usage has been fixed.
+      * Checks for iterator ranges and container sizes have been added to
+        RAJA scans, which fixes an issue when users attempted to run a 
+        scan over a range of size zero.
+      * Several type errors in the Layout.hpp header file have been fixed.
+      * Several fixes have been made in the Layout and Static Layout types.
+      * Several fixes have been made to the OpenMP target offload back-end
+        to address host-device memory issues.
+      * A variety of RAJA User Guide issues have been addressed, as well as
+        issues in RAJA example codes.
+
 Version v0.11.0 -- Release date 2020-01-29
 ==========================================
 
@@ -85,7 +189,7 @@ Notable changes include:
       * Added a bounds checking option to RAJA Layout types as a debugging
         feature. This is a compile-time option that will report user errors
         when given View or Layout indices are out-of-bounds. See View/Layout
-        section in the RAjA User Guide for instructions on enabling this and 
+        section in the RAJA User Guide for instructions on enabling this and 
         how this feature works. 
       * We've added a RAJA Template Project on GitHub, which shows how to
         use RAJA in an application, either as a Git submodule or as an

cmake/RAJAMacros.cmake

@@ -49,6 +49,50 @@ macro(raja_add_executable)
     )
 endmacro(raja_add_executable)
 
+macro(raja_add_plugin_library)
+  set(options )
+  set(singleValueArgs NAME SHARED)
+  set(multiValueArgs SOURCES DEPENDS_ON)
+
+  cmake_parse_arguments(arg
+    "${options}" "${singleValueArgs}" "${multiValueArgs}" ${ARGN})
+
+  list(APPEND arg_DEPENDS_ON RAJA)
+
+  if (ENABLE_OPENMP)
+    list (APPEND arg_DEPENDS_ON openmp)
+  endif ()
+
+  if (ENABLE_CUDA)
+    list (APPEND arg_DEPENDS_ON cuda)
+  endif ()
+
+  if (ENABLE_HIP)
+    list (APPEND arg_DEPENDS_ON hip)
+  endif ()
+
+  if (ENABLE_TBB)
+    list (APPEND arg_DEPENDS_ON tbb)
+  endif ()
+
+  blt_add_library(
+    NAME ${arg_NAME}
+    SOURCES ${arg_SOURCES}
+    DEPENDS_ON ${arg_DEPENDS_ON}
+    SHARED ${arg_SHARED}
+    )
+
+  #target_include_directories(${arg_NAME}
+  #PUBLIC
+  #$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>
+  #$<BUILD_INTERFACE:${PROJECT_BINARY_DIR}/include>
+  #$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/tpl/cub>
+  #$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/tpl/camp/include>
+  #$<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/tpl/rocPRIM/rocprim/include>
+  #$<INSTALL_INTERFACE:include>)
+
+endmacro(raja_add_plugin_library)
+
 macro(raja_add_test)
   set(options )
   set(singleValueArgs NAME)