Merging r318848:

------------------------------------------------------------------------
r318848 | hahnfeld | 2017-11-22 09:15:20 -0800 (Wed, 22 Nov 2017) | 7 lines

Fix for OMP doacross implementation on Power

Power has a weak consistency model so we need memory barriers to
make writes (both from runtime and from user code) available for
all threads.

Differential Revision: https://reviews.llvm.org/D40175
------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/openmp/branches/release_50@319057 91177308-0d34-0410-b5e6-96231b3b80d8

.arcconfig

@@ -0,0 +1,4 @@
+{
+  "project_id" : "openmp",
+  "conduit_uri" : "https://reviews.llvm.org/"
+}

.gitignore

@@ -0,0 +1,42 @@
+#==============================================================================#
+# This file specifies intentionally untracked files that git should ignore.
+# See: http://www.kernel.org/pub/software/scm/git/docs/gitignore.html
+#
+# This file is intentionally different from the output of `git svn show-ignore`,
+# as most of those are useless.
+#==============================================================================#
+
+#==============================================================================#
+# File extensions to be ignored anywhere in the tree.
+#==============================================================================#
+# Temp files created by most text editors.
+*~
+# Merge files created by git.
+*.orig
+# Byte compiled python modules.
+*.pyc
+# vim swap files
+.*.sw?
+.sw?
+#OS X specific files.
+.DS_store
+
+#==============================================================================#
+# Explicit files to ignore (only matches one).
+#==============================================================================#
+# Various tag programs
+tags
+/TAGS
+/GPATH
+/GRTAGS
+/GSYMS
+/GTAGS
+.gitusers
+
+#==============================================================================#
+# Directories to ignore (do not add trailing '/'s, they skip symlinks).
+#==============================================================================#
+runtime/exports
+
+# Nested build directory
+/build

CMakeLists.txt

@@ -3,3 +3,21 @@ cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
 set(OPENMP_LLVM_TOOLS_DIR "" CACHE PATH "Path to LLVM tools for testing")
 
 add_subdirectory(runtime)
+
+
+# The tests currently don't pass if the generic ELF plugin is built.
+# TODO: Fix the tests and enable libomptarget by default on supported
+#       architectures and platforms.
+set(ENABLE_LIBOMPTARGET OFF)
+# Currently libomptarget cannot be compiled on Windows or MacOS X.
+# Since the device plugins are only supported on Linux anyway,
+# there is no point in trying to compile libomptarget on other OSes.
+if (WIN32 OR ${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
+  set(ENABLE_LIBOMPTARGET OFF)
+endif()
+
+option(OPENMP_ENABLE_LIBOMPTARGET "Enable building libomptarget for offloading."
+       ${ENABLE_LIBOMPTARGET})
+if (OPENMP_ENABLE_LIBOMPTARGET)
+  add_subdirectory(libomptarget)
+endif()

libomptarget/Build_With_CMake.txt

@@ -0,0 +1,142 @@
+#
+#//===----------------------------------------------------------------------===//
+#//
+#//                     The LLVM Compiler Infrastructure
+#//
+#// This file is dual licensed under the MIT and the University of Illinois Open
+#// Source Licenses. See LICENSE.txt for details.
+#//
+#//===----------------------------------------------------------------------===//
+#
+
+=====================================================================
+How to Build the LLVM* OpenMP* Offloading Runtime Library using CMake
+=====================================================================
+
+==== Version of CMake required: v2.8.0 or above ====
+ 
+============================================
+How to call cmake initially, then repeatedly
+============================================
+- When calling cmake for the first time, all needed compiler options
+  must be specified on the command line.  After this initial call to
+  cmake, the compiler definitions must not be included for further calls
+  to cmake.  Other options can be specified on the command line multiple
+  times including all definitions in the Build options section below.
+- Example of configuring, building, reconfiguring, rebuilding:
+  $ mkdir build
+  $ cd build
+  $ cmake -DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++ ..  # Initial configuration
+  $ make
+  ...
+  $ make clean
+  $ cmake -DCMAKE_BUILD_TYPE=Debug ..                         # Second configuration
+  $ make
+  ...
+  $ rm -rf *
+  $ cmake -DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++ ..  # Third configuration
+  $ make
+- Notice in the example how the compiler definitions are only specified
+  for an empty build directory, but other Build options are used at any time.
+- The file CMakeCache.txt which is created after the first call to cmake
+  is a configuration file which holds all the values for the Build options.
+  These configuration values can be changed using a text editor to modify 
+  CMakeCache.txt as opposed to using definitions on the command line.
+- To have cmake create a particular type of build generator file simply 
+  inlude the -G <Generator name> option:
+  $ cmake -G "Unix Makefiles" ...
+  You can see a list of generators cmake supports by executing cmake with
+  no arguments and a list will be printed.
+
+=====================
+Instructions to Build
+=====================
+ $ cd libomptarget_top_level/ [ directory with plugins/ , deviceRTLs/ , etc. ]
+ $ mkdir build
+ $ cd build
+
+ [ Unix* Libraries ]
+ $ cmake -DCMAKE_C_COMPILER=<C Compiler> -DCMAKE_CXX_COMPILER=<C++ Compiler> ..
+
+ $ make
+ $ make install
+
+===========
+Tests
+===========
+After the library has been built, there are optional tests that can be 
+performed.  Some will be skipped based upon the platform.
+To run the tests,
+$ make check-libomptarget
+
+=============
+CMake options
+=============
+-DCMAKE_C_COMPILER=<C compiler name>
+Specify the C compiler
+
+-DCMAKE_CXX_COMPILER=<C++ compiler name>
+Specify the C++ compiler
+
+==== First values listed are the default value ====
+-DCMAKE_BUILD_TYPE=Release|Debug|RelWithDebInfo
+Build type can be Release, Debug, or RelWithDebInfo.
+
+-DLIBOMPTARGET_ENABLE_WERROR=true|false
+Should consider warnings as errors.
+
+-DLIBOMPTARGET_LLVM_LIT_EXECUTABLE=""
+Full path to the llvm-lit tool. Required for testing in out-of-tree builds.
+
+-DLIBOMPTARGET_FILECHECK_EXECUTABLE=""
+Full path to the FileCheck tool. Required for testing in out-of-tree builds.
+
+-DLIBOMPTARGET_OPENMP_HEADER_FOLDER=""
+Path of the folder that contains omp.h. This is required for testing 
+out-of-tree builds.
+
+-DLIBOMPTARGET_OPENMP_HOST_RTL_FOLDER=""
+Path of the folder that contains libomp.so. This is required for testing 
+out-of-tree builds.
+
+==== NVPTX device RTL specific ====
+-DLIBOMPTARGET_NVPTX_ENABLE_BCLIB=false|true
+Enable CUDA LLVM bitcode offloading device RTL. This is used for
+link time optimization of the omp runtime and application code.
+
+-DLIBOMPTARGET_NVPTX_CUDA_COMPILER=<CUDA compiler name>
+Location of a CUDA compiler capable of emitting LLVM bitcode.
+Currently only the Clang compiler is supported. This is only used
+when building the CUDA LLVM bitcode offloading device RTL. If
+unspecified, the default paths are inspected.
+
+-DLIBOMPTARGET_NVPTX_BC_LINKER=<LLVM bitcode linker>
+Location of a linker capable of linking LLVM bitcode objects.
+This is only used when building the CUDA LLVM bitcode offloading
+device RTL. If unspecified, the default paths are inspected.
+
+-DLIBOMPTARGET_NVPTX_ALTERNATE_HOST_COMPILER=""
+Host compiler to use with NVCC. This compiler is not going to be used to produce
+any binary. Instead, this is used to overcome the input compiler checks done by
+NVCC. E.g. if using a default host compiler that is not compatible with NVCC,
+this option can be use to pass to NVCC a valid compiler to avoid the error. 
+
+-DLIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY="35"
+Comma-separated list of CUDA compute capabilities that should be supported by
+the NVPTX device RTL. E.g. for compute capabilities 3.0 and 3.5, the option 
+"30,35" should be used.
+
+=======================
+Example usages of CMake
+=======================
+---- Typical usage ----
+cmake -DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++ ..
+cmake -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ ..
+
+---- Request an NVPTX runtime library that supports compute capability 5.0 ----
+cmake -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DLIBOMPTARGET_NVPTX_COMPUTE_CAPABILITY="50"
+
+=========
+Footnotes
+=========
+[*] Other names and brands may be claimed as the property of others.

libomptarget/CMakeLists.txt

@@ -0,0 +1,119 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build offloading library libomptarget.so.
+#
+##===----------------------------------------------------------------------===##
+
+# CMAKE libomptarget
+cmake_minimum_required(VERSION 2.8 FATAL_ERROR)
+
+# Add cmake directory to search for custom cmake functions.
+set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/Modules ${CMAKE_MODULE_PATH})
+
+# Standalone build or part of LLVM?
+set(LIBOMPTARGET_STANDALONE_BUILD FALSE)
+if("${CMAKE_SOURCE_DIR}" STREQUAL "${CMAKE_CURRENT_SOURCE_DIR}" OR
+   "${CMAKE_SOURCE_DIR}/libomptarget" STREQUAL "${CMAKE_CURRENT_SOURCE_DIR}")
+  project(libomptarget C CXX)
+  set(LIBOMPTARGET_STANDALONE_BUILD TRUE)
+endif()
+  
+  
+if(${LIBOMPTARGET_STANDALONE_BUILD})
+  set(LIBOMPTARGET_ENABLE_WERROR FALSE CACHE BOOL
+    "Enable -Werror flags to turn warnings into errors for supporting compilers.")
+  # CMAKE_BUILD_TYPE was not defined, set default to Release
+  if(NOT CMAKE_BUILD_TYPE)
+    set(CMAKE_BUILD_TYPE Release)
+  endif()
+  set(LIBOMPTARGET_LIBDIR_SUFFIX "" CACHE STRING
+    "suffix of lib installation directory, e.g. 64 => lib64")
+else()
+  set(LIBOMPTARGET_ENABLE_WERROR ${LLVM_ENABLE_WERROR})
+  # If building in tree, we honor the same install suffix LLVM uses.
+  set(LIBOMPTARGET_LIBDIR_SUFFIX ${LLVM_LIBDIR_SUFFIX})
+endif()
+
+# Compiler flag checks.
+include(config-ix)
+
+# Message utilities.
+include(LibomptargetUtils)
+
+# Get dependencies for the different components of the project.
+include(LibomptargetGetDependencies)
+
+# This is a list of all the targets that are supported/tested right now.
+set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} aarch64-unknown-linux-gnu")
+set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} powerpc64le-ibm-linux-gnu")
+set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} powerpc64-ibm-linux-gnu")
+set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} x86_64-pc-linux-gnu")
+set (LIBOMPTARGET_ALL_TARGETS "${LIBOMPTARGET_ALL_TARGETS} nvptx64-nvidia-cuda")
+
+# Once the plugins for the different targets are validated, they will be added to
+# the list of supported targets in the current system.
+set (LIBOMPTARGET_SYSTEM_TARGETS "")
+
+# Set base directories - required for lit to locate the tests.
+set(LIBOMPTARGET_BASE_DIR ${CMAKE_CURRENT_SOURCE_DIR})
+set(LIBOMPTARGET_BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR})
+
+# We need C++11 support.
+if(LIBOMPTARGET_HAVE_STD_CPP11_FLAG)
+  
+  libomptarget_say("Building offloading runtime library libomptarget.")
+
+  # Enable support for C++11.
+  add_definitions(-std=c++11)
+  
+  if(LIBOMPTARGET_ENABLE_WERROR AND LIBOMPTARGET_HAVE_WERROR_FLAG)
+    add_definitions(-Werror)
+  endif()
+  
+  # If building this library in debug mode, we define a macro to enable
+  # dumping progress messages at runtime.
+  string( TOLOWER "${CMAKE_BUILD_TYPE}" LIBOMPTARGET_CMAKE_BUILD_TYPE)
+  if(LIBOMPTARGET_CMAKE_BUILD_TYPE MATCHES debug)
+    add_definitions(-DOMPTARGET_DEBUG)
+    add_definitions(-g)
+    add_definitions(-O0)
+  endif()
+  
+  set(src_files
+    src/omptarget.cpp
+  )
+  
+  include_directories(src/)
+  
+  # Build libomptarget library with libdl dependency.
+  add_library(omptarget SHARED ${src_files})
+  target_link_libraries(omptarget
+    ${CMAKE_DL_LIBS}
+    "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/exports")
+  
+  # Install libomptarget under the lib destination folder.
+  install(TARGETS omptarget LIBRARY DESTINATION lib${LIBOMPTARGET_LIBDIR_SUFFIX})
+  
+  # Retrieve the path to the resulting library so that it can be used for 
+  # testing.
+  get_target_property(LIBOMPTARGET_LIBRARY_DIR omptarget LIBRARY_OUTPUT_DIRECTORY)
+  if(NOT LIBOMPTARGET_LIBRARY_DIR)
+    set(LIBOMPTARGET_LIBRARY_DIR ${CMAKE_CURRENT_BINARY_DIR})
+  endif()
+
+  # Build offloading plugins and device RTLs if they are available.
+  add_subdirectory(plugins)
+  
+  # Add tests.
+  add_subdirectory(test)
+  
+else(LIBOMPTARGET_HAVE_STD_CPP11_FLAG)
+  libomptarget_say("Not building offloading runtime library libomptarget: host compiler must have c++11 support.")
+endif(LIBOMPTARGET_HAVE_STD_CPP11_FLAG)

libomptarget/README.txt

@@ -0,0 +1,74 @@
+
+    README for the LLVM* OpenMP* Offloading Runtime Library (libomptarget)
+    ======================================================================
+
+How to Build the LLVM* OpenMP* Offloading Runtime Library (libomptarget)
+========================================================================
+In-tree build:
+
+$ cd where-you-want-to-live
+Check out openmp (libomptarget lives under ./libomptarget) into llvm/projects
+$ cd where-you-want-to-build
+$ mkdir build && cd build
+$ cmake path/to/llvm -DCMAKE_C_COMPILER=<C compiler> -DCMAKE_CXX_COMPILER=<C++ compiler>
+$ make omptarget
+
+Out-of-tree build:
+
+$ cd where-you-want-to-live
+Check out openmp (libomptarget lives under ./libomptarget)
+$ cd where-you-want-to-live/openmp/libomptarget
+$ mkdir build && cd build
+$ cmake path/to/openmp -DCMAKE_C_COMPILER=<C compiler> -DCMAKE_CXX_COMPILER=<C++ compiler>
+$ make
+
+For details about building, please look at Build_With_CMake.txt
+
+Architectures Supported
+=======================
+The current library has been only tested in Linux operating system and the 
+following host architectures: 
+* Intel(R) 64 architecture
+* IBM(R) Power architecture (big endian)
+* IBM(R) Power architecture (little endian)
+* ARM(R) AArch64 architecture (little endian)
+
+The currently supported offloading device architectures are:
+* Intel(R) 64 architecture (generic 64-bit plugin - mostly for testing purposes)
+* IBM(R) Power architecture (big endian) (generic 64-bit plugin - mostly for testing purposes)
+* IBM(R) Power architecture (little endian) (generic 64-bit plugin - mostly for testing purposes)
+* ARM(R) AArch64 architecture (little endian) (generic 64-bit plugin - mostly for testing purposes)
+* CUDA(R) enabled 64-bit NVIDIA(R) GPU architectures
+
+Supported RTL Build Configurations
+==================================
+Supported Architectures: Intel(R) 64, IBM(R) Power 7 and Power 8
+
+              ---------------------------
+              |   gcc      |   clang    |
+--------------|------------|------------|
+| Linux* OS   |  Yes(1)    |  Yes(2)    |
+-----------------------------------------
+
+(1) gcc version 4.8.2 or later is supported.
+(2) clang version 3.7 or later is supported.
+
+
+Front-end Compilers that work with this RTL
+===========================================
+
+The following compilers are known to do compatible code generation for
+this RTL: 
+  - clang (from https://github.com/clang-ykt )
+  - clang (development branch at http://clang.llvm.org - several features still 
+    under development)
+
+-----------------------------------------------------------------------
+
+Notices
+=======
+This library and related compiler support is still under development, so the 
+employed interface is likely to change in the future.
+
+*Other names and brands may be claimed as the property of others.
+

libomptarget/cmake/Modules/LibomptargetGetDependencies.cmake

@@ -0,0 +1,124 @@
+#
+#//===----------------------------------------------------------------------===//
+#//
+#//                     The LLVM Compiler Infrastructure
+#//
+#// This file is dual licensed under the MIT and the University of Illinois Open
+#// Source Licenses. See LICENSE.txt for details.
+#//
+#//===----------------------------------------------------------------------===//
+#
+
+# Try to detect in the system several dependencies required by the different
+# components of libomptarget. These are the dependencies we have:
+#
+# libelf : required by some targets to handle the ELF files at runtime.
+# libffi : required to launch target kernels given function and argument 
+#          pointers.
+# CUDA : required to control offloading to NVIDIA GPUs.
+
+include (FindPackageHandleStandardArgs)
+
+################################################################################
+# Looking for libelf...
+################################################################################
+
+find_path (
+  LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIR
+  NAMES
+    libelf.h
+  PATHS
+    /usr/include
+    /usr/local/include
+    /opt/local/include
+    /sw/include
+    ENV CPATH
+  PATH_SUFFIXES
+    libelf)
+
+find_library (
+  LIBOMPTARGET_DEP_LIBELF_LIBRARIES
+  NAMES
+    elf
+  PATHS
+    /usr/lib
+    /usr/local/lib
+    /opt/local/lib
+    /sw/lib
+    ENV LIBRARY_PATH
+    ENV LD_LIBRARY_PATH)
+    
+set(LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS ${LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIR})
+find_package_handle_standard_args(
+  LIBOMPTARGET_DEP_LIBELF 
+  DEFAULT_MSG
+  LIBOMPTARGET_DEP_LIBELF_LIBRARIES
+  LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS)
+
+mark_as_advanced(
+  LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS 
+  LIBOMPTARGET_DEP_LIBELF_LIBRARIES)
+  
+################################################################################
+# Looking for libffi...
+################################################################################
+find_package(PkgConfig)
+
+pkg_check_modules(LIBOMPTARGET_SEARCH_LIBFFI QUIET libffi)
+
+find_path (
+  LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIR
+  NAMES
+    ffi.h
+  HINTS
+    ${LIBOMPTARGET_SEARCH_LIBFFI_INCLUDEDIR}
+    ${LIBOMPTARGET_SEARCH_LIBFFI_INCLUDE_DIRS}
+  PATHS
+    /usr/include
+    /usr/local/include
+    /opt/local/include
+    /sw/include
+    ENV CPATH)
+
+# Don't bother look for the library if the header files were not found.
+if (LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIR)
+  find_library (
+      LIBOMPTARGET_DEP_LIBFFI_LIBRARIES
+    NAMES
+      ffi
+    HINTS
+      ${LIBOMPTARGET_SEARCH_LIBFFI_LIBDIR}
+      ${LIBOMPTARGET_SEARCH_LIBFFI_LIBRARY_DIRS}
+    PATHS
+      /usr/lib
+      /usr/local/lib
+      /opt/local/lib
+      /sw/lib
+      ENV LIBRARY_PATH
+      ENV LD_LIBRARY_PATH)
+endif()
+
+set(LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS ${LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIR})
+find_package_handle_standard_args(
+  LIBOMPTARGET_DEP_LIBFFI 
+  DEFAULT_MSG
+  LIBOMPTARGET_DEP_LIBFFI_LIBRARIES
+  LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS)
+
+mark_as_advanced(
+  LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIRS 
+  LIBOMPTARGET_DEP_LIBFFI_LIBRARIES)
+  
+################################################################################
+# Looking for CUDA...
+################################################################################
+find_package(CUDA QUIET)
+
+set(LIBOMPTARGET_DEP_CUDA_FOUND ${CUDA_FOUND})
+set(LIBOMPTARGET_DEP_CUDA_LIBRARIES ${CUDA_LIBRARIES})
+set(LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS ${CUDA_INCLUDE_DIRS})
+
+mark_as_advanced(
+  LIBOMPTARGET_DEP_CUDA_FOUND 
+  LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS
+  LIBOMPTARGET_DEP_CUDA_LIBRARIES)

libomptarget/cmake/Modules/LibomptargetUtils.cmake

@@ -0,0 +1,28 @@
+#
+#//===----------------------------------------------------------------------===//
+#//
+#//                     The LLVM Compiler Infrastructure
+#//
+#// This file is dual licensed under the MIT and the University of Illinois Open
+#// Source Licenses. See LICENSE.txt for details.
+#//
+#//===----------------------------------------------------------------------===//
+#
+
+# void libomptarget_say(string message_to_user);
+# - prints out message_to_user
+macro(libomptarget_say message_to_user)
+  message(STATUS "LIBOMPTARGET: ${message_to_user}")
+endmacro()
+
+# void libomptarget_warning_say(string message_to_user);
+# - prints out message_to_user with a warning
+macro(libomptarget_warning_say message_to_user)
+  message(WARNING "LIBOMPTARGET: ${message_to_user}")
+endmacro()
+
+# void libomptarget_error_say(string message_to_user);
+# - prints out message_to_user with an error and exits cmake
+macro(libomptarget_error_say message_to_user)
+  message(FATAL_ERROR "LIBOMPTARGET: ${message_to_user}")
+endmacro()

libomptarget/cmake/Modules/config-ix.cmake

@@ -0,0 +1,17 @@
+#
+#//===----------------------------------------------------------------------===//
+#//
+#//                     The LLVM Compiler Infrastructure
+#//
+#// This file is dual licensed under the MIT and the University of Illinois Open
+#// Source Licenses. See LICENSE.txt for details.
+#//
+#//===----------------------------------------------------------------------===//
+#
+
+include(CheckCCompilerFlag)
+include(CheckCXXCompilerFlag)
+
+# Checking C, CXX
+check_cxx_compiler_flag(-std=c++11 LIBOMPTARGET_HAVE_STD_CPP11_FLAG)
+check_c_compiler_flag(-Werror LIBOMPTARGET_HAVE_WERROR_FLAG)

libomptarget/exports

@@ -0,0 +1,28 @@
+VERS1.0 {
+  global:
+    __tgt_register_lib;
+    __tgt_unregister_lib;
+    __tgt_target_data_begin;
+    __tgt_target_data_end;
+    __tgt_target_data_update;
+    __tgt_target;
+    __tgt_target_teams;
+    __tgt_target_data_begin_nowait;
+    __tgt_target_data_end_nowait;
+    __tgt_target_data_update_nowait;
+    __tgt_target_nowait;
+    __tgt_target_teams_nowait;
+    omp_get_num_devices;
+    omp_get_initial_device;
+    omp_target_alloc;
+    omp_target_free;
+    omp_target_is_present;
+    omp_target_memcpy;
+    omp_target_memcpy_rect;
+    omp_target_associate_ptr;
+    omp_target_disassociate_ptr;
+    __kmpc_push_target_tripcount;
+  local:
+    *;
+};
+

libomptarget/plugins/CMakeLists.txt

@@ -0,0 +1,72 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build plugins for the user system if available.
+#
+##===----------------------------------------------------------------------===##
+
+# void build_generic_elf64(string tmachine, string tmachine_name, string tmachine_libname, string elf_machine_id);
+# - build a plugin for an ELF based generic 64-bit target based on libffi.
+# - tmachine: name of the machine processor as used in the cmake build system.
+# - tmachine_name: name of the machine to be printed with the debug messages.
+# - tmachine_libname: machine name to be appended to the plugin library name.
+macro(build_generic_elf64 tmachine tmachine_name tmachine_libname tmachine_triple elf_machine_id)
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "${tmachine}$")
+  if(LIBOMPTARGET_DEP_LIBELF_FOUND)
+    if(LIBOMPTARGET_DEP_LIBFFI_FOUND)
+    
+      libomptarget_say("Building ${tmachine_name} offloading plugin.")
+    
+      include_directories(${LIBOMPTARGET_DEP_LIBFFI_INCLUDE_DIR})
+      include_directories(${LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIR})
+      
+      # Define macro to be used as prefix of the runtime messages for this target.
+      add_definitions("-DTARGET_NAME=${tmachine_name}")
+      
+      # Define macro with the ELF ID for this target.
+      add_definitions("-DTARGET_ELF_ID=${elf_machine_id}")
+    
+      add_library("omptarget.rtl.${tmachine_libname}" SHARED 
+        ${CMAKE_CURRENT_SOURCE_DIR}/../generic-elf-64bit/src/rtl.cpp)
+        
+      # Install plugin under the lib destination folder.
+      install(TARGETS "omptarget.rtl.${tmachine_libname}" 
+        LIBRARY DESTINATION lib${LIBOMPTARGET_LIBDIR_SUFFIX})
+        
+      target_link_libraries(
+        "omptarget.rtl.${tmachine_libname}"
+        ${LIBOMPTARGET_DEP_LIBFFI_LIBRARIES} 
+        ${LIBOMPTARGET_DEP_LIBELF_LIBRARIES}
+        dl
+        "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/../exports")
+    
+      # Report to the parent scope that we are building a plugin.
+      set(LIBOMPTARGET_SYSTEM_TARGETS 
+        "${LIBOMPTARGET_SYSTEM_TARGETS} ${tmachine_triple}" PARENT_SCOPE)
+      
+    else(LIBOMPTARGET_DEP_LIBFFI_FOUND)
+      libomptarget_say("Not building ${tmachine_name} offloading plugin: libffi dependency not found.")
+    endif(LIBOMPTARGET_DEP_LIBFFI_FOUND)
+  else(LIBOMPTARGET_DEP_LIBELF_FOUND)
+    libomptarget_say("Not building ${tmachine_name} offloading plugin: libelf dependency not found.")
+  endif(LIBOMPTARGET_DEP_LIBELF_FOUND)
+else()
+  libomptarget_say("Not building ${tmachine_name} offloading plugin: machine not found in the system.")
+endif()
+endmacro()
+
+add_subdirectory(aarch64)
+add_subdirectory(cuda)
+add_subdirectory(ppc64)
+add_subdirectory(ppc64le)
+add_subdirectory(x86_64)
+
+# Make sure the parent scope can see the plugins that will be created.
+set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)
+

libomptarget/plugins/aarch64/CMakeLists.txt

@@ -0,0 +1,18 @@
+##===----------------------------------------------------------------------===##
+#
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+#
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for an aarch64 machine if available.
+#
+##===----------------------------------------------------------------------===##
+
+if(CMAKE_SYSTEM_NAME MATCHES "Linux")
+  build_generic_elf64("aarch64" "aarch64" "aarch64" "aarch64-unknown-linux-gnu" "183")
+else()
+ libomptarget_say("Not building aarch64 offloading plugin: machine not found in the system.")
+endif()

libomptarget/plugins/common/elf_common.c

@@ -0,0 +1,73 @@
+//===-- elf_common.c - Common ELF functionality -------------------*- C -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Common ELF functionality for target plugins.
+// Must be included in the plugin source file AFTER omptarget.h has been
+// included and macro DP(...) has been defined.
+// .
+//
+//===----------------------------------------------------------------------===//
+
+#if !(defined(_OMPTARGET_H_) && defined(DP))
+#error Include elf_common.c in the plugin source AFTER omptarget.h has been\
+ included and macro DP(...) has been defined.
+#endif
+
+#include <elf.h>
+#include <libelf.h>
+
+// Check whether an image is valid for execution on target_id
+static inline int32_t elf_check_machine(__tgt_device_image *image,
+    uint16_t target_id) {
+
+  // Is the library version incompatible with the header file?
+  if (elf_version(EV_CURRENT) == EV_NONE) {
+    DP("Incompatible ELF library!\n");
+    return 0;
+  }
+
+  char *img_begin = (char *)image->ImageStart;
+  char *img_end = (char *)image->ImageEnd;
+  size_t img_size = img_end - img_begin;
+
+  // Obtain elf handler
+  Elf *e = elf_memory(img_begin, img_size);
+  if (!e) {
+    DP("Unable to get ELF handle: %s!\n", elf_errmsg(-1));
+    return 0;
+  }
+
+  // Check if ELF is the right kind.
+  if (elf_kind(e) != ELF_K_ELF) {
+    DP("Unexpected ELF type!\n");
+    return 0;
+  }
+  Elf64_Ehdr *eh64 = elf64_getehdr(e);
+  Elf32_Ehdr *eh32 = elf32_getehdr(e);
+
+  if (!eh64 && !eh32) {
+    DP("Unable to get machine ID from ELF file!\n");
+    elf_end(e);
+    return 0;
+  }
+
+  uint16_t MachineID;
+  if (eh64 && !eh32)
+    MachineID = eh64->e_machine;
+  else if (eh32 && !eh64)
+    MachineID = eh32->e_machine;
+  else {
+    DP("Ambiguous ELF header!\n");
+    elf_end(e);
+    return 0;
+  }
+
+  elf_end(e);
+  return MachineID == target_id;
+}

libomptarget/plugins/cuda/CMakeLists.txt

@@ -0,0 +1,50 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for a CUDA machine if available.
+#
+##===----------------------------------------------------------------------===##
+if(LIBOMPTARGET_DEP_LIBELF_FOUND)
+  if(LIBOMPTARGET_DEP_CUDA_FOUND)
+    if(CMAKE_SYSTEM_PROCESSOR MATCHES "(x86_64)|(ppc64le)$" AND CMAKE_SYSTEM_NAME MATCHES "Linux")
+    
+      libomptarget_say("Building CUDA offloading plugin.")
+    
+      # Define the suffix for the runtime messaging dumps.
+      add_definitions(-DTARGET_NAME=CUDA)
+    
+      if(LIBOMPTARGET_CMAKE_BUILD_TYPE MATCHES debug)
+          add_definitions(-DCUDA_ERROR_REPORT)
+      endif()
+      
+      include_directories(${LIBOMPTARGET_DEP_CUDA_INCLUDE_DIRS})
+      include_directories(${LIBOMPTARGET_DEP_LIBELF_INCLUDE_DIRS})
+    
+      add_library(omptarget.rtl.cuda SHARED src/rtl.cpp)
+      
+      # Install plugin under the lib destination folder.
+      install(TARGETS omptarget.rtl.cuda LIBRARY DESTINATION lib${LIBOMPTARGET_LIBDIR_SUFFIX})
+      
+      target_link_libraries(omptarget.rtl.cuda 
+        ${LIBOMPTARGET_DEP_CUDA_LIBRARIES} 
+        cuda 
+        ${LIBOMPTARGET_DEP_LIBELF_LIBRARIES}
+        "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/../exports")
+    
+      # Report to the parent scope that we are building a plugin for CUDA.
+      set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS} nvptx64-nvidia-cuda" PARENT_SCOPE)
+    else()
+      libomptarget_say("Not building CUDA offloading plugin: only support CUDA in Linux x86_64 or ppc64le hosts.")
+    endif()
+  else()
+    libomptarget_say("Not building CUDA offloading plugin: CUDA not found in system.")
+  endif()
+else(LIBOMPTARGET_DEP_LIBELF_FOUND)
+  libomptarget_say("Not building CUDA offloading plugin: libelf dependency not found.")
+endif(LIBOMPTARGET_DEP_LIBELF_FOUND)

libomptarget/plugins/cuda/src/rtl.cpp

@@ -0,0 +1,694 @@
+//===----RTLs/cuda/src/rtl.cpp - Target RTLs Implementation ------- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// RTL for CUDA machine
+//
+//===----------------------------------------------------------------------===//
+
+#include <cassert>
+#include <cstddef>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <list>
+#include <string>
+#include <vector>
+
+#include "omptargetplugin.h"
+
+#ifndef TARGET_NAME
+#define TARGET_NAME CUDA
+#endif
+
+#define GETNAME2(name) #name
+#define GETNAME(name) GETNAME2(name)
+#define DP(...) DEBUGP("Target " GETNAME(TARGET_NAME) " RTL", __VA_ARGS__)
+
+#include "../../common/elf_common.c"
+
+// Utility for retrieving and printing CUDA error string.
+#ifdef CUDA_ERROR_REPORT
+#define CUDA_ERR_STRING(err)                                                   \
+  do {                                                                         \
+    const char *errStr;                                                        \
+    cuGetErrorString(err, &errStr);                                            \
+    DP("CUDA error is: %s\n", errStr);                                         \
+  } while (0)
+#else
+#define CUDA_ERR_STRING(err)                                                   \
+  {}
+#endif
+
+/// Keep entries table per device.
+struct FuncOrGblEntryTy {
+  __tgt_target_table Table;
+  std::vector<__tgt_offload_entry> Entries;
+};
+
+enum ExecutionModeType {
+  SPMD, // constructors, destructors,
+        // combined constructs (`teams distribute parallel for [simd]`)
+  GENERIC, // everything else
+  NONE
+};
+
+/// Use a single entity to encode a kernel and a set of flags
+struct KernelTy {
+  CUfunction Func;
+
+  // execution mode of kernel
+  // 0 - SPMD mode (without master warp)
+  // 1 - Generic mode (with master warp)
+  int8_t ExecutionMode;
+
+  KernelTy(CUfunction _Func, int8_t _ExecutionMode)
+      : Func(_Func), ExecutionMode(_ExecutionMode) {}
+};
+
+/// List that contains all the kernels.
+/// FIXME: we may need this to be per device and per library.
+std::list<KernelTy> KernelsList;
+
+/// Class containing all the device information.
+class RTLDeviceInfoTy {
+  std::vector<FuncOrGblEntryTy> FuncGblEntries;
+
+public:
+  int NumberOfDevices;
+  std::vector<CUmodule> Modules;
+  std::vector<CUcontext> Contexts;
+
+  // Device properties
+  std::vector<int> ThreadsPerBlock;
+  std::vector<int> BlocksPerGrid;
+  std::vector<int> WarpSize;
+
+  // OpenMP properties
+  std::vector<int> NumTeams;
+  std::vector<int> NumThreads;
+
+  // OpenMP Environment properties
+  int EnvNumTeams;
+  int EnvTeamLimit;
+
+  //static int EnvNumThreads;
+  static const int HardTeamLimit = 1<<16; // 64k
+  static const int HardThreadLimit = 1024;
+  static const int DefaultNumTeams = 128;
+  static const int DefaultNumThreads = 128;
+
+  // Record entry point associated with device
+  void addOffloadEntry(int32_t device_id, __tgt_offload_entry entry) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    E.Entries.push_back(entry);
+  }
+
+  // Return true if the entry is associated with device
+  bool findOffloadEntry(int32_t device_id, void *addr) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    for (auto &it : E.Entries) {
+      if (it.addr == addr)
+        return true;
+    }
+
+    return false;
+  }
+
+  // Return the pointer to the target entries table
+  __tgt_target_table *getOffloadEntriesTable(int32_t device_id) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    int32_t size = E.Entries.size();
+
+    // Table is empty
+    if (!size)
+      return 0;
+
+    __tgt_offload_entry *begin = &E.Entries[0];
+    __tgt_offload_entry *end = &E.Entries[size - 1];
+
+    // Update table info according to the entries and return the pointer
+    E.Table.EntriesBegin = begin;
+    E.Table.EntriesEnd = ++end;
+
+    return &E.Table;
+  }
+
+  // Clear entries table for a device
+  void clearOffloadEntriesTable(int32_t device_id) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+    E.Entries.clear();
+    E.Table.EntriesBegin = E.Table.EntriesEnd = 0;
+  }
+
+  RTLDeviceInfoTy() {
+    DP("Start initializing CUDA\n");
+
+    CUresult err = cuInit(0);
+    if (err != CUDA_SUCCESS) {
+      DP("Error when initializing CUDA\n");
+      CUDA_ERR_STRING(err);
+      return;
+    }
+
+    NumberOfDevices = 0;
+
+    err = cuDeviceGetCount(&NumberOfDevices);
+    if (err != CUDA_SUCCESS) {
+      DP("Error when getting CUDA device count\n");
+      CUDA_ERR_STRING(err);
+      return;
+    }
+
+    if (NumberOfDevices == 0) {
+      DP("There are no devices supporting CUDA.\n");
+      return;
+    }
+
+    FuncGblEntries.resize(NumberOfDevices);
+    Contexts.resize(NumberOfDevices);
+    ThreadsPerBlock.resize(NumberOfDevices);
+    BlocksPerGrid.resize(NumberOfDevices);
+    WarpSize.resize(NumberOfDevices);
+    NumTeams.resize(NumberOfDevices);
+    NumThreads.resize(NumberOfDevices);
+
+    // Get environment variables regarding teams
+    char *envStr = getenv("OMP_TEAM_LIMIT");
+    if (envStr) {
+      // OMP_TEAM_LIMIT has been set
+      EnvTeamLimit = std::stoi(envStr);
+      DP("Parsed OMP_TEAM_LIMIT=%d\n", EnvTeamLimit);
+    } else {
+      EnvTeamLimit = -1;
+    }
+    envStr = getenv("OMP_NUM_TEAMS");
+    if (envStr) {
+      // OMP_NUM_TEAMS has been set
+      EnvNumTeams = std::stoi(envStr);
+      DP("Parsed OMP_NUM_TEAMS=%d\n", EnvNumTeams);
+    } else {
+      EnvNumTeams = -1;
+    }
+  }
+
+  ~RTLDeviceInfoTy() {
+    // Close modules
+    for (auto &module : Modules)
+      if (module) {
+        CUresult err = cuModuleUnload(module);
+        if (err != CUDA_SUCCESS) {
+          DP("Error when unloading CUDA module\n");
+          CUDA_ERR_STRING(err);
+        }
+      }
+
+    // Destroy contexts
+    for (auto &ctx : Contexts)
+      if (ctx) {
+        CUresult err = cuCtxDestroy(ctx);
+        if (err != CUDA_SUCCESS) {
+          DP("Error when destroying CUDA context\n");
+          CUDA_ERR_STRING(err);
+        }
+      }
+  }
+};
+
+static RTLDeviceInfoTy DeviceInfo;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *image) {
+  return elf_check_machine(image, 190); // EM_CUDA = 190.
+}
+
+int32_t __tgt_rtl_number_of_devices() { return DeviceInfo.NumberOfDevices; }
+
+int32_t __tgt_rtl_init_device(int32_t device_id) {
+
+  CUdevice cuDevice;
+  DP("Getting device %d\n", device_id);
+  CUresult err = cuDeviceGet(&cuDevice, device_id);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when getting CUDA device with id = %d\n", device_id);
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  // Create the context and save it to use whenever this device is selected.
+  err = cuCtxCreate(&DeviceInfo.Contexts[device_id], CU_CTX_SCHED_BLOCKING_SYNC,
+                    cuDevice);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when creating a CUDA context\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  // scan properties to determine number of threads/block and blocks/grid.
+  struct cudaDeviceProp Properties;
+  cudaError_t error = cudaGetDeviceProperties(&Properties, device_id);
+  if (error != cudaSuccess) {
+    DP("Error getting device Properties, use defaults\n");
+    DeviceInfo.BlocksPerGrid[device_id] = RTLDeviceInfoTy::DefaultNumTeams;
+    DeviceInfo.ThreadsPerBlock[device_id] = RTLDeviceInfoTy::DefaultNumThreads;
+    DeviceInfo.WarpSize[device_id] = 32;
+  } else {
+    // Get blocks per grid
+    if (Properties.maxGridSize[0] <= RTLDeviceInfoTy::HardTeamLimit) {
+      DeviceInfo.BlocksPerGrid[device_id] = Properties.maxGridSize[0];
+      DP("Using %d CUDA blocks per grid\n", Properties.maxGridSize[0]);
+    } else {
+      DeviceInfo.BlocksPerGrid[device_id] = RTLDeviceInfoTy::HardTeamLimit;
+      DP("Max CUDA blocks per grid %d exceeds the hard team limit %d, capping "
+          "at the hard limit\n", Properties.maxGridSize[0],
+          RTLDeviceInfoTy::HardTeamLimit);
+    }
+
+    // Get threads per block, exploit threads only along x axis
+    if (Properties.maxThreadsDim[0] <= RTLDeviceInfoTy::HardThreadLimit) {
+      DeviceInfo.ThreadsPerBlock[device_id] = Properties.maxThreadsDim[0];
+      DP("Using %d CUDA threads per block\n", Properties.maxThreadsDim[0]);
+      if (Properties.maxThreadsDim[0] < Properties.maxThreadsPerBlock) {
+        DP("(fewer than max per block along all xyz dims %d)\n",
+            Properties.maxThreadsPerBlock);
+      }
+    } else {
+      DeviceInfo.ThreadsPerBlock[device_id] = RTLDeviceInfoTy::HardThreadLimit;
+      DP("Max CUDA threads per block %d exceeds the hard thread limit %d, "
+          "capping at the hard limit\n", Properties.maxThreadsDim[0],
+          RTLDeviceInfoTy::HardThreadLimit);
+    }
+
+    // Get warp size
+    DeviceInfo.WarpSize[device_id] = Properties.warpSize;
+  }
+
+  // Adjust teams to the env variables
+  if (DeviceInfo.EnvTeamLimit > 0 &&
+      DeviceInfo.BlocksPerGrid[device_id] > DeviceInfo.EnvTeamLimit) {
+    DeviceInfo.BlocksPerGrid[device_id] = DeviceInfo.EnvTeamLimit;
+    DP("Capping max CUDA blocks per grid to OMP_TEAM_LIMIT=%d\n",
+        DeviceInfo.EnvTeamLimit);
+  }
+
+  DP("Max number of CUDA blocks %d, threads %d & warp size %d\n",
+     DeviceInfo.BlocksPerGrid[device_id], DeviceInfo.ThreadsPerBlock[device_id],
+     DeviceInfo.WarpSize[device_id]);
+
+  // Set default number of teams
+  if (DeviceInfo.EnvNumTeams > 0) {
+    DeviceInfo.NumTeams[device_id] = DeviceInfo.EnvNumTeams;
+    DP("Default number of teams set according to environment %d\n",
+        DeviceInfo.EnvNumTeams);
+  } else {
+    DeviceInfo.NumTeams[device_id] = RTLDeviceInfoTy::DefaultNumTeams;
+    DP("Default number of teams set according to library's default %d\n",
+        RTLDeviceInfoTy::DefaultNumTeams);
+  }
+  if (DeviceInfo.NumTeams[device_id] > DeviceInfo.BlocksPerGrid[device_id]) {
+    DeviceInfo.NumTeams[device_id] = DeviceInfo.BlocksPerGrid[device_id];
+    DP("Default number of teams exceeds device limit, capping at %d\n",
+        DeviceInfo.BlocksPerGrid[device_id]);
+  }
+
+  // Set default number of threads
+  DeviceInfo.NumThreads[device_id] = RTLDeviceInfoTy::DefaultNumThreads;
+  DP("Default number of threads set according to library's default %d\n",
+          RTLDeviceInfoTy::DefaultNumThreads);
+  if (DeviceInfo.NumThreads[device_id] >
+      DeviceInfo.ThreadsPerBlock[device_id]) {
+    DeviceInfo.NumTeams[device_id] = DeviceInfo.ThreadsPerBlock[device_id];
+    DP("Default number of threads exceeds device limit, capping at %d\n",
+        DeviceInfo.ThreadsPerBlock[device_id]);
+  }
+
+  return OFFLOAD_SUCCESS;
+}
+
+__tgt_target_table *__tgt_rtl_load_binary(int32_t device_id,
+    __tgt_device_image *image) {
+
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when setting a CUDA context for device %d\n", device_id);
+    CUDA_ERR_STRING(err);
+    return NULL;
+  }
+
+  // Clear the offload table as we are going to create a new one.
+  DeviceInfo.clearOffloadEntriesTable(device_id);
+
+  // Create the module and extract the function pointers.
+
+  CUmodule cumod;
+  DP("Load data from image " DPxMOD "\n", DPxPTR(image->ImageStart));
+  err = cuModuleLoadDataEx(&cumod, image->ImageStart, 0, NULL, NULL);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when loading CUDA module\n");
+    CUDA_ERR_STRING(err);
+    return NULL;
+  }
+
+  DP("CUDA module successfully loaded!\n");
+  DeviceInfo.Modules.push_back(cumod);
+
+  // Find the symbols in the module by name.
+  __tgt_offload_entry *HostBegin = image->EntriesBegin;
+  __tgt_offload_entry *HostEnd = image->EntriesEnd;
+
+  for (__tgt_offload_entry *e = HostBegin; e != HostEnd; ++e) {
+
+    if (!e->addr) {
+      // We return NULL when something like this happens, the host should have
+      // always something in the address to uniquely identify the target region.
+      DP("Invalid binary: host entry '<null>' (size = %zd)...\n", e->size);
+
+      return NULL;
+    }
+
+    if (e->size) {
+      __tgt_offload_entry entry = *e;
+
+      CUdeviceptr cuptr;
+      size_t cusize;
+      err = cuModuleGetGlobal(&cuptr, &cusize, cumod, e->name);
+
+      if (err != CUDA_SUCCESS) {
+        DP("Loading global '%s' (Failed)\n", e->name);
+        CUDA_ERR_STRING(err);
+        return NULL;
+      }
+
+      if (cusize != e->size) {
+        DP("Loading global '%s' - size mismatch (%zd != %zd)\n", e->name,
+            cusize, e->size);
+        CUDA_ERR_STRING(err);
+        return NULL;
+      }
+
+      DP("Entry point " DPxMOD " maps to global %s (" DPxMOD ")\n",
+          DPxPTR(e - HostBegin), e->name, DPxPTR(cuptr));
+      entry.addr = (void *)cuptr;
+
+      DeviceInfo.addOffloadEntry(device_id, entry);
+
+      continue;
+    }
+
+    CUfunction fun;
+    err = cuModuleGetFunction(&fun, cumod, e->name);
+
+    if (err != CUDA_SUCCESS) {
+      DP("Loading '%s' (Failed)\n", e->name);
+      CUDA_ERR_STRING(err);
+      return NULL;
+    }
+
+    DP("Entry point " DPxMOD " maps to %s (" DPxMOD ")\n",
+        DPxPTR(e - HostBegin), e->name, DPxPTR(fun));
+
+    // default value GENERIC (in case symbol is missing from cubin file)
+    int8_t ExecModeVal = ExecutionModeType::GENERIC;
+    std::string ExecModeNameStr (e->name);
+    ExecModeNameStr += "_exec_mode";
+    const char *ExecModeName = ExecModeNameStr.c_str();
+
+    CUdeviceptr ExecModePtr;
+    size_t cusize;
+    err = cuModuleGetGlobal(&ExecModePtr, &cusize, cumod, ExecModeName);
+    if (err == CUDA_SUCCESS) {
+      if ((size_t)cusize != sizeof(int8_t)) {
+        DP("Loading global exec_mode '%s' - size mismatch (%zd != %zd)\n",
+           ExecModeName, cusize, sizeof(int8_t));
+        CUDA_ERR_STRING(err);
+        return NULL;
+      }
+
+      err = cuMemcpyDtoH(&ExecModeVal, ExecModePtr, cusize);
+      if (err != CUDA_SUCCESS) {
+        DP("Error when copying data from device to host. Pointers: "
+           "host = " DPxMOD ", device = " DPxMOD ", size = %zd\n",
+           DPxPTR(&ExecModeVal), DPxPTR(ExecModePtr), cusize);
+        CUDA_ERR_STRING(err);
+        return NULL;
+      }
+
+      if (ExecModeVal < 0 || ExecModeVal > 1) {
+        DP("Error wrong exec_mode value specified in cubin file: %d\n",
+           ExecModeVal);
+        return NULL;
+      }
+    } else {
+      DP("Loading global exec_mode '%s' - symbol missing, using default value "
+          "GENERIC (1)\n", ExecModeName);
+      CUDA_ERR_STRING(err);
+    }
+
+    KernelsList.push_back(KernelTy(fun, ExecModeVal));
+
+    __tgt_offload_entry entry = *e;
+    entry.addr = (void *)&KernelsList.back();
+    DeviceInfo.addOffloadEntry(device_id, entry);
+  }
+
+  return DeviceInfo.getOffloadEntriesTable(device_id);
+}
+
+void *__tgt_rtl_data_alloc(int32_t device_id, int64_t size, void *hst_ptr) {
+  if (size == 0) {
+    return NULL;
+  }
+
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error while trying to set CUDA current context\n");
+    CUDA_ERR_STRING(err);
+    return NULL;
+  }
+
+  CUdeviceptr ptr;
+  err = cuMemAlloc(&ptr, size);
+  if (err != CUDA_SUCCESS) {
+    DP("Error while trying to allocate %d\n", err);
+    CUDA_ERR_STRING(err);
+    return NULL;
+  }
+
+  void *vptr = (void *)ptr;
+  return vptr;
+}
+
+int32_t __tgt_rtl_data_submit(int32_t device_id, void *tgt_ptr, void *hst_ptr,
+    int64_t size) {
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when setting CUDA context\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  err = cuMemcpyHtoD((CUdeviceptr)tgt_ptr, hst_ptr, size);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when copying data from host to device. Pointers: host = " DPxMOD
+       ", device = " DPxMOD ", size = %" PRId64 "\n", DPxPTR(hst_ptr),
+       DPxPTR(tgt_ptr), size);
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_data_retrieve(int32_t device_id, void *hst_ptr, void *tgt_ptr,
+    int64_t size) {
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when setting CUDA context\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  err = cuMemcpyDtoH(hst_ptr, (CUdeviceptr)tgt_ptr, size);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when copying data from device to host. Pointers: host = " DPxMOD
+        ", device = " DPxMOD ", size = %" PRId64 "\n", DPxPTR(hst_ptr),
+        DPxPTR(tgt_ptr), size);
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_data_delete(int32_t device_id, void *tgt_ptr) {
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when setting CUDA context\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  err = cuMemFree((CUdeviceptr)tgt_ptr);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when freeing CUDA memory\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_run_target_team_region(int32_t device_id, void *tgt_entry_ptr,
+    void **tgt_args, ptrdiff_t *tgt_offsets, int32_t arg_num, int32_t team_num,
+    int32_t thread_limit, uint64_t loop_tripcount) {
+  // Set the context we are using.
+  CUresult err = cuCtxSetCurrent(DeviceInfo.Contexts[device_id]);
+  if (err != CUDA_SUCCESS) {
+    DP("Error when setting CUDA context\n");
+    CUDA_ERR_STRING(err);
+    return OFFLOAD_FAIL;
+  }
+
+  // All args are references.
+  std::vector<void *> args(arg_num);
+  std::vector<void *> ptrs(arg_num);
+
+  for (int32_t i = 0; i < arg_num; ++i) {
+    ptrs[i] = (void *)((intptr_t)tgt_args[i] + tgt_offsets[i]);
+    args[i] = &ptrs[i];
+  }
+
+  KernelTy *KernelInfo = (KernelTy *)tgt_entry_ptr;
+
+  int cudaThreadsPerBlock;
+
+  if (thread_limit > 0) {
+    cudaThreadsPerBlock = thread_limit;
+    DP("Setting CUDA threads per block to requested %d\n", thread_limit);
+    // Add master warp if necessary
+    if (KernelInfo->ExecutionMode == GENERIC) {
+      cudaThreadsPerBlock += DeviceInfo.WarpSize[device_id];
+      DP("Adding master warp: +%d threads\n", DeviceInfo.WarpSize[device_id]);
+    }
+  } else {
+    cudaThreadsPerBlock = DeviceInfo.NumThreads[device_id];
+    DP("Setting CUDA threads per block to default %d\n",
+        DeviceInfo.NumThreads[device_id]);
+  }
+
+  if (cudaThreadsPerBlock > DeviceInfo.ThreadsPerBlock[device_id]) {
+    cudaThreadsPerBlock = DeviceInfo.ThreadsPerBlock[device_id];
+    DP("Threads per block capped at device limit %d\n",
+        DeviceInfo.ThreadsPerBlock[device_id]);
+  }
+
+  int kernel_limit;
+  err = cuFuncGetAttribute(&kernel_limit,
+      CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK, KernelInfo->Func);
+  if (err == CUDA_SUCCESS) {
+    if (kernel_limit < cudaThreadsPerBlock) {
+      cudaThreadsPerBlock = kernel_limit;
+      DP("Threads per block capped at kernel limit %d\n", kernel_limit);
+    }
+  }
+
+  int cudaBlocksPerGrid;
+  if (team_num <= 0) {
+    if (loop_tripcount > 0 && DeviceInfo.EnvNumTeams < 0) {
+      if (KernelInfo->ExecutionMode == SPMD) {
+        // We have a combined construct, i.e. `target teams distribute parallel
+        // for [simd]`. We launch so many teams so that each thread will
+        // execute one iteration of the loop.
+        // round up to the nearest integer
+        cudaBlocksPerGrid = ((loop_tripcount - 1) / cudaThreadsPerBlock) + 1;
+      } else {
+        // If we reach this point, then we have a non-combined construct, i.e.
+        // `teams distribute` with a nested `parallel for` and each team is
+        // assigned one iteration of the `distribute` loop. E.g.:
+        //
+        // #pragma omp target teams distribute
+        // for(...loop_tripcount...) {
+        //   #pragma omp parallel for
+        //   for(...) {}
+        // }
+        //
+        // Threads within a team will execute the iterations of the `parallel`
+        // loop.
+        cudaBlocksPerGrid = loop_tripcount;
+      }
+      DP("Using %d teams due to loop trip count %" PRIu64 " and number of "
+          "threads per block %d\n", cudaBlocksPerGrid, loop_tripcount,
+          cudaThreadsPerBlock);
+    } else {
+      cudaBlocksPerGrid = DeviceInfo.NumTeams[device_id];
+      DP("Using default number of teams %d\n", DeviceInfo.NumTeams[device_id]);
+    }
+  } else if (team_num > DeviceInfo.BlocksPerGrid[device_id]) {
+    cudaBlocksPerGrid = DeviceInfo.BlocksPerGrid[device_id];
+    DP("Capping number of teams to team limit %d\n",
+        DeviceInfo.BlocksPerGrid[device_id]);
+  } else {
+    cudaBlocksPerGrid = team_num;
+    DP("Using requested number of teams %d\n", team_num);
+  }
+
+  // Run on the device.
+  DP("Launch kernel with %d blocks and %d threads\n", cudaBlocksPerGrid,
+     cudaThreadsPerBlock);
+
+  err = cuLaunchKernel(KernelInfo->Func, cudaBlocksPerGrid, 1, 1,
+      cudaThreadsPerBlock, 1, 1, 0 /*bytes of shared memory*/, 0, &args[0], 0);
+  if (err != CUDA_SUCCESS) {
+    DP("Device kernel launch failed!\n");
+    CUDA_ERR_STRING(err);
+    assert(err == CUDA_SUCCESS && "Unable to launch target execution!");
+    return OFFLOAD_FAIL;
+  }
+
+  DP("Launch of entry point at " DPxMOD " successful!\n",
+      DPxPTR(tgt_entry_ptr));
+
+  cudaError_t sync_error = cudaDeviceSynchronize();
+  if (sync_error != cudaSuccess) {
+  DP("Kernel execution error at " DPxMOD ", %s.\n", DPxPTR(tgt_entry_ptr),
+      cudaGetErrorString(sync_error));
+    return OFFLOAD_FAIL;
+  } else {
+    DP("Kernel execution at " DPxMOD " successful!\n", DPxPTR(tgt_entry_ptr));
+  }
+
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_run_target_region(int32_t device_id, void *tgt_entry_ptr,
+    void **tgt_args, ptrdiff_t *tgt_offsets, int32_t arg_num) {
+  // use one team and the default number of threads.
+  const int32_t team_num = 1;
+  const int32_t thread_limit = 0;
+  return __tgt_rtl_run_target_team_region(device_id, tgt_entry_ptr, tgt_args,
+      tgt_offsets, arg_num, team_num, thread_limit, 0);
+}
+
+#ifdef __cplusplus
+}
+#endif

libomptarget/plugins/exports

@@ -0,0 +1,15 @@
+VERS1.0 {
+  global:
+    __tgt_rtl_is_valid_binary;
+    __tgt_rtl_number_of_devices;
+    __tgt_rtl_init_device;
+    __tgt_rtl_load_binary;
+    __tgt_rtl_data_alloc;
+    __tgt_rtl_data_submit;
+    __tgt_rtl_data_retrieve;
+    __tgt_rtl_data_delete;
+    __tgt_rtl_run_target_team_region;
+    __tgt_rtl_run_target_region;
+  local:
+    *;
+};

libomptarget/plugins/generic-elf-64bit/src/rtl.cpp

@@ -0,0 +1,319 @@
+//===-RTLs/generic-64bit/src/rtl.cpp - Target RTLs Implementation - C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// RTL for generic 64-bit machine
+//
+//===----------------------------------------------------------------------===//
+
+#include <cassert>
+#include <cstdio>
+#include <cstring>
+#include <cstdlib>
+#include <dlfcn.h>
+#include <ffi.h>
+#include <gelf.h>
+#include <link.h>
+#include <list>
+#include <vector>
+
+#include "omptargetplugin.h"
+
+#ifndef TARGET_NAME
+#define TARGET_NAME Generic ELF - 64bit
+#endif
+
+#ifndef TARGET_ELF_ID
+#define TARGET_ELF_ID 0
+#endif
+
+#define GETNAME2(name) #name
+#define GETNAME(name) GETNAME2(name)
+#define DP(...) DEBUGP("Target " GETNAME(TARGET_NAME) " RTL", __VA_ARGS__)
+
+#include "../../common/elf_common.c"
+
+#define NUMBER_OF_DEVICES 4
+#define OFFLOADSECTIONNAME ".omp_offloading.entries"
+
+/// Array of Dynamic libraries loaded for this target.
+struct DynLibTy {
+  char *FileName;
+  void *Handle;
+};
+
+/// Keep entries table per device.
+struct FuncOrGblEntryTy {
+  __tgt_target_table Table;
+};
+
+/// Class containing all the device information.
+class RTLDeviceInfoTy {
+  std::vector<FuncOrGblEntryTy> FuncGblEntries;
+
+public:
+  std::list<DynLibTy> DynLibs;
+
+  // Record entry point associated with device.
+  void createOffloadTable(int32_t device_id, __tgt_offload_entry *begin,
+                          __tgt_offload_entry *end) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    E.Table.EntriesBegin = begin;
+    E.Table.EntriesEnd = end;
+  }
+
+  // Return true if the entry is associated with device.
+  bool findOffloadEntry(int32_t device_id, void *addr) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    for (__tgt_offload_entry *i = E.Table.EntriesBegin, *e = E.Table.EntriesEnd;
+         i < e; ++i) {
+      if (i->addr == addr)
+        return true;
+    }
+
+    return false;
+  }
+
+  // Return the pointer to the target entries table.
+  __tgt_target_table *getOffloadEntriesTable(int32_t device_id) {
+    assert(device_id < (int32_t)FuncGblEntries.size() &&
+           "Unexpected device id!");
+    FuncOrGblEntryTy &E = FuncGblEntries[device_id];
+
+    return &E.Table;
+  }
+
+  RTLDeviceInfoTy(int32_t num_devices) { FuncGblEntries.resize(num_devices); }
+
+  ~RTLDeviceInfoTy() {
+    // Close dynamic libraries
+    for (auto &lib : DynLibs) {
+      if (lib.Handle) {
+        dlclose(lib.Handle);
+        remove(lib.FileName);
+      }
+    }
+  }
+};
+
+static RTLDeviceInfoTy DeviceInfo(NUMBER_OF_DEVICES);
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *image) {
+// If we don't have a valid ELF ID we can just fail.
+#if TARGET_ELF_ID < 1
+  return 0;
+#else
+  return elf_check_machine(image, TARGET_ELF_ID);
+#endif
+}
+
+int32_t __tgt_rtl_number_of_devices() { return NUMBER_OF_DEVICES; }
+
+int32_t __tgt_rtl_init_device(int32_t device_id) { return OFFLOAD_SUCCESS; }
+
+__tgt_target_table *__tgt_rtl_load_binary(int32_t device_id,
+                                          __tgt_device_image *image) {
+
+  DP("Dev %d: load binary from " DPxMOD " image\n", device_id,
+     DPxPTR(image->ImageStart));
+
+  assert(device_id >= 0 && device_id < NUMBER_OF_DEVICES && "bad dev id");
+
+  size_t ImageSize = (size_t)image->ImageEnd - (size_t)image->ImageStart;
+  size_t NumEntries = (size_t)(image->EntriesEnd - image->EntriesBegin);
+  DP("Expecting to have %zd entries defined.\n", NumEntries);
+
+  // Is the library version incompatible with the header file?
+  if (elf_version(EV_CURRENT) == EV_NONE) {
+    DP("Incompatible ELF library!\n");
+    return NULL;
+  }
+
+  // Obtain elf handler
+  Elf *e = elf_memory((char *)image->ImageStart, ImageSize);
+  if (!e) {
+    DP("Unable to get ELF handle: %s!\n", elf_errmsg(-1));
+    return NULL;
+  }
+
+  if (elf_kind(e) != ELF_K_ELF) {
+    DP("Invalid Elf kind!\n");
+    elf_end(e);
+    return NULL;
+  }
+
+  // Find the entries section offset
+  Elf_Scn *section = 0;
+  Elf64_Off entries_offset = 0;
+
+  size_t shstrndx;
+
+  if (elf_getshdrstrndx(e, &shstrndx)) {
+    DP("Unable to get ELF strings index!\n");
+    elf_end(e);
+    return NULL;
+  }
+
+  while ((section = elf_nextscn(e, section))) {
+    GElf_Shdr hdr;
+    gelf_getshdr(section, &hdr);
+
+    if (!strcmp(elf_strptr(e, shstrndx, hdr.sh_name), OFFLOADSECTIONNAME)) {
+      entries_offset = hdr.sh_addr;
+      break;
+    }
+  }
+
+  if (!entries_offset) {
+    DP("Entries Section Offset Not Found\n");
+    elf_end(e);
+    return NULL;
+  }
+
+  DP("Offset of entries section is (" DPxMOD ").\n", DPxPTR(entries_offset));
+
+  // load dynamic library and get the entry points. We use the dl library
+  // to do the loading of the library, but we could do it directly to avoid the
+  // dump to the temporary file.
+  //
+  // 1) Create tmp file with the library contents.
+  // 2) Use dlopen to load the file and dlsym to retrieve the symbols.
+  char tmp_name[] = "/tmp/tmpfile_XXXXXX";
+  int tmp_fd = mkstemp(tmp_name);
+
+  if (tmp_fd == -1) {
+    elf_end(e);
+    return NULL;
+  }
+
+  FILE *ftmp = fdopen(tmp_fd, "wb");
+
+  if (!ftmp) {
+    elf_end(e);
+    return NULL;
+  }
+
+  fwrite(image->ImageStart, ImageSize, 1, ftmp);
+  fclose(ftmp);
+
+  DynLibTy Lib = {tmp_name, dlopen(tmp_name, RTLD_LAZY)};
+
+  if (!Lib.Handle) {
+    DP("Target library loading error: %s\n", dlerror());
+    elf_end(e);
+    return NULL;
+  }
+
+  DeviceInfo.DynLibs.push_back(Lib);
+
+  struct link_map *libInfo = (struct link_map *)Lib.Handle;
+
+  // The place where the entries info is loaded is the library base address
+  // plus the offset determined from the ELF file.
+  Elf64_Addr entries_addr = libInfo->l_addr + entries_offset;
+
+  DP("Pointer to first entry to be loaded is (" DPxMOD ").\n",
+      DPxPTR(entries_addr));
+
+  // Table of pointers to all the entries in the target.
+  __tgt_offload_entry *entries_table = (__tgt_offload_entry *)entries_addr;
+
+  __tgt_offload_entry *entries_begin = &entries_table[0];
+  __tgt_offload_entry *entries_end = entries_begin + NumEntries;
+
+  if (!entries_begin) {
+    DP("Can't obtain entries begin\n");
+    elf_end(e);
+    return NULL;
+  }
+
+  DP("Entries table range is (" DPxMOD ")->(" DPxMOD ")\n",
+      DPxPTR(entries_begin), DPxPTR(entries_end));
+  DeviceInfo.createOffloadTable(device_id, entries_begin, entries_end);
+
+  elf_end(e);
+
+  return DeviceInfo.getOffloadEntriesTable(device_id);
+}
+
+void *__tgt_rtl_data_alloc(int32_t device_id, int64_t size, void *hst_ptr) {
+  void *ptr = malloc(size);
+  return ptr;
+}
+
+int32_t __tgt_rtl_data_submit(int32_t device_id, void *tgt_ptr, void *hst_ptr,
+                              int64_t size) {
+  memcpy(tgt_ptr, hst_ptr, size);
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_data_retrieve(int32_t device_id, void *hst_ptr, void *tgt_ptr,
+                                int64_t size) {
+  memcpy(hst_ptr, tgt_ptr, size);
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_data_delete(int32_t device_id, void *tgt_ptr) {
+  free(tgt_ptr);
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_run_target_team_region(int32_t device_id, void *tgt_entry_ptr,
+    void **tgt_args, ptrdiff_t *tgt_offsets, int32_t arg_num, int32_t team_num,
+    int32_t thread_limit, uint64_t loop_tripcount /*not used*/) {
+  // ignore team num and thread limit.
+
+  // Use libffi to launch execution.
+  ffi_cif cif;
+
+  // All args are references.
+  std::vector<ffi_type *> args_types(arg_num, &ffi_type_pointer);
+  std::vector<void *> args(arg_num);
+  std::vector<void *> ptrs(arg_num);
+
+  for (int32_t i = 0; i < arg_num; ++i) {
+    ptrs[i] = (void *)((intptr_t)tgt_args[i] + tgt_offsets[i]);
+    args[i] = &ptrs[i];
+  }
+
+  ffi_status status = ffi_prep_cif(&cif, FFI_DEFAULT_ABI, arg_num,
+                                   &ffi_type_void, &args_types[0]);
+
+  assert(status == FFI_OK && "Unable to prepare target launch!");
+
+  if (status != FFI_OK)
+    return OFFLOAD_FAIL;
+
+  DP("Running entry point at " DPxMOD "...\n", DPxPTR(tgt_entry_ptr));
+
+  void (*entry)(void);
+  *((void**) &entry) = tgt_entry_ptr;
+  ffi_call(&cif, entry, NULL, &args[0]);
+  return OFFLOAD_SUCCESS;
+}
+
+int32_t __tgt_rtl_run_target_region(int32_t device_id, void *tgt_entry_ptr,
+    void **tgt_args, ptrdiff_t *tgt_offsets, int32_t arg_num) {
+  // use one team and one thread.
+  return __tgt_rtl_run_target_team_region(device_id, tgt_entry_ptr, tgt_args,
+      tgt_offsets, arg_num, 1, 1, 0);
+}
+
+#ifdef __cplusplus
+}
+#endif

libomptarget/plugins/ppc64/CMakeLists.txt

@@ -0,0 +1,18 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for a ppc64 machine if available.
+#
+##===----------------------------------------------------------------------===##
+
+if(CMAKE_SYSTEM_NAME MATCHES "Linux")
+  build_generic_elf64("ppc64" "PPC64" "ppc64" "powerpc64-ibm-linux-gnu" "21")
+else()
+ libomptarget_say("Not building ppc64 offloading plugin: machine not found in the system.")
+endif()

libomptarget/plugins/ppc64le/CMakeLists.txt

@@ -0,0 +1,18 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for a ppc64le machine if available.
+#
+##===----------------------------------------------------------------------===##
+
+if(CMAKE_SYSTEM_NAME MATCHES "Linux")
+  build_generic_elf64("ppc64le" "PPC64le" "ppc64" "powerpc64le-ibm-linux-gnu" "21")
+else()
+ libomptarget_say("Not building ppc64le offloading plugin: machine not found in the system.")
+endif()

libomptarget/plugins/x86_64/CMakeLists.txt

@@ -0,0 +1,18 @@
+##===----------------------------------------------------------------------===##
+# 
+#                     The LLVM Compiler Infrastructure
+#
+# This file is dual licensed under the MIT and the University of Illinois Open
+# Source Licenses. See LICENSE.txt for details.
+# 
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for a x86_64 machine if available.
+#
+##===----------------------------------------------------------------------===##
+
+if(CMAKE_SYSTEM_NAME MATCHES "Linux")
+  build_generic_elf64("x86_64" "x86_64" "x86_64" "x86_64-pc-linux-gnu" "62")
+else()
+ libomptarget_say("Not building x86_64 offloading plugin: machine not found in the system.")
+endif()

libomptarget/src/omptarget.h

@@ -0,0 +1,237 @@
+//===-------- omptarget.h - Target independent OpenMP target RTL -- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// Interface to be used by Clang during the codegen of a
+// target region.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _OMPTARGET_H_
+#define _OMPTARGET_H_
+
+#include <stdint.h>
+#include <stddef.h>
+
+#define OFFLOAD_SUCCESS (0)
+#define OFFLOAD_FAIL (~0)
+
+#define OFFLOAD_DEVICE_DEFAULT     -1
+#define HOST_DEVICE                -10
+
+/// Data attributes for each data reference used in an OpenMP target region.
+enum tgt_map_type {
+  // No flags
+  OMP_TGT_MAPTYPE_NONE            = 0x000,
+  // copy data from host to device
+  OMP_TGT_MAPTYPE_TO              = 0x001,
+  // copy data from device to host
+  OMP_TGT_MAPTYPE_FROM            = 0x002,
+  // copy regardless of the reference count
+  OMP_TGT_MAPTYPE_ALWAYS          = 0x004,
+  // force unmapping of data
+  OMP_TGT_MAPTYPE_DELETE          = 0x008,
+  // map the pointer as well as the pointee
+  OMP_TGT_MAPTYPE_PTR_AND_OBJ     = 0x010,
+  // pass device base address to kernel
+  OMP_TGT_MAPTYPE_TARGET_PARAM    = 0x020,
+  // return base device address of mapped data
+  OMP_TGT_MAPTYPE_RETURN_PARAM    = 0x040,
+  // private variable - not mapped
+  OMP_TGT_MAPTYPE_PRIVATE         = 0x080,
+  // copy by value - not mapped
+  OMP_TGT_MAPTYPE_LITERAL         = 0x100,
+  // mapping is implicit
+  OMP_TGT_MAPTYPE_IMPLICIT        = 0x200,
+  // member of struct, member given by 4 MSBs - 1
+  OMP_TGT_MAPTYPE_MEMBER_OF       = 0xffff000000000000
+};
+
+enum OpenMPOffloadingDeclareTargetFlags {
+  /// Mark the entry as having a 'link' attribute.
+  OMP_DECLARE_TARGET_LINK = 0x01,
+  /// Mark the entry as being a global constructor.
+  OMP_DECLARE_TARGET_CTOR = 0x02,
+  /// Mark the entry as being a global destructor.
+  OMP_DECLARE_TARGET_DTOR = 0x04
+};
+
+/// This struct is a record of an entry point or global. For a function
+/// entry point the size is expected to be zero
+struct __tgt_offload_entry {
+  void *addr;   // Pointer to the offload entry info (function or global)
+  char *name;   // Name of the function or global
+  size_t size;  // Size of the entry info (0 if it is a function)
+  int32_t flags; // Flags associated with the entry, e.g. 'link'.
+  int32_t reserved; // Reserved, to be used by the runtime library.
+};
+
+/// This struct is a record of the device image information
+struct __tgt_device_image {
+  void *ImageStart;                  // Pointer to the target code start
+  void *ImageEnd;                    // Pointer to the target code end
+  __tgt_offload_entry *EntriesBegin; // Begin of table with all target entries
+  __tgt_offload_entry *EntriesEnd;   // End of table (non inclusive)
+};
+
+/// This struct is a record of all the host code that may be offloaded to a
+/// target.
+struct __tgt_bin_desc {
+  int32_t NumDeviceImages;           // Number of device types supported
+  __tgt_device_image *DeviceImages;  // Array of device images (1 per dev. type)
+  __tgt_offload_entry *HostEntriesBegin; // Begin of table with all host entries
+  __tgt_offload_entry *HostEntriesEnd;   // End of table (non inclusive)
+};
+
+/// This struct contains the offload entries identified by the target runtime
+struct __tgt_target_table {
+  __tgt_offload_entry *EntriesBegin; // Begin of the table with all the entries
+  __tgt_offload_entry
+      *EntriesEnd; // End of the table with all the entries (non inclusive)
+};
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+// Implemented in libomp, they are called from within __tgt_* functions.
+int omp_get_default_device(void) __attribute__((weak));
+int32_t __kmpc_omp_taskwait(void *loc_ref, int32_t gtid) __attribute__((weak));
+
+int omp_get_num_devices(void);
+int omp_get_initial_device(void);
+void *omp_target_alloc(size_t size, int device_num);
+void omp_target_free(void *device_ptr, int device_num);
+int omp_target_is_present(void *ptr, int device_num);
+int omp_target_memcpy(void *dst, void *src, size_t length, size_t dst_offset,
+    size_t src_offset, int dst_device, int src_device);
+int omp_target_memcpy_rect(void *dst, void *src, size_t element_size,
+    int num_dims, const size_t *volume, const size_t *dst_offsets,
+    const size_t *src_offsets, const size_t *dst_dimensions,
+    const size_t *src_dimensions, int dst_device, int src_device);
+int omp_target_associate_ptr(void *host_ptr, void *device_ptr, size_t size,
+    size_t device_offset, int device_num);
+int omp_target_disassociate_ptr(void *host_ptr, int device_num);
+
+/// adds a target shared library to the target execution image
+void __tgt_register_lib(__tgt_bin_desc *desc);
+
+/// removes a target shared library from the target execution image
+void __tgt_unregister_lib(__tgt_bin_desc *desc);
+
+// creates the host to target data mapping, stores it in the
+// libomptarget.so internal structure (an entry in a stack of data maps) and
+// passes the data to the device;
+void __tgt_target_data_begin(int32_t device_id, int32_t arg_num,
+                             void **args_base, void **args, int64_t *arg_sizes,
+                             int32_t *arg_types);
+void __tgt_target_data_begin_nowait(int32_t device_id, int32_t arg_num,
+                                    void **args_base, void **args,
+                                    int64_t *arg_sizes, int32_t *arg_types,
+                                    int32_t depNum, void *depList,
+                                    int32_t noAliasDepNum,
+                                    void *noAliasDepList);
+
+// passes data from the target, release target memory and destroys the
+// host-target mapping (top entry from the stack of data maps) created by
+// the last __tgt_target_data_begin
+void __tgt_target_data_end(int32_t device_id, int32_t arg_num, void **args_base,
+                           void **args, int64_t *arg_sizes, int32_t *arg_types);
+void __tgt_target_data_end_nowait(int32_t device_id, int32_t arg_num,
+                                  void **args_base, void **args,
+                                  int64_t *arg_sizes, int32_t *arg_types,
+                                  int32_t depNum, void *depList,
+                                  int32_t noAliasDepNum, void *noAliasDepList);
+
+/// passes data to/from the target
+void __tgt_target_data_update(int32_t device_id, int32_t arg_num,
+                              void **args_base, void **args, int64_t *arg_sizes,
+                              int32_t *arg_types);
+void __tgt_target_data_update_nowait(int32_t device_id, int32_t arg_num,
+                                     void **args_base, void **args,
+                                     int64_t *arg_sizes, int32_t *arg_types,
+                                     int32_t depNum, void *depList,
+                                     int32_t noAliasDepNum,
+                                     void *noAliasDepList);
+
+// Performs the same actions as data_begin in case arg_num is non-zero
+// and initiates run of offloaded region on target platform; if arg_num
+// is non-zero after the region execution is done it also performs the
+// same action as data_end above. The following types are used; this
+// function returns 0 if it was able to transfer the execution to a
+// target and an int different from zero otherwise.
+int __tgt_target(int32_t device_id, void *host_ptr, int32_t arg_num,
+                 void **args_base, void **args, int64_t *arg_sizes,
+                 int32_t *arg_types);
+int __tgt_target_nowait(int32_t device_id, void *host_ptr, int32_t arg_num,
+                        void **args_base, void **args, int64_t *arg_sizes,
+                        int32_t *arg_types, int32_t depNum, void *depList,
+                        int32_t noAliasDepNum, void *noAliasDepList);
+
+int __tgt_target_teams(int32_t device_id, void *host_ptr, int32_t arg_num,
+                       void **args_base, void **args, int64_t *arg_sizes,
+                       int32_t *arg_types, int32_t num_teams,
+                       int32_t thread_limit);
+int __tgt_target_teams_nowait(int32_t device_id, void *host_ptr,
+                              int32_t arg_num, void **args_base, void **args,
+                              int64_t *arg_sizes, int32_t *arg_types,
+                              int32_t num_teams, int32_t thread_limit,
+                              int32_t depNum, void *depList,
+                              int32_t noAliasDepNum, void *noAliasDepList);
+void __kmpc_push_target_tripcount(int32_t device_id, uint64_t loop_tripcount);
+
+#ifdef __cplusplus
+}
+#endif
+
+#ifdef OMPTARGET_DEBUG
+#include <stdio.h>
+#define DEBUGP(prefix, ...)                                                    \
+  {                                                                            \
+    fprintf(stderr, "%s --> ", prefix);                                        \
+    fprintf(stderr, __VA_ARGS__);                                              \
+  }
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
+#define DPxMOD "0x%0*" PRIxPTR
+#define DPxPTR(ptr) ((int)(2*sizeof(uintptr_t))), ((uintptr_t) (ptr))
+
+/*
+ * To printf a pointer in hex with a fixed width of 16 digits and a leading 0x,
+ * use printf("ptr=" DPxMOD "...\n", DPxPTR(ptr));
+ *
+ * DPxMOD expands to:
+ *   "0x%0*" PRIxPTR
+ * where PRIxPTR expands to an appropriate modifier for the type uintptr_t on a
+ * specific platform, e.g. "lu" if uintptr_t is typedef'd as unsigned long:
+ *   "0x%0*lu"
+ *
+ * Ultimately, the whole statement expands to:
+ *   printf("ptr=0x%0*lu...\n",  // the 0* modifier expects an extra argument
+ *                               // specifying the width of the output
+ *   (int)(2*sizeof(uintptr_t)), // the extra argument specifying the width
+ *                               // 8 digits for 32bit systems
+ *                               // 16 digits for 64bit
+ *   (uintptr_t) ptr);
+ */
+#else
+#define DEBUGP(prefix, ...)                                                    \
+  {}
+#endif
+
+#ifdef __cplusplus
+#define EXTERN extern "C"
+#else
+#define EXTERN extern
+#endif
+
+#endif // _OMPTARGET_H_

libomptarget/src/omptargetplugin.h

@@ -0,0 +1,92 @@
+//===-- omptargetplugin.h - Target dependent OpenMP Plugin API --*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines an interface between target independent OpenMP offload
+// runtime library libomptarget and target dependent plugin.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _OMPTARGETPLUGIN_H_
+#define _OMPTARGETPLUGIN_H_
+
+#include <omptarget.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+// Return the number of available devices of the type supported by the
+// target RTL.
+int32_t __tgt_rtl_number_of_devices(void);
+
+// Return an integer different from zero if the provided device image can be
+// supported by the runtime. The functionality is similar to comparing the
+// result of __tgt__rtl__load__binary to NULL. However, this is meant to be a
+// lightweight query to determine if the RTL is suitable for an image without
+// having to load the library, which can be expensive.
+int32_t __tgt_rtl_is_valid_binary(__tgt_device_image *Image);
+
+// Initialize the specified device. In case of success return 0; otherwise
+// return an error code.
+int32_t __tgt_rtl_init_device(int32_t ID);
+
+// Pass an executable image section described by image to the specified
+// device and prepare an address table of target entities. In case of error,
+// return NULL. Otherwise, return a pointer to the built address table.
+// Individual entries in the table may also be NULL, when the corresponding
+// offload region is not supported on the target device.
+__tgt_target_table *__tgt_rtl_load_binary(int32_t ID,
+                                          __tgt_device_image *Image);
+
+// Allocate data on the particular target device, of the specified size.
+// HostPtr is a address of the host data the allocated target data
+// will be associated with (HostPtr may be NULL if it is not known at
+// allocation time, like for example it would be for target data that
+// is allocated by omp_target_alloc() API). Return address of the
+// allocated data on the target that will be used by libomptarget.so to
+// initialize the target data mapping structures. These addresses are
+// used to generate a table of target variables to pass to
+// __tgt_rtl_run_region(). The __tgt_rtl_data_alloc() returns NULL in
+// case an error occurred on the target device.
+void *__tgt_rtl_data_alloc(int32_t ID, int64_t Size, void *HostPtr);
+
+// Pass the data content to the target device using the target address.
+// In case of success, return zero. Otherwise, return an error code.
+int32_t __tgt_rtl_data_submit(int32_t ID, void *TargetPtr, void *HostPtr,
+                              int64_t Size);
+
+// Retrieve the data content from the target device using its address.
+// In case of success, return zero. Otherwise, return an error code.
+int32_t __tgt_rtl_data_retrieve(int32_t ID, void *HostPtr, void *TargetPtr,
+                                int64_t Size);
+
+// De-allocate the data referenced by target ptr on the device. In case of
+// success, return zero. Otherwise, return an error code.
+int32_t __tgt_rtl_data_delete(int32_t ID, void *TargetPtr);
+
+// Transfer control to the offloaded entry Entry on the target device.
+// Args and Offsets are arrays of NumArgs size of target addresses and
+// offsets. An offset should be added to the target address before passing it
+// to the outlined function on device side. In case of success, return zero.
+// Otherwise, return an error code.
+int32_t __tgt_rtl_run_target_region(int32_t ID, void *Entry, void **Args,
+                                    ptrdiff_t *Offsets, int32_t NumArgs);
+
+// Similar to __tgt_rtl_run_target_region, but additionally specify the
+// number of teams to be created and a number of threads in each team.
+int32_t __tgt_rtl_run_target_team_region(int32_t ID, void *Entry, void **Args,
+                                         ptrdiff_t *Offsets, int32_t NumArgs,
+                                         int32_t NumTeams, int32_t ThreadLimit,
+                                         uint64_t loop_tripcount);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif // _OMPTARGETPLUGIN_H_

libomptarget/test/CMakeLists.txt

@@ -0,0 +1,92 @@
+# CMakeLists.txt file for unit testing OpenMP Library
+include(FindPythonInterp)
+include(CheckTypeSize)
+if(NOT PYTHONINTERP_FOUND)
+  libomptarget_warning_say("Could not find Python.")
+  libomptarget_warning_say("The check-libomptarget target will not be available!")
+  return()
+endif()
+
+set(LIBOMPTARGET_TEST_CFLAGS "" CACHE STRING
+  "Extra compiler flags to send to the test compiler")
+
+if(${LIBOMPTARGET_STANDALONE_BUILD})
+  # Make sure we can use the console pool for recent cmake and ninja > 1.5
+  if(CMAKE_VERSION VERSION_LESS 3.1.20141117)
+    set(cmake_3_2_USES_TERMINAL)
+  else()
+    set(cmake_3_2_USES_TERMINAL USES_TERMINAL)
+  endif()
+  set(LIBOMPTARGET_TEST_C_COMPILER ${CMAKE_C_COMPILER} CACHE STRING
+    "C compiler to use for testing OpenMP offloading library")
+  set(LIBOMPTARGET_TEST_CXX_COMPILER ${CMAKE_CXX_COMPILER} CACHE STRING
+    "C++ compiler to use for testing OpenMP offloading library")
+  set(LIBOMPTARGET_TEST_OPENMP_FLAG -fopenmp CACHE STRING
+    "OpenMP compiler flag to use for testing OpenMP offloading library")
+  find_program(LIBOMPTARGET_LLVM_LIT_EXECUTABLE
+    NAMES llvm-lit lit.py lit
+    PATHS ${OPENMP_LLVM_TOOLS_DIR})
+  if(NOT LIBOMPTARGET_LLVM_LIT_EXECUTABLE)
+    libomptarget_say("Cannot find llvm-lit.")
+    libomptarget_say("Please put llvm-lit in your PATH or set LIBOMPTARGET_LLVM_LIT_EXECUTABLE to its full path or point OPENMP_LLVM_TOOLS_DIR to its directory")
+    libomptarget_warning_say("The check-libomptarget target will not be available!")
+    return()
+  endif()
+  
+  find_program(LIBOMPTARGET_FILECHECK_EXECUTABLE
+    NAMES FileCheck
+    PATHS ${OPENMP_LLVM_TOOLS_DIR})
+  if(NOT LIBOMPTARGET_FILECHECK_EXECUTABLE)
+    libomptarget_say("Cannot find FileCheck.")
+    libomptarget_say("Please put FileCheck in your PATH or set LIBOMPTARGET_FILECHECK_EXECUTABLE to its full path or point OPENMP_LLVM_TOOLS_DIR to its directory")
+    libomptarget_warning_say("The check-libomptarget target will not be available!")
+    return()
+  endif()
+  
+  # Set lit arguments
+  # The -j 1 lets the actual tests run with the entire machine.
+  # We have one test thread that spawns the tests serially.  This allows
+  # Each test to use the entire machine.
+  set(LIBOMPTARGET_LIT_ARGS_DEFAULT "-sv --show-unsupported --show-xfail -j 1")
+  if(MSVC OR XCODE)
+    set(LIBOMPTARGET_LIT_ARGS_DEFAULT "${LIBOMPTARGET_LIT_ARGS_DEFAULT} --no-progress-bar")
+  endif()
+  set(LIBOMPTARGET_LIT_ARGS "${LIBOMPTARGET_LIT_ARGS_DEFAULT}" CACHE STRING
+    "Default options for lit")
+  separate_arguments(LIBOMPTARGET_LIT_ARGS)
+  add_custom_target(check-libomptarget
+    COMMAND ${PYTHON_EXECUTABLE} ${LIBOMPTARGET_LLVM_LIT_EXECUTABLE} ${LIBOMPTARGET_LIT_ARGS} ${CMAKE_CURRENT_BINARY_DIR}
+    DEPENDS omptarget
+    COMMENT "Running libomptarget tests"
+    ${cmake_3_2_USES_TERMINAL}
+  )
+  
+  set(LIBOMPTARGET_OPENMP_HEADER_FOLDER "${CMAKE_CURRENT_BINARY_DIR}/../../runtime/src" CACHE STRING
+    "Path to folder containing omp.h")
+  set(LIBOMPTARGET_OPENMP_HOST_RTL_FOLDER "${CMAKE_CURRENT_BINARY_DIR}/../../runtime/src" CACHE STRING
+    "Path to folder containing libomp.so")
+else()
+  # LLVM source tree build, test just-built clang
+  if(NOT MSVC)
+    set(LIBOMPTARGET_TEST_C_COMPILER ${LLVM_RUNTIME_OUTPUT_INTDIR}/clang)
+    set(LIBOMPTARGET_TEST_CXX_COMPILER ${LLVM_RUNTIME_OUTPUT_INTDIR}/clang++)
+    set(LIBOMPTARGET_FILECHECK_EXECUTABLE ${LLVM_RUNTIME_OUTPUT_INTDIR}/FileCheck)
+  else()
+    libomptarget_warning_say("Not prepared to run tests on Windows systems.")
+  endif()
+  set(LIBOMPTARGET_TEST_OPENMP_FLAG -fopenmp=libomp)
+  # Use add_lit_testsuite() from LLVM CMake. This also depends on OpenMP
+  # implementation because it uses omp.h.
+  add_lit_testsuite(check-libomptarget
+    "Running libomptarget tests"
+    ${CMAKE_CURRENT_BINARY_DIR}
+    DEPENDS omptarget omp
+  )
+  
+  set(LIBOMPTARGET_OPENMP_HEADER_FOLDER "${LIBOMPTARGET_BINARY_DIR}/../runtime/src")
+endif()
+
+# Configure the lit.site.cfg.in file
+set(AUTO_GEN_COMMENT "## Autogenerated by libomptarget configuration.\n# Do not edit!")
+configure_file(lit.site.cfg.in lit.site.cfg @ONLY)
+

libomptarget/test/lit.cfg

@@ -0,0 +1,116 @@
+# -*- Python -*- vim: set ft=python ts=4 sw=4 expandtab tw=79:
+# Configuration file for the 'lit' test runner.
+
+import os
+import lit.formats
+
+# Tell pylint that we know config and lit_config exist somewhere.
+if 'PYLINT_IMPORT' in os.environ:
+    config = object()
+    lit_config = object()
+
+def append_dynamic_library_path(name, value, sep):
+    if name in config.environment:
+        config.environment[name] = value + sep + config.environment[name]
+    else:
+        config.environment[name] = value
+
+# name: The name of this test suite.
+config.name = 'libomptarget'
+
+# suffixes: A list of file extensions to treat as test files.
+config.suffixes = ['.c', '.cpp', '.cc']
+
+# test_source_root: The root path where tests are located.
+config.test_source_root = os.path.dirname(__file__)
+
+# test_exec_root: The root object directory where output is placed
+config.test_exec_root = config.libomptarget_obj_root
+
+# test format
+config.test_format = lit.formats.ShTest()
+
+# compiler flags
+config.test_cflags = config.test_openmp_flag + \
+    " -I " + config.test_source_root + \
+    " -I " + config.omp_header_directory + \
+    " -L " + config.library_dir;
+    
+if config.omp_host_rtl_directory:
+    config.test_cflags = config.test_cflags + " -L " + \
+        config.omp_host_rtl_directory  
+    
+config.test_cflags = config.test_cflags + " " + config.test_extra_cflags
+
+# Setup environment to find dynamic library at runtime
+if config.operating_system == 'Windows':
+    append_dynamic_library_path('PATH', config.library_dir, ";")
+    append_dynamic_library_path('PATH', config.omp_host_rtl_directory, ";")
+elif config.operating_system == 'Darwin':
+    append_dynamic_library_path('DYLD_LIBRARY_PATH', config.library_dir, ":")
+    append_dynamic_library_path('DYLD_LIBRARY_PATH', \
+        config.omp_host_rtl_directory, ";")
+    config.test_cflags += " -Wl,-rpath," + config.library_dir
+    config.test_cflags += " -Wl,-rpath," + config.omp_host_rtl_directory
+else: # Unices
+    append_dynamic_library_path('LD_LIBRARY_PATH', config.library_dir, ":")
+    append_dynamic_library_path('LD_LIBRARY_PATH', \
+        config.omp_host_rtl_directory, ":")
+    
+# substitutions
+# - for targets that exist in the system create the actual command.
+# - for valid targets that do not exist in the system, return false, so that the
+#   same test can be used for different targets.
+
+# Scan all the valid targets.
+for libomptarget_target in config.libomptarget_all_targets:
+    # Is this target in the current system? If so create a compile, run and test
+    # command. Otherwise create command that return false.
+    if libomptarget_target in config.libomptarget_system_targets:
+        config.substitutions.append(("%libomptarget-compilexx-run-and-check-" + \
+            libomptarget_target, \
+            "%libomptarget-compilexx-and-run-" + libomptarget_target + \
+            " | " + config.libomptarget_filecheck + " %s"))
+        config.substitutions.append(("%libomptarget-compile-run-and-check-" + \
+            libomptarget_target, \
+            "%libomptarget-compile-and-run-" + libomptarget_target + \
+            " | " + config.libomptarget_filecheck + " %s"))      
+        config.substitutions.append(("%libomptarget-compilexx-and-run-" + \
+            libomptarget_target, \
+            "%clangxx-" + libomptarget_target + " %s -o %t-" + \
+            libomptarget_target + " && %t-" + libomptarget_target))    
+        config.substitutions.append(("%libomptarget-compile-and-run-" + \
+            libomptarget_target, \
+            "%clang-" + libomptarget_target + " %s -o %t-" + \
+            libomptarget_target + " && %t-" + libomptarget_target))
+        config.substitutions.append(("%clangxx-" + libomptarget_target, \
+            "%clangxx %cflags -fopenmp-targets=" + libomptarget_target))    
+        config.substitutions.append(("%clang-" + libomptarget_target, \
+            "%clang %cflags -fopenmp-targets=" + libomptarget_target))
+        config.substitutions.append(("%fcheck-" + libomptarget_target, \
+            config.libomptarget_filecheck + " %s"))
+    else:
+        config.substitutions.append(("%libomptarget-compile-run-and-check-" + \
+            libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%libomptarget-compilexx-run-and-check-" + \
+            libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%libomptarget-compile-and-run-" + \
+            libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%libomptarget-compilexx-and-run-" + \
+            libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%clang-" + libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%clangxx-" + libomptarget_target, \
+            "echo ignored-command"))
+        config.substitutions.append(("%fcheck-" + libomptarget_target, \
+            "echo ignored-command"))
+
+config.substitutions.append(("%clangxx", config.test_cxx_compiler))
+config.substitutions.append(("%clang", config.test_c_compiler))
+config.substitutions.append(("%openmp_flag", config.test_openmp_flag))
+config.substitutions.append(("%cflags", config.test_cflags))
+

libomptarget/test/lit.site.cfg.in

@@ -0,0 +1,20 @@
+@AUTO_GEN_COMMENT@
+
+config.test_c_compiler = "@LIBOMPTARGET_TEST_C_COMPILER@"
+config.test_cxx_compiler = "@LIBOMPTARGET_TEST_CXX_COMPILER@"
+config.test_openmp_flag = "@LIBOMPTARGET_TEST_OPENMP_FLAG@"
+# For the moment we still need to pass libomptarget explicitly. Once the driver
+# patch, lands, this is not required anymore.
+config.test_extra_cflags = "-lomptarget @LIBOMPTARGET_TEST_CFLAGS@"
+config.libomptarget_obj_root = "@CMAKE_CURRENT_BINARY_DIR@"
+config.library_dir = "@LIBOMPTARGET_LIBRARY_DIR@"
+config.omp_header_directory = "@LIBOMPTARGET_OPENMP_HEADER_FOLDER@"
+config.omp_host_rtl_directory = "@LIBOMPTARGET_OPENMP_HOST_RTL_FOLDER@"
+config.operating_system = "@CMAKE_SYSTEM_NAME@"
+config.libomptarget_all_targets = "@LIBOMPTARGET_ALL_TARGETS@".split()
+config.libomptarget_system_targets = "@LIBOMPTARGET_SYSTEM_TARGETS@".split()
+config.libomptarget_filecheck = "@LIBOMPTARGET_FILECHECK_EXECUTABLE@"
+
+# Let the main config do the real work.
+lit_config.load_config(config, "@LIBOMPTARGET_BASE_DIR@/test/lit.cfg")
+

libomptarget/test/offloading/offloading_success.c

@@ -0,0 +1,23 @@
+// RUN: %libomptarget-compile-run-and-check-aarch64-unknown-linux-gnu
+// RUN: %libomptarget-compile-run-and-check-powerpc64-ibm-linux-gnu
+// RUN: %libomptarget-compile-run-and-check-powerpc64le-ibm-linux-gnu
+// RUN: %libomptarget-compile-run-and-check-x86_64-pc-linux-gnu
+
+#include <stdio.h>
+#include <omp.h>
+
+int main(void) {
+  int isHost = -1;
+
+#pragma omp target map(from: isHost)
+  { isHost = omp_is_initial_device(); }
+
+  if (isHost < 0) {
+    printf("Runtime error, isHost=%d\n", isHost);
+  }
+
+  // CHECK: Target region executed on the device
+  printf("Target region executed on the %s\n", isHost ? "host" : "device");
+
+  return isHost;
+}

libomptarget/test/offloading/offloading_success.cpp

@@ -0,0 +1,23 @@
+// RUN: %libomptarget-compilexx-run-and-check-aarch64-unknown-linux-gnu
+// RUN: %libomptarget-compilexx-run-and-check-powerpc64-ibm-linux-gnu
+// RUN: %libomptarget-compilexx-run-and-check-powerpc64le-ibm-linux-gnu
+// RUN: %libomptarget-compilexx-run-and-check-x86_64-pc-linux-gnu
+
+#include <stdio.h>
+#include <omp.h>
+
+int main(void) {
+  int isHost = 0;
+
+#pragma omp target map(from: isHost)
+  { isHost = omp_is_initial_device(); }
+
+  if (isHost < 0) {
+    printf("Runtime error, isHost=%d\n", isHost);
+  }
+
+  // CHECK: Target region executed on the device
+  printf("Target region executed on the %s\n", isHost ? "host" : "device");
+
+  return isHost;
+}

runtime/.clang-format

@@ -0,0 +1,91 @@
+---
+BasedOnStyle:  LLVM
+AlignTrailingComments: false
+SortIncludes:    false
+---
+# Language: Cpp
+# AccessModifierOffset: -2
+# AlignAfterOpenBracket: Align
+# AlignConsecutiveAssignments: false
+# AlignConsecutiveDeclarations: false
+# AlignEscapedNewlinesLeft: false
+# AlignOperands: false
+# AlignTrailingComments: false
+# AllowAllParametersOfDeclarationOnNextLine: true
+# AllowShortBlocksOnASingleLine: false
+# AllowShortCaseLabelsOnASingleLine: false
+# AllowShortFunctionsOnASingleLine: All
+# AllowShortIfStatementsOnASingleLine: false
+# AllowShortLoopsOnASingleLine: false
+# AlwaysBreakAfterDefinitionReturnType: None
+# AlwaysBreakAfterReturnType: None
+# AlwaysBreakBeforeMultilineStrings: false
+# AlwaysBreakTemplateDeclarations: false
+# BinPackArguments: true
+# BinPackParameters: true
+# BraceWrapping:   
+#   AfterClass:      false
+#   AfterControlStatement: false
+#   AfterEnum:       false
+#   AfterFunction:   false
+#   AfterNamespace:  false
+#   AfterObjCDeclaration: false
+#   AfterStruct:     false
+#   AfterUnion:      false
+#   BeforeCatch:     false
+#   BeforeElse:      false
+#   IndentBraces:    false
+# # BreakBeforeBinaryOperators: None
+# BreakBeforeBraces: Attach
+# BreakBeforeTernaryOperators: true
+# BreakConstructorInitializersBeforeComma: false
+# ColumnLimit:     80
+# CommentPragmas:  '^ IWYU pragma:'
+# ConstructorInitializerAllOnOneLineOrOnePerLine: false
+# ConstructorInitializerIndentWidth: 4
+# ContinuationIndentWidth: 4
+# Cpp11BracedListStyle: true
+# DerivePointerAlignment: false
+# DisableFormat:   true
+# ExperimentalAutoDetectBinPacking: false
+# ForEachMacros:   [ foreach, Q_FOREACH, BOOST_FOREACH ]
+# IncludeCategories: 
+#   - Regex:           '^"(llvm|llvm-c|clang|clang-c)/'
+#     Priority:        2
+#   - Regex:           '^(<|"(gtest|isl|json)/)'
+#     Priority:        3
+#   - Regex:           '.*'
+#     Priority:        1
+# IndentCaseLabels: false
+# IndentWidth:     2
+# IndentWrappedFunctionNames: false
+# KeepEmptyLinesAtTheStartOfBlocks: false
+# MacroBlockBegin: ''
+# MacroBlockEnd:   ''
+# MaxEmptyLinesToKeep: 2
+# NamespaceIndentation: None
+# ObjCBlockIndentWidth: 2
+# ObjCSpaceAfterProperty: false
+# ObjCSpaceBeforeProtocolList: true
+# PenaltyBreakBeforeFirstCallParameter: 19
+# PenaltyBreakComment: 300
+# PenaltyBreakFirstLessLess: 120
+# PenaltyBreakString: 1000
+# PenaltyExcessCharacter: 1000000
+# PenaltyReturnTypeOnItsOwnLine: 60
+# PointerAlignment: Right
+# ReflowComments:  true
+# SpaceAfterCStyleCast: false
+# SpaceBeforeAssignmentOperators: true
+# SpaceBeforeParens: ControlStatements
+# SpaceInEmptyParentheses: false
+# SpacesBeforeTrailingComments: 1
+# SpacesInAngles:  false
+# SpacesInContainerLiterals: true
+# SpacesInCStyleCastParentheses: false
+# SpacesInParentheses: false
+# SpacesInSquareBrackets: false
+# Standard:        Cpp11
+# TabWidth:        8
+# UseTab:          Never
+...

runtime/Build_With_CMake.txt

@@ -116,8 +116,8 @@ Library type can be normal, profile, or stubs.
 -DCMAKE_BUILD_TYPE=Release|Debug|RelWithDebInfo
 Build type can be Release, Debug, or RelWithDebInfo.
 
--DLIBOMP_OMP_VERSION=45|40|30
-OpenMP version can be either 45, 40 or 30.
+-DLIBOMP_OMP_VERSION=50|45|40|30
+OpenMP version can be either 50, 45, 40 or 30.
 
 -DLIBOMP_MIC_ARCH=knc|knf
 This value is ignored if LIBOMP_ARCH != mic

runtime/CMakeLists.txt

@@ -89,15 +89,13 @@ libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc64 ppc64le aarch64 m
 set(LIBOMP_LIB_TYPE normal CACHE STRING
   "Performance,Profiling,Stubs library (normal/profile/stubs)")
 libomp_check_variable(LIBOMP_LIB_TYPE normal profile stubs)
-set(LIBOMP_OMP_VERSION 45 CACHE STRING
-  "The OpenMP version (45/40/30)")
-if(LIBOMP_OMP_VERSION EQUAL 41)
-  libomp_warning_say("LIBOMP_OMP_VERSION=41 is deprecated and will be removed in a later version. Please use 45.")
-  set(LIBOMP_OMP_VERSION 45)
-endif()
-libomp_check_variable(LIBOMP_OMP_VERSION 45 40 30)
+set(LIBOMP_OMP_VERSION 50 CACHE STRING
+  "The OpenMP version (50/45/40/30)")
+libomp_check_variable(LIBOMP_OMP_VERSION 50 45 40 30)
 # Set the OpenMP Year and Month assiociated with version
-if(${LIBOMP_OMP_VERSION} GREATER 45 OR ${LIBOMP_OMP_VERSION} EQUAL 45)
+if(${LIBOMP_OMP_VERSION} GREATER 50 OR ${LIBOMP_OMP_VERSION} EQUAL 50)
+  set(LIBOMP_OMP_YEAR_MONTH 201611)
+elseif(${LIBOMP_OMP_VERSION} GREATER 45 OR ${LIBOMP_OMP_VERSION} EQUAL 45)
   set(LIBOMP_OMP_YEAR_MONTH 201511)
 elseif(${LIBOMP_OMP_VERSION} GREATER 40 OR ${LIBOMP_OMP_VERSION} EQUAL 40)
   set(LIBOMP_OMP_YEAR_MONTH 201307)
@@ -309,6 +307,11 @@ if(WIN32 AND NOT LIBOMP_ENABLE_SHARED)
   libomp_error_say("Static libraries requested but not available on Windows")
 endif()
 
+if(LIBOMP_USE_ITT_NOTIFY AND NOT LIBOMP_ENABLE_SHARED)
+  message(STATUS "ITT Notify not supported for static libraries - forcing ITT Notify off")
+  set(LIBOMP_USE_ITT_NOTIFY FALSE)
+endif()
+
 # OMPT-support
 set(LIBOMP_OMPT_DEBUG FALSE CACHE BOOL
   "Trace OMPT initialization?")

runtime/cmake/LibompHandleFlags.cmake

@@ -192,6 +192,9 @@ function(libomp_get_gdflags gdflags)
   libomp_append(gdflags_local "-D stub" STUBS_LIBRARY)
   libomp_append(gdflags_local "-D HAVE_QUAD" LIBOMP_USE_QUAD_PRECISION)
   libomp_append(gdflags_local "-D USE_DEBUGGER" LIBOMP_USE_DEBUGGER)
+  if(${LIBOMP_OMP_VERSION} GREATER 50 OR ${LIBOMP_OMP_VERSION} EQUAL 50)
+    libomp_append(gdflags_local "-D OMP_50")
+  endif()
   if(${LIBOMP_OMP_VERSION} GREATER 45 OR ${LIBOMP_OMP_VERSION} EQUAL 45)
     libomp_append(gdflags_local "-D OMP_45")
   endif()

runtime/src/CMakeLists.txt

@@ -93,7 +93,7 @@ else()
     # Unix specific files
     libomp_append(LIBOMP_CXXFILES z_Linux_util.cpp)
     libomp_append(LIBOMP_CXXFILES kmp_gsupport.cpp)
-    libomp_append(LIBOMP_ASMFILES z_Linux_asm.s) # Unix assembly file
+    libomp_append(LIBOMP_ASMFILES z_Linux_asm.S) # Unix assembly file
   endif()
   libomp_append(LIBOMP_CFILES thirdparty/ittnotify/ittnotify_static.c LIBOMP_USE_ITT_NOTIFY)
   libomp_append(LIBOMP_CXXFILES kmp_debugger.cpp LIBOMP_USE_DEBUGGER)

runtime/src/dllexports

@@ -351,7 +351,7 @@ kmpc_set_defaults                           224
     %ifdef OMP_30
         __kmpc_omp_taskyield                235
     %endif # OMP_30
-    __kmpc_place_threads                    236
+#    __kmpc_place_threads                    236
 %endif
 
 # OpenMP 4.0 entry points
@@ -397,6 +397,15 @@ kmpc_set_defaults                           224
 kmpc_aligned_malloc                         265
 kmpc_set_disp_num_buffers                   267
 
+# OpenMP 5.0 entry points
+# TODO: change to OMP_50 once it is implemented
+%ifndef stub
+    %ifdef OMP_45
+        __kmpc_task_reduction_init          268
+        __kmpc_task_reduction_get_th_data   269
+    %endif
+%endif
+
 # User API entry points that have both lower- and upper- case versions for Fortran.
 # Number for lowercase version is indicated.  Number for uppercase is obtained by adding 1000.
 # User API entry points are entry points that start with 'kmp_' or 'omp_'.
@@ -1108,15 +1117,19 @@ kmp_set_disp_num_buffers                    890
 
             %ifdef HAVE_QUAD
             __kmpc_atomic_fixed1_sub_rev_fp
+            __kmpc_atomic_fixed1u_sub_rev_fp
             __kmpc_atomic_fixed1_div_rev_fp
             __kmpc_atomic_fixed1u_div_rev_fp
             __kmpc_atomic_fixed2_sub_rev_fp
+            __kmpc_atomic_fixed2u_sub_rev_fp
             __kmpc_atomic_fixed2_div_rev_fp
             __kmpc_atomic_fixed2u_div_rev_fp
             __kmpc_atomic_fixed4_sub_rev_fp
+            __kmpc_atomic_fixed4u_sub_rev_fp
             __kmpc_atomic_fixed4_div_rev_fp
             __kmpc_atomic_fixed4u_div_rev_fp
             __kmpc_atomic_fixed8_sub_rev_fp
+            __kmpc_atomic_fixed8u_sub_rev_fp
             __kmpc_atomic_fixed8_div_rev_fp
             __kmpc_atomic_fixed8u_div_rev_fp
             __kmpc_atomic_float4_sub_rev_fp

runtime/src/exports_so.txt

@@ -84,10 +84,7 @@ VERSION {
         __kmp_acquire_tas_lock;
         __kmp_acquire_ticket_lock;
         __kmp_fork_call;
-        __kmp_get_reduce_method;
         __kmp_invoke_microtask;
-        __kmp_itt_fini_ittlib;
-        __kmp_itt_init_ittlib;
 #if KMP_USE_MONITOR
         __kmp_launch_monitor;
         __kmp_reap_monitor;

runtime/src/extractExternal.cpp

@@ -13,13 +13,13 @@
 //===----------------------------------------------------------------------===//
 
 
-#include <stdlib.h>
-#include <iostream>
-#include <strstream>
 #include <fstream>
-#include <string>
-#include <set>
+#include <iostream>
 #include <map>
+#include <set>
+#include <stdlib.h>
+#include <string>
+#include <strstream>
 
 /* Given a set of n object files h ('external' object files) and a set of m
    object files o ('internal' object files),
@@ -30,468 +30,457 @@
    Usage:
    hide.exe <n> <filenames for h> <filenames for o>
 
-   Thus, the prefixed symbols become hidden in the sense that they now have a special
-   prefix.
+   Thus, the prefixed symbols become hidden in the sense that they now have a
+   special prefix.
 */
 
 using namespace std;
 
-void stop(char* errorMsg) {
-    printf("%s\n", errorMsg);
-    exit(1);
+void stop(char *errorMsg) {
+  printf("%s\n", errorMsg);
+  exit(1);
 }
 
 // an entry in the symbol table of a .OBJ file
 class Symbol {
 public:
-    __int64 name;
-    unsigned value;
-    unsigned short sectionNum, type;
-    char storageClass, nAux;
+  __int64 name;
+  unsigned value;
+  unsigned short sectionNum, type;
+  char storageClass, nAux;
 };
 
 class _rstream : public istrstream {
 private:
-    const char *buf;
+  const char *buf;
+
 protected:
-    _rstream(pair<const char*, streamsize> p):istrstream(p.first,p.second),buf(p.first){}
-    ~_rstream() {
-	delete[]buf;
-    }
+  _rstream(pair<const char *, streamsize> p)
+      : istrstream(p.first, p.second), buf(p.first) {}
+  ~_rstream() { delete[] buf; }
 };
 
-/* A stream encapuslating the content of a file or the content of a string, overriding the
-   >> operator to read various integer types in binary form, as well as a symbol table
-   entry.
-*/
+// A stream encapuslating the content of a file or the content of a string,
+// overriding the >> operator to read various integer types in binary form,
+// as well as a symbol table entry.
 class rstream : public _rstream {
 private:
-    template<class T>
-    inline rstream& doRead(T &x) {
-	read((char*)&x, sizeof(T));
-	return *this;
-    }
-    static pair<const char*, streamsize> getBuf(const char *fileName) {
-	ifstream raw(fileName,ios::binary | ios::in);
-	if(!raw.is_open())
-	    stop("rstream.getBuf: Error opening file");
-	raw.seekg(0,ios::end);
-	streampos fileSize = raw.tellg();
-	if(fileSize < 0)
-	    stop("rstream.getBuf: Error reading file");
-	char *buf = new char[fileSize];
-	raw.seekg(0,ios::beg);
-	raw.read(buf, fileSize);
-	return pair<const char*, streamsize>(buf,fileSize);
-    }
+  template <class T> inline rstream &doRead(T &x) {
+    read((char *)&x, sizeof(T));
+    return *this;
+  }
+  static pair<const char *, streamsize> getBuf(const char *fileName) {
+    ifstream raw(fileName, ios::binary | ios::in);
+    if (!raw.is_open())
+      stop("rstream.getBuf: Error opening file");
+    raw.seekg(0, ios::end);
+    streampos fileSize = raw.tellg();
+    if (fileSize < 0)
+      stop("rstream.getBuf: Error reading file");
+    char *buf = new char[fileSize];
+    raw.seekg(0, ios::beg);
+    raw.read(buf, fileSize);
+    return pair<const char *, streamsize>(buf, fileSize);
+  }
+
 public:
-    // construct from a string
-    rstream(const char *buf,streamsize size):_rstream(pair<const char*,streamsize>(buf, size)){}
-    /* construct from a file whole content is fully read once to initialize the content of
-       this stream
-    */
-    rstream(const char *fileName):_rstream(getBuf(fileName)){}
-    rstream& operator>>(int &x) {
-	return doRead(x);
-    }
-    rstream& operator>>(unsigned &x) {
-	return doRead(x);
-    }
-    rstream& operator>>(short &x) {
-	return doRead(x);
-    }
-    rstream& operator>>(unsigned short &x) {
-	return doRead(x);
-    }
-    rstream& operator>>(Symbol &e) {
-	read((char*)&e, 18);
-	return *this;
-    }
+  // construct from a string
+  rstream(const char *buf, streamsize size)
+      : _rstream(pair<const char *, streamsize>(buf, size)) {}
+  // construct from a file whole content is fully read once to initialize the
+  // content of this stream
+  rstream(const char *fileName) : _rstream(getBuf(fileName)) {}
+  rstream &operator>>(int &x) { return doRead(x); }
+  rstream &operator>>(unsigned &x) { return doRead(x); }
+  rstream &operator>>(short &x) { return doRead(x); }
+  rstream &operator>>(unsigned short &x) { return doRead(x); }
+  rstream &operator>>(Symbol &e) {
+    read((char *)&e, 18);
+    return *this;
+  }
 };
 
 // string table in a .OBJ file
 class StringTable {
 private:
-    map<string, unsigned> directory;
-    size_t length;
-    char *data;
+  map<string, unsigned> directory;
+  size_t length;
+  char *data;
 
-    // make <directory> from <length> bytes in <data>
-    void makeDirectory(void) {
-	unsigned i = 4;
-	while(i < length) {
-	    string s = string(data + i);
-	    directory.insert(make_pair(s, i));
-	    i += s.size() + 1;
-	}
+  // make <directory> from <length> bytes in <data>
+  void makeDirectory(void) {
+    unsigned i = 4;
+    while (i < length) {
+      string s = string(data + i);
+      directory.insert(make_pair(s, i));
+      i += s.size() + 1;
     }
-    // initialize <length> and <data> with contents specified by the arguments
-    void init(const char *_data) {
-	unsigned _length = *(unsigned*)_data;
+  }
+  // initialize <length> and <data> with contents specified by the arguments
+  void init(const char *_data) {
+    unsigned _length = *(unsigned *)_data;
 
-	if(_length < sizeof(unsigned) || _length != *(unsigned*)_data)
-	    stop("StringTable.init: Invalid symbol table");
-	if(_data[_length - 1]) {
-	    // to prevent runaway strings, make sure the data ends with a zero
-	    data = new char[length = _length + 1];
-	    data[_length] = 0;
-	} else {
-	    data = new char[length = _length];
-	}
-	*(unsigned*)data = length;
-	KMP_MEMCPY(data + sizeof(unsigned), _data + sizeof(unsigned),
-	           length - sizeof(unsigned));
-	makeDirectory();
+    if (_length < sizeof(unsigned) || _length != *(unsigned *)_data)
+      stop("StringTable.init: Invalid symbol table");
+    if (_data[_length - 1]) {
+      // to prevent runaway strings, make sure the data ends with a zero
+      data = new char[length = _length + 1];
+      data[_length] = 0;
+    } else {
+      data = new char[length = _length];
     }
+    *(unsigned *)data = length;
+    KMP_MEMCPY(data + sizeof(unsigned), _data + sizeof(unsigned),
+               length - sizeof(unsigned));
+    makeDirectory();
+  }
+
 public:
-    StringTable(rstream &f) {
-	/* Construct string table by reading from f.
-	 */
-	streampos s;
-	unsigned strSize;
-	char *strData;
+  StringTable(rstream &f) {
+    // Construct string table by reading from f.
+    streampos s;
+    unsigned strSize;
+    char *strData;
 
-	s = f.tellg();
-	f>>strSize;
-	if(strSize < sizeof(unsigned))
-	    stop("StringTable: Invalid string table");
-	strData = new char[strSize];
-	*(unsigned*)strData = strSize;
-	// read the raw data into <strData>
-	f.read(strData + sizeof(unsigned), strSize - sizeof(unsigned));
-	s = f.tellg() - s;
-	if(s < strSize)
-	    stop("StringTable: Unexpected EOF");
-	init(strData);
-	delete[]strData;
-    }
-    StringTable(const set<string> &strings) {
-	/* Construct string table from given strings.
-	 */
-	char *p;
-	set<string>::const_iterator it;
-	size_t s;
+    s = f.tellg();
+    f >> strSize;
+    if (strSize < sizeof(unsigned))
+      stop("StringTable: Invalid string table");
+    strData = new char[strSize];
+    *(unsigned *)strData = strSize;
+    // read the raw data into <strData>
+    f.read(strData + sizeof(unsigned), strSize - sizeof(unsigned));
+    s = f.tellg() - s;
+    if (s < strSize)
+      stop("StringTable: Unexpected EOF");
+    init(strData);
+    delete[] strData;
+  }
+  StringTable(const set<string> &strings) {
+    // Construct string table from given strings.
+    char *p;
+    set<string>::const_iterator it;
+    size_t s;
 
-	// count required size for data
-	for(length = sizeof(unsigned), it = strings.begin(); it != strings.end(); ++it) {
-	    size_t l = (*it).size();
+    // count required size for data
+    for (length = sizeof(unsigned), it = strings.begin(); it != strings.end();
+         ++it) {
+      size_t l = (*it).size();
 
-	    if(l > (unsigned) 0xFFFFFFFF)
-		stop("StringTable: String too long");
-	    if(l > 8) {
-		length += l + 1;
-		if(length > (unsigned) 0xFFFFFFFF)
-		    stop("StringTable: Symbol table too long");
-	    }
-	}
-	data = new char[length];
-	*(unsigned*)data = length;
-	// populate data and directory
-	for(p = data + sizeof(unsigned), it = strings.begin(); it != strings.end(); ++it) {
-	    const string &str = *it;
-	    size_t l = str.size();
-	    if(l > 8) {
-		directory.insert(make_pair(str, p - data));
-		KMP_MEMCPY(p, str.c_str(), l);
-		p[l] = 0;
-		p += l + 1;
-	    }
-	}
+      if (l > (unsigned)0xFFFFFFFF)
+        stop("StringTable: String too long");
+      if (l > 8) {
+        length += l + 1;
+        if (length > (unsigned)0xFFFFFFFF)
+          stop("StringTable: Symbol table too long");
+      }
     }
-    ~StringTable() {
-	delete[] data;
+    data = new char[length];
+    *(unsigned *)data = length;
+    // populate data and directory
+    for (p = data + sizeof(unsigned), it = strings.begin(); it != strings.end();
+         ++it) {
+      const string &str = *it;
+      size_t l = str.size();
+      if (l > 8) {
+        directory.insert(make_pair(str, p - data));
+        KMP_MEMCPY(p, str.c_str(), l);
+        p[l] = 0;
+        p += l + 1;
+      }
     }
-    /* Returns encoding for given string based on this string table.
-       Error if string length is greater than 8 but string is not in
-       the string table--returns 0.
-    */
-    __int64 encode(const string &str) {
-	__int64 r;
+  }
+  ~StringTable() { delete[] data; }
+  // Returns encoding for given string based on this string table. Error if
+  // string length is greater than 8 but string is not in the string table
+  // -- returns 0.
+  __int64 encode(const string &str) {
+    __int64 r;
 
-	if(str.size() <= 8) {
-	    // encoded directly
-	    ((char*)&r)[7] = 0;
-	    KMP_STRNCPY_S((char*)&r, sizeof(r), str.c_str(), 8);
-	    return r;
-	} else {
-	    // represented as index into table
-	    map<string,unsigned>::const_iterator it = directory.find(str);
-	    if(it == directory.end())
-		stop("StringTable::encode: String now found in string table");
-	    ((unsigned*)&r)[0] = 0;
-	    ((unsigned*)&r)[1] = (*it).second;
-	    return r;
-	}
+    if (str.size() <= 8) {
+      // encoded directly
+      ((char *)&r)[7] = 0;
+      KMP_STRNCPY_S((char *)&r, sizeof(r), str.c_str(), 8);
+      return r;
+    } else {
+      // represented as index into table
+      map<string, unsigned>::const_iterator it = directory.find(str);
+      if (it == directory.end())
+        stop("StringTable::encode: String now found in string table");
+      ((unsigned *)&r)[0] = 0;
+      ((unsigned *)&r)[1] = (*it).second;
+      return r;
     }
-    /* Returns string represented by x based on this string table.
-       Error if x references an invalid position in the table--returns
-       the empty string.
-    */
-    string decode(__int64 x) const {
-	if(*(unsigned*)&x == 0) {
-	    // represented as index into table
-	    unsigned &p = ((unsigned*)&x)[1];
-	    if(p >= length)
-		stop("StringTable::decode: Invalid string table lookup");
-	    return string(data + p);
-	} else {
-	    // encoded directly
-	    char *p = (char*)&x;
-	    int i;
+  }
+  // Returns string represented by x based on this string table. Error if x
+  // references an invalid position in the table--returns the empty string.
+  string decode(__int64 x) const {
+    if (*(unsigned *)&x == 0) {
+      // represented as index into table
+      unsigned &p = ((unsigned *)&x)[1];
+      if (p >= length)
+        stop("StringTable::decode: Invalid string table lookup");
+      return string(data + p);
+    } else {
+      // encoded directly
+      char *p = (char *)&x;
+      int i;
 
-	    for(i = 0; i < 8 && p[i]; ++i);
-	    return string(p, i);
-	}
-    }
-    void write(ostream &os) {
-	os.write(data, length);
+      for (i = 0; i < 8 && p[i]; ++i)
+        ;
+      return string(p, i);
     }
+  }
+  void write(ostream &os) { os.write(data, length); }
 };
 
-/* for the named object file, determines the set of defined symbols and the set of undefined external symbols
-   and writes them to <defined> and <undefined> respectively
-*/
-void computeExternalSymbols(const char *fileName, set<string> *defined, set<string> *undefined){
-    streampos fileSize;
-    size_t strTabStart;
-    unsigned symTabStart, symNEntries;
-    rstream f(fileName);
+// for the named object file, determines the set of defined symbols and the set
+// of undefined external symbols and writes them to <defined> and <undefined>
+// respectively
+void computeExternalSymbols(const char *fileName, set<string> *defined,
+                            set<string> *undefined) {
+  streampos fileSize;
+  size_t strTabStart;
+  unsigned symTabStart, symNEntries;
+  rstream f(fileName);
 
-    f.seekg(0,ios::end);
-    fileSize = f.tellg();
+  f.seekg(0, ios::end);
+  fileSize = f.tellg();
 
-    f.seekg(8);
-    f >> symTabStart >> symNEntries;
-    // seek to the string table
-    f.seekg(strTabStart = symTabStart + 18 * (size_t)symNEntries);
-    if(f.eof()) {
-	printf("computeExternalSymbols: fileName='%s', fileSize = %lu, symTabStart = %u, symNEntries = %u\n",
-	       fileName, (unsigned long) fileSize, symTabStart, symNEntries);
-	stop("computeExternalSymbols: Unexpected EOF 1");
-    }
-    StringTable stringTable(f); // read the string table
-    if(f.tellg() != fileSize)
-	stop("computeExternalSymbols: Unexpected data after string table");
-
-    f.clear();
-    f.seekg(symTabStart); // seek to the symbol table
-
-    defined->clear(); undefined->clear();
-    for(int i = 0; i < symNEntries; ++i) {
-	// process each entry
-	Symbol e;
-
-	if(f.eof())
-	    stop("computeExternalSymbols: Unexpected EOF 2");
-	f>>e;
-	if(f.fail())
-	    stop("computeExternalSymbols: File read error");
-	if(e.nAux) { // auxiliary entry: skip
-	    f.seekg(e.nAux * 18, ios::cur);
-	    i += e.nAux;
-	}
-	// if symbol is extern and defined in the current file, insert it
-	if(e.storageClass == 2)
-	    if(e.sectionNum)
-		defined->insert(stringTable.decode(e.name));
-	    else
-		undefined->insert(stringTable.decode(e.name));
+  f.seekg(8);
+  f >> symTabStart >> symNEntries;
+  // seek to the string table
+  f.seekg(strTabStart = symTabStart + 18 * (size_t)symNEntries);
+  if (f.eof()) {
+    printf("computeExternalSymbols: fileName='%s', fileSize = %lu, symTabStart "
+           "= %u, symNEntries = %u\n",
+           fileName, (unsigned long)fileSize, symTabStart, symNEntries);
+    stop("computeExternalSymbols: Unexpected EOF 1");
+  }
+  StringTable stringTable(f); // read the string table
+  if (f.tellg() != fileSize)
+    stop("computeExternalSymbols: Unexpected data after string table");
+
+  f.clear();
+  f.seekg(symTabStart); // seek to the symbol table
+
+  defined->clear();
+  undefined->clear();
+  for (int i = 0; i < symNEntries; ++i) {
+    // process each entry
+    Symbol e;
+
+    if (f.eof())
+      stop("computeExternalSymbols: Unexpected EOF 2");
+    f >> e;
+    if (f.fail())
+      stop("computeExternalSymbols: File read error");
+    if (e.nAux) { // auxiliary entry: skip
+      f.seekg(e.nAux * 18, ios::cur);
+      i += e.nAux;
     }
+    // if symbol is extern and defined in the current file, insert it
+    if (e.storageClass == 2)
+      if (e.sectionNum)
+        defined->insert(stringTable.decode(e.name));
+      else
+        undefined->insert(stringTable.decode(e.name));
+  }
 }
 
-/* For each occurrence of an external symbol in the object file named by
-   by <fileName> that is a member of <hide>, renames it by prefixing
-   with "__kmp_external_", writing back the file in-place
-*/
+// For each occurrence of an external symbol in the object file named by
+// by <fileName> that is a member of <hide>, renames it by prefixing
+// with "__kmp_external_", writing back the file in-place
 void hideSymbols(char *fileName, const set<string> &hide) {
-    static const string prefix("__kmp_external_");
-    set<string> strings; // set of all occurring symbols, appropriately prefixed
-    streampos fileSize;
-    size_t strTabStart;
-    unsigned symTabStart, symNEntries;
-    int i;
-    rstream in(fileName);
+  static const string prefix("__kmp_external_");
+  set<string> strings; // set of all occurring symbols, appropriately prefixed
+  streampos fileSize;
+  size_t strTabStart;
+  unsigned symTabStart, symNEntries;
+  int i;
+  rstream in(fileName);
 
-    in.seekg(0,ios::end);
-    fileSize = in.tellg();
+  in.seekg(0, ios::end);
+  fileSize = in.tellg();
 
-    in.seekg(8);
-    in >> symTabStart >> symNEntries;
-    in.seekg(strTabStart = symTabStart + 18 * (size_t)symNEntries);
-    if(in.eof())
-	stop("hideSymbols: Unexpected EOF");
-    StringTable stringTableOld(in); // read original string table
+  in.seekg(8);
+  in >> symTabStart >> symNEntries;
+  in.seekg(strTabStart = symTabStart + 18 * (size_t)symNEntries);
+  if (in.eof())
+    stop("hideSymbols: Unexpected EOF");
+  StringTable stringTableOld(in); // read original string table
 
-    if(in.tellg() != fileSize)
-	stop("hideSymbols: Unexpected data after string table");
+  if (in.tellg() != fileSize)
+    stop("hideSymbols: Unexpected data after string table");
 
-    // compute set of occurring strings with prefix added
-    for(i = 0; i < symNEntries; ++i) {
-	Symbol e;
+  // compute set of occurring strings with prefix added
+  for (i = 0; i < symNEntries; ++i) {
+    Symbol e;
 
-	in.seekg(symTabStart + i * 18);
-	if(in.eof())
-	    stop("hideSymbols: Unexpected EOF");
-	in >> e;
-	if(in.fail())
-	    stop("hideSymbols: File read error");
-	if(e.nAux)
-	    i += e.nAux;
-	const string &s = stringTableOld.decode(e.name);
-	// if symbol is extern and found in <hide>, prefix and insert into strings,
-	// otherwise, just insert into strings without prefix
-	strings.insert( (e.storageClass == 2 && hide.find(s) != hide.end()) ?
-			prefix + s : s);
+    in.seekg(symTabStart + i * 18);
+    if (in.eof())
+      stop("hideSymbols: Unexpected EOF");
+    in >> e;
+    if (in.fail())
+      stop("hideSymbols: File read error");
+    if (e.nAux)
+      i += e.nAux;
+    const string &s = stringTableOld.decode(e.name);
+    // if symbol is extern and found in <hide>, prefix and insert into strings,
+    // otherwise, just insert into strings without prefix
+    strings.insert(
+        (e.storageClass == 2 && hide.find(s) != hide.end()) ? prefix + s : s);
+  }
+
+  ofstream out(fileName, ios::trunc | ios::out | ios::binary);
+  if (!out.is_open())
+    stop("hideSymbols: Error opening output file");
+
+  // make new string table from string set
+  StringTable stringTableNew = StringTable(strings);
+
+  // copy input file to output file up to just before the symbol table
+  in.seekg(0);
+  char *buf = new char[symTabStart];
+  in.read(buf, symTabStart);
+  out.write(buf, symTabStart);
+  delete[] buf;
+
+  // copy input symbol table to output symbol table with name translation
+  for (i = 0; i < symNEntries; ++i) {
+    Symbol e;
+
+    in.seekg(symTabStart + i * 18);
+    if (in.eof())
+      stop("hideSymbols: Unexpected EOF");
+    in >> e;
+    if (in.fail())
+      stop("hideSymbols: File read error");
+    const string &s = stringTableOld.decode(e.name);
+    out.seekp(symTabStart + i * 18);
+    e.name = stringTableNew.encode(
+        (e.storageClass == 2 && hide.find(s) != hide.end()) ? prefix + s : s);
+    out.write((char *)&e, 18);
+    if (out.fail())
+      stop("hideSymbols: File write error");
+    if (e.nAux) {
+      // copy auxiliary symbol table entries
+      int nAux = e.nAux;
+      for (int j = 1; j <= nAux; ++j) {
+        in >> e;
+        out.seekp(symTabStart + (i + j) * 18);
+        out.write((char *)&e, 18);
+      }
+      i += nAux;
     }
-
-    ofstream out(fileName, ios::trunc | ios::out | ios::binary);
-    if(!out.is_open())
-	stop("hideSymbols: Error opening output file");
-
-    // make new string table from string set
-    StringTable stringTableNew = StringTable(strings);
-
-    // copy input file to output file up to just before the symbol table
-    in.seekg(0);
-    char *buf = new char[symTabStart];
-    in.read(buf, symTabStart);
-    out.write(buf, symTabStart);
-    delete []buf;
-
-    // copy input symbol table to output symbol table with name translation
-    for(i = 0; i < symNEntries; ++i) {
-	Symbol e;
-
-	in.seekg(symTabStart + i*18);
-	if(in.eof())
-	    stop("hideSymbols: Unexpected EOF");
-	in >> e;
-	if(in.fail())
-	    stop("hideSymbols: File read error");
-	const string &s = stringTableOld.decode(e.name);
-	out.seekp(symTabStart + i*18);
-	e.name = stringTableNew.encode( (e.storageClass == 2 && hide.find(s) != hide.end()) ?
-					prefix + s : s);
-	out.write((char*)&e, 18);
-	if(out.fail())
-	    stop("hideSymbols: File write error");
-	if(e.nAux) {
-	    // copy auxiliary symbol table entries
-	    int nAux = e.nAux;
-	    for(int j = 1; j <= nAux; ++j) {
-		in >> e;
-		out.seekp(symTabStart + (i + j) * 18);
-		out.write((char*)&e, 18);
-	    }
-	    i += nAux;
-	}
-    }
-    // output string table
-    stringTableNew.write(out);
+  }
+  // output string table
+  stringTableNew.write(out);
 }
 
 // returns true iff <a> and <b> have no common element
-template <class T>
-bool isDisjoint(const set<T> &a, const set<T> &b) {
-    set<T>::const_iterator ita, itb;
+template <class T> bool isDisjoint(const set<T> &a, const set<T> &b) {
+  set<T>::const_iterator ita, itb;
 
-    for(ita = a.begin(), itb = b.begin(); ita != a.end() && itb != b.end();) {
-	const T &ta = *ita, &tb = *itb;
-	if(ta < tb)
-	    ++ita;
-	else if (tb < ta)
-	    ++itb;
-	else
-	    return false;
-    }
-    return true;
+  for (ita = a.begin(), itb = b.begin(); ita != a.end() && itb != b.end();) {
+    const T &ta = *ita, &tb = *itb;
+    if (ta < tb)
+      ++ita;
+    else if (tb < ta)
+      ++itb;
+    else
+      return false;
+  }
+  return true;
 }
 
-/* precondition: <defined> and <undefined> are arrays with <nTotal> elements where
-   <nTotal> >= <nExternal>.  The first <nExternal> elements correspond to the external object
-   files and the rest correspond to the internal object files.
-   postcondition: file x is said to depend on file y if undefined[x] and defined[y] are not
-   disjoint.  Returns the transitive closure of the set of internal object files, as a set of
-   file indexes, under the 'depends on' relation, minus the set of internal object files.
-*/
-set<int> *findRequiredExternal(int nExternal, int nTotal, set<string> *defined, set<string> *undefined) {
-    set<int> *required = new set<int>;
-    set<int> fresh[2];
-    int i, cur = 0;
-    bool changed;
+// PRE: <defined> and <undefined> are arrays with <nTotal> elements where
+// <nTotal> >= <nExternal>.  The first <nExternal> elements correspond to the
+// external object files and the rest correspond to the internal object files.
+// POST: file x is said to depend on file y if undefined[x] and defined[y] are
+// not disjoint. Returns the transitive closure of the set of internal object
+// files, as a set of file indexes, under the 'depends on' relation, minus the
+// set of internal object files.
+set<int> *findRequiredExternal(int nExternal, int nTotal, set<string> *defined,
+                               set<string> *undefined) {
+  set<int> *required = new set<int>;
+  set<int> fresh[2];
+  int i, cur = 0;
+  bool changed;
 
-    for(i = nTotal - 1; i >= nExternal; --i)
-	fresh[cur].insert(i);
-    do {
-	changed = false;
-	for(set<int>::iterator it = fresh[cur].begin(); it != fresh[cur].end(); ++it) {
-	    set<string> &s = undefined[*it];
+  for (i = nTotal - 1; i >= nExternal; --i)
+    fresh[cur].insert(i);
+  do {
+    changed = false;
+    for (set<int>::iterator it = fresh[cur].begin(); it != fresh[cur].end();
+         ++it) {
+      set<string> &s = undefined[*it];
 
-	    for(i = 0; i < nExternal; ++i) {
-		if(required->find(i) == required->end()) {
-		    if(!isDisjoint(defined[i], s)) {
-			// found a new qualifying element
-			required->insert(i);
-			fresh[1 - cur].insert(i);
-			changed = true;
-		    }
-		}
-	    }
-	}
-	fresh[cur].clear();
-	cur = 1 - cur;
-    } while(changed);
-    return required;
+      for (i = 0; i < nExternal; ++i) {
+        if (required->find(i) == required->end()) {
+          if (!isDisjoint(defined[i], s)) {
+            // found a new qualifying element
+            required->insert(i);
+            fresh[1 - cur].insert(i);
+            changed = true;
+          }
+        }
+      }
+    }
+    fresh[cur].clear();
+    cur = 1 - cur;
+  } while (changed);
+  return required;
 }
 
 int main(int argc, char **argv) {
-    int nExternal, nInternal, i;
-    set<string> *defined, *undefined;
-    set<int>::iterator it;
+  int nExternal, nInternal, i;
+  set<string> *defined, *undefined;
+  set<int>::iterator it;
 
-    if(argc < 3)
-	stop("Please specify a positive integer followed by a list of object filenames");
-    nExternal = atoi(argv[1]);
-    if(nExternal <= 0)
-	stop("Please specify a positive integer followed by a list of object filenames");
-    if(nExternal +  2 > argc)
-	stop("Too few external objects");
-    nInternal = argc - nExternal - 2;
-    defined = new set<string>[argc - 2];
-    undefined = new set<string>[argc - 2];
+  if (argc < 3)
+    stop("Please specify a positive integer followed by a list of object "
+         "filenames");
+  nExternal = atoi(argv[1]);
+  if (nExternal <= 0)
+    stop("Please specify a positive integer followed by a list of object "
+         "filenames");
+  if (nExternal + 2 > argc)
+    stop("Too few external objects");
+  nInternal = argc - nExternal - 2;
+  defined = new set<string>[argc - 2];
+  undefined = new set<string>[argc - 2];
 
-    // determine the set of defined and undefined external symbols
-    for(i = 2; i < argc; ++i)
-	computeExternalSymbols(argv[i], defined + i - 2, undefined + i - 2);
+  // determine the set of defined and undefined external symbols
+  for (i = 2; i < argc; ++i)
+    computeExternalSymbols(argv[i], defined + i - 2, undefined + i - 2);
 
-    // determine the set of required external files
-    set<int> *requiredExternal = findRequiredExternal(nExternal, argc - 2, defined, undefined);
-    set<string> hide;
+  // determine the set of required external files
+  set<int> *requiredExternal =
+      findRequiredExternal(nExternal, argc - 2, defined, undefined);
+  set<string> hide;
 
-    /* determine the set of symbols to hide--namely defined external symbols of the
-       required external files
-    */
-    for(it = requiredExternal->begin(); it != requiredExternal->end(); ++it) {
-	int idx = *it;
-	set<string>::iterator it2;
-	/* We have to insert one element at a time instead of inserting a range because
-	   the insert member function taking a range doesn't exist on Windows* OS, at least
-	   at the time of this writing.
-	*/
-	for(it2 = defined[idx].begin(); it2 != defined[idx].end(); ++it2)
-	    hide.insert(*it2);
-    }
+  // determine the set of symbols to hide--namely defined external symbols of
+  // the required external files
+  for (it = requiredExternal->begin(); it != requiredExternal->end(); ++it) {
+    int idx = *it;
+    set<string>::iterator it2;
+    // We have to insert one element at a time instead of inserting a range
+    // because the insert member function taking a range doesn't exist on
+    // Windows* OS, at least at the time of this writing.
+    for (it2 = defined[idx].begin(); it2 != defined[idx].end(); ++it2)
+      hide.insert(*it2);
+  }
 
-    /* process the external files--removing those that are not required and hiding
-       the appropriate symbols in the others
-    */
-    for(i = 0; i < nExternal; ++i)
-	if(requiredExternal->find(i) != requiredExternal->end())
-	    hideSymbols(argv[2 + i], hide);
-	else
-	    remove(argv[2 + i]);
-    // hide the appropriate symbols in the internal files
-    for(i = nExternal + 2; i < argc; ++i)
-	hideSymbols(argv[i], hide);
-    return 0;
+  // process the external files--removing those that are not required and hiding
+  //   the appropriate symbols in the others
+  for (i = 0; i < nExternal; ++i)
+    if (requiredExternal->find(i) != requiredExternal->end())
+      hideSymbols(argv[2 + i], hide);
+    else
+      remove(argv[2 + i]);
+  // hide the appropriate symbols in the internal files
+  for (i = nExternal + 2; i < argc; ++i)
+    hideSymbols(argv[i], hide);
+  return 0;
 }

runtime/src/i18n/en_US.txt

@@ -38,7 +38,7 @@ Language "English"
 Country  "USA"
 LangId   "1033"
 Version  "2"
-Revision "20160714"
+Revision "20161216"
 
 
 
@@ -388,15 +388,15 @@ OBSOLETE                     "%1$s: granularity=core will be used."
 EnvLockWarn                  "%1$s must be set prior to first OMP lock call or critical section; ignored."
 FutexNotSupported            "futex system call not supported; %1$s=%2$s ignored."
 AffGranUsing                 "%1$s: granularity=%2$s will be used."
-AffHWSubsetInvalid           "%1$s: invalid value \"%2$s\", valid format is \"Ns[@N],Nc[@N],Nt "
-                             "(nSockets@offset, nCores@offset, nTthreads per core)\"."
+AffHWSubsetInvalid           "%1$s: invalid value \"%2$s\", valid format is \"N<item>[@N][,...][,Nt] "
+                             "(<item> can be S, N, L2, C, T  for Socket, NUMA Node, L2 Cache, Core, Thread)\"."
 AffHWSubsetUnsupported       "KMP_HW_SUBSET ignored: unsupported architecture."
 AffHWSubsetManyCores         "KMP_HW_SUBSET ignored: too many cores requested."
 SyntaxErrorUsing             "%1$s: syntax error, using %2$s."
 AdaptiveNotSupported         "%1$s: Adaptive locks are not supported; using queuing."
 EnvSyntaxError               "%1$s: Invalid symbols found. Check the value \"%2$s\"."
 EnvSpacesNotAllowed          "%1$s: Spaces between digits are not allowed \"%2$s\"."
-BoundToOSProcSet             "%1$s: pid %2$d thread %3$d bound to OS proc set %4$s"
+BoundToOSProcSet             "%1$s: pid %2$d tid %3$d thread %4$d bound to OS proc set %5$s"
 CnsLoopIncrIllegal           "%1$s error: parallel loop increment and condition are inconsistent."
 NoGompCancellation           "libgomp cancellation is not currently supported."
 AffHWSubsetNonUniform        "KMP_HW_SUBSET ignored: non-uniform topology."
@@ -411,6 +411,10 @@ AffHwlocErrorOccurred        "%1$s: Hwloc failed in %2$s. Relying on internal af
 EnvSerialWarn                "%1$s must be set prior to OpenMP runtime library initialization; ignored."
 EnvVarDeprecated             "%1$s variable deprecated, please use %2$s instead."
 RedMethodNotSupported        "KMP_FORCE_REDUCTION: %1$s method is not supported; using critical."
+AffHWSubsetNoHWLOC           "KMP_HW_SUBSET ignored: unsupported item requested for non-HWLOC topology method (KMP_TOPOLOGY_METHOD)"
+AffHWSubsetManyNodes         "KMP_HW_SUBSET ignored: too many NUMA Nodes requested."
+AffHWSubsetManyTiles         "KMP_HW_SUBSET ignored: too many L2 Caches requested."
+AffHWSubsetManyProcs         "KMP_HW_SUBSET ignored: too many Procs requested."
 
 
 # --------------------------------------------------------------------------------------------------
@@ -425,7 +429,7 @@ SubmitBugReport              "Please submit a bug report with this message, comp
                              "compiler and operating system versions. Faster response will be "
                              "obtained by including all program sources. For information on "
                              "submitting this issue, please see "
-                             "http://www.intel.com/software/products/support/."
+                             "https://bugs.llvm.org/."
 OBSOLETE                     "Check NLSPATH environment variable, its value is \"%1$s\"."
 ChangeStackLimit             "Please try changing the shell stack limit or adjusting the "
                              "OMP_STACKSIZE environment variable."
@@ -441,7 +445,7 @@ DuplicateLibrary             "This means that multiple copies of the OpenMP runt
                              "you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow "
                              "the program to continue to execute, but that may cause crashes or "
                              "silently produce incorrect results. "
-                             "For more information, please see http://www.intel.com/software/products/support/."
+                             "For more information, please see http://openmp.llvm.org/"
 NameComesFrom_CPUINFO_FILE   "This name is specified in environment variable KMP_CPUINFO_FILE."
 NotEnoughMemory              "Seems application required too much memory."
 ValidBoolValues              "Use \"0\", \"FALSE\". \".F.\", \"off\", \"no\" as false values, "

runtime/src/include/50/omp.h.var

@@ -0,0 +1,198 @@
+/*
+ * include/50/omp.h.var
+ */
+
+
+//===----------------------------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is dual licensed under the MIT and the University of Illinois Open
+// Source Licenses. See LICENSE.txt for details.
+//
+//===----------------------------------------------------------------------===//
+
+
+#ifndef __OMP_H
+#   define __OMP_H
+
+#   define KMP_VERSION_MAJOR    @LIBOMP_VERSION_MAJOR@
+#   define KMP_VERSION_MINOR    @LIBOMP_VERSION_MINOR@
+#   define KMP_VERSION_BUILD    @LIBOMP_VERSION_BUILD@
+#   define KMP_BUILD_DATE       "@LIBOMP_BUILD_DATE@"
+
+#   ifdef __cplusplus
+    extern "C" {
+#   endif
+
+#   if defined(_WIN32)
+#       define __KAI_KMPC_CONVENTION __cdecl
+#   else
+#       define __KAI_KMPC_CONVENTION
+#   endif
+
+    /* schedule kind constants */
+    typedef enum omp_sched_t {
+	omp_sched_static  = 1,
+	omp_sched_dynamic = 2,
+	omp_sched_guided  = 3,
+	omp_sched_auto    = 4
+    } omp_sched_t;
+
+    /* set API functions */
+    extern void   __KAI_KMPC_CONVENTION  omp_set_num_threads (int);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_dynamic     (int);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_nested      (int);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_max_active_levels (int);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_schedule          (omp_sched_t, int);
+
+    /* query API functions */
+    extern int    __KAI_KMPC_CONVENTION  omp_get_num_threads  (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_dynamic      (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_nested       (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_max_threads  (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_thread_num   (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_num_procs    (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_in_parallel      (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_in_final         (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_active_level        (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_level               (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_ancestor_thread_num (int);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_team_size           (int);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_thread_limit        (void);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_max_active_levels   (void);
+    extern void   __KAI_KMPC_CONVENTION  omp_get_schedule            (omp_sched_t *, int *);
+    extern int    __KAI_KMPC_CONVENTION  omp_get_max_task_priority   (void);
+
+    /* lock API functions */
+    typedef struct omp_lock_t {
+        void * _lk;
+    } omp_lock_t;
+
+    extern void   __KAI_KMPC_CONVENTION  omp_init_lock    (omp_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_lock     (omp_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_unset_lock   (omp_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_destroy_lock (omp_lock_t *);
+    extern int    __KAI_KMPC_CONVENTION  omp_test_lock    (omp_lock_t *);
+
+    /* nested lock API functions */
+    typedef struct omp_nest_lock_t {
+        void * _lk;
+    } omp_nest_lock_t;
+
+    extern void   __KAI_KMPC_CONVENTION  omp_init_nest_lock    (omp_nest_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_set_nest_lock     (omp_nest_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_unset_nest_lock   (omp_nest_lock_t *);
+    extern void   __KAI_KMPC_CONVENTION  omp_destroy_nest_lock (omp_nest_lock_t *);
+    extern int    __KAI_KMPC_CONVENTION  omp_test_nest_lock    (omp_nest_lock_t *);
+
+    /* lock hint type for dynamic user lock */
+    typedef enum omp_lock_hint_t {
+        omp_lock_hint_none           = 0,
+        omp_lock_hint_uncontended    = 1,
+        omp_lock_hint_contended      = (1<<1 ),
+        omp_lock_hint_nonspeculative = (1<<2 ),
+        omp_lock_hint_speculative    = (1<<3 ),
+        kmp_lock_hint_hle            = (1<<16),
+        kmp_lock_hint_rtm            = (1<<17),
+        kmp_lock_hint_adaptive       = (1<<18)
+    } omp_lock_hint_t;
+
+    /* hinted lock initializers */
+    extern void __KAI_KMPC_CONVENTION omp_init_lock_with_hint(omp_lock_t *, omp_lock_hint_t);
+    extern void __KAI_KMPC_CONVENTION omp_init_nest_lock_with_hint(omp_nest_lock_t *, omp_lock_hint_t);
+
+    /* time API functions */
+    extern double __KAI_KMPC_CONVENTION  omp_get_wtime (void);
+    extern double __KAI_KMPC_CONVENTION  omp_get_wtick (void);
+
+    /* OpenMP 4.0 */
+    extern int  __KAI_KMPC_CONVENTION  omp_get_default_device (void);
+    extern void __KAI_KMPC_CONVENTION  omp_set_default_device (int);
+    extern int  __KAI_KMPC_CONVENTION  omp_is_initial_device (void);
+    extern int  __KAI_KMPC_CONVENTION  omp_get_num_devices (void);
+    extern int  __KAI_KMPC_CONVENTION  omp_get_num_teams (void);
+    extern int  __KAI_KMPC_CONVENTION  omp_get_team_num (void);
+    extern int  __KAI_KMPC_CONVENTION  omp_get_cancellation (void);
+
+#   include <stdlib.h>
+    /* OpenMP 4.5 */
+    extern int   __KAI_KMPC_CONVENTION  omp_get_initial_device (void);
+    extern void* __KAI_KMPC_CONVENTION  omp_target_alloc(size_t, int);
+    extern void  __KAI_KMPC_CONVENTION  omp_target_free(void *, int);
+    extern int   __KAI_KMPC_CONVENTION  omp_target_is_present(void *, int);
+    extern int   __KAI_KMPC_CONVENTION  omp_target_memcpy(void *, void *, size_t, size_t, size_t, int, int);
+    extern int   __KAI_KMPC_CONVENTION  omp_target_memcpy_rect(void *, void *, size_t, int, const size_t *,
+                                            const size_t *, const size_t *, const size_t *, const size_t *, int, int);
+    extern int   __KAI_KMPC_CONVENTION  omp_target_associate_ptr(void *, void *, size_t, size_t, int);
+    extern int   __KAI_KMPC_CONVENTION  omp_target_disassociate_ptr(void *, int);
+
+    /* kmp API functions */
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_stacksize          (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_stacksize          (int);
+    extern size_t __KAI_KMPC_CONVENTION  kmp_get_stacksize_s        (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_stacksize_s        (size_t);
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_blocktime          (void);
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_library            (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_blocktime          (int);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_library            (int);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_library_serial     (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_library_turnaround (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_library_throughput (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_defaults           (char const *);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_disp_num_buffers   (int);
+
+    /* Intel affinity API */
+    typedef void * kmp_affinity_mask_t;
+
+    extern int    __KAI_KMPC_CONVENTION  kmp_set_affinity             (kmp_affinity_mask_t *);
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_affinity             (kmp_affinity_mask_t *);
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_affinity_max_proc    (void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_create_affinity_mask     (kmp_affinity_mask_t *);
+    extern void   __KAI_KMPC_CONVENTION  kmp_destroy_affinity_mask    (kmp_affinity_mask_t *);
+    extern int    __KAI_KMPC_CONVENTION  kmp_set_affinity_mask_proc   (int, kmp_affinity_mask_t *);
+    extern int    __KAI_KMPC_CONVENTION  kmp_unset_affinity_mask_proc (int, kmp_affinity_mask_t *);
+    extern int    __KAI_KMPC_CONVENTION  kmp_get_affinity_mask_proc   (int, kmp_affinity_mask_t *);
+
+    /* OpenMP 4.0 affinity API */
+    typedef enum omp_proc_bind_t {
+        omp_proc_bind_false = 0,
+        omp_proc_bind_true = 1,
+        omp_proc_bind_master = 2,
+        omp_proc_bind_close = 3,
+        omp_proc_bind_spread = 4
+    } omp_proc_bind_t;
+
+    extern omp_proc_bind_t __KAI_KMPC_CONVENTION omp_get_proc_bind (void);
+
+    /* OpenMP 4.5 affinity API */
+    extern int  __KAI_KMPC_CONVENTION omp_get_num_places (void);
+    extern int  __KAI_KMPC_CONVENTION omp_get_place_num_procs (int);
+    extern void __KAI_KMPC_CONVENTION omp_get_place_proc_ids (int, int *);
+    extern int  __KAI_KMPC_CONVENTION omp_get_place_num (void);
+    extern int  __KAI_KMPC_CONVENTION omp_get_partition_num_places (void);
+    extern void __KAI_KMPC_CONVENTION omp_get_partition_place_nums (int *);
+
+    extern void * __KAI_KMPC_CONVENTION  kmp_malloc  (size_t);
+    extern void * __KAI_KMPC_CONVENTION  kmp_aligned_malloc  (size_t, size_t);
+    extern void * __KAI_KMPC_CONVENTION  kmp_calloc  (size_t, size_t);
+    extern void * __KAI_KMPC_CONVENTION  kmp_realloc (void *, size_t);
+    extern void   __KAI_KMPC_CONVENTION  kmp_free    (void *);
+
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_warnings_on(void);
+    extern void   __KAI_KMPC_CONVENTION  kmp_set_warnings_off(void);
+
+#   undef __KAI_KMPC_CONVENTION
+
+    /* Warning:
+       The following typedefs are not standard, deprecated and will be removed in a future release.
+    */
+    typedef int     omp_int_t;
+    typedef double  omp_wtime_t;
+
+#   ifdef __cplusplus
+    }
+#   endif
+
+#endif /* __OMP_H */
+

runtime/src/include/50/omp_lib.f.var

@@ -0,0 +1,855 @@
+! include/50/omp_lib.f.var
+
+!
+!//===----------------------------------------------------------------------===//
+!//
+!//                     The LLVM Compiler Infrastructure
+!//
+!// This file is dual licensed under the MIT and the University of Illinois Open
+!// Source Licenses. See LICENSE.txt for details.
+!//
+!//===----------------------------------------------------------------------===//
+!
+
+!***
+!*** Some of the directives for the following routine extend past column 72,
+!*** so process this file in 132-column mode.
+!***
+
+!dec$ fixedformlinesize:132
+
+      module omp_lib_kinds
+
+        integer, parameter :: omp_integer_kind       = 4
+        integer, parameter :: omp_logical_kind       = 4
+        integer, parameter :: omp_real_kind          = 4
+        integer, parameter :: omp_lock_kind          = int_ptr_kind()
+        integer, parameter :: omp_nest_lock_kind     = int_ptr_kind()
+        integer, parameter :: omp_sched_kind         = omp_integer_kind
+        integer, parameter :: omp_proc_bind_kind     = omp_integer_kind
+        integer, parameter :: kmp_pointer_kind       = int_ptr_kind()
+        integer, parameter :: kmp_size_t_kind        = int_ptr_kind()
+        integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
+        integer, parameter :: kmp_cancel_kind        = omp_integer_kind
+        integer, parameter :: omp_lock_hint_kind     = omp_integer_kind
+
+      end module omp_lib_kinds
+
+      module omp_lib
+
+        use omp_lib_kinds
+
+        integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
+        integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
+        integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
+        character(*), parameter :: kmp_build_date    = '@LIBOMP_BUILD_DATE@'
+        integer (kind=omp_integer_kind), parameter :: openmp_version    = @LIBOMP_OMP_YEAR_MONTH@
+
+        integer(kind=omp_sched_kind), parameter :: omp_sched_static  = 1
+        integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
+        integer(kind=omp_sched_kind), parameter :: omp_sched_guided  = 3
+        integer(kind=omp_sched_kind), parameter :: omp_sched_auto    = 4
+
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
+
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
+
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none           = 0
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended    = 1
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended      = 2
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative    = 8
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle            = 65536
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm            = 131072
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive       = 262144
+
+        interface
+
+!         ***
+!         *** omp_* entry points
+!         ***
+
+          subroutine omp_set_num_threads(num_threads)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) num_threads
+          end subroutine omp_set_num_threads
+
+          subroutine omp_set_dynamic(dynamic_threads)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) dynamic_threads
+          end subroutine omp_set_dynamic
+
+          subroutine omp_set_nested(nested)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) nested
+          end subroutine omp_set_nested
+
+          function omp_get_num_threads()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_threads
+          end function omp_get_num_threads
+
+          function omp_get_max_threads()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_threads
+          end function omp_get_max_threads
+
+          function omp_get_thread_num()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_thread_num
+          end function omp_get_thread_num
+
+          function omp_get_num_procs()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_procs
+          end function omp_get_num_procs
+
+          function omp_in_parallel()
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_in_parallel
+          end function omp_in_parallel
+
+          function omp_in_final()
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_in_final
+          end function omp_in_final
+
+          function omp_get_dynamic()
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_get_dynamic
+          end function omp_get_dynamic
+
+          function omp_get_nested()
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_get_nested
+          end function omp_get_nested
+
+          function omp_get_thread_limit()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_thread_limit
+          end function omp_get_thread_limit
+
+          subroutine omp_set_max_active_levels(max_levels)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) max_levels
+          end subroutine omp_set_max_active_levels
+
+          function omp_get_max_active_levels()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_active_levels
+          end function omp_get_max_active_levels
+
+          function omp_get_level()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_level
+          end function omp_get_level
+
+          function omp_get_active_level()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_active_level
+          end function omp_get_active_level
+
+          function omp_get_ancestor_thread_num(level)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) level
+            integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
+          end function omp_get_ancestor_thread_num
+
+          function omp_get_team_size(level)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) level
+            integer (kind=omp_integer_kind) omp_get_team_size
+          end function omp_get_team_size
+
+          subroutine omp_set_schedule(kind, chunk_size)
+            use omp_lib_kinds
+            integer (kind=omp_sched_kind) kind
+            integer (kind=omp_integer_kind) chunk_size
+          end subroutine omp_set_schedule
+
+          subroutine omp_get_schedule(kind, chunk_size)
+            use omp_lib_kinds
+            integer (kind=omp_sched_kind) kind
+            integer (kind=omp_integer_kind) chunk_size
+          end subroutine omp_get_schedule
+
+          function omp_get_proc_bind()
+            use omp_lib_kinds
+            integer (kind=omp_proc_bind_kind) omp_get_proc_bind
+          end function omp_get_proc_bind
+
+          function omp_get_num_places()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_places
+          end function omp_get_num_places
+
+          function omp_get_place_num_procs(place_num)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) place_num
+            integer (kind=omp_integer_kind) omp_get_place_num_procs
+          end function omp_get_place_num_procs
+
+          subroutine omp_get_place_proc_ids(place_num, ids)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) place_num
+            integer (kind=kmp_pointer_kind) ids(*)
+          end subroutine omp_get_place_proc_ids
+
+          function omp_get_place_num()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_place_num
+          end function omp_get_place_num
+
+          function omp_get_partition_num_places()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_partition_num_places
+          end function omp_get_partition_num_places
+
+          subroutine omp_get_partition_place_nums(place_nums)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) place_nums(*)
+          end subroutine omp_get_partition_place_nums
+
+          function omp_get_wtime()
+            double precision omp_get_wtime
+          end function omp_get_wtime
+
+          function omp_get_wtick ()
+            double precision omp_get_wtick
+          end function omp_get_wtick
+
+          function omp_get_default_device()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_default_device
+          end function omp_get_default_device
+
+          subroutine omp_set_default_device(device_num)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) device_num
+          end subroutine omp_set_default_device
+
+          function omp_get_num_devices()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_devices
+          end function omp_get_num_devices
+
+          function omp_get_num_teams()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_teams
+          end function omp_get_num_teams
+
+          function omp_get_team_num()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_team_num
+          end function omp_get_team_num
+
+          function omp_get_cancellation()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_cancellation
+          end function omp_get_cancellation
+
+          function omp_is_initial_device()
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_is_initial_device
+          end function omp_is_initial_device
+
+          function omp_get_initial_device()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_initial_device
+          end function omp_get_initial_device
+
+          subroutine omp_init_lock(svar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_init_lock
+
+          subroutine omp_destroy_lock(svar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_destroy_lock
+
+          subroutine omp_set_lock(svar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_set_lock
+
+          subroutine omp_unset_lock(svar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_unset_lock
+
+          function omp_test_lock(svar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_test_lock
+            integer (kind=omp_lock_kind) svar
+          end function omp_test_lock
+
+          subroutine omp_init_nest_lock(nvar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_init_nest_lock
+
+          subroutine omp_destroy_nest_lock(nvar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_destroy_nest_lock
+
+          subroutine omp_set_nest_lock(nvar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_set_nest_lock
+
+          subroutine omp_unset_nest_lock(nvar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_unset_nest_lock
+
+          function omp_test_nest_lock(nvar)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_test_nest_lock
+            integer (kind=omp_nest_lock_kind) nvar
+          end function omp_test_nest_lock
+
+          function omp_get_max_task_priority()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_task_priority
+          end function omp_get_max_task_priority
+
+!         ***
+!         *** kmp_* entry points
+!         ***
+
+          subroutine kmp_set_stacksize(size)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) size
+          end subroutine kmp_set_stacksize
+
+          subroutine kmp_set_stacksize_s(size)
+            use omp_lib_kinds
+            integer (kind=kmp_size_t_kind) size
+          end subroutine kmp_set_stacksize_s
+
+          subroutine kmp_set_blocktime(msec)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) msec
+          end subroutine kmp_set_blocktime
+
+          subroutine kmp_set_library_serial()
+          end subroutine kmp_set_library_serial
+
+          subroutine kmp_set_library_turnaround()
+          end subroutine kmp_set_library_turnaround
+
+          subroutine kmp_set_library_throughput()
+          end subroutine kmp_set_library_throughput
+
+          subroutine kmp_set_library(libnum)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) libnum
+          end subroutine kmp_set_library
+
+          subroutine kmp_set_defaults(string)
+            character*(*) string
+          end subroutine kmp_set_defaults
+
+          function kmp_get_stacksize()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_stacksize
+          end function kmp_get_stacksize
+
+          function kmp_get_stacksize_s()
+            use omp_lib_kinds
+            integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
+          end function kmp_get_stacksize_s
+
+          function kmp_get_blocktime()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_blocktime
+          end function kmp_get_blocktime
+
+          function kmp_get_library()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_library
+          end function kmp_get_library
+
+          subroutine kmp_set_disp_num_buffers(num)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) num
+          end subroutine kmp_set_disp_num_buffers
+
+          function kmp_set_affinity(mask)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_set_affinity
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_set_affinity
+
+          function kmp_get_affinity(mask)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_get_affinity
+
+          function kmp_get_affinity_max_proc()
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
+          end function kmp_get_affinity_max_proc
+
+          subroutine kmp_create_affinity_mask(mask)
+            use omp_lib_kinds
+            integer (kind=kmp_affinity_mask_kind) mask
+          end subroutine kmp_create_affinity_mask
+
+          subroutine kmp_destroy_affinity_mask(mask)
+            use omp_lib_kinds
+            integer (kind=kmp_affinity_mask_kind) mask
+          end subroutine kmp_destroy_affinity_mask
+
+          function kmp_set_affinity_mask_proc(proc, mask)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
+            integer (kind=omp_integer_kind) proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_set_affinity_mask_proc
+
+          function kmp_unset_affinity_mask_proc(proc, mask)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
+            integer (kind=omp_integer_kind) proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_unset_affinity_mask_proc
+
+          function kmp_get_affinity_mask_proc(proc, mask)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
+            integer (kind=omp_integer_kind) proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_get_affinity_mask_proc
+
+          function kmp_malloc(size)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_malloc
+            integer (kind=kmp_size_t_kind) size
+          end function kmp_malloc
+
+          function kmp_aligned_malloc(size, alignment)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_aligned_malloc
+            integer (kind=kmp_size_t_kind) size
+            integer (kind=kmp_size_t_kind) alignment
+          end function kmp_aligned_malloc
+
+          function kmp_calloc(nelem, elsize)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_calloc
+            integer (kind=kmp_size_t_kind) nelem
+            integer (kind=kmp_size_t_kind) elsize
+          end function kmp_calloc
+
+          function kmp_realloc(ptr, size)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_realloc
+            integer (kind=kmp_pointer_kind) ptr
+            integer (kind=kmp_size_t_kind) size
+          end function kmp_realloc
+
+          subroutine kmp_free(ptr)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) ptr
+          end subroutine kmp_free
+
+          subroutine kmp_set_warnings_on()
+          end subroutine kmp_set_warnings_on
+
+          subroutine kmp_set_warnings_off()
+          end subroutine kmp_set_warnings_off
+
+          function kmp_get_cancellation_status(cancelkind)
+            use omp_lib_kinds
+            integer (kind=kmp_cancel_kind) cancelkind
+            logical (kind=omp_logical_kind) kmp_get_cancellation_status
+          end function kmp_get_cancellation_status
+
+          subroutine omp_init_lock_with_hint(svar, hint)
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+            integer (kind=omp_lock_hint_kind) hint
+          end subroutine omp_init_lock_with_hint
+
+          subroutine omp_init_nest_lock_with_hint(nvar, hint)
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+            integer (kind=omp_lock_hint_kind) hint
+          end subroutine omp_init_nest_lock_with_hint
+
+        end interface
+
+!dec$ if defined(_WIN32)
+!dec$   if defined(_WIN64) .or. defined(_M_AMD64)
+
+!***
+!*** The Fortran entry points must be in uppercase, even if the /Qlowercase
+!*** option is specified.  The alias attribute ensures that the specified
+!*** string is used as the entry point.
+!***
+!*** On the Windows* OS IA-32 architecture, the Fortran entry points have an
+!*** underscore prepended.  On the Windows* OS Intel(R) 64
+!*** architecture, no underscore is prepended.
+!***
+
+!dec$ attributes alias:'OMP_SET_NUM_THREADS' :: omp_set_num_threads
+!dec$ attributes alias:'OMP_SET_DYNAMIC' :: omp_set_dynamic
+!dec$ attributes alias:'OMP_SET_NESTED' :: omp_set_nested
+!dec$ attributes alias:'OMP_GET_NUM_THREADS' :: omp_get_num_threads
+!dec$ attributes alias:'OMP_GET_MAX_THREADS' :: omp_get_max_threads
+!dec$ attributes alias:'OMP_GET_THREAD_NUM' :: omp_get_thread_num
+!dec$ attributes alias:'OMP_GET_NUM_PROCS' :: omp_get_num_procs
+!dec$ attributes alias:'OMP_IN_PARALLEL' :: omp_in_parallel
+!dec$ attributes alias:'OMP_GET_DYNAMIC' :: omp_get_dynamic
+!dec$ attributes alias:'OMP_GET_NESTED' :: omp_get_nested
+!dec$ attributes alias:'OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
+!dec$ attributes alias:'OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
+!dec$ attributes alias:'OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
+!dec$ attributes alias:'OMP_GET_LEVEL' :: omp_get_level
+!dec$ attributes alias:'OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
+!dec$ attributes alias:'OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
+!dec$ attributes alias:'OMP_GET_TEAM_SIZE' :: omp_get_team_size
+!dec$ attributes alias:'OMP_SET_SCHEDULE' :: omp_set_schedule
+!dec$ attributes alias:'OMP_GET_SCHEDULE' :: omp_get_schedule
+!dec$ attributes alias:'OMP_GET_PROC_BIND' :: omp_get_proc_bind
+!dec$ attributes alias:'OMP_GET_WTIME' :: omp_get_wtime
+!dec$ attributes alias:'OMP_GET_WTICK' :: omp_get_wtick
+!dec$ attributes alias:'OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
+!dec$ attributes alias:'OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
+!dec$ attributes alias:'OMP_GET_NUM_DEVICES' :: omp_get_num_devices
+!dec$ attributes alias:'OMP_GET_NUM_TEAMS' :: omp_get_num_teams
+!dec$ attributes alias:'OMP_GET_TEAM_NUM' :: omp_get_team_num
+!dec$ attributes alias:'OMP_GET_CANCELLATION' :: omp_get_cancellation
+!dec$ attributes alias:'OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
+!dec$ attributes alias:'OMP_GET_MAX_TASK_PRIORITY' :: omp_get_max_task_priority
+
+!dec$ attributes alias:'omp_init_lock' :: omp_init_lock
+!dec$ attributes alias:'omp_init_lock_with_hint' :: omp_init_lock_with_hint
+!dec$ attributes alias:'omp_destroy_lock' :: omp_destroy_lock
+!dec$ attributes alias:'omp_set_lock' :: omp_set_lock
+!dec$ attributes alias:'omp_unset_lock' :: omp_unset_lock
+!dec$ attributes alias:'omp_test_lock' :: omp_test_lock
+!dec$ attributes alias:'omp_init_nest_lock' :: omp_init_nest_lock
+!dec$ attributes alias:'omp_init_nest_lock_with_hint' :: omp_init_nest_lock_with_hint
+!dec$ attributes alias:'omp_destroy_nest_lock' :: omp_destroy_nest_lock
+!dec$ attributes alias:'omp_set_nest_lock' :: omp_set_nest_lock
+!dec$ attributes alias:'omp_unset_nest_lock' :: omp_unset_nest_lock
+!dec$ attributes alias:'omp_test_nest_lock' :: omp_test_nest_lock
+
+!dec$ attributes alias:'KMP_SET_STACKSIZE'::kmp_set_stacksize
+!dec$ attributes alias:'KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
+!dec$ attributes alias:'KMP_SET_BLOCKTIME'::kmp_set_blocktime
+!dec$ attributes alias:'KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
+!dec$ attributes alias:'KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
+!dec$ attributes alias:'KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
+!dec$ attributes alias:'KMP_SET_LIBRARY'::kmp_set_library
+!dec$ attributes alias:'KMP_GET_STACKSIZE'::kmp_get_stacksize
+!dec$ attributes alias:'KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
+!dec$ attributes alias:'KMP_GET_BLOCKTIME'::kmp_get_blocktime
+!dec$ attributes alias:'KMP_GET_LIBRARY'::kmp_get_library
+!dec$ attributes alias:'KMP_SET_AFFINITY'::kmp_set_affinity
+!dec$ attributes alias:'KMP_GET_AFFINITY'::kmp_get_affinity
+!dec$ attributes alias:'KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
+!dec$ attributes alias:'KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
+!dec$ attributes alias:'KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
+!dec$ attributes alias:'KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
+!dec$ attributes alias:'KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
+!dec$ attributes alias:'KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
+!dec$ attributes alias:'KMP_MALLOC'::kmp_malloc
+!dec$ attributes alias:'KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
+!dec$ attributes alias:'KMP_CALLOC'::kmp_calloc
+!dec$ attributes alias:'KMP_REALLOC'::kmp_realloc
+!dec$ attributes alias:'KMP_FREE'::kmp_free
+
+!dec$ attributes alias:'KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
+!dec$ attributes alias:'KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
+
+!dec$ attributes alias:'KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
+
+!dec$   else
+
+!***
+!*** On Windows* OS IA-32 architecture, the Fortran entry points have an underscore prepended.
+!***
+
+!dec$ attributes alias:'_OMP_SET_NUM_THREADS' :: omp_set_num_threads
+!dec$ attributes alias:'_OMP_SET_DYNAMIC' :: omp_set_dynamic
+!dec$ attributes alias:'_OMP_SET_NESTED' :: omp_set_nested
+!dec$ attributes alias:'_OMP_GET_NUM_THREADS' :: omp_get_num_threads
+!dec$ attributes alias:'_OMP_GET_MAX_THREADS' :: omp_get_max_threads
+!dec$ attributes alias:'_OMP_GET_THREAD_NUM' :: omp_get_thread_num
+!dec$ attributes alias:'_OMP_GET_NUM_PROCS' :: omp_get_num_procs
+!dec$ attributes alias:'_OMP_IN_PARALLEL' :: omp_in_parallel
+!dec$ attributes alias:'_OMP_GET_DYNAMIC' :: omp_get_dynamic
+!dec$ attributes alias:'_OMP_GET_NESTED' :: omp_get_nested
+!dec$ attributes alias:'_OMP_GET_THREAD_LIMIT' :: omp_get_thread_limit
+!dec$ attributes alias:'_OMP_SET_MAX_ACTIVE_LEVELS' :: omp_set_max_active_levels
+!dec$ attributes alias:'_OMP_GET_MAX_ACTIVE_LEVELS' :: omp_get_max_active_levels
+!dec$ attributes alias:'_OMP_GET_LEVEL' :: omp_get_level
+!dec$ attributes alias:'_OMP_GET_ACTIVE_LEVEL' :: omp_get_active_level
+!dec$ attributes alias:'_OMP_GET_ANCESTOR_THREAD_NUM' :: omp_get_ancestor_thread_num
+!dec$ attributes alias:'_OMP_GET_TEAM_SIZE' :: omp_get_team_size
+!dec$ attributes alias:'_OMP_SET_SCHEDULE' :: omp_set_schedule
+!dec$ attributes alias:'_OMP_GET_SCHEDULE' :: omp_get_schedule
+!dec$ attributes alias:'_OMP_GET_PROC_BIND' :: omp_get_proc_bind
+!dec$ attributes alias:'_OMP_GET_WTIME' :: omp_get_wtime
+!dec$ attributes alias:'_OMP_GET_WTICK' :: omp_get_wtick
+!dec$ attributes alias:'_OMP_GET_DEFAULT_DEVICE' :: omp_get_default_device
+!dec$ attributes alias:'_OMP_SET_DEFAULT_DEVICE' :: omp_set_default_device
+!dec$ attributes alias:'_OMP_GET_NUM_DEVICES' :: omp_get_num_devices
+!dec$ attributes alias:'_OMP_GET_NUM_TEAMS' :: omp_get_num_teams
+!dec$ attributes alias:'_OMP_GET_TEAM_NUM' :: omp_get_team_num
+!dec$ attributes alias:'_OMP_GET_CANCELLATION' :: omp_get_cancellation
+!dec$ attributes alias:'_OMP_IS_INITIAL_DEVICE' :: omp_is_initial_device
+!dec$ attributes alias:'_OMP_GET_MAX_TASK_PRIORTY' :: omp_get_max_task_priority
+
+!dec$ attributes alias:'_omp_init_lock' :: omp_init_lock
+!dec$ attributes alias:'_omp_init_lock_with_hint' :: omp_init_lock_with_hint
+!dec$ attributes alias:'_omp_destroy_lock' :: omp_destroy_lock
+!dec$ attributes alias:'_omp_set_lock' :: omp_set_lock
+!dec$ attributes alias:'_omp_unset_lock' :: omp_unset_lock
+!dec$ attributes alias:'_omp_test_lock' :: omp_test_lock
+!dec$ attributes alias:'_omp_init_nest_lock' :: omp_init_nest_lock
+!dec$ attributes alias:'_omp_init_nest_lock_with_hint' :: omp_init_nest_lock_with_hint
+!dec$ attributes alias:'_omp_destroy_nest_lock' :: omp_destroy_nest_lock
+!dec$ attributes alias:'_omp_set_nest_lock' :: omp_set_nest_lock
+!dec$ attributes alias:'_omp_unset_nest_lock' :: omp_unset_nest_lock
+!dec$ attributes alias:'_omp_test_nest_lock' :: omp_test_nest_lock
+
+!dec$ attributes alias:'_KMP_SET_STACKSIZE'::kmp_set_stacksize
+!dec$ attributes alias:'_KMP_SET_STACKSIZE_S'::kmp_set_stacksize_s
+!dec$ attributes alias:'_KMP_SET_BLOCKTIME'::kmp_set_blocktime
+!dec$ attributes alias:'_KMP_SET_LIBRARY_SERIAL'::kmp_set_library_serial
+!dec$ attributes alias:'_KMP_SET_LIBRARY_TURNAROUND'::kmp_set_library_turnaround
+!dec$ attributes alias:'_KMP_SET_LIBRARY_THROUGHPUT'::kmp_set_library_throughput
+!dec$ attributes alias:'_KMP_SET_LIBRARY'::kmp_set_library
+!dec$ attributes alias:'_KMP_GET_STACKSIZE'::kmp_get_stacksize
+!dec$ attributes alias:'_KMP_GET_STACKSIZE_S'::kmp_get_stacksize_s
+!dec$ attributes alias:'_KMP_GET_BLOCKTIME'::kmp_get_blocktime
+!dec$ attributes alias:'_KMP_GET_LIBRARY'::kmp_get_library
+!dec$ attributes alias:'_KMP_SET_AFFINITY'::kmp_set_affinity
+!dec$ attributes alias:'_KMP_GET_AFFINITY'::kmp_get_affinity
+!dec$ attributes alias:'_KMP_GET_AFFINITY_MAX_PROC'::kmp_get_affinity_max_proc
+!dec$ attributes alias:'_KMP_CREATE_AFFINITY_MASK'::kmp_create_affinity_mask
+!dec$ attributes alias:'_KMP_DESTROY_AFFINITY_MASK'::kmp_destroy_affinity_mask
+!dec$ attributes alias:'_KMP_SET_AFFINITY_MASK_PROC'::kmp_set_affinity_mask_proc
+!dec$ attributes alias:'_KMP_UNSET_AFFINITY_MASK_PROC'::kmp_unset_affinity_mask_proc
+!dec$ attributes alias:'_KMP_GET_AFFINITY_MASK_PROC'::kmp_get_affinity_mask_proc
+!dec$ attributes alias:'_KMP_MALLOC'::kmp_malloc
+!dec$ attributes alias:'_KMP_ALIGNED_MALLOC'::kmp_aligned_malloc
+!dec$ attributes alias:'_KMP_CALLOC'::kmp_calloc
+!dec$ attributes alias:'_KMP_REALLOC'::kmp_realloc
+!dec$ attributes alias:'_KMP_FREE'::kmp_free
+
+!dec$ attributes alias:'_KMP_SET_WARNINGS_ON'::kmp_set_warnings_on
+!dec$ attributes alias:'_KMP_SET_WARNINGS_OFF'::kmp_set_warnings_off
+
+!dec$ attributes alias:'_KMP_GET_CANCELLATION_STATUS' :: kmp_get_cancellation_status
+
+!dec$   endif
+!dec$ endif
+
+!dec$ if defined(__linux)
+
+!***
+!*** The Linux* OS entry points are in lowercase, with an underscore appended.
+!***
+
+!dec$ attributes alias:'omp_set_num_threads_'::omp_set_num_threads
+!dec$ attributes alias:'omp_set_dynamic_'::omp_set_dynamic
+!dec$ attributes alias:'omp_set_nested_'::omp_set_nested
+!dec$ attributes alias:'omp_get_num_threads_'::omp_get_num_threads
+!dec$ attributes alias:'omp_get_max_threads_'::omp_get_max_threads
+!dec$ attributes alias:'omp_get_thread_num_'::omp_get_thread_num
+!dec$ attributes alias:'omp_get_num_procs_'::omp_get_num_procs
+!dec$ attributes alias:'omp_in_parallel_'::omp_in_parallel
+!dec$ attributes alias:'omp_get_dynamic_'::omp_get_dynamic
+!dec$ attributes alias:'omp_get_nested_'::omp_get_nested
+!dec$ attributes alias:'omp_get_thread_limit_'::omp_get_thread_limit
+!dec$ attributes alias:'omp_set_max_active_levels_'::omp_set_max_active_levels
+!dec$ attributes alias:'omp_get_max_active_levels_'::omp_get_max_active_levels
+!dec$ attributes alias:'omp_get_level_'::omp_get_level
+!dec$ attributes alias:'omp_get_active_level_'::omp_get_active_level
+!dec$ attributes alias:'omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
+!dec$ attributes alias:'omp_get_team_size_'::omp_get_team_size
+!dec$ attributes alias:'omp_set_schedule_'::omp_set_schedule
+!dec$ attributes alias:'omp_get_schedule_'::omp_get_schedule
+!dec$ attributes alias:'omp_get_proc_bind_' :: omp_get_proc_bind
+!dec$ attributes alias:'omp_get_wtime_'::omp_get_wtime
+!dec$ attributes alias:'omp_get_wtick_'::omp_get_wtick
+!dec$ attributes alias:'omp_get_default_device_'::omp_get_default_device
+!dec$ attributes alias:'omp_set_default_device_'::omp_set_default_device
+!dec$ attributes alias:'omp_get_num_devices_'::omp_get_num_devices
+!dec$ attributes alias:'omp_get_num_teams_'::omp_get_num_teams
+!dec$ attributes alias:'omp_get_team_num_'::omp_get_team_num
+!dec$ attributes alias:'omp_get_cancellation_'::omp_get_cancellation
+!dec$ attributes alias:'omp_is_initial_device_'::omp_is_initial_device
+!dec$ attributes alias:'omp_get_max_task_priority_'::omp_get_max_task_priority
+
+!dec$ attributes alias:'omp_init_lock_'::omp_init_lock
+!dec$ attributes alias:'omp_init_lock_with_hint_'::omp_init_lock_with_hint
+!dec$ attributes alias:'omp_destroy_lock_'::omp_destroy_lock
+!dec$ attributes alias:'omp_set_lock_'::omp_set_lock
+!dec$ attributes alias:'omp_unset_lock_'::omp_unset_lock
+!dec$ attributes alias:'omp_test_lock_'::omp_test_lock
+!dec$ attributes alias:'omp_init_nest_lock_'::omp_init_nest_lock
+!dec$ attributes alias:'omp_init_nest_lock_with_hint_'::omp_init_nest_lock_with_hint
+!dec$ attributes alias:'omp_destroy_nest_lock_'::omp_destroy_nest_lock
+!dec$ attributes alias:'omp_set_nest_lock_'::omp_set_nest_lock
+!dec$ attributes alias:'omp_unset_nest_lock_'::omp_unset_nest_lock
+!dec$ attributes alias:'omp_test_nest_lock_'::omp_test_nest_lock
+
+!dec$ attributes alias:'kmp_set_stacksize_'::kmp_set_stacksize
+!dec$ attributes alias:'kmp_set_stacksize_s_'::kmp_set_stacksize_s
+!dec$ attributes alias:'kmp_set_blocktime_'::kmp_set_blocktime
+!dec$ attributes alias:'kmp_set_library_serial_'::kmp_set_library_serial
+!dec$ attributes alias:'kmp_set_library_turnaround_'::kmp_set_library_turnaround
+!dec$ attributes alias:'kmp_set_library_throughput_'::kmp_set_library_throughput
+!dec$ attributes alias:'kmp_set_library_'::kmp_set_library
+!dec$ attributes alias:'kmp_get_stacksize_'::kmp_get_stacksize
+!dec$ attributes alias:'kmp_get_stacksize_s_'::kmp_get_stacksize_s
+!dec$ attributes alias:'kmp_get_blocktime_'::kmp_get_blocktime
+!dec$ attributes alias:'kmp_get_library_'::kmp_get_library
+!dec$ attributes alias:'kmp_set_affinity_'::kmp_set_affinity
+!dec$ attributes alias:'kmp_get_affinity_'::kmp_get_affinity
+!dec$ attributes alias:'kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
+!dec$ attributes alias:'kmp_create_affinity_mask_'::kmp_create_affinity_mask
+!dec$ attributes alias:'kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
+!dec$ attributes alias:'kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
+!dec$ attributes alias:'kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
+!dec$ attributes alias:'kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
+!dec$ attributes alias:'kmp_malloc_'::kmp_malloc
+!dec$ attributes alias:'kmp_aligned_malloc_'::kmp_aligned_malloc
+!dec$ attributes alias:'kmp_calloc_'::kmp_calloc
+!dec$ attributes alias:'kmp_realloc_'::kmp_realloc
+!dec$ attributes alias:'kmp_free_'::kmp_free
+
+!dec$ attributes alias:'kmp_set_warnings_on_'::kmp_set_warnings_on
+!dec$ attributes alias:'kmp_set_warnings_off_'::kmp_set_warnings_off
+!dec$ attributes alias:'kmp_get_cancellation_status_'::kmp_get_cancellation_status
+
+!dec$ endif
+
+!dec$ if defined(__APPLE__)
+
+!***
+!*** The Mac entry points are in lowercase, with an both an underscore
+!*** appended and an underscore prepended.
+!***
+
+!dec$ attributes alias:'_omp_set_num_threads_'::omp_set_num_threads
+!dec$ attributes alias:'_omp_set_dynamic_'::omp_set_dynamic
+!dec$ attributes alias:'_omp_set_nested_'::omp_set_nested
+!dec$ attributes alias:'_omp_get_num_threads_'::omp_get_num_threads
+!dec$ attributes alias:'_omp_get_max_threads_'::omp_get_max_threads
+!dec$ attributes alias:'_omp_get_thread_num_'::omp_get_thread_num
+!dec$ attributes alias:'_omp_get_num_procs_'::omp_get_num_procs
+!dec$ attributes alias:'_omp_in_parallel_'::omp_in_parallel
+!dec$ attributes alias:'_omp_get_dynamic_'::omp_get_dynamic
+!dec$ attributes alias:'_omp_get_nested_'::omp_get_nested
+!dec$ attributes alias:'_omp_get_thread_limit_'::omp_get_thread_limit
+!dec$ attributes alias:'_omp_set_max_active_levels_'::omp_set_max_active_levels
+!dec$ attributes alias:'_omp_get_max_active_levels_'::omp_get_max_active_levels
+!dec$ attributes alias:'_omp_get_level_'::omp_get_level
+!dec$ attributes alias:'_omp_get_active_level_'::omp_get_active_level
+!dec$ attributes alias:'_omp_get_ancestor_thread_num_'::omp_get_ancestor_thread_num
+!dec$ attributes alias:'_omp_get_team_size_'::omp_get_team_size
+!dec$ attributes alias:'_omp_set_schedule_'::omp_set_schedule
+!dec$ attributes alias:'_omp_get_schedule_'::omp_get_schedule
+!dec$ attributes alias:'_omp_get_proc_bind_' :: omp_get_proc_bind
+!dec$ attributes alias:'_omp_get_wtime_'::omp_get_wtime
+!dec$ attributes alias:'_omp_get_wtick_'::omp_get_wtick
+!dec$ attributes alias:'_omp_get_num_teams_'::omp_get_num_teams
+!dec$ attributes alias:'_omp_get_team_num_'::omp_get_team_num
+!dec$ attributes alias:'_omp_get_cancellation_'::omp_get_cancellation
+!dec$ attributes alias:'_omp_is_initial_device_'::omp_is_initial_device
+!dec$ attributes alias:'_omp_get_max_task_priorty_'::omp_get_max_task_priority
+
+!dec$ attributes alias:'_omp_init_lock_'::omp_init_lock
+!dec$ attributes alias:'_omp_init_lock_with_hint_'::omp_init_lock_with_hint
+!dec$ attributes alias:'_omp_destroy_lock_'::omp_destroy_lock
+!dec$ attributes alias:'_omp_set_lock_'::omp_set_lock
+!dec$ attributes alias:'_omp_unset_lock_'::omp_unset_lock
+!dec$ attributes alias:'_omp_test_lock_'::omp_test_lock
+!dec$ attributes alias:'_omp_init_nest_lock_'::omp_init_nest_lock
+!dec$ attributes alias:'_omp_init_nest_lock_with_hint_'::omp_init_nest_lock_with_hint
+!dec$ attributes alias:'_omp_destroy_nest_lock_'::omp_destroy_nest_lock
+!dec$ attributes alias:'_omp_set_nest_lock_'::omp_set_nest_lock
+!dec$ attributes alias:'_omp_unset_nest_lock_'::omp_unset_nest_lock
+!dec$ attributes alias:'_omp_test_nest_lock_'::omp_test_nest_lock
+
+!dec$ attributes alias:'_kmp_set_stacksize_'::kmp_set_stacksize
+!dec$ attributes alias:'_kmp_set_stacksize_s_'::kmp_set_stacksize_s
+!dec$ attributes alias:'_kmp_set_blocktime_'::kmp_set_blocktime
+!dec$ attributes alias:'_kmp_set_library_serial_'::kmp_set_library_serial
+!dec$ attributes alias:'_kmp_set_library_turnaround_'::kmp_set_library_turnaround
+!dec$ attributes alias:'_kmp_set_library_throughput_'::kmp_set_library_throughput
+!dec$ attributes alias:'_kmp_set_library_'::kmp_set_library
+!dec$ attributes alias:'_kmp_get_stacksize_'::kmp_get_stacksize
+!dec$ attributes alias:'_kmp_get_stacksize_s_'::kmp_get_stacksize_s
+!dec$ attributes alias:'_kmp_get_blocktime_'::kmp_get_blocktime
+!dec$ attributes alias:'_kmp_get_library_'::kmp_get_library
+!dec$ attributes alias:'_kmp_set_affinity_'::kmp_set_affinity
+!dec$ attributes alias:'_kmp_get_affinity_'::kmp_get_affinity
+!dec$ attributes alias:'_kmp_get_affinity_max_proc_'::kmp_get_affinity_max_proc
+!dec$ attributes alias:'_kmp_create_affinity_mask_'::kmp_create_affinity_mask
+!dec$ attributes alias:'_kmp_destroy_affinity_mask_'::kmp_destroy_affinity_mask
+!dec$ attributes alias:'_kmp_set_affinity_mask_proc_'::kmp_set_affinity_mask_proc
+!dec$ attributes alias:'_kmp_unset_affinity_mask_proc_'::kmp_unset_affinity_mask_proc
+!dec$ attributes alias:'_kmp_get_affinity_mask_proc_'::kmp_get_affinity_mask_proc
+!dec$ attributes alias:'_kmp_malloc_'::kmp_malloc
+!dec$ attributes alias:'_kmp_aligned_malloc_'::kmp_aligned_malloc
+!dec$ attributes alias:'_kmp_calloc_'::kmp_calloc
+!dec$ attributes alias:'_kmp_realloc_'::kmp_realloc
+!dec$ attributes alias:'_kmp_free_'::kmp_free
+
+!dec$ attributes alias:'_kmp_set_warnings_on_'::kmp_set_warnings_on
+!dec$ attributes alias:'_kmp_set_warnings_off_'::kmp_set_warnings_off
+
+!dec$ attributes alias:'_kmp_get_cancellation_status_'::kmp_get_cancellation_status
+
+!dec$ endif
+
+      end module omp_lib
+

runtime/src/include/50/omp_lib.f90.var

@@ -0,0 +1,524 @@
+! include/50/omp_lib.f90.var
+
+!
+!//===----------------------------------------------------------------------===//
+!//
+!//                     The LLVM Compiler Infrastructure
+!//
+!// This file is dual licensed under the MIT and the University of Illinois Open
+!// Source Licenses. See LICENSE.txt for details.
+!//
+!//===----------------------------------------------------------------------===//
+!
+
+      module omp_lib_kinds
+
+        use, intrinsic :: iso_c_binding
+
+        integer, parameter :: omp_integer_kind       = c_int
+        integer, parameter :: omp_logical_kind       = 4
+        integer, parameter :: omp_real_kind          = c_float
+        integer, parameter :: kmp_double_kind        = c_double
+        integer, parameter :: omp_lock_kind          = c_intptr_t
+        integer, parameter :: omp_nest_lock_kind     = c_intptr_t
+        integer, parameter :: omp_sched_kind         = omp_integer_kind
+        integer, parameter :: omp_proc_bind_kind     = omp_integer_kind
+        integer, parameter :: kmp_pointer_kind       = c_intptr_t
+        integer, parameter :: kmp_size_t_kind        = c_size_t
+        integer, parameter :: kmp_affinity_mask_kind = c_intptr_t
+        integer, parameter :: kmp_cancel_kind        = omp_integer_kind
+        integer, parameter :: omp_lock_hint_kind     = omp_integer_kind
+
+      end module omp_lib_kinds
+
+      module omp_lib
+
+        use omp_lib_kinds
+
+        integer (kind=omp_integer_kind), parameter :: openmp_version    = @LIBOMP_OMP_YEAR_MONTH@
+        integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
+        integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
+        integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
+        character(*)               kmp_build_date
+        parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
+
+        integer(kind=omp_sched_kind), parameter :: omp_sched_static  = 1
+        integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
+        integer(kind=omp_sched_kind), parameter :: omp_sched_guided  = 3
+        integer(kind=omp_sched_kind), parameter :: omp_sched_auto    = 4
+
+
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
+        integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
+
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_parallel = 1
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_loop = 2
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_sections = 3
+        integer (kind=kmp_cancel_kind), parameter :: kmp_cancel_taskgroup = 4
+
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none           = 0
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended    = 1
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended      = 2
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
+        integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative    = 8
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle            = 65536
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm            = 131072
+        integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive       = 262144
+
+        interface
+
+!         ***
+!         *** omp_* entry points
+!         ***
+
+          subroutine omp_set_num_threads(num_threads) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: num_threads
+          end subroutine omp_set_num_threads
+
+          subroutine omp_set_dynamic(dynamic_threads) bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind), value :: dynamic_threads
+          end subroutine omp_set_dynamic
+
+          subroutine omp_set_nested(nested) bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind), value :: nested
+          end subroutine omp_set_nested
+
+          function omp_get_num_threads() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_threads
+          end function omp_get_num_threads
+
+          function omp_get_max_threads() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_threads
+          end function omp_get_max_threads
+
+          function omp_get_thread_num() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_thread_num
+          end function omp_get_thread_num
+
+          function omp_get_num_procs() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_procs
+          end function omp_get_num_procs
+
+          function omp_in_parallel() bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_in_parallel
+          end function omp_in_parallel
+
+          function omp_in_final() bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_in_final
+          end function omp_in_final
+
+          function omp_get_dynamic() bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_get_dynamic
+          end function omp_get_dynamic
+
+          function omp_get_nested() bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_get_nested
+          end function omp_get_nested
+
+          function omp_get_thread_limit() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_thread_limit
+          end function omp_get_thread_limit
+
+          subroutine omp_set_max_active_levels(max_levels) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: max_levels
+          end subroutine omp_set_max_active_levels
+
+          function omp_get_max_active_levels() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_active_levels
+          end function omp_get_max_active_levels
+
+          function omp_get_level() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_level
+          end function omp_get_level
+
+          function omp_get_active_level() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_active_level
+          end function omp_get_active_level
+
+          function omp_get_ancestor_thread_num(level) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
+            integer (kind=omp_integer_kind), value :: level
+          end function omp_get_ancestor_thread_num
+
+          function omp_get_team_size(level) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_team_size
+            integer (kind=omp_integer_kind), value :: level
+          end function omp_get_team_size
+
+          subroutine omp_set_schedule(kind, chunk_size) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_sched_kind), value :: kind
+            integer (kind=omp_integer_kind), value :: chunk_size
+          end subroutine omp_set_schedule
+
+          subroutine omp_get_schedule(kind, chunk_size) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_sched_kind) kind
+            integer (kind=omp_integer_kind) chunk_size
+          end subroutine omp_get_schedule
+
+          function omp_get_proc_bind() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_proc_bind_kind) omp_get_proc_bind
+          end function omp_get_proc_bind
+
+          function omp_get_num_places() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_places
+          end function omp_get_num_places
+
+          function omp_get_place_num_procs(place_num) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: place_num
+            integer (kind=omp_integer_kind) omp_get_place_num_procs
+          end function omp_get_place_num_procs
+
+          subroutine omp_get_place_proc_ids(place_num, ids) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: place_num
+            integer (kind=kmp_pointer_kind) ids(*)
+          end subroutine omp_get_place_proc_ids
+
+          function omp_get_place_num() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_place_num
+          end function omp_get_place_num
+
+          function omp_get_partition_num_places() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_partition_num_places
+          end function omp_get_partition_num_places
+
+          subroutine omp_get_partition_place_nums(place_nums) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) place_nums(*)
+          end subroutine omp_get_partition_place_nums
+
+          function omp_get_wtime() bind(c)
+            use omp_lib_kinds
+            real (kind=kmp_double_kind) omp_get_wtime
+          end function omp_get_wtime
+
+          function omp_get_wtick() bind(c)
+            use omp_lib_kinds
+            real (kind=kmp_double_kind) omp_get_wtick
+          end function omp_get_wtick
+
+          function omp_get_default_device() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_default_device
+          end function omp_get_default_device
+
+          subroutine omp_set_default_device(device_num) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: device_num
+          end subroutine omp_set_default_device
+
+          function omp_get_num_devices() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_devices
+          end function omp_get_num_devices
+
+          function omp_get_num_teams() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_num_teams
+          end function omp_get_num_teams
+
+          function omp_get_team_num() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_team_num
+          end function omp_get_team_num
+
+          function omp_get_cancellation() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_cancellation
+          end function omp_get_cancellation
+
+          function omp_is_initial_device() bind(c)
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_is_initial_device
+          end function omp_is_initial_device
+
+          function omp_get_initial_device() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_initial_device
+          end function omp_get_initial_device
+
+          subroutine omp_init_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_init_lock
+
+          subroutine omp_destroy_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_destroy_lock
+
+          subroutine omp_set_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_set_lock
+
+          subroutine omp_unset_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+          end subroutine omp_unset_lock
+
+          function omp_test_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            logical (kind=omp_logical_kind) omp_test_lock
+            integer (kind=omp_lock_kind) svar
+          end function omp_test_lock
+
+          subroutine omp_init_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_init_nest_lock
+
+          subroutine omp_destroy_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_destroy_nest_lock
+
+          subroutine omp_set_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_set_nest_lock
+
+          subroutine omp_unset_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+          end subroutine omp_unset_nest_lock
+
+          function omp_test_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_nest_lock
+!DIR$ ENDIF
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_test_nest_lock
+            integer (kind=omp_nest_lock_kind) nvar
+          end function omp_test_nest_lock
+
+          function omp_get_max_task_priority() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) omp_get_max_task_priority
+          end function omp_get_max_task_priority
+
+!         ***
+!         *** kmp_* entry points
+!         ***
+
+          subroutine kmp_set_stacksize(size) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: size
+          end subroutine kmp_set_stacksize
+
+          subroutine kmp_set_stacksize_s(size) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_size_t_kind), value :: size
+          end subroutine kmp_set_stacksize_s
+
+          subroutine kmp_set_blocktime(msec) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: msec
+          end subroutine kmp_set_blocktime
+
+          subroutine kmp_set_library_serial() bind(c)
+          end subroutine kmp_set_library_serial
+
+          subroutine kmp_set_library_turnaround() bind(c)
+          end subroutine kmp_set_library_turnaround
+
+          subroutine kmp_set_library_throughput() bind(c)
+          end subroutine kmp_set_library_throughput
+
+          subroutine kmp_set_library(libnum) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: libnum
+          end subroutine kmp_set_library
+
+          subroutine kmp_set_defaults(string) bind(c)
+            use, intrinsic :: iso_c_binding
+            character (kind=c_char) :: string(*)
+          end subroutine kmp_set_defaults
+
+          function kmp_get_stacksize() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_stacksize
+          end function kmp_get_stacksize
+
+          function kmp_get_stacksize_s() bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
+          end function kmp_get_stacksize_s
+
+          function kmp_get_blocktime() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_blocktime
+          end function kmp_get_blocktime
+
+          function kmp_get_library() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_library
+          end function kmp_get_library
+
+          subroutine kmp_set_disp_num_buffers(num) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind), value :: num
+          end subroutine kmp_set_disp_num_buffers
+
+          function kmp_set_affinity(mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_set_affinity
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_set_affinity
+
+          function kmp_get_affinity(mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_get_affinity
+
+          function kmp_get_affinity_max_proc() bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
+          end function kmp_get_affinity_max_proc
+
+          subroutine kmp_create_affinity_mask(mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_affinity_mask_kind) mask
+          end subroutine kmp_create_affinity_mask
+
+          subroutine kmp_destroy_affinity_mask(mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_affinity_mask_kind) mask
+          end subroutine kmp_destroy_affinity_mask
+
+          function kmp_set_affinity_mask_proc(proc, mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
+            integer (kind=omp_integer_kind), value :: proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_set_affinity_mask_proc
+
+          function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
+            integer (kind=omp_integer_kind), value :: proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_unset_affinity_mask_proc
+
+          function kmp_get_affinity_mask_proc(proc, mask) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
+            integer (kind=omp_integer_kind), value :: proc
+            integer (kind=kmp_affinity_mask_kind) mask
+          end function kmp_get_affinity_mask_proc
+
+          function kmp_malloc(size) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_malloc
+            integer (kind=kmp_size_t_kind), value :: size
+          end function kmp_malloc
+
+          function kmp_aligned_malloc(size, alignment) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_aligned_malloc
+            integer (kind=kmp_size_t_kind), value :: size
+            integer (kind=kmp_size_t_kind), value :: alignment
+          end function kmp_aligned_malloc
+
+          function kmp_calloc(nelem, elsize) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_calloc
+            integer (kind=kmp_size_t_kind), value :: nelem
+            integer (kind=kmp_size_t_kind), value :: elsize
+          end function kmp_calloc
+
+          function kmp_realloc(ptr, size) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind) kmp_realloc
+            integer (kind=kmp_pointer_kind), value :: ptr
+            integer (kind=kmp_size_t_kind), value :: size
+          end function kmp_realloc
+
+          subroutine kmp_free(ptr) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_pointer_kind), value :: ptr
+          end subroutine kmp_free
+
+          subroutine kmp_set_warnings_on() bind(c)
+          end subroutine kmp_set_warnings_on
+
+          subroutine kmp_set_warnings_off() bind(c)
+          end subroutine kmp_set_warnings_off
+
+          function kmp_get_cancellation_status(cancelkind) bind(c)
+            use omp_lib_kinds
+            integer (kind=kmp_cancel_kind), value :: cancelkind
+            logical (kind=omp_logical_kind) kmp_get_cancellation_status
+          end function kmp_get_cancellation_status
+
+          subroutine omp_init_lock_with_hint(svar, hint) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_lock_kind) svar
+            integer (kind=omp_lock_hint_kind), value :: hint
+          end subroutine omp_init_lock_with_hint
+
+          subroutine omp_init_nest_lock_with_hint(nvar, hint) bind(c)
+            use omp_lib_kinds
+            integer (kind=omp_nest_lock_kind) nvar
+            integer (kind=omp_lock_hint_kind), value :: hint
+          end subroutine omp_init_nest_lock_with_hint
+
+        end interface
+
+      end module omp_lib

runtime/src/include/50/omp_lib.h.var

@@ -0,0 +1,644 @@
+! include/50/omp_lib.h.var
+
+!
+!//===----------------------------------------------------------------------===//
+!//
+!//                     The LLVM Compiler Infrastructure
+!//
+!// This file is dual licensed under the MIT and the University of Illinois Open
+!// Source Licenses. See LICENSE.txt for details.
+!//
+!//===----------------------------------------------------------------------===//
+!
+
+!***
+!*** Some of the directives for the following routine extend past column 72,
+!*** so process this file in 132-column mode.
+!***
+
+!DIR$ fixedformlinesize:132
+
+      integer, parameter :: omp_integer_kind       = 4
+      integer, parameter :: omp_logical_kind       = 4
+      integer, parameter :: omp_real_kind          = 4
+      integer, parameter :: omp_lock_kind          = int_ptr_kind()
+      integer, parameter :: omp_nest_lock_kind     = int_ptr_kind()
+      integer, parameter :: omp_sched_kind         = omp_integer_kind
+      integer, parameter :: omp_proc_bind_kind     = omp_integer_kind
+      integer, parameter :: kmp_pointer_kind       = int_ptr_kind()
+      integer, parameter :: kmp_size_t_kind        = int_ptr_kind()
+      integer, parameter :: kmp_affinity_mask_kind = int_ptr_kind()
+      integer, parameter :: omp_lock_hint_kind     = omp_integer_kind
+
+      integer (kind=omp_integer_kind), parameter :: openmp_version    = @LIBOMP_OMP_YEAR_MONTH@
+      integer (kind=omp_integer_kind), parameter :: kmp_version_major = @LIBOMP_VERSION_MAJOR@
+      integer (kind=omp_integer_kind), parameter :: kmp_version_minor = @LIBOMP_VERSION_MINOR@
+      integer (kind=omp_integer_kind), parameter :: kmp_version_build = @LIBOMP_VERSION_BUILD@
+      character(*)               kmp_build_date
+      parameter( kmp_build_date = '@LIBOMP_BUILD_DATE@' )
+
+      integer(kind=omp_sched_kind), parameter :: omp_sched_static  = 1
+      integer(kind=omp_sched_kind), parameter :: omp_sched_dynamic = 2
+      integer(kind=omp_sched_kind), parameter :: omp_sched_guided  = 3
+      integer(kind=omp_sched_kind), parameter :: omp_sched_auto    = 4
+
+      integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_false = 0
+      integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_true = 1
+      integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_master = 2
+      integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_close = 3
+      integer (kind=omp_proc_bind_kind), parameter :: omp_proc_bind_spread = 4
+
+      integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_none           = 0
+      integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_uncontended    = 1
+      integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_contended      = 2
+      integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_nonspeculative = 4
+      integer (kind=omp_lock_hint_kind), parameter :: omp_lock_hint_speculative    = 8
+      integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_hle            = 65536
+      integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_rtm            = 131072
+      integer (kind=omp_lock_hint_kind), parameter :: kmp_lock_hint_adaptive       = 262144
+
+      interface
+
+!       ***
+!       *** omp_* entry points
+!       ***
+
+        subroutine omp_set_num_threads(num_threads) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: num_threads
+        end subroutine omp_set_num_threads
+
+        subroutine omp_set_dynamic(dynamic_threads) bind(c)
+          import
+          logical (kind=omp_logical_kind), value :: dynamic_threads
+        end subroutine omp_set_dynamic
+
+        subroutine omp_set_nested(nested) bind(c)
+          import
+          logical (kind=omp_logical_kind), value :: nested
+        end subroutine omp_set_nested
+
+        function omp_get_num_threads() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_num_threads
+        end function omp_get_num_threads
+
+        function omp_get_max_threads() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_max_threads
+        end function omp_get_max_threads
+
+        function omp_get_thread_num() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_thread_num
+        end function omp_get_thread_num
+
+        function omp_get_num_procs() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_num_procs
+        end function omp_get_num_procs
+
+        function omp_in_parallel() bind(c)
+          import
+          logical (kind=omp_logical_kind) omp_in_parallel
+        end function omp_in_parallel
+
+        function omp_in_final() bind(c)
+          import
+          logical (kind=omp_logical_kind) omp_in_final
+        end function omp_in_final
+
+        function omp_get_dynamic() bind(c)
+          import
+          logical (kind=omp_logical_kind) omp_get_dynamic
+        end function omp_get_dynamic
+
+        function omp_get_nested() bind(c)
+          import
+          logical (kind=omp_logical_kind) omp_get_nested
+        end function omp_get_nested
+
+        function omp_get_thread_limit() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_thread_limit
+        end function omp_get_thread_limit
+
+        subroutine omp_set_max_active_levels(max_levels) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: max_levels
+        end subroutine omp_set_max_active_levels
+
+        function omp_get_max_active_levels() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_max_active_levels
+        end function omp_get_max_active_levels
+
+        function omp_get_level() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_level
+        end function omp_get_level
+
+        function omp_get_active_level() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_active_level
+        end function omp_get_active_level
+
+        function omp_get_ancestor_thread_num(level) bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_ancestor_thread_num
+          integer (kind=omp_integer_kind), value :: level
+        end function omp_get_ancestor_thread_num
+
+        function omp_get_team_size(level) bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_team_size
+          integer (kind=omp_integer_kind), value :: level
+        end function omp_get_team_size
+
+        subroutine omp_set_schedule(kind, chunk_size) bind(c)
+          import
+          integer (kind=omp_sched_kind), value :: kind
+          integer (kind=omp_integer_kind), value :: chunk_size
+        end subroutine omp_set_schedule
+
+        subroutine omp_get_schedule(kind, chunk_size) bind(c)
+          import
+          integer (kind=omp_sched_kind) kind
+          integer (kind=omp_integer_kind) chunk_size
+        end subroutine omp_get_schedule
+
+        function omp_get_proc_bind() bind(c)
+          import
+          integer (kind=omp_proc_bind_kind) omp_get_proc_bind
+        end function omp_get_proc_bind
+
+        function omp_get_num_places() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_num_places
+        end function omp_get_num_places
+
+        function omp_get_place_num_procs(place_num) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: place_num
+          integer (kind=omp_integer_kind) omp_get_place_num_procs
+        end function omp_get_place_num_procs
+
+        subroutine omp_get_place_proc_ids(place_num, ids) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: place_num
+          integer (kind=kmp_pointer_kind) ids(*)
+        end subroutine omp_get_place_proc_ids
+
+        function omp_get_place_num() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_place_num
+        end function omp_get_place_num
+
+        function omp_get_partition_num_places() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_partition_num_places
+        end function omp_get_partition_num_places
+
+        subroutine omp_get_partition_place_nums(place_nums) bind(c)
+          import
+          integer (kind=kmp_pointer_kind) place_nums(*)
+        end subroutine omp_get_partition_place_nums
+
+        function omp_get_wtime() bind(c)
+          double precision omp_get_wtime
+        end function omp_get_wtime
+
+        function omp_get_wtick() bind(c)
+          double precision omp_get_wtick
+        end function omp_get_wtick
+
+        function omp_get_default_device() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_default_device
+        end function omp_get_default_device
+
+        subroutine omp_set_default_device(device_num) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: device_num
+        end subroutine omp_set_default_device
+
+        function omp_get_num_devices() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_num_devices
+        end function omp_get_num_devices
+
+        function omp_get_num_teams() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_num_teams
+        end function omp_get_num_teams
+
+        function omp_get_team_num() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_team_num
+        end function omp_get_team_num
+
+        function omp_is_initial_device() bind(c)
+          import
+          logical (kind=omp_logical_kind) omp_is_initial_device
+        end function omp_is_initial_device
+
+        function omp_get_initial_device() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_initial_device
+        end function omp_get_initial_device
+
+        subroutine omp_init_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_lock_kind) svar
+        end subroutine omp_init_lock
+
+        subroutine omp_destroy_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_lock_kind) svar
+        end subroutine omp_destroy_lock
+
+        subroutine omp_set_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_lock_kind) svar
+        end subroutine omp_set_lock
+
+        subroutine omp_unset_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_lock_kind) svar
+        end subroutine omp_unset_lock
+
+        function omp_test_lock(svar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_lock
+!DIR$ ENDIF
+          import
+          logical (kind=omp_logical_kind) omp_test_lock
+          integer (kind=omp_lock_kind) svar
+        end function omp_test_lock
+
+        subroutine omp_init_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_init_nest_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_nest_lock_kind) nvar
+        end subroutine omp_init_nest_lock
+
+        subroutine omp_destroy_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_destroy_nest_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_nest_lock_kind) nvar
+        end subroutine omp_destroy_nest_lock
+
+        subroutine omp_set_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_set_nest_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_nest_lock_kind) nvar
+        end subroutine omp_set_nest_lock
+
+        subroutine omp_unset_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_unset_nest_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_nest_lock_kind) nvar
+        end subroutine omp_unset_nest_lock
+
+        function omp_test_nest_lock(nvar) bind(c)
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!DIR$ attributes known_intrinsic :: omp_test_nest_lock
+!DIR$ ENDIF
+          import
+          integer (kind=omp_integer_kind) omp_test_nest_lock
+          integer (kind=omp_nest_lock_kind) nvar
+        end function omp_test_nest_lock
+
+        function omp_get_max_task_priority() bind(c)
+          import
+          integer (kind=omp_integer_kind) omp_get_max_task_priority
+        end function omp_get_max_task_priority
+
+!       ***
+!       *** kmp_* entry points
+!       ***
+
+        subroutine kmp_set_stacksize(size) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: size
+        end subroutine kmp_set_stacksize
+
+        subroutine kmp_set_stacksize_s(size) bind(c)
+          import
+          integer (kind=kmp_size_t_kind), value :: size
+        end subroutine kmp_set_stacksize_s
+
+        subroutine kmp_set_blocktime(msec) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: msec
+        end subroutine kmp_set_blocktime
+
+        subroutine kmp_set_library_serial() bind(c)
+        end subroutine kmp_set_library_serial
+
+        subroutine kmp_set_library_turnaround() bind(c)
+        end subroutine kmp_set_library_turnaround
+
+        subroutine kmp_set_library_throughput() bind(c)
+        end subroutine kmp_set_library_throughput
+
+        subroutine kmp_set_library(libnum) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: libnum
+        end subroutine kmp_set_library
+
+        subroutine kmp_set_defaults(string) bind(c)
+          character string(*)
+        end subroutine kmp_set_defaults
+
+        function kmp_get_stacksize() bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_stacksize
+        end function kmp_get_stacksize
+
+        function kmp_get_stacksize_s() bind(c)
+          import
+          integer (kind=kmp_size_t_kind) kmp_get_stacksize_s
+        end function kmp_get_stacksize_s
+
+        function kmp_get_blocktime() bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_blocktime
+        end function kmp_get_blocktime
+
+        function kmp_get_library() bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_library
+        end function kmp_get_library
+
+        subroutine kmp_set_disp_num_buffers(num) bind(c)
+          import
+          integer (kind=omp_integer_kind), value :: num
+        end subroutine kmp_set_disp_num_buffers
+
+        function kmp_set_affinity(mask) bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_set_affinity
+          integer (kind=kmp_affinity_mask_kind) mask
+        end function kmp_set_affinity
+
+        function kmp_get_affinity(mask) bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_affinity
+          integer (kind=kmp_affinity_mask_kind) mask
+        end function kmp_get_affinity
+
+        function kmp_get_affinity_max_proc() bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_affinity_max_proc
+        end function kmp_get_affinity_max_proc
+
+        subroutine kmp_create_affinity_mask(mask) bind(c)
+          import
+          integer (kind=kmp_affinity_mask_kind) mask
+        end subroutine kmp_create_affinity_mask
+
+        subroutine kmp_destroy_affinity_mask(mask) bind(c)
+          import
+          integer (kind=kmp_affinity_mask_kind) mask
+        end subroutine kmp_destroy_affinity_mask
+
+        function kmp_set_affinity_mask_proc(proc, mask) bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_set_affinity_mask_proc
+          integer (kind=omp_integer_kind), value :: proc
+          integer (kind=kmp_affinity_mask_kind) mask
+        end function kmp_set_affinity_mask_proc
+
+        function kmp_unset_affinity_mask_proc(proc, mask) bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_unset_affinity_mask_proc
+          integer (kind=omp_integer_kind), value :: proc
+          integer (kind=kmp_affinity_mask_kind) mask
+        end function kmp_unset_affinity_mask_proc
+
+        function kmp_get_affinity_mask_proc(proc, mask) bind(c)
+          import
+          integer (kind=omp_integer_kind) kmp_get_affinity_mask_proc
+          integer (kind=omp_integer_kind), value :: proc
+          integer (kind=kmp_affinity_mask_kind) mask
+        end function kmp_get_affinity_mask_proc
+
+        function kmp_malloc(size) bind(c)
+          import
+          integer (kind=kmp_pointer_kind) kmp_malloc
+          integer (kind=kmp_size_t_kind), value :: size
+        end function kmp_malloc
+
+        function kmp_aligned_malloc(size, alignment) bind(c)
+          import
+          integer (kind=kmp_pointer_kind) kmp_aligned_malloc
+          integer (kind=kmp_size_t_kind), value :: size
+          integer (kind=kmp_size_t_kind), value :: alignment
+        end function kmp_aligned_malloc
+
+        function kmp_calloc(nelem, elsize) bind(c)
+          import
+          integer (kind=kmp_pointer_kind) kmp_calloc
+          integer (kind=kmp_size_t_kind), value :: nelem
+          integer (kind=kmp_size_t_kind), value :: elsize
+        end function kmp_calloc
+
+        function kmp_realloc(ptr, size) bind(c)
+          import
+          integer (kind=kmp_pointer_kind) kmp_realloc
+          integer (kind=kmp_pointer_kind), value :: ptr
+          integer (kind=kmp_size_t_kind), value :: size
+        end function kmp_realloc
+
+        subroutine kmp_free(ptr) bind(c)
+          import
+          integer (kind=kmp_pointer_kind), value :: ptr
+        end subroutine kmp_free
+
+        subroutine kmp_set_warnings_on() bind(c)
+        end subroutine kmp_set_warnings_on
+
+        subroutine kmp_set_warnings_off() bind(c)
+        end subroutine kmp_set_warnings_off
+
+        subroutine omp_init_lock_with_hint(svar, hint) bind(c)
+          import
+          integer (kind=omp_lock_kind) svar
+          integer (kind=omp_lock_hint_kind), value :: hint
+        end subroutine omp_init_lock_with_hint
+
+        subroutine omp_init_nest_lock_with_hint(nvar, hint) bind(c)
+          import
+          integer (kind=omp_nest_lock_kind) nvar
+          integer (kind=omp_lock_hint_kind), value :: hint
+        end subroutine omp_init_nest_lock_with_hint
+
+      end interface
+
+!DIR$ IF DEFINED (__INTEL_OFFLOAD)
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_num_threads
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_dynamic
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nested
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_threads
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_threads
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_num
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_procs
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_parallel
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_in_final
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_dynamic
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_nested
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_thread_limit
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_max_active_levels
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_active_levels
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_level
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_active_level
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_ancestor_thread_num
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_size
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_schedule
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_schedule
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_proc_bind
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtime
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_wtick
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_default_device
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_default_device
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_is_initial_device
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_devices
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_num_teams
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_team_num
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_nest_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_destroy_nest_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_set_nest_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_unset_nest_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_test_nest_lock
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_get_max_task_priority
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_stacksize_s
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_blocktime
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_serial
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_turnaround
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library_throughput
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_library
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_defaults
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_stacksize_s
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_blocktime
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_library
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_disp_num_buffers
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_max_proc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_create_affinity_mask
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_destroy_affinity_mask
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_affinity_mask_proc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_unset_affinity_mask_proc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_get_affinity_mask_proc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_malloc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_aligned_malloc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_calloc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_realloc
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_free
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_on
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: kmp_set_warnings_off
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_lock_with_hint
+!DIR$ ATTRIBUTES OFFLOAD:MIC :: omp_init_nest_lock_with_hint
+
+!DIR$ IF(__INTEL_COMPILER.GE.1400)
+!$omp declare target(omp_set_num_threads )
+!$omp declare target(omp_set_dynamic )
+!$omp declare target(omp_set_nested )
+!$omp declare target(omp_get_num_threads )
+!$omp declare target(omp_get_max_threads )
+!$omp declare target(omp_get_thread_num )
+!$omp declare target(omp_get_num_procs )
+!$omp declare target(omp_in_parallel )
+!$omp declare target(omp_in_final )
+!$omp declare target(omp_get_dynamic )
+!$omp declare target(omp_get_nested )
+!$omp declare target(omp_get_thread_limit )
+!$omp declare target(omp_set_max_active_levels )
+!$omp declare target(omp_get_max_active_levels )
+!$omp declare target(omp_get_level )
+!$omp declare target(omp_get_active_level )
+!$omp declare target(omp_get_ancestor_thread_num )
+!$omp declare target(omp_get_team_size )
+!$omp declare target(omp_set_schedule )
+!$omp declare target(omp_get_schedule )
+!$omp declare target(omp_get_proc_bind )
+!$omp declare target(omp_get_wtime )
+!$omp declare target(omp_get_wtick )
+!$omp declare target(omp_get_default_device )
+!$omp declare target(omp_set_default_device )
+!$omp declare target(omp_is_initial_device )
+!$omp declare target(omp_get_num_devices )
+!$omp declare target(omp_get_num_teams )
+!$omp declare target(omp_get_team_num )
+!$omp declare target(omp_init_lock )
+!$omp declare target(omp_destroy_lock )
+!$omp declare target(omp_set_lock )
+!$omp declare target(omp_unset_lock )
+!$omp declare target(omp_test_lock )
+!$omp declare target(omp_init_nest_lock )
+!$omp declare target(omp_destroy_nest_lock )
+!$omp declare target(omp_set_nest_lock )
+!$omp declare target(omp_unset_nest_lock )
+!$omp declare target(omp_test_nest_lock )
+!$omp declare target(omp_get_max_task_priority )
+!$omp declare target(kmp_set_stacksize )
+!$omp declare target(kmp_set_stacksize_s )
+!$omp declare target(kmp_set_blocktime )
+!$omp declare target(kmp_set_library_serial )
+!$omp declare target(kmp_set_library_turnaround )
+!$omp declare target(kmp_set_library_throughput )
+!$omp declare target(kmp_set_library )
+!$omp declare target(kmp_set_defaults )
+!$omp declare target(kmp_get_stacksize )
+!$omp declare target(kmp_get_stacksize_s )
+!$omp declare target(kmp_get_blocktime )
+!$omp declare target(kmp_get_library )
+!$omp declare target(kmp_set_disp_num_buffers )
+!$omp declare target(kmp_set_affinity )
+!$omp declare target(kmp_get_affinity )
+!$omp declare target(kmp_get_affinity_max_proc )
+!$omp declare target(kmp_create_affinity_mask )
+!$omp declare target(kmp_destroy_affinity_mask )
+!$omp declare target(kmp_set_affinity_mask_proc )
+!$omp declare target(kmp_unset_affinity_mask_proc )
+!$omp declare target(kmp_get_affinity_mask_proc )
+!$omp declare target(kmp_malloc )
+!$omp declare target(kmp_aligned_malloc )
+!$omp declare target(kmp_calloc )
+!$omp declare target(kmp_realloc )
+!$omp declare target(kmp_free )
+!$omp declare target(kmp_set_warnings_on )
+!$omp declare target(kmp_set_warnings_off )
+!$omp declare target(omp_init_lock_with_hint )
+!$omp declare target(omp_init_nest_lock_with_hint )
+!DIR$ ENDIF
+!DIR$ ENDIF
+

runtime/src/include/50/ompt.h.var

@@ -0,0 +1,515 @@
+/*
+ * include/50/ompt.h.var
+ */
+
+#ifndef __OMPT__
+#define __OMPT__
+
+/*****************************************************************************
+ * system include files
+ *****************************************************************************/
+
+#include <stdint.h>
+
+
+
+/*****************************************************************************
+ * iteration macros
+ *****************************************************************************/
+
+#define FOREACH_OMPT_INQUIRY_FN(macro)  \
+    macro (ompt_enumerate_state)        \
+                                        \
+    macro (ompt_set_callback)           \
+    macro (ompt_get_callback)           \
+                                        \
+    macro (ompt_get_idle_frame)         \
+    macro (ompt_get_task_frame)         \
+                                        \
+    macro (ompt_get_state)              \
+                                        \
+    macro (ompt_get_parallel_id)        \
+    macro (ompt_get_parallel_team_size) \
+    macro (ompt_get_task_id)            \
+    macro (ompt_get_thread_id)
+
+#define FOREACH_OMPT_PLACEHOLDER_FN(macro)  \
+    macro (ompt_idle)                       \
+    macro (ompt_overhead)                   \
+    macro (ompt_barrier_wait)               \
+    macro (ompt_task_wait)                  \
+    macro (ompt_mutex_wait)
+
+#define FOREACH_OMPT_STATE(macro)                                                               \
+                                                                                                \
+    /* first */                                                                                 \
+    macro (ompt_state_first, 0x71)          /* initial enumeration state */                     \
+                                                                                                \
+    /* work states (0..15) */                                                                   \
+    macro (ompt_state_work_serial, 0x00)    /* working outside parallel */                      \
+    macro (ompt_state_work_parallel, 0x01)  /* working within parallel */                       \
+    macro (ompt_state_work_reduction, 0x02) /* performing a reduction */                        \
+                                                                                                \
+    /* idle (16..31) */                                                                         \
+    macro (ompt_state_idle, 0x10)            /* waiting for work */                             \
+                                                                                                \
+    /* overhead states (32..63) */                                                              \
+    macro (ompt_state_overhead, 0x20)        /* overhead excluding wait states */               \
+                                                                                                \
+    /* barrier wait states (64..79) */                                                          \
+    macro (ompt_state_wait_barrier, 0x40)    /* waiting at a barrier */                         \
+    macro (ompt_state_wait_barrier_implicit, 0x41)    /* implicit barrier */                    \
+    macro (ompt_state_wait_barrier_explicit, 0x42)    /* explicit barrier */                    \
+                                                                                                \
+    /* task wait states (80..95) */                                                             \
+    macro (ompt_state_wait_taskwait, 0x50)   /* waiting at a taskwait */                        \
+    macro (ompt_state_wait_taskgroup, 0x51)  /* waiting at a taskgroup */                       \
+                                                                                                \
+    /* mutex wait states (96..111) */                                                           \
+    macro (ompt_state_wait_lock, 0x60)       /* waiting for lock */                             \
+    macro (ompt_state_wait_nest_lock, 0x61)  /* waiting for nest lock */                        \
+    macro (ompt_state_wait_critical, 0x62)   /* waiting for critical */                         \
+    macro (ompt_state_wait_atomic, 0x63)     /* waiting for atomic */                           \
+    macro (ompt_state_wait_ordered, 0x64)    /* waiting for ordered */                          \
+    macro (ompt_state_wait_single, 0x6F)     /* waiting for single region (non-standard!) */    \
+                                                                                                \
+    /* misc (112..127) */                                                                       \
+    macro (ompt_state_undefined, 0x70)       /* undefined thread state */
+
+
+#define FOREACH_OMPT_EVENT(macro)                                                                               \
+                                                                                                                \
+    /*--- Mandatory Events ---*/                                                                                \
+    macro (ompt_event_parallel_begin,           ompt_new_parallel_callback_t,   1) /* parallel begin */         \
+    macro (ompt_event_parallel_end,             ompt_end_parallel_callback_t,   2) /* parallel end */           \
+                                                                                                                \
+    macro (ompt_event_task_begin,               ompt_new_task_callback_t,       3) /* task begin */             \
+    macro (ompt_event_task_end,                 ompt_task_callback_t,           4) /* task destroy */           \
+                                                                                                                \
+    macro (ompt_event_thread_begin,             ompt_thread_type_callback_t,    5) /* thread begin */           \
+    macro (ompt_event_thread_end,               ompt_thread_type_callback_t,    6) /* thread end */             \
+                                                                                                                \
+    macro (ompt_event_control,                  ompt_control_callback_t,        7) /* support control calls */  \
+                                                                                                                \
+    macro (ompt_event_runtime_shutdown,         ompt_callback_t,                8) /* runtime shutdown */       \
+                                                                                                                \
+    /*--- Optional Events (blame shifting, ompt_event_unimplemented) ---*/                                      \
+    macro (ompt_event_idle_begin,               ompt_thread_callback_t,         9) /* begin idle state */       \
+    macro (ompt_event_idle_end,                 ompt_thread_callback_t,        10) /* end idle state */         \
+                                                                                                                \
+    macro (ompt_event_wait_barrier_begin,       ompt_parallel_callback_t,      11) /* begin wait at barrier */  \
+    macro (ompt_event_wait_barrier_end,         ompt_parallel_callback_t,      12) /* end wait at barrier */    \
+                                                                                                                \
+    macro (ompt_event_wait_taskwait_begin,      ompt_parallel_callback_t,      13) /* begin wait at taskwait */ \
+    macro (ompt_event_wait_taskwait_end,        ompt_parallel_callback_t,      14) /* end wait at taskwait */   \
+                                                                                                                \
+    macro (ompt_event_wait_taskgroup_begin,     ompt_parallel_callback_t,      15) /* begin wait at taskgroup */\
+    macro (ompt_event_wait_taskgroup_end,       ompt_parallel_callback_t,      16) /* end wait at taskgroup */  \
+                                                                                                                \
+    macro (ompt_event_release_lock,             ompt_wait_callback_t,          17) /* lock release */           \
+    macro (ompt_event_release_nest_lock_last,   ompt_wait_callback_t,          18) /* last nest lock release */ \
+    macro (ompt_event_release_critical,         ompt_wait_callback_t,          19) /* critical release */       \
+                                                                                                                \
+    macro (ompt_event_release_atomic,           ompt_wait_callback_t,          20) /* atomic release */         \
+                                                                                                                \
+    macro (ompt_event_release_ordered,          ompt_wait_callback_t,          21) /* ordered release */        \
+                                                                                                                \
+    /*--- Optional Events (synchronous events, ompt_event_unimplemented) --- */                                 \
+    macro (ompt_event_implicit_task_begin,      ompt_parallel_callback_t,      22) /* implicit task begin   */  \
+    macro (ompt_event_implicit_task_end,        ompt_parallel_callback_t,      23) /* implicit task end  */     \
+                                                                                                                \
+    macro (ompt_event_initial_task_begin,       ompt_parallel_callback_t,      24) /* initial task begin   */   \
+    macro (ompt_event_initial_task_end,         ompt_parallel_callback_t,      25) /* initial task end  */      \
+                                                                                                                \
+    macro (ompt_event_task_switch,              ompt_task_pair_callback_t,     26) /* task switch */            \
+                                                                                                                \
+    macro (ompt_event_loop_begin,               ompt_new_workshare_callback_t, 27) /* task at loop begin */     \
+    macro (ompt_event_loop_end,                 ompt_parallel_callback_t,      28) /* task at loop end */       \
+                                                                                                                \
+    macro (ompt_event_sections_begin,           ompt_new_workshare_callback_t, 29) /* task at sections begin  */\
+    macro (ompt_event_sections_end,             ompt_parallel_callback_t,      30) /* task at sections end */   \
+                                                                                                                \
+    macro (ompt_event_single_in_block_begin,    ompt_new_workshare_callback_t, 31) /* task at single begin*/    \
+    macro (ompt_event_single_in_block_end,      ompt_parallel_callback_t,      32) /* task at single end */     \
+                                                                                                                \
+    macro (ompt_event_single_others_begin,      ompt_parallel_callback_t,      33) /* task at single begin */   \
+    macro (ompt_event_single_others_end,        ompt_parallel_callback_t,      34) /* task at single end */     \
+                                                                                                                \
+    macro (ompt_event_workshare_begin,          ompt_new_workshare_callback_t, 35) /* task at workshare begin */\
+    macro (ompt_event_workshare_end,            ompt_parallel_callback_t,      36) /* task at workshare end */  \
+                                                                                                                \
+    macro (ompt_event_master_begin,             ompt_parallel_callback_t,      37) /* task at master begin */   \
+    macro (ompt_event_master_end,               ompt_parallel_callback_t,      38) /* task at master end */     \
+                                                                                                                \
+    macro (ompt_event_barrier_begin,            ompt_parallel_callback_t,      39) /* task at barrier begin  */ \
+    macro (ompt_event_barrier_end,              ompt_parallel_callback_t,      40) /* task at barrier end */    \
+                                                                                                                \
+    macro (ompt_event_taskwait_begin,           ompt_parallel_callback_t,      41) /* task at taskwait begin */ \
+    macro (ompt_event_taskwait_end,             ompt_parallel_callback_t,      42) /* task at task wait end */  \
+                                                                                                                \
+    macro (ompt_event_taskgroup_begin,          ompt_parallel_callback_t,      43) /* task at taskgroup begin */\
+    macro (ompt_event_taskgroup_end,            ompt_parallel_callback_t,      44) /* task at taskgroup end */  \
+                                                                                                                \
+    macro (ompt_event_release_nest_lock_prev,   ompt_wait_callback_t,          45) /* prev nest lock release */ \
+                                                                                                                \
+    macro (ompt_event_wait_lock,                ompt_wait_callback_t,          46) /* lock wait */              \
+    macro (ompt_event_wait_nest_lock,           ompt_wait_callback_t,          47) /* nest lock wait */         \
+    macro (ompt_event_wait_critical,            ompt_wait_callback_t,          48) /* critical wait */          \
+    macro (ompt_event_wait_atomic,              ompt_wait_callback_t,          49) /* atomic wait */            \
+    macro (ompt_event_wait_ordered,             ompt_wait_callback_t,          50) /* ordered wait */           \
+                                                                                                                \
+    macro (ompt_event_acquired_lock,            ompt_wait_callback_t,          51) /* lock acquired */          \
+    macro (ompt_event_acquired_nest_lock_first, ompt_wait_callback_t,          52) /* 1st nest lock acquired */ \
+    macro (ompt_event_acquired_nest_lock_next,  ompt_wait_callback_t,          53) /* next nest lock acquired*/ \
+    macro (ompt_event_acquired_critical,        ompt_wait_callback_t,          54) /* critical acquired */      \
+    macro (ompt_event_acquired_atomic,          ompt_wait_callback_t,          55) /* atomic acquired */        \
+    macro (ompt_event_acquired_ordered,         ompt_wait_callback_t,          56) /* ordered acquired */       \
+                                                                                                                \
+    macro (ompt_event_init_lock,                ompt_wait_callback_t,          57) /* lock init */              \
+    macro (ompt_event_init_nest_lock,           ompt_wait_callback_t,          58) /* nest lock init */         \
+                                                                                                                \
+    macro (ompt_event_destroy_lock,             ompt_wait_callback_t,          59) /* lock destruction */       \
+    macro (ompt_event_destroy_nest_lock,        ompt_wait_callback_t,          60) /* nest lock destruction */  \
+                                                                                                                \
+    macro (ompt_event_flush,                    ompt_callback_t,               61) /* after executing flush */  \
+                                                                                                                \
+    macro (ompt_event_task_dependences,         ompt_task_dependences_callback_t, 69) /* report task dependences  */\
+    macro (ompt_event_task_dependence_pair,     ompt_task_pair_callback_t,     70) /* report task dependence pair */
+
+
+
+/*****************************************************************************
+ * data types
+ *****************************************************************************/
+
+/*---------------------
+ * identifiers
+ *---------------------*/
+
+typedef uint64_t ompt_thread_id_t;
+#define ompt_thread_id_none ((ompt_thread_id_t) 0)     /* non-standard */
+
+typedef uint64_t ompt_task_id_t;
+#define ompt_task_id_none ((ompt_task_id_t) 0)         /* non-standard */
+
+typedef uint64_t ompt_parallel_id_t;
+#define ompt_parallel_id_none ((ompt_parallel_id_t) 0) /* non-standard */
+
+typedef uint64_t ompt_wait_id_t;
+#define ompt_wait_id_none ((ompt_wait_id_t) 0)         /* non-standard */
+
+
+/*---------------------
+ * ompt_frame_t
+ *---------------------*/
+
+typedef struct ompt_frame_s {
+    void *exit_runtime_frame;    /* next frame is user code     */
+    void *reenter_runtime_frame; /* previous frame is user code */
+} ompt_frame_t;
+
+
+/*---------------------
+ * dependences types
+ *---------------------*/
+
+typedef enum ompt_task_dependence_flag_e {
+    // a two bit field for the dependence type
+    ompt_task_dependence_type_out   = 1,
+    ompt_task_dependence_type_in    = 2,
+    ompt_task_dependence_type_inout = 3,
+} ompt_task_dependence_flag_t;
+
+typedef struct ompt_task_dependence_s {
+    void *variable_addr;
+    uint32_t  dependence_flags;
+} ompt_task_dependence_t;
+
+
+/*****************************************************************************
+ * enumerations for thread states and runtime events
+ *****************************************************************************/
+
+/*---------------------
+ * runtime states
+ *---------------------*/
+
+typedef enum {
+#define ompt_state_macro(state, code) state = code,
+    FOREACH_OMPT_STATE(ompt_state_macro)
+#undef ompt_state_macro
+} ompt_state_t;
+
+
+/*---------------------
+ * runtime events
+ *---------------------*/
+
+typedef enum {
+#define ompt_event_macro(event, callback, eventid) event = eventid,
+    FOREACH_OMPT_EVENT(ompt_event_macro)
+#undef ompt_event_macro
+} ompt_event_t;
+
+
+/*---------------------
+ * set callback results
+ *---------------------*/
+typedef enum {
+    ompt_set_result_registration_error              = 0,
+    ompt_set_result_event_may_occur_no_callback     = 1,
+    ompt_set_result_event_never_occurs              = 2,
+    ompt_set_result_event_may_occur_callback_some   = 3,
+    ompt_set_result_event_may_occur_callback_always = 4,
+} ompt_set_result_t;
+
+
+
+/*****************************************************************************
+ * callback signatures
+ *****************************************************************************/
+
+/* initialization */
+typedef void (*ompt_interface_fn_t)(void);
+
+typedef ompt_interface_fn_t (*ompt_function_lookup_t)(
+    const char *                      /* entry point to look up       */
+);
+
+/* threads */
+typedef void (*ompt_thread_callback_t) (
+    ompt_thread_id_t thread_id        /* ID of thread                 */
+);
+
+typedef enum {
+    ompt_thread_initial = 1, // start the enumeration at 1
+    ompt_thread_worker  = 2,
+    ompt_thread_other   = 3
+} ompt_thread_type_t;
+
+typedef enum {
+    ompt_invoker_program = 0,         /* program invokes master task  */
+    ompt_invoker_runtime = 1          /* runtime invokes master task  */
+} ompt_invoker_t;
+
+typedef void (*ompt_thread_type_callback_t) (
+    ompt_thread_type_t thread_type,   /* type of thread               */
+    ompt_thread_id_t thread_id        /* ID of thread                 */
+);
+
+typedef void (*ompt_wait_callback_t) (
+    ompt_wait_id_t wait_id            /* wait id                      */
+);
+
+/* parallel and workshares */
+typedef void (*ompt_parallel_callback_t) (
+    ompt_parallel_id_t parallel_id,    /* id of parallel region       */
+    ompt_task_id_t task_id             /* id of task                  */
+);
+
+typedef void (*ompt_new_workshare_callback_t) (
+    ompt_parallel_id_t parallel_id,   /* id of parallel region        */
+    ompt_task_id_t parent_task_id,    /* id of parent task            */
+    void *workshare_function          /* pointer to outlined function */
+);
+
+typedef void (*ompt_new_parallel_callback_t) (
+    ompt_task_id_t parent_task_id,    /* id of parent task            */
+    ompt_frame_t *parent_task_frame,  /* frame data of parent task    */
+    ompt_parallel_id_t parallel_id,   /* id of parallel region        */
+    uint32_t requested_team_size,     /* number of threads in team    */
+    void *parallel_function,          /* pointer to outlined function */
+    ompt_invoker_t invoker            /* who invokes master task?     */
+);
+
+typedef void (*ompt_end_parallel_callback_t) (
+    ompt_parallel_id_t parallel_id,   /* id of parallel region       */
+    ompt_task_id_t task_id,           /* id of task                  */
+    ompt_invoker_t invoker            /* who invokes master task?    */
+);
+
+/* tasks */
+typedef void (*ompt_task_callback_t) (
+    ompt_task_id_t task_id            /* id of task                   */
+);
+
+typedef void (*ompt_task_pair_callback_t) (
+    ompt_task_id_t first_task_id,
+    ompt_task_id_t second_task_id
+);
+
+typedef void (*ompt_new_task_callback_t) (
+    ompt_task_id_t parent_task_id,    /* id of parent task            */
+    ompt_frame_t *parent_task_frame,  /* frame data for parent task   */
+    ompt_task_id_t  new_task_id,      /* id of created task           */
+    void *task_function               /* pointer to outlined function */
+);
+
+/* task dependences */
+typedef void (*ompt_task_dependences_callback_t) (
+    ompt_task_id_t task_id,            /* ID of task with dependences */
+    const ompt_task_dependence_t *deps,/* vector of task dependences  */
+    int ndeps                          /* number of dependences       */
+);
+
+/* program */
+typedef void (*ompt_control_callback_t) (
+    uint64_t command,                 /* command of control call      */
+    uint64_t modifier                 /* modifier of control call     */
+);
+
+typedef void (*ompt_callback_t)(void);
+
+
+/****************************************************************************
+ * ompt API
+ ***************************************************************************/
+
+#ifdef  __cplusplus
+extern "C" {
+#endif
+
+#define OMPT_API_FNTYPE(fn) fn##_t
+
+#define OMPT_API_FUNCTION(return_type, fn, args)  \
+    typedef return_type (*OMPT_API_FNTYPE(fn)) args
+
+
+
+/****************************************************************************
+ * INQUIRY FUNCTIONS
+ ***************************************************************************/
+
+/* state */
+OMPT_API_FUNCTION(ompt_state_t, ompt_get_state, (
+    ompt_wait_id_t *ompt_wait_id
+));
+
+/* thread */
+OMPT_API_FUNCTION(ompt_thread_id_t, ompt_get_thread_id, (void));
+
+OMPT_API_FUNCTION(void *, ompt_get_idle_frame, (void));
+
+/* parallel region */
+OMPT_API_FUNCTION(ompt_parallel_id_t, ompt_get_parallel_id, (
+    int ancestor_level
+));
+
+OMPT_API_FUNCTION(int, ompt_get_parallel_team_size, (
+    int ancestor_level
+));
+
+/* task */
+OMPT_API_FUNCTION(ompt_task_id_t, ompt_get_task_id, (
+    int depth
+));
+
+OMPT_API_FUNCTION(ompt_frame_t *, ompt_get_task_frame, (
+    int depth
+));
+
+
+
+/****************************************************************************
+ * PLACEHOLDERS FOR PERFORMANCE REPORTING
+ ***************************************************************************/
+
+/* idle */
+OMPT_API_FUNCTION(void, ompt_idle, (
+    void
+));
+
+/* overhead */
+OMPT_API_FUNCTION(void, ompt_overhead, (
+    void
+));
+
+/* barrier wait */
+OMPT_API_FUNCTION(void, ompt_barrier_wait, (
+    void
+));
+
+/* task wait */
+OMPT_API_FUNCTION(void, ompt_task_wait, (
+    void
+));
+
+/* mutex wait */
+OMPT_API_FUNCTION(void, ompt_mutex_wait, (
+    void
+));
+
+
+
+/****************************************************************************
+ * INITIALIZATION FUNCTIONS
+ ***************************************************************************/
+
+OMPT_API_FUNCTION(void, ompt_initialize, (
+    ompt_function_lookup_t ompt_fn_lookup,
+    const char *runtime_version,
+    unsigned int ompt_version
+));
+
+
+/* initialization interface to be defined by tool */
+ompt_initialize_t ompt_tool(void);
+
+typedef enum opt_init_mode_e {
+    ompt_init_mode_never  = 0,
+    ompt_init_mode_false  = 1,
+    ompt_init_mode_true   = 2,
+    ompt_init_mode_always = 3
+} ompt_init_mode_t;
+
+OMPT_API_FUNCTION(int, ompt_set_callback, (
+    ompt_event_t event,
+    ompt_callback_t callback
+));
+
+typedef enum ompt_set_callback_rc_e {  /* non-standard */
+    ompt_set_callback_error      = 0,
+    ompt_has_event_no_callback   = 1,
+    ompt_no_event_no_callback    = 2,
+    ompt_has_event_may_callback  = 3,
+    ompt_has_event_must_callback = 4,
+} ompt_set_callback_rc_t;
+
+
+OMPT_API_FUNCTION(int, ompt_get_callback, (
+    ompt_event_t event,
+    ompt_callback_t *callback
+));
+
+
+
+/****************************************************************************
+ * MISCELLANEOUS FUNCTIONS
+ ***************************************************************************/
+
+/* control */
+// FIXME: remove workaround for clang
+#if !defined(__clang__) && defined(_OPENMP) && (_OPENMP >= 201307)
+#pragma omp declare target
+#endif
+void ompt_control(
+    uint64_t command,
+    uint64_t modifier
+);
+#if !defined(__clang__) && defined(_OPENMP) && (_OPENMP >= 201307)
+#pragma omp end declare target
+#endif
+
+/* state enumeration */
+OMPT_API_FUNCTION(int, ompt_enumerate_state, (
+    int current_state,
+    int *next_state,
+    const char **next_state_name
+));
+
+#ifdef  __cplusplus
+};
+#endif
+
+#endif
+

runtime/src/kmp_cancel.cpp

@@ -22,76 +22,80 @@
 @param gtid Global thread ID of encountering thread
 @param cncl_kind Cancellation kind (parallel, for, sections, taskgroup)
 
-@return returns true if the cancellation request has been activated and the execution thread
-needs to proceed to the end of the canceled region.
+@return returns true if the cancellation request has been activated and the
+execution thread needs to proceed to the end of the canceled region.
 
 Request cancellation of the binding OpenMP region.
 */
-kmp_int32 __kmpc_cancel(ident_t* loc_ref, kmp_int32 gtid, kmp_int32 cncl_kind) {
-    kmp_info_t *this_thr = __kmp_threads [ gtid ];
+kmp_int32 __kmpc_cancel(ident_t *loc_ref, kmp_int32 gtid, kmp_int32 cncl_kind) {
+  kmp_info_t *this_thr = __kmp_threads[gtid];
 
-    KC_TRACE( 10, ("__kmpc_cancel: T#%d request %d OMP_CANCELLATION=%d\n", gtid, cncl_kind, __kmp_omp_cancellation) );
+  KC_TRACE(10, ("__kmpc_cancel: T#%d request %d OMP_CANCELLATION=%d\n", gtid,
+                cncl_kind, __kmp_omp_cancellation));
 
-    KMP_DEBUG_ASSERT(cncl_kind != cancel_noreq);
-    KMP_DEBUG_ASSERT(cncl_kind == cancel_parallel || cncl_kind == cancel_loop ||
-                     cncl_kind == cancel_sections || cncl_kind == cancel_taskgroup);
-    KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
+  KMP_DEBUG_ASSERT(cncl_kind != cancel_noreq);
+  KMP_DEBUG_ASSERT(cncl_kind == cancel_parallel || cncl_kind == cancel_loop ||
+                   cncl_kind == cancel_sections ||
+                   cncl_kind == cancel_taskgroup);
+  KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
 
-    if (__kmp_omp_cancellation) {
-        switch (cncl_kind) {
-        case cancel_parallel:
-        case cancel_loop:
-        case cancel_sections:
-            // cancellation requests for parallel and worksharing constructs
-            // are handled through the team structure
-            {
-                kmp_team_t *this_team = this_thr->th.th_team;
-                KMP_DEBUG_ASSERT(this_team);
-                kmp_int32 old = KMP_COMPARE_AND_STORE_RET32(&(this_team->t.t_cancel_request), cancel_noreq, cncl_kind);
-                if (old == cancel_noreq || old == cncl_kind) {
-                    //printf("__kmpc_cancel: this_team->t.t_cancel_request=%d @ %p\n",
-                    //       this_team->t.t_cancel_request, &(this_team->t.t_cancel_request));
-                    // we do not have a cancellation request in this team or we do have one
-                    // that matches the current request -> cancel
-                    return 1 /* true */;
-                }
-                break;
-            }
-        case cancel_taskgroup:
-            // cancellation requests for a task group
-            // are handled through the taskgroup structure
-            {
-                kmp_taskdata_t*  task;
-                kmp_taskgroup_t* taskgroup;
-
-                task = this_thr->th.th_current_task;
-                KMP_DEBUG_ASSERT( task );
-
-                taskgroup = task->td_taskgroup;
-                if (taskgroup) {
-                    kmp_int32 old = KMP_COMPARE_AND_STORE_RET32(&(taskgroup->cancel_request), cancel_noreq, cncl_kind);
-                    if (old == cancel_noreq || old == cncl_kind) {
-                        // we do not have a cancellation request in this taskgroup or we do have one
-                        // that matches the current request -> cancel
-                        return 1 /* true */;
-                    }
-                }
-                else {
-                    // TODO: what needs to happen here?
-                    // the specification disallows cancellation w/o taskgroups
-                    // so we might do anything here, let's abort for now
-                    KMP_ASSERT( 0 /* false */);
-                }
-            }
-            break;
-        default:
-            KMP_ASSERT (0 /* false */);
+  if (__kmp_omp_cancellation) {
+    switch (cncl_kind) {
+    case cancel_parallel:
+    case cancel_loop:
+    case cancel_sections:
+      // cancellation requests for parallel and worksharing constructs
+      // are handled through the team structure
+      {
+        kmp_team_t *this_team = this_thr->th.th_team;
+        KMP_DEBUG_ASSERT(this_team);
+        kmp_int32 old = KMP_COMPARE_AND_STORE_RET32(
+            &(this_team->t.t_cancel_request), cancel_noreq, cncl_kind);
+        if (old == cancel_noreq || old == cncl_kind) {
+          // printf("__kmpc_cancel: this_team->t.t_cancel_request=%d @ %p\n",
+          //       this_team->t.t_cancel_request,
+          //       &(this_team->t.t_cancel_request));
+          // we do not have a cancellation request in this team or we do have
+          // one that matches the current request -> cancel
+          return 1 /* true */;
         }
-    }
+        break;
+      }
+    case cancel_taskgroup:
+      // cancellation requests for a task group
+      // are handled through the taskgroup structure
+      {
+        kmp_taskdata_t *task;
+        kmp_taskgroup_t *taskgroup;
 
-    // ICV OMP_CANCELLATION=false, so we ignored this cancel request
-    KMP_DEBUG_ASSERT(!__kmp_omp_cancellation);
-    return 0 /* false */;
+        task = this_thr->th.th_current_task;
+        KMP_DEBUG_ASSERT(task);
+
+        taskgroup = task->td_taskgroup;
+        if (taskgroup) {
+          kmp_int32 old = KMP_COMPARE_AND_STORE_RET32(
+              &(taskgroup->cancel_request), cancel_noreq, cncl_kind);
+          if (old == cancel_noreq || old == cncl_kind) {
+            // we do not have a cancellation request in this taskgroup or we do
+            // have one that matches the current request -> cancel
+            return 1 /* true */;
+          }
+        } else {
+          // TODO: what needs to happen here?
+          // the specification disallows cancellation w/o taskgroups
+          // so we might do anything here, let's abort for now
+          KMP_ASSERT(0 /* false */);
+        }
+      }
+      break;
+    default:
+      KMP_ASSERT(0 /* false */);
+    }
+  }
+
+  // ICV OMP_CANCELLATION=false, so we ignored this cancel request
+  KMP_DEBUG_ASSERT(!__kmp_omp_cancellation);
+  return 0 /* false */;
 }
 
 /*!
@@ -100,77 +104,77 @@ kmp_int32 __kmpc_cancel(ident_t* loc_ref, kmp_int32 gtid, kmp_int32 cncl_kind) {
 @param gtid Global thread ID of encountering thread
 @param cncl_kind Cancellation kind (parallel, for, sections, taskgroup)
 
-@return returns true if a matching cancellation request has been flagged in the RTL and the
-encountering thread has to cancel..
+@return returns true if a matching cancellation request has been flagged in the
+RTL and the encountering thread has to cancel..
 
 Cancellation point for the encountering thread.
 */
-kmp_int32 __kmpc_cancellationpoint(ident_t* loc_ref, kmp_int32 gtid, kmp_int32 cncl_kind) {
-    kmp_info_t *this_thr = __kmp_threads [ gtid ];
+kmp_int32 __kmpc_cancellationpoint(ident_t *loc_ref, kmp_int32 gtid,
+                                   kmp_int32 cncl_kind) {
+  kmp_info_t *this_thr = __kmp_threads[gtid];
 
-    KC_TRACE( 10, ("__kmpc_cancellationpoint: T#%d request %d OMP_CANCELLATION=%d\n", gtid, cncl_kind, __kmp_omp_cancellation) );
+  KC_TRACE(10,
+           ("__kmpc_cancellationpoint: T#%d request %d OMP_CANCELLATION=%d\n",
+            gtid, cncl_kind, __kmp_omp_cancellation));
 
-    KMP_DEBUG_ASSERT(cncl_kind != cancel_noreq);
-    KMP_DEBUG_ASSERT(cncl_kind == cancel_parallel || cncl_kind == cancel_loop ||
-                     cncl_kind == cancel_sections || cncl_kind == cancel_taskgroup);
-    KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
+  KMP_DEBUG_ASSERT(cncl_kind != cancel_noreq);
+  KMP_DEBUG_ASSERT(cncl_kind == cancel_parallel || cncl_kind == cancel_loop ||
+                   cncl_kind == cancel_sections ||
+                   cncl_kind == cancel_taskgroup);
+  KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
 
-    if (__kmp_omp_cancellation) {
-        switch (cncl_kind) {
-        case cancel_parallel:
-        case cancel_loop:
-        case cancel_sections:
-            // cancellation requests for parallel and worksharing constructs
-            // are handled through the team structure
-            {
-                kmp_team_t *this_team = this_thr->th.th_team;
-                KMP_DEBUG_ASSERT(this_team);
-                if (this_team->t.t_cancel_request) {
-                    if (cncl_kind == this_team->t.t_cancel_request) {
-                        // the request in the team structure matches the type of
-                        // cancellation point so we can cancel
-                        return 1 /* true */;
-                    }
-                    KMP_ASSERT( 0 /* false */);
-                }
-                else {
-                    // we do not have a cancellation request pending, so we just
-                    // ignore this cancellation point
-                    return 0;
-                }
-                break;
-            }
-        case cancel_taskgroup:
-            // cancellation requests for a task group
-            // are handled through the taskgroup structure
-            {
-                kmp_taskdata_t*  task;
-                kmp_taskgroup_t* taskgroup;
-
-                task = this_thr->th.th_current_task;
-                KMP_DEBUG_ASSERT( task );
-
-                taskgroup = task->td_taskgroup;
-                if (taskgroup) {
-                    // return the current status of cancellation for the
-                    // taskgroup
-                    return !!taskgroup->cancel_request;
-                }
-                else {
-                    // if a cancellation point is encountered by a task
-                    // that does not belong to a taskgroup, it is OK
-                    // to ignore it
-                    return 0 /* false */;
-                }
-            }
-        default:
-            KMP_ASSERT (0 /* false */);
+  if (__kmp_omp_cancellation) {
+    switch (cncl_kind) {
+    case cancel_parallel:
+    case cancel_loop:
+    case cancel_sections:
+      // cancellation requests for parallel and worksharing constructs
+      // are handled through the team structure
+      {
+        kmp_team_t *this_team = this_thr->th.th_team;
+        KMP_DEBUG_ASSERT(this_team);
+        if (this_team->t.t_cancel_request) {
+          if (cncl_kind == this_team->t.t_cancel_request) {
+            // the request in the team structure matches the type of
+            // cancellation point so we can cancel
+            return 1 /* true */;
+          }
+          KMP_ASSERT(0 /* false */);
+        } else {
+          // we do not have a cancellation request pending, so we just
+          // ignore this cancellation point
+          return 0;
         }
-    }
+        break;
+      }
+    case cancel_taskgroup:
+      // cancellation requests for a task group
+      // are handled through the taskgroup structure
+      {
+        kmp_taskdata_t *task;
+        kmp_taskgroup_t *taskgroup;
 
-    // ICV OMP_CANCELLATION=false, so we ignore the cancellation point
-    KMP_DEBUG_ASSERT(!__kmp_omp_cancellation);
-    return 0 /* false */;
+        task = this_thr->th.th_current_task;
+        KMP_DEBUG_ASSERT(task);
+
+        taskgroup = task->td_taskgroup;
+        if (taskgroup) {
+          // return the current status of cancellation for the taskgroup
+          return !!taskgroup->cancel_request;
+        } else {
+          // if a cancellation point is encountered by a task that does not
+          // belong to a taskgroup, it is OK to ignore it
+          return 0 /* false */;
+        }
+      }
+    default:
+      KMP_ASSERT(0 /* false */);
+    }
+  }
+
+  // ICV OMP_CANCELLATION=false, so we ignore the cancellation point
+  KMP_DEBUG_ASSERT(!__kmp_omp_cancellation);
+  return 0 /* false */;
 }
 
 /*!
@@ -178,63 +182,61 @@ kmp_int32 __kmpc_cancellationpoint(ident_t* loc_ref, kmp_int32 gtid, kmp_int32 c
 @param loc_ref location of the original task directive
 @param gtid Global thread ID of encountering thread
 
-@return returns true if a matching cancellation request has been flagged in the RTL and the
-encountering thread has to cancel..
+@return returns true if a matching cancellation request has been flagged in the
+RTL and the encountering thread has to cancel..
 
 Barrier with cancellation point to send threads from the barrier to the
 end of the parallel region.  Needs a special code pattern as documented
 in the design document for the cancellation feature.
 */
-kmp_int32
-__kmpc_cancel_barrier(ident_t *loc, kmp_int32 gtid) {
-    int ret = 0 /* false */;
-    kmp_info_t *this_thr = __kmp_threads [ gtid ];
-    kmp_team_t *this_team = this_thr->th.th_team;
+kmp_int32 __kmpc_cancel_barrier(ident_t *loc, kmp_int32 gtid) {
+  int ret = 0 /* false */;
+  kmp_info_t *this_thr = __kmp_threads[gtid];
+  kmp_team_t *this_team = this_thr->th.th_team;
 
-    KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
+  KMP_DEBUG_ASSERT(__kmp_get_gtid() == gtid);
 
-    // call into the standard barrier
-    __kmpc_barrier(loc, gtid);
+  // call into the standard barrier
+  __kmpc_barrier(loc, gtid);
 
-    // if cancellation is active, check cancellation flag
-    if (__kmp_omp_cancellation) {
-        // depending on which construct to cancel, check the flag and
-        // reset the flag
-        switch (this_team->t.t_cancel_request) {
-        case cancel_parallel:
-            ret = 1;
-            // ensure that threads have checked the flag, when
-            // leaving the above barrier
-            __kmpc_barrier(loc, gtid);
-            this_team->t.t_cancel_request = cancel_noreq;
-            // the next barrier is the fork/join barrier, which
-            // synchronizes the threads leaving here
-            break;
-        case cancel_loop:
-        case cancel_sections:
-            ret = 1;
-            // ensure that threads have checked the flag, when
-            // leaving the above barrier
-            __kmpc_barrier(loc, gtid);
-            this_team->t.t_cancel_request = cancel_noreq;
-            // synchronize the threads again to make sure we
-            // do not have any run-away threads that cause a race
-            // on the cancellation flag
-            __kmpc_barrier(loc, gtid);
-            break;
-        case cancel_taskgroup:
-            // this case should not occur
-            KMP_ASSERT (0 /* false */ );
-            break;
-        case cancel_noreq:
-            // do nothing
-            break;
-        default:
-            KMP_ASSERT ( 0 /* false */);
-        }
+  // if cancellation is active, check cancellation flag
+  if (__kmp_omp_cancellation) {
+    // depending on which construct to cancel, check the flag and
+    // reset the flag
+    switch (this_team->t.t_cancel_request) {
+    case cancel_parallel:
+      ret = 1;
+      // ensure that threads have checked the flag, when
+      // leaving the above barrier
+      __kmpc_barrier(loc, gtid);
+      this_team->t.t_cancel_request = cancel_noreq;
+      // the next barrier is the fork/join barrier, which
+      // synchronizes the threads leaving here
+      break;
+    case cancel_loop:
+    case cancel_sections:
+      ret = 1;
+      // ensure that threads have checked the flag, when
+      // leaving the above barrier
+      __kmpc_barrier(loc, gtid);
+      this_team->t.t_cancel_request = cancel_noreq;
+      // synchronize the threads again to make sure we do not have any run-away
+      // threads that cause a race on the cancellation flag
+      __kmpc_barrier(loc, gtid);
+      break;
+    case cancel_taskgroup:
+      // this case should not occur
+      KMP_ASSERT(0 /* false */);
+      break;
+    case cancel_noreq:
+      // do nothing
+      break;
+    default:
+      KMP_ASSERT(0 /* false */);
     }
+  }
 
-    return ret;
+  return ret;
 }
 
 /*!
@@ -242,8 +244,8 @@ __kmpc_cancel_barrier(ident_t *loc, kmp_int32 gtid) {
 @param loc_ref location of the original task directive
 @param gtid Global thread ID of encountering thread
 
-@return returns true if a matching cancellation request has been flagged in the RTL and the
-encountering thread has to cancel..
+@return returns true if a matching cancellation request has been flagged in the
+RTL and the encountering thread has to cancel..
 
 Query function to query the current status of cancellation requests.
 Can be used to implement the following pattern:
@@ -254,29 +256,27 @@ if (kmp_get_cancellation_status(kmp_cancel_parallel)) {
 }
 */
 int __kmp_get_cancellation_status(int cancel_kind) {
-    if (__kmp_omp_cancellation) {
-        kmp_info_t *this_thr = __kmp_entry_thread();
+  if (__kmp_omp_cancellation) {
+    kmp_info_t *this_thr = __kmp_entry_thread();
 
-        switch (cancel_kind) {
-        case cancel_parallel:
-        case cancel_loop:
-        case cancel_sections:
-            {
-                kmp_team_t *this_team = this_thr->th.th_team;
-                return this_team->t.t_cancel_request == cancel_kind;
-            }
-        case cancel_taskgroup:
-            {
-                kmp_taskdata_t*  task;
-                kmp_taskgroup_t* taskgroup;
-                task = this_thr->th.th_current_task;
-                taskgroup = task->td_taskgroup;
-                return taskgroup && taskgroup->cancel_request;
-            }
-        }
+    switch (cancel_kind) {
+    case cancel_parallel:
+    case cancel_loop:
+    case cancel_sections: {
+      kmp_team_t *this_team = this_thr->th.th_team;
+      return this_team->t.t_cancel_request == cancel_kind;
     }
+    case cancel_taskgroup: {
+      kmp_taskdata_t *task;
+      kmp_taskgroup_t *taskgroup;
+      task = this_thr->th.th_current_task;
+      taskgroup = task->td_taskgroup;
+      return taskgroup && taskgroup->cancel_request;
+    }
+    }
+  }
 
-    return 0 /* false */;
+  return 0 /* false */;
 }
 
 #endif

runtime/src/kmp_debug.cpp

@@ -19,124 +19,116 @@
 #include "kmp_io.h"
 
 #ifdef KMP_DEBUG
-void
-__kmp_debug_printf_stdout( char const * format, ... )
-{
-    va_list ap;
-    va_start( ap, format );
+void __kmp_debug_printf_stdout(char const *format, ...) {
+  va_list ap;
+  va_start(ap, format);
 
-    __kmp_vprintf( kmp_out, format, ap );
+  __kmp_vprintf(kmp_out, format, ap);
 
-    va_end(ap);
+  va_end(ap);
 }
 #endif
 
-void
-__kmp_debug_printf( char const * format, ... )
-{
-    va_list ap;
-    va_start( ap, format );
+void __kmp_debug_printf(char const *format, ...) {
+  va_list ap;
+  va_start(ap, format);
 
-    __kmp_vprintf( kmp_err, format, ap );
+  __kmp_vprintf(kmp_err, format, ap);
 
-    va_end( ap );
+  va_end(ap);
 }
 
 #ifdef KMP_USE_ASSERT
-    int
-    __kmp_debug_assert(
-        char const *  msg,
-        char const *  file,
-        int           line
-    ) {
+int __kmp_debug_assert(char const *msg, char const *file, int line) {
 
-        if ( file == NULL ) {
-            file = KMP_I18N_STR( UnknownFile );
-        } else {
-            // Remove directories from path, leave only file name. File name is enough, there is no need
-            // in bothering developers and customers with full paths.
-            char const * slash = strrchr( file, '/' );
-            if ( slash != NULL ) {
-                file = slash + 1;
-            }; // if
-        }; // if
+  if (file == NULL) {
+    file = KMP_I18N_STR(UnknownFile);
+  } else {
+    // Remove directories from path, leave only file name. File name is enough,
+    // there is no need in bothering developers and customers with full paths.
+    char const *slash = strrchr(file, '/');
+    if (slash != NULL) {
+      file = slash + 1;
+    }; // if
+  }; // if
 
-        #ifdef KMP_DEBUG
-            __kmp_acquire_bootstrap_lock( & __kmp_stdio_lock );
-            __kmp_debug_printf( "Assertion failure at %s(%d): %s.\n", file, line, msg );
-            __kmp_release_bootstrap_lock( & __kmp_stdio_lock );
-            #ifdef USE_ASSERT_BREAK
-                #if KMP_OS_WINDOWS
-                    DebugBreak();
-                #endif
-            #endif // USE_ASSERT_BREAK
-            #ifdef USE_ASSERT_STALL
-                /*    __kmp_infinite_loop(); */
-                for(;;);
-            #endif // USE_ASSERT_STALL
-            #ifdef USE_ASSERT_SEG
-                {
-                    int volatile * ZERO = (int*) 0;
-                    ++ (*ZERO);
-                }
-            #endif // USE_ASSERT_SEG
-        #endif
+#ifdef KMP_DEBUG
+  __kmp_acquire_bootstrap_lock(&__kmp_stdio_lock);
+  __kmp_debug_printf("Assertion failure at %s(%d): %s.\n", file, line, msg);
+  __kmp_release_bootstrap_lock(&__kmp_stdio_lock);
+#ifdef USE_ASSERT_BREAK
+#if KMP_OS_WINDOWS
+  DebugBreak();
+#endif
+#endif // USE_ASSERT_BREAK
+#ifdef USE_ASSERT_STALL
+  /*    __kmp_infinite_loop(); */
+  for (;;)
+    ;
+#endif // USE_ASSERT_STALL
+#ifdef USE_ASSERT_SEG
+  {
+    int volatile *ZERO = (int *)0;
+    ++(*ZERO);
+  }
+#endif // USE_ASSERT_SEG
+#endif
 
-        __kmp_msg(
-            kmp_ms_fatal,
-            KMP_MSG( AssertionFailure, file, line ),
-            KMP_HNT( SubmitBugReport ),
-            __kmp_msg_null
-        );
+  __kmp_msg(kmp_ms_fatal, KMP_MSG(AssertionFailure, file, line),
+            KMP_HNT(SubmitBugReport), __kmp_msg_null);
 
-        return 0;
+  return 0;
 
-    } // __kmp_debug_assert
+} // __kmp_debug_assert
 
 #endif // KMP_USE_ASSERT
 
 /* Dump debugging buffer to stderr */
-void
-__kmp_dump_debug_buffer( void )
-{
-    if ( __kmp_debug_buffer != NULL ) {
-        int i;
-        int dc = __kmp_debug_count;
-        char *db = & __kmp_debug_buffer[ (dc % __kmp_debug_buf_lines) * __kmp_debug_buf_chars ];
-        char *db_end = & __kmp_debug_buffer[ __kmp_debug_buf_lines * __kmp_debug_buf_chars ];
-        char *db2;
+void __kmp_dump_debug_buffer(void) {
+  if (__kmp_debug_buffer != NULL) {
+    int i;
+    int dc = __kmp_debug_count;
+    char *db = &__kmp_debug_buffer[(dc % __kmp_debug_buf_lines) *
+                                   __kmp_debug_buf_chars];
+    char *db_end =
+        &__kmp_debug_buffer[__kmp_debug_buf_lines * __kmp_debug_buf_chars];
+    char *db2;
 
-        __kmp_acquire_bootstrap_lock( & __kmp_stdio_lock );
-        __kmp_printf_no_lock( "\nStart dump of debugging buffer (entry=%d):\n",
-                 dc % __kmp_debug_buf_lines );
+    __kmp_acquire_bootstrap_lock(&__kmp_stdio_lock);
+    __kmp_printf_no_lock("\nStart dump of debugging buffer (entry=%d):\n",
+                         dc % __kmp_debug_buf_lines);
 
-        for ( i = 0; i < __kmp_debug_buf_lines; i++ ) {
+    for (i = 0; i < __kmp_debug_buf_lines; i++) {
 
-            if ( *db != '\0' ) {
-                /* Fix up where no carriage return before string termination char */
-                for ( db2 = db + 1; db2 < db + __kmp_debug_buf_chars - 1; db2 ++) {
-                    if ( *db2 == '\0' ) {
-                        if ( *(db2-1) != '\n' ) { *db2 = '\n'; *(db2+1) = '\0'; }
-                        break;
-                    }
-                }
-                /* Handle case at end by shortening the printed message by one char if necessary */
-                if ( db2 == db + __kmp_debug_buf_chars - 1 &&
-                     *db2 == '\0' && *(db2-1) != '\n' ) {
-                    *(db2-1) = '\n';
-                }
-
-                __kmp_printf_no_lock( "%4d: %.*s", i, __kmp_debug_buf_chars, db );
-                *db = '\0'; /* only let it print once! */
+      if (*db != '\0') {
+        /* Fix up where no carriage return before string termination char */
+        for (db2 = db + 1; db2 < db + __kmp_debug_buf_chars - 1; db2++) {
+          if (*db2 == '\0') {
+            if (*(db2 - 1) != '\n') {
+              *db2 = '\n';
+              *(db2 + 1) = '\0';
             }
-
-            db += __kmp_debug_buf_chars;
-            if ( db >= db_end )
-                db = __kmp_debug_buffer;
+            break;
+          }
+        }
+        /* Handle case at end by shortening the printed message by one char if
+         * necessary */
+        if (db2 == db + __kmp_debug_buf_chars - 1 && *db2 == '\0' &&
+            *(db2 - 1) != '\n') {
+          *(db2 - 1) = '\n';
         }
 
-        __kmp_printf_no_lock( "End dump of debugging buffer (entry=%d).\n\n",
-                 ( dc+i-1 ) % __kmp_debug_buf_lines );
-        __kmp_release_bootstrap_lock( & __kmp_stdio_lock );
+        __kmp_printf_no_lock("%4d: %.*s", i, __kmp_debug_buf_chars, db);
+        *db = '\0'; /* only let it print once! */
+      }
+
+      db += __kmp_debug_buf_chars;
+      if (db >= db_end)
+        db = __kmp_debug_buffer;
     }
+
+    __kmp_printf_no_lock("End dump of debugging buffer (entry=%d).\n\n",
+                         (dc + i - 1) % __kmp_debug_buf_lines);
+    __kmp_release_bootstrap_lock(&__kmp_stdio_lock);
+  }
 }

runtime/src/kmp_debug.h

@@ -19,113 +19,155 @@
 #include <stdarg.h>
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
-// -------------------------------------------------------------------------------------------------
+// -----------------------------------------------------------------------------
 // Build-time assertion.
-// -------------------------------------------------------------------------------------------------
 
-/*
-    Build-time assertion can do compile-time checking of data structure sizes, etc. This works by
-    declaring a negative-length array if the conditional expression evaluates to false.  In that
-    case, the compiler issues a syntax error and stops the compilation. If the expression is
-    true, we get an extraneous static single character array in the scope of the macro.
+// New C++11 style build assert
+#define KMP_BUILD_ASSERT(expr) static_assert(expr, "Build condition error")
 
-    Usage:
-
-        KMP_BUILD_ASSERT( sizeof( some_t ) <= 32 );
-        KMP_BUILD_ASSERT( offsetof( some_t, field ) % 8 == 0 );
-
-    Do not use _KMP_BUILD_ASSERT and __KMP_BUILD_ASSERT directly, it is working guts.
-*/
-
-#define __KMP_BUILD_ASSERT( expr, suffix )  typedef char __kmp_build_check_##suffix[ (expr) ? 1 : -1 ]
-#define _KMP_BUILD_ASSERT( expr, suffix )   __KMP_BUILD_ASSERT( (expr), suffix )
-#ifdef KMP_USE_ASSERT
-    #define KMP_BUILD_ASSERT( expr )            _KMP_BUILD_ASSERT( (expr), __LINE__ )
-#else
-    #define KMP_BUILD_ASSERT( expr )            /* nothing to do */
-#endif
-
-// -------------------------------------------------------------------------------------------------
+// -----------------------------------------------------------------------------
 // Run-time assertions.
-// -------------------------------------------------------------------------------------------------
 
-extern void __kmp_dump_debug_buffer( void );
+extern void __kmp_dump_debug_buffer(void);
 
 #ifdef KMP_USE_ASSERT
-    extern int __kmp_debug_assert( char const * expr, char const * file, int line );
-    #ifdef KMP_DEBUG
-        #define KMP_ASSERT( cond )             ( (cond) ? 0 : __kmp_debug_assert( #cond, __FILE__, __LINE__ ) )
-        #define KMP_ASSERT2( cond, msg )       ( (cond) ? 0 : __kmp_debug_assert( (msg), __FILE__, __LINE__ ) )
-        #define KMP_DEBUG_ASSERT( cond )       KMP_ASSERT( cond )
-        #define KMP_DEBUG_ASSERT2( cond, msg ) KMP_ASSERT2( cond, msg )
-    #else
-        // Do not expose condition in release build. Use "assertion failure".
-        #define KMP_ASSERT( cond )             ( (cond) ? 0 : __kmp_debug_assert( "assertion failure", __FILE__, __LINE__ ) )
-        #define KMP_ASSERT2( cond, msg )       KMP_ASSERT( cond )
-        #define KMP_DEBUG_ASSERT( cond )       0
-        #define KMP_DEBUG_ASSERT2( cond, msg ) 0
-    #endif // KMP_DEBUG
+extern int __kmp_debug_assert(char const *expr, char const *file, int line);
+#ifdef KMP_DEBUG
+#define KMP_ASSERT(cond)                                                       \
+  ((cond) ? 0 : __kmp_debug_assert(#cond, __FILE__, __LINE__))
+#define KMP_ASSERT2(cond, msg)                                                 \
+  ((cond) ? 0 : __kmp_debug_assert((msg), __FILE__, __LINE__))
+#define KMP_DEBUG_ASSERT(cond) KMP_ASSERT(cond)
+#define KMP_DEBUG_ASSERT2(cond, msg) KMP_ASSERT2(cond, msg)
 #else
-    #define KMP_ASSERT( cond )             0
-    #define KMP_ASSERT2( cond, msg )       0
-    #define KMP_DEBUG_ASSERT( cond )       0
-    #define KMP_DEBUG_ASSERT2( cond, msg ) 0
+// Do not expose condition in release build. Use "assertion failure".
+#define KMP_ASSERT(cond)                                                       \
+  ((cond) ? 0 : __kmp_debug_assert("assertion failure", __FILE__, __LINE__))
+#define KMP_ASSERT2(cond, msg) KMP_ASSERT(cond)
+#define KMP_DEBUG_ASSERT(cond) 0
+#define KMP_DEBUG_ASSERT2(cond, msg) 0
+#endif // KMP_DEBUG
+#else
+#define KMP_ASSERT(cond) 0
+#define KMP_ASSERT2(cond, msg) 0
+#define KMP_DEBUG_ASSERT(cond) 0
+#define KMP_DEBUG_ASSERT2(cond, msg) 0
 #endif // KMP_USE_ASSERT
 
 #ifdef KMP_DEBUG
-    extern void __kmp_debug_printf_stdout( char const * format, ... );
+extern void __kmp_debug_printf_stdout(char const *format, ...);
 #endif
-extern void __kmp_debug_printf( char const * format, ... );
+extern void __kmp_debug_printf(char const *format, ...);
 
 #ifdef KMP_DEBUG
 
-    extern int kmp_a_debug;
-    extern int kmp_b_debug;
-    extern int kmp_c_debug;
-    extern int kmp_d_debug;
-    extern int kmp_e_debug;
-    extern int kmp_f_debug;
-    extern int kmp_diag;
+extern int kmp_a_debug;
+extern int kmp_b_debug;
+extern int kmp_c_debug;
+extern int kmp_d_debug;
+extern int kmp_e_debug;
+extern int kmp_f_debug;
+extern int kmp_diag;
 
-    #define KA_TRACE(d,x)     if (kmp_a_debug >= d) { __kmp_debug_printf x ; }
-    #define KB_TRACE(d,x)     if (kmp_b_debug >= d) { __kmp_debug_printf x ; }
-    #define KC_TRACE(d,x)     if (kmp_c_debug >= d) { __kmp_debug_printf x ; }
-    #define KD_TRACE(d,x)     if (kmp_d_debug >= d) { __kmp_debug_printf x ; }
-    #define KE_TRACE(d,x)     if (kmp_e_debug >= d) { __kmp_debug_printf x ; }
-    #define KF_TRACE(d,x)     if (kmp_f_debug >= d) { __kmp_debug_printf x ; }
-    #define K_DIAG(d,x)       {if (kmp_diag == d) { __kmp_debug_printf_stdout x ; } }
+#define KA_TRACE(d, x)                                                         \
+  if (kmp_a_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define KB_TRACE(d, x)                                                         \
+  if (kmp_b_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define KC_TRACE(d, x)                                                         \
+  if (kmp_c_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define KD_TRACE(d, x)                                                         \
+  if (kmp_d_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define KE_TRACE(d, x)                                                         \
+  if (kmp_e_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define KF_TRACE(d, x)                                                         \
+  if (kmp_f_debug >= d) {                                                      \
+    __kmp_debug_printf x;                                                      \
+  }
+#define K_DIAG(d, x)                                                           \
+  {                                                                            \
+    if (kmp_diag == d) {                                                       \
+      __kmp_debug_printf_stdout x;                                             \
+    }                                                                          \
+  }
 
-    #define KA_DUMP(d,x)     if (kmp_a_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
-    #define KB_DUMP(d,x)     if (kmp_b_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
-    #define KC_DUMP(d,x)     if (kmp_c_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
-    #define KD_DUMP(d,x)     if (kmp_d_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
-    #define KE_DUMP(d,x)     if (kmp_e_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
-    #define KF_DUMP(d,x)     if (kmp_f_debug >= d) { int ks; __kmp_disable(&ks); (x) ; __kmp_enable(ks); }
+#define KA_DUMP(d, x)                                                          \
+  if (kmp_a_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
+#define KB_DUMP(d, x)                                                          \
+  if (kmp_b_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
+#define KC_DUMP(d, x)                                                          \
+  if (kmp_c_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
+#define KD_DUMP(d, x)                                                          \
+  if (kmp_d_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
+#define KE_DUMP(d, x)                                                          \
+  if (kmp_e_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
+#define KF_DUMP(d, x)                                                          \
+  if (kmp_f_debug >= d) {                                                      \
+    int ks;                                                                    \
+    __kmp_disable(&ks);                                                        \
+    (x);                                                                       \
+    __kmp_enable(ks);                                                          \
+  }
 
 #else
 
-    #define KA_TRACE(d,x)     /* nothing to do */
-    #define KB_TRACE(d,x)     /* nothing to do */
-    #define KC_TRACE(d,x)     /* nothing to do */
-    #define KD_TRACE(d,x)     /* nothing to do */
-    #define KE_TRACE(d,x)     /* nothing to do */
-    #define KF_TRACE(d,x)     /* nothing to do */
-    #define K_DIAG(d,x)       {}/* nothing to do */
+#define KA_TRACE(d, x) /* nothing to do */
+#define KB_TRACE(d, x) /* nothing to do */
+#define KC_TRACE(d, x) /* nothing to do */
+#define KD_TRACE(d, x) /* nothing to do */
+#define KE_TRACE(d, x) /* nothing to do */
+#define KF_TRACE(d, x) /* nothing to do */
+#define K_DIAG(d, x)                                                           \
+  {} /* nothing to do */
 
-    #define KA_DUMP(d,x)     /* nothing to do */
-    #define KB_DUMP(d,x)     /* nothing to do */
-    #define KC_DUMP(d,x)     /* nothing to do */
-    #define KD_DUMP(d,x)     /* nothing to do */
-    #define KE_DUMP(d,x)     /* nothing to do */
-    #define KF_DUMP(d,x)     /* nothing to do */
+#define KA_DUMP(d, x) /* nothing to do */
+#define KB_DUMP(d, x) /* nothing to do */
+#define KC_DUMP(d, x) /* nothing to do */
+#define KD_DUMP(d, x) /* nothing to do */
+#define KE_DUMP(d, x) /* nothing to do */
+#define KF_DUMP(d, x) /* nothing to do */
 
 #endif // KMP_DEBUG
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif // __cplusplus
 
 #endif /* KMP_DEBUG_H */

runtime/src/kmp_debugger.cpp

@@ -1,6 +1,6 @@
 #if USE_DEBUGGER
 /*
- * kmp_debugger.c -- debugger support.
+ * kmp_debugger.cpp -- debugger support.
  */
 
 
@@ -19,47 +19,36 @@
 #include "kmp_omp.h"
 #include "kmp_str.h"
 
-/*
-    NOTE: All variable names are known to the debugger, do not change!
-*/
+// NOTE: All variable names are known to the debugger, do not change!
 
 #ifdef __cplusplus
-    extern "C" {
-        extern kmp_omp_struct_info_t __kmp_omp_debug_struct_info;
-    } // extern "C"
+extern "C" {
+extern kmp_omp_struct_info_t __kmp_omp_debug_struct_info;
+} // extern "C"
 #endif // __cplusplus
 
-int __kmp_debugging          = FALSE;    // Boolean whether currently debugging OpenMP RTL.
+int __kmp_debugging = FALSE; // Boolean whether currently debugging OpenMP RTL.
 
-#define offset_and_size_of( structure, field )     \
-    {                                              \
-        offsetof( structure,           field ),    \
-        sizeof( ( (structure *) NULL)->field )     \
-    }
+#define offset_and_size_of(structure, field)                                   \
+  { offsetof(structure, field), sizeof(((structure *)NULL)->field) }
 
-#define offset_and_size_not_available \
-    { -1, -1 }
+#define offset_and_size_not_available                                          \
+  { -1, -1 }
 
-#define addr_and_size_of( var )                    \
-    {                                              \
-        (kmp_uint64)( & var ),                     \
-        sizeof( var )                              \
-    }
+#define addr_and_size_of(var)                                                  \
+  { (kmp_uint64)(&var), sizeof(var) }
 
 #define nthr_buffer_size 1024
-static kmp_int32
-kmp_omp_nthr_info_buffer[ nthr_buffer_size ] =
-    { nthr_buffer_size * sizeof( kmp_int32 ) };
+static kmp_int32 kmp_omp_nthr_info_buffer[nthr_buffer_size] = {
+    nthr_buffer_size * sizeof(kmp_int32)};
 
 /* TODO: Check punctuation for various platforms here */
-static char func_microtask[]    = "__kmp_invoke_microtask";
-static char func_fork[]         = "__kmpc_fork_call";
-static char func_fork_teams[]   = "__kmpc_fork_teams";
-
+static char func_microtask[] = "__kmp_invoke_microtask";
+static char func_fork[] = "__kmpc_fork_call";
+static char func_fork_teams[] = "__kmpc_fork_teams";
 
 // Various info about runtime structures: addresses, field offsets, sizes, etc.
-kmp_omp_struct_info_t
-__kmp_omp_debug_struct_info = {
+kmp_omp_struct_info_t __kmp_omp_debug_struct_info = {
 
     /* Change this only if you make a fundamental data structure change here */
     KMP_OMP_VERSION,
@@ -67,166 +56,167 @@ __kmp_omp_debug_struct_info = {
     /* sanity check.  Only should be checked if versions are identical
      * This is also used for backward compatibility to get the runtime
      * structure size if it the runtime is older than the interface */
-    sizeof( kmp_omp_struct_info_t ),
+    sizeof(kmp_omp_struct_info_t),
 
     /* OpenMP RTL version info. */
-    addr_and_size_of( __kmp_version_major ),
-    addr_and_size_of( __kmp_version_minor ),
-    addr_and_size_of( __kmp_version_build ),
-    addr_and_size_of( __kmp_openmp_version ),
-    { (kmp_uint64)( __kmp_copyright ) + KMP_VERSION_MAGIC_LEN, 0 },        // Skip magic prefix.
+    addr_and_size_of(__kmp_version_major),
+    addr_and_size_of(__kmp_version_minor),
+    addr_and_size_of(__kmp_version_build),
+    addr_and_size_of(__kmp_openmp_version),
+    {(kmp_uint64)(__kmp_copyright) + KMP_VERSION_MAGIC_LEN,
+     0}, // Skip magic prefix.
 
     /* Various globals. */
-    addr_and_size_of( __kmp_threads ),
-    addr_and_size_of( __kmp_root ),
-    addr_and_size_of( __kmp_threads_capacity ),
-    addr_and_size_of( __kmp_monitor ),
-#if ! KMP_USE_DYNAMIC_LOCK
-    addr_and_size_of( __kmp_user_lock_table ),
+    addr_and_size_of(__kmp_threads),
+    addr_and_size_of(__kmp_root),
+    addr_and_size_of(__kmp_threads_capacity),
+    addr_and_size_of(__kmp_monitor),
+#if !KMP_USE_DYNAMIC_LOCK
+    addr_and_size_of(__kmp_user_lock_table),
 #endif
-    addr_and_size_of( func_microtask ),
-    addr_and_size_of( func_fork ),
-    addr_and_size_of( func_fork_teams ),
-    addr_and_size_of( __kmp_team_counter ),
-    addr_and_size_of( __kmp_task_counter ),
-    addr_and_size_of( kmp_omp_nthr_info_buffer ),
-    sizeof( void * ),
+    addr_and_size_of(func_microtask),
+    addr_and_size_of(func_fork),
+    addr_and_size_of(func_fork_teams),
+    addr_and_size_of(__kmp_team_counter),
+    addr_and_size_of(__kmp_task_counter),
+    addr_and_size_of(kmp_omp_nthr_info_buffer),
+    sizeof(void *),
     OMP_LOCK_T_SIZE < sizeof(void *),
     bs_last_barrier,
     INITIAL_TASK_DEQUE_SIZE,
 
     // thread structure information
-    sizeof( kmp_base_info_t ),
-    offset_and_size_of( kmp_base_info_t, th_info ),
-    offset_and_size_of( kmp_base_info_t, th_team ),
-    offset_and_size_of( kmp_base_info_t, th_root ),
-    offset_and_size_of( kmp_base_info_t, th_serial_team ),
-    offset_and_size_of( kmp_base_info_t, th_ident ),
-    offset_and_size_of( kmp_base_info_t, th_spin_here    ),
-    offset_and_size_of( kmp_base_info_t, th_next_waiting ),
-    offset_and_size_of( kmp_base_info_t, th_task_team    ),
-    offset_and_size_of( kmp_base_info_t, th_current_task ),
-    offset_and_size_of( kmp_base_info_t, th_task_state   ),
-    offset_and_size_of( kmp_base_info_t,   th_bar ),
-    offset_and_size_of( kmp_bstate_t,      b_worker_arrived ),
+    sizeof(kmp_base_info_t),
+    offset_and_size_of(kmp_base_info_t, th_info),
+    offset_and_size_of(kmp_base_info_t, th_team),
+    offset_and_size_of(kmp_base_info_t, th_root),
+    offset_and_size_of(kmp_base_info_t, th_serial_team),
+    offset_and_size_of(kmp_base_info_t, th_ident),
+    offset_and_size_of(kmp_base_info_t, th_spin_here),
+    offset_and_size_of(kmp_base_info_t, th_next_waiting),
+    offset_and_size_of(kmp_base_info_t, th_task_team),
+    offset_and_size_of(kmp_base_info_t, th_current_task),
+    offset_and_size_of(kmp_base_info_t, th_task_state),
+    offset_and_size_of(kmp_base_info_t, th_bar),
+    offset_and_size_of(kmp_bstate_t, b_worker_arrived),
 
 #if OMP_40_ENABLED
     // teams information
-    offset_and_size_of( kmp_base_info_t, th_teams_microtask),
-    offset_and_size_of( kmp_base_info_t, th_teams_level),
-    offset_and_size_of( kmp_teams_size_t, nteams ),
-    offset_and_size_of( kmp_teams_size_t, nth ),
+    offset_and_size_of(kmp_base_info_t, th_teams_microtask),
+    offset_and_size_of(kmp_base_info_t, th_teams_level),
+    offset_and_size_of(kmp_teams_size_t, nteams),
+    offset_and_size_of(kmp_teams_size_t, nth),
 #endif
 
     // kmp_desc structure (for info field above)
-    sizeof( kmp_desc_base_t ),
-    offset_and_size_of( kmp_desc_base_t, ds_tid    ),
-    offset_and_size_of( kmp_desc_base_t, ds_gtid   ),
-    // On Windows* OS, ds_thread contains a thread /handle/, which is not usable, while thread /id/
-    // is in ds_thread_id.
-    #if KMP_OS_WINDOWS
-    offset_and_size_of( kmp_desc_base_t, ds_thread_id),
-    #else
-    offset_and_size_of( kmp_desc_base_t, ds_thread),
-    #endif
+    sizeof(kmp_desc_base_t),
+    offset_and_size_of(kmp_desc_base_t, ds_tid),
+    offset_and_size_of(kmp_desc_base_t, ds_gtid),
+// On Windows* OS, ds_thread contains a thread /handle/, which is not usable,
+// while thread /id/ is in ds_thread_id.
+#if KMP_OS_WINDOWS
+    offset_and_size_of(kmp_desc_base_t, ds_thread_id),
+#else
+    offset_and_size_of(kmp_desc_base_t, ds_thread),
+#endif
 
     // team structure information
-    sizeof( kmp_base_team_t ),
-    offset_and_size_of( kmp_base_team_t,   t_master_tid ),
-    offset_and_size_of( kmp_base_team_t,   t_ident      ),
-    offset_and_size_of( kmp_base_team_t,   t_parent     ),
-    offset_and_size_of( kmp_base_team_t,   t_nproc      ),
-    offset_and_size_of( kmp_base_team_t,   t_threads    ),
-    offset_and_size_of( kmp_base_team_t,   t_serialized ),
-    offset_and_size_of( kmp_base_team_t,   t_id         ),
-    offset_and_size_of( kmp_base_team_t,   t_pkfn       ),
-    offset_and_size_of( kmp_base_team_t,   t_task_team ),
-    offset_and_size_of( kmp_base_team_t,   t_implicit_task_taskdata ),
+    sizeof(kmp_base_team_t),
+    offset_and_size_of(kmp_base_team_t, t_master_tid),
+    offset_and_size_of(kmp_base_team_t, t_ident),
+    offset_and_size_of(kmp_base_team_t, t_parent),
+    offset_and_size_of(kmp_base_team_t, t_nproc),
+    offset_and_size_of(kmp_base_team_t, t_threads),
+    offset_and_size_of(kmp_base_team_t, t_serialized),
+    offset_and_size_of(kmp_base_team_t, t_id),
+    offset_and_size_of(kmp_base_team_t, t_pkfn),
+    offset_and_size_of(kmp_base_team_t, t_task_team),
+    offset_and_size_of(kmp_base_team_t, t_implicit_task_taskdata),
 #if OMP_40_ENABLED
-    offset_and_size_of( kmp_base_team_t,   t_cancel_request ),
+    offset_and_size_of(kmp_base_team_t, t_cancel_request),
 #endif
-    offset_and_size_of( kmp_base_team_t,   t_bar ),
-    offset_and_size_of( kmp_balign_team_t, b_master_arrived ),
-    offset_and_size_of( kmp_balign_team_t, b_team_arrived ),
+    offset_and_size_of(kmp_base_team_t, t_bar),
+    offset_and_size_of(kmp_balign_team_t, b_master_arrived),
+    offset_and_size_of(kmp_balign_team_t, b_team_arrived),
 
     // root structure information
-    sizeof( kmp_base_root_t ),
-    offset_and_size_of( kmp_base_root_t, r_root_team   ),
-    offset_and_size_of( kmp_base_root_t, r_hot_team    ),
-    offset_and_size_of( kmp_base_root_t, r_uber_thread ),
+    sizeof(kmp_base_root_t),
+    offset_and_size_of(kmp_base_root_t, r_root_team),
+    offset_and_size_of(kmp_base_root_t, r_hot_team),
+    offset_and_size_of(kmp_base_root_t, r_uber_thread),
     offset_and_size_not_available,
 
     // ident structure information
-    sizeof( ident_t ),
-    offset_and_size_of( ident_t, psource ),
-    offset_and_size_of( ident_t, flags   ),
+    sizeof(ident_t),
+    offset_and_size_of(ident_t, psource),
+    offset_and_size_of(ident_t, flags),
 
     // lock structure information
-    sizeof( kmp_base_queuing_lock_t ),
-    offset_and_size_of( kmp_base_queuing_lock_t, initialized  ),
-    offset_and_size_of( kmp_base_queuing_lock_t, location ),
-    offset_and_size_of( kmp_base_queuing_lock_t, tail_id  ),
-    offset_and_size_of( kmp_base_queuing_lock_t, head_id  ),
-    offset_and_size_of( kmp_base_queuing_lock_t, next_ticket  ),
-    offset_and_size_of( kmp_base_queuing_lock_t, now_serving  ),
-    offset_and_size_of( kmp_base_queuing_lock_t, owner_id     ),
-    offset_and_size_of( kmp_base_queuing_lock_t, depth_locked ),
-    offset_and_size_of( kmp_base_queuing_lock_t, flags ),
+    sizeof(kmp_base_queuing_lock_t),
+    offset_and_size_of(kmp_base_queuing_lock_t, initialized),
+    offset_and_size_of(kmp_base_queuing_lock_t, location),
+    offset_and_size_of(kmp_base_queuing_lock_t, tail_id),
+    offset_and_size_of(kmp_base_queuing_lock_t, head_id),
+    offset_and_size_of(kmp_base_queuing_lock_t, next_ticket),
+    offset_and_size_of(kmp_base_queuing_lock_t, now_serving),
+    offset_and_size_of(kmp_base_queuing_lock_t, owner_id),
+    offset_and_size_of(kmp_base_queuing_lock_t, depth_locked),
+    offset_and_size_of(kmp_base_queuing_lock_t, flags),
 
-#if ! KMP_USE_DYNAMIC_LOCK
+#if !KMP_USE_DYNAMIC_LOCK
     /* Lock table. */
-    sizeof( kmp_lock_table_t ),
-    offset_and_size_of( kmp_lock_table_t, used       ),
-    offset_and_size_of( kmp_lock_table_t, allocated  ),
-    offset_and_size_of( kmp_lock_table_t, table      ),
+    sizeof(kmp_lock_table_t),
+    offset_and_size_of(kmp_lock_table_t, used),
+    offset_and_size_of(kmp_lock_table_t, allocated),
+    offset_and_size_of(kmp_lock_table_t, table),
 #endif
 
     // Task team structure information.
-    sizeof( kmp_base_task_team_t ),
-    offset_and_size_of( kmp_base_task_team_t, tt_threads_data       ),
-    offset_and_size_of( kmp_base_task_team_t, tt_found_tasks        ),
-    offset_and_size_of( kmp_base_task_team_t, tt_nproc              ),
-    offset_and_size_of( kmp_base_task_team_t, tt_unfinished_threads ),
-    offset_and_size_of( kmp_base_task_team_t, tt_active             ),
+    sizeof(kmp_base_task_team_t),
+    offset_and_size_of(kmp_base_task_team_t, tt_threads_data),
+    offset_and_size_of(kmp_base_task_team_t, tt_found_tasks),
+    offset_and_size_of(kmp_base_task_team_t, tt_nproc),
+    offset_and_size_of(kmp_base_task_team_t, tt_unfinished_threads),
+    offset_and_size_of(kmp_base_task_team_t, tt_active),
 
     // task_data_t.
-    sizeof( kmp_taskdata_t ),
-    offset_and_size_of( kmp_taskdata_t, td_task_id                ),
-    offset_and_size_of( kmp_taskdata_t, td_flags                  ),
-    offset_and_size_of( kmp_taskdata_t, td_team                   ),
-    offset_and_size_of( kmp_taskdata_t, td_parent                 ),
-    offset_and_size_of( kmp_taskdata_t, td_level                  ),
-    offset_and_size_of( kmp_taskdata_t, td_ident                  ),
-    offset_and_size_of( kmp_taskdata_t, td_allocated_child_tasks  ),
-    offset_and_size_of( kmp_taskdata_t, td_incomplete_child_tasks ),
+    sizeof(kmp_taskdata_t),
+    offset_and_size_of(kmp_taskdata_t, td_task_id),
+    offset_and_size_of(kmp_taskdata_t, td_flags),
+    offset_and_size_of(kmp_taskdata_t, td_team),
+    offset_and_size_of(kmp_taskdata_t, td_parent),
+    offset_and_size_of(kmp_taskdata_t, td_level),
+    offset_and_size_of(kmp_taskdata_t, td_ident),
+    offset_and_size_of(kmp_taskdata_t, td_allocated_child_tasks),
+    offset_and_size_of(kmp_taskdata_t, td_incomplete_child_tasks),
 
-    offset_and_size_of( kmp_taskdata_t, td_taskwait_ident   ),
-    offset_and_size_of( kmp_taskdata_t, td_taskwait_counter ),
-    offset_and_size_of( kmp_taskdata_t, td_taskwait_thread  ),
+    offset_and_size_of(kmp_taskdata_t, td_taskwait_ident),
+    offset_and_size_of(kmp_taskdata_t, td_taskwait_counter),
+    offset_and_size_of(kmp_taskdata_t, td_taskwait_thread),
 
 #if OMP_40_ENABLED
-    offset_and_size_of( kmp_taskdata_t, td_taskgroup        ),
-    offset_and_size_of( kmp_taskgroup_t, count              ),
-    offset_and_size_of( kmp_taskgroup_t, cancel_request     ),
+    offset_and_size_of(kmp_taskdata_t, td_taskgroup),
+    offset_and_size_of(kmp_taskgroup_t, count),
+    offset_and_size_of(kmp_taskgroup_t, cancel_request),
 
-    offset_and_size_of( kmp_taskdata_t, td_depnode          ),
-    offset_and_size_of( kmp_depnode_list_t, node            ),
-    offset_and_size_of( kmp_depnode_list_t, next            ),
-    offset_and_size_of( kmp_base_depnode_t, successors      ),
-    offset_and_size_of( kmp_base_depnode_t, task            ),
-    offset_and_size_of( kmp_base_depnode_t, npredecessors   ),
-    offset_and_size_of( kmp_base_depnode_t, nrefs           ),
+    offset_and_size_of(kmp_taskdata_t, td_depnode),
+    offset_and_size_of(kmp_depnode_list_t, node),
+    offset_and_size_of(kmp_depnode_list_t, next),
+    offset_and_size_of(kmp_base_depnode_t, successors),
+    offset_and_size_of(kmp_base_depnode_t, task),
+    offset_and_size_of(kmp_base_depnode_t, npredecessors),
+    offset_and_size_of(kmp_base_depnode_t, nrefs),
 #endif
-    offset_and_size_of( kmp_task_t, routine                 ),
+    offset_and_size_of(kmp_task_t, routine),
 
     // thread_data_t.
-    sizeof( kmp_thread_data_t ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque             ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque_size        ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque_head        ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque_tail        ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque_ntasks      ),
-    offset_and_size_of( kmp_base_thread_data_t, td_deque_last_stolen ),
+    sizeof(kmp_thread_data_t),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque_size),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque_head),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque_tail),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque_ntasks),
+    offset_and_size_of(kmp_base_thread_data_t, td_deque_last_stolen),
 
     // The last field.
     KMP_OMP_VERSION,
@@ -236,80 +226,66 @@ __kmp_omp_debug_struct_info = {
 #undef offset_and_size_of
 #undef addr_and_size_of
 
-/*
-  Intel compiler on IA-32 architecture issues a warning "conversion
+/* Intel compiler on IA-32 architecture issues a warning "conversion
   from "unsigned long long" to "char *" may lose significant bits"
   when 64-bit value is assigned to 32-bit pointer. Use this function
-  to suppress the warning.
-*/
-static inline
-void *
-__kmp_convert_to_ptr(
-    kmp_uint64    addr
-) {
-    #if KMP_COMPILER_ICC
-        #pragma warning( push )
-        #pragma warning( disable:  810 ) // conversion from "unsigned long long" to "char *" may lose significant bits
-        #pragma warning( disable: 1195 ) // conversion from integer to smaller pointer
-    #endif // KMP_COMPILER_ICC
-    return (void *) addr;
-    #if KMP_COMPILER_ICC
-        #pragma warning( pop )
-    #endif // KMP_COMPILER_ICC
+  to suppress the warning. */
+static inline void *__kmp_convert_to_ptr(kmp_uint64 addr) {
+#if KMP_COMPILER_ICC
+#pragma warning(push)
+#pragma warning(disable : 810) // conversion from "unsigned long long" to "char
+// *" may lose significant bits
+#pragma warning(disable : 1195) // conversion from integer to smaller pointer
+#endif // KMP_COMPILER_ICC
+  return (void *)addr;
+#if KMP_COMPILER_ICC
+#pragma warning(pop)
+#endif // KMP_COMPILER_ICC
 } // __kmp_convert_to_ptr
 
+static int kmp_location_match(kmp_str_loc_t *loc, kmp_omp_nthr_item_t *item) {
 
-static int
-kmp_location_match(
-    kmp_str_loc_t *        loc,
-    kmp_omp_nthr_item_t *  item
-) {
+  int file_match = 0;
+  int func_match = 0;
+  int line_match = 0;
 
-    int file_match = 0;
-    int func_match = 0;
-    int line_match = 0;
+  char *file = (char *)__kmp_convert_to_ptr(item->file);
+  char *func = (char *)__kmp_convert_to_ptr(item->func);
+  file_match = __kmp_str_fname_match(&loc->fname, file);
+  func_match =
+      item->func == 0 // If item->func is NULL, it allows any func name.
+      || strcmp(func, "*") == 0 ||
+      (loc->func != NULL && strcmp(loc->func, func) == 0);
+  line_match =
+      item->begin <= loc->line &&
+      (item->end <= 0 ||
+       loc->line <= item->end); // if item->end <= 0, it means "end of file".
 
-    char * file = (char *) __kmp_convert_to_ptr( item->file );
-    char * func = (char *) __kmp_convert_to_ptr( item->func );
-    file_match = __kmp_str_fname_match( & loc->fname, file );
-    func_match =
-        item->func == 0  // If item->func is NULL, it allows any func name.
-        ||
-        strcmp( func, "*" ) == 0
-        ||
-        ( loc->func != NULL && strcmp( loc->func, func ) == 0 );
-    line_match =
-        item->begin <= loc->line
-        &&
-        ( item->end <= 0 || loc->line <= item->end ); // if item->end <= 0, it means "end of file".
-
-    return ( file_match && func_match && line_match );
+  return (file_match && func_match && line_match);
 
 } // kmp_location_match
 
+int __kmp_omp_num_threads(ident_t const *ident) {
 
-int
-__kmp_omp_num_threads(
-    ident_t const * ident
-) {
+  int num_threads = 0;
 
-    int num_threads = 0;
+  kmp_omp_nthr_info_t *info = (kmp_omp_nthr_info_t *)__kmp_convert_to_ptr(
+      __kmp_omp_debug_struct_info.nthr_info.addr);
+  if (info->num > 0 && info->array != 0) {
+    kmp_omp_nthr_item_t *items =
+        (kmp_omp_nthr_item_t *)__kmp_convert_to_ptr(info->array);
+    kmp_str_loc_t loc = __kmp_str_loc_init(ident->psource, 1);
+    int i;
+    for (i = 0; i < info->num; ++i) {
+      if (kmp_location_match(&loc, &items[i])) {
+        num_threads = items[i].num_threads;
+      }; // if
+    }; // for
+    __kmp_str_loc_free(&loc);
+  }; // if
 
-    kmp_omp_nthr_info_t * info =
-        (kmp_omp_nthr_info_t *) __kmp_convert_to_ptr(  __kmp_omp_debug_struct_info.nthr_info.addr );
-    if ( info->num > 0 && info->array != 0 ) {
-        kmp_omp_nthr_item_t * items = (kmp_omp_nthr_item_t *) __kmp_convert_to_ptr( info->array );
-        kmp_str_loc_t         loc   = __kmp_str_loc_init( ident->psource, 1 );
-        int i;
-        for ( i = 0; i < info->num; ++ i ) {
-            if ( kmp_location_match( & loc, & items[ i ] ) ) {
-                num_threads = items[ i ].num_threads;
-            }; // if
-        }; // for
-        __kmp_str_loc_free( & loc );
-    }; // if
-
-    return num_threads;;
+  return num_threads;
+  ;
 
 } // __kmp_omp_num_threads
 #endif /* USE_DEBUGGER */

runtime/src/kmp_debugger.h

@@ -18,34 +18,34 @@
 #define KMP_DEBUGGER_H
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
-/* * This external variable can be set by any debugger to flag to the runtime that we
-   are currently executing inside a debugger.  This will allow the debugger to override
-   the number of threads spawned in a parallel region by using __kmp_omp_num_threads() (below).
-   * When __kmp_debugging is TRUE, each team and each task gets a unique integer identifier
-   that can be used by debugger to conveniently identify teams and tasks.
-   * The debugger has access to __kmp_omp_debug_struct_info which contains information
-   about the OpenMP library's important internal structures.  This access will allow the debugger
-   to read detailed information from the typical OpenMP constructs (teams, threads, tasking, etc. )
-   during a debugging session and offer detailed and useful information which the user can probe
-   about the OpenMP portion of their code.
-   */
-extern int __kmp_debugging;             /* Boolean whether currently debugging OpenMP RTL */
+/* This external variable can be set by any debugger to flag to the runtime
+   that we are currently executing inside a debugger.  This will allow the
+   debugger to override the number of threads spawned in a parallel region by
+   using __kmp_omp_num_threads() (below).
+   * When __kmp_debugging is TRUE, each team and each task gets a unique integer
+   identifier that can be used by debugger to conveniently identify teams and
+   tasks.
+   * The debugger has access to __kmp_omp_debug_struct_info which contains
+   information about the OpenMP library's important internal structures.  This
+   access will allow the debugger to read detailed information from the typical
+   OpenMP constructs (teams, threads, tasking, etc. ) during a debugging
+   session and offer detailed and useful information which the user can probe
+   about the OpenMP portion of their code. */
+extern int __kmp_debugging; /* Boolean whether currently debugging OpenMP RTL */
 // Return number of threads specified by the debugger for given parallel region.
-/* The ident field, which represents a source file location, is used to check if the
-   debugger has changed the number of threads for the parallel region at source file
-   location ident.  This way, specific parallel regions' number of threads can be changed
-   at the debugger's request.
- */
-int __kmp_omp_num_threads( ident_t const * ident );
+/* The ident field, which represents a source file location, is used to check if
+   the debugger has changed the number of threads for the parallel region at
+   source file location ident.  This way, specific parallel regions' number of
+   threads can be changed at the debugger's request. */
+int __kmp_omp_num_threads(ident_t const *ident);
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif // __cplusplus
 
-
 #endif // KMP_DEBUGGER_H
 
 #endif // USE_DEBUGGER

runtime/src/kmp_environment.cpp

@@ -13,355 +13,297 @@
 //===----------------------------------------------------------------------===//
 
 
-/*
-    ------------------------------------------------------------------------------------------------
-    We use GetEnvironmentVariable for Windows* OS instead of getenv because the act of
-    loading a DLL on Windows* OS makes any user-set environment variables (i.e. with putenv())
-    unavailable.  getenv() apparently gets a clean copy of the env variables as they existed
-    at the start of the run.
-    JH 12/23/2002
-    ------------------------------------------------------------------------------------------------
-    On Windows* OS, there are two environments (at least, see below):
+/* We use GetEnvironmentVariable for Windows* OS instead of getenv because the
+   act of loading a DLL on Windows* OS makes any user-set environment variables
+   (i.e. with putenv()) unavailable.  getenv() apparently gets a clean copy of
+   the env variables as they existed at the start of the run. JH 12/23/2002
 
-        1. Environment maintained by Windows* OS on IA-32 architecture.
-	   Accessible through GetEnvironmentVariable(),
-           SetEnvironmentVariable(), and GetEnvironmentStrings().
+   On Windows* OS, there are two environments (at least, see below):
 
-        2. Environment maintained by C RTL. Accessible through getenv(), putenv().
+   1. Environment maintained by Windows* OS on IA-32 architecture. Accessible
+      through GetEnvironmentVariable(), SetEnvironmentVariable(), and
+      GetEnvironmentStrings().
 
-    putenv() function updates both C and Windows* OS on IA-32 architecture. getenv() function
-    search for variables in C RTL environment only. Windows* OS on IA-32 architecture functions work *only*
-    with Windows* OS on IA-32 architecture.
+   2. Environment maintained by C RTL. Accessible through getenv(), putenv().
 
-    Windows* OS on IA-32 architecture maintained by OS, so there is always only one Windows* OS on
-    IA-32 architecture per process. Changes in Windows* OS on IA-32 architecture are process-visible.
+   putenv() function updates both C and Windows* OS on IA-32 architecture.
+   getenv() function search for variables in C RTL environment only.
+   Windows* OS on IA-32 architecture functions work *only* with Windows* OS on
+   IA-32 architecture.
 
-    C environment maintained by C RTL. Multiple copies of C RTL may be present in the process, and
-    each C RTL maintains its own environment. :-(
+   Windows* OS on IA-32 architecture maintained by OS, so there is always only
+   one Windows* OS on IA-32 architecture per process. Changes in Windows* OS on
+   IA-32 architecture are process-visible.
 
-    Thus, proper way to work with environment on Windows* OS is:
+   C environment maintained by C RTL. Multiple copies of C RTL may be present
+   in the process, and each C RTL maintains its own environment. :-(
 
-        1. Set variables with putenv() function -- both C and Windows* OS on
-	   IA-32 architecture are being updated. Windows* OS on
-	   IA-32 architecture may be considered as primary target,
-	   while updating C RTL environment is a free bonus.
+   Thus, proper way to work with environment on Windows* OS is:
 
-        2. Get variables with GetEnvironmentVariable() -- getenv() does not
-	   search Windows* OS on IA-32 architecture, and can not see variables
-	   set with SetEnvironmentVariable().
+   1. Set variables with putenv() function -- both C and Windows* OS on IA-32
+      architecture are being updated. Windows* OS on IA-32 architecture may be
+      considered primary target, while updating C RTL environment is free bonus.
 
-    2007-04-05 -- lev
-    ------------------------------------------------------------------------------------------------
+   2. Get variables with GetEnvironmentVariable() -- getenv() does not
+      search Windows* OS on IA-32 architecture, and can not see variables
+      set with SetEnvironmentVariable().
+
+   2007-04-05 -- lev
 */
 
 #include "kmp_environment.h"
 
-#include "kmp_os.h"    // KMP_OS_*.
-#include "kmp.h"       //
-#include "kmp_str.h"   // __kmp_str_*().
+#include "kmp.h" //
 #include "kmp_i18n.h"
+#include "kmp_os.h" // KMP_OS_*.
+#include "kmp_str.h" // __kmp_str_*().
 
 #if KMP_OS_UNIX
-    #include <stdlib.h>    // getenv, setenv, unsetenv.
-    #include <string.h>    // strlen, strcpy.
-    #if KMP_OS_DARWIN
-        #include <crt_externs.h>
-        #define environ (*_NSGetEnviron())
-    #else
-        extern char * * environ;
-    #endif
-#elif KMP_OS_WINDOWS
-    #include <windows.h>   // GetEnvironmentVariable, SetEnvironmentVariable, GetLastError.
+#include <stdlib.h> // getenv, setenv, unsetenv.
+#include <string.h> // strlen, strcpy.
+#if KMP_OS_DARWIN
+#include <crt_externs.h>
+#define environ (*_NSGetEnviron())
 #else
-    #error Unknown or unsupported OS.
+extern char **environ;
+#endif
+#elif KMP_OS_WINDOWS
+#include <windows.h> // GetEnvironmentVariable, SetEnvironmentVariable,
+// GetLastError.
+#else
+#error Unknown or unsupported OS.
 #endif
-
 
 // TODO: Eliminate direct memory allocations, use string operations instead.
 
-static inline
-void *
-allocate(
-    size_t size
-) {
-    void * ptr = KMP_INTERNAL_MALLOC( size );
-    if ( ptr == NULL ) {
-	KMP_FATAL( MemoryAllocFailed );
-    }; // if
-    return ptr;
+static inline void *allocate(size_t size) {
+  void *ptr = KMP_INTERNAL_MALLOC(size);
+  if (ptr == NULL) {
+    KMP_FATAL(MemoryAllocFailed);
+  }; // if
+  return ptr;
 } // allocate
 
+char *__kmp_env_get(char const *name) {
 
-char *
-__kmp_env_get( char const * name ) {
+  char *result = NULL;
 
-    char * result = NULL;
+#if KMP_OS_UNIX
+  char const *value = getenv(name);
+  if (value != NULL) {
+    size_t len = KMP_STRLEN(value) + 1;
+    result = (char *)KMP_INTERNAL_MALLOC(len);
+    if (result == NULL) {
+      KMP_FATAL(MemoryAllocFailed);
+    }; // if
+    KMP_STRNCPY_S(result, len, value, len);
+  }; // if
+#elif KMP_OS_WINDOWS
+  /* We use GetEnvironmentVariable for Windows* OS instead of getenv because the
+     act of loading a DLL on Windows* OS makes any user-set environment
+     variables (i.e. with putenv()) unavailable. getenv() apparently gets a
+     clean copy of the env variables as they existed at the start of the run.
+     JH 12/23/2002 */
+  DWORD rc;
+  rc = GetEnvironmentVariable(name, NULL, 0);
+  if (!rc) {
+    DWORD error = GetLastError();
+    if (error != ERROR_ENVVAR_NOT_FOUND) {
+      __kmp_msg(kmp_ms_fatal, KMP_MSG(CantGetEnvVar, name), KMP_ERR(error),
+                __kmp_msg_null);
+    }; // if
+    // Variable is not found, it's ok, just continue.
+  } else {
+    DWORD len = rc;
+    result = (char *)KMP_INTERNAL_MALLOC(len);
+    if (result == NULL) {
+      KMP_FATAL(MemoryAllocFailed);
+    }; // if
+    rc = GetEnvironmentVariable(name, result, len);
+    if (!rc) {
+      // GetEnvironmentVariable() may return 0 if variable is empty.
+      // In such a case GetLastError() returns ERROR_SUCCESS.
+      DWORD error = GetLastError();
+      if (error != ERROR_SUCCESS) {
+        // Unexpected error. The variable should be in the environment,
+        // and buffer should be large enough.
+        __kmp_msg(kmp_ms_fatal, KMP_MSG(CantGetEnvVar, name), KMP_ERR(error),
+                  __kmp_msg_null);
+        KMP_INTERNAL_FREE((void *)result);
+        result = NULL;
+      }; // if
+    }; // if
+  }; // if
+#else
+#error Unknown or unsupported OS.
+#endif
 
-    #if KMP_OS_UNIX
-        char const * value = getenv( name );
-        if ( value != NULL ) {
-            size_t len = KMP_STRLEN( value ) + 1;
-            result = (char *) KMP_INTERNAL_MALLOC( len );
-            if ( result == NULL ) {
-		KMP_FATAL( MemoryAllocFailed );
-            }; // if
-            KMP_STRNCPY_S( result, len, value, len );
-        }; // if
-    #elif KMP_OS_WINDOWS
-        /*
-            We use GetEnvironmentVariable for Windows* OS instead of getenv because the act of
-            loading a DLL on Windows* OS makes any user-set environment variables (i.e. with putenv())
-            unavailable.  getenv() apparently gets a clean copy of the env variables as they existed
-            at the start of the run.
-            JH 12/23/2002
-        */
-        DWORD rc;
-        rc = GetEnvironmentVariable( name, NULL, 0 );
-        if ( ! rc ) {
-            DWORD error = GetLastError();
-            if ( error != ERROR_ENVVAR_NOT_FOUND ) {
-                __kmp_msg(
-                    kmp_ms_fatal,
-                    KMP_MSG( CantGetEnvVar, name ),
-                    KMP_ERR( error ),
-                    __kmp_msg_null
-                );
-            }; // if
-            // Variable is not found, it's ok, just continue.
-        } else {
-            DWORD len = rc;
-            result = (char *) KMP_INTERNAL_MALLOC( len );
-            if ( result == NULL ) {
-		KMP_FATAL( MemoryAllocFailed );
-            }; // if
-            rc = GetEnvironmentVariable( name, result, len );
-            if ( ! rc ) {
-                // GetEnvironmentVariable() may return 0 if variable is empty.
-                // In such a case GetLastError() returns ERROR_SUCCESS.
-                DWORD error = GetLastError();
-                if ( error != ERROR_SUCCESS ) {
-                    // Unexpected error. The variable should be in the environment,
-                    // and buffer should be large enough.
-                    __kmp_msg(
-                        kmp_ms_fatal,
-                        KMP_MSG( CantGetEnvVar, name ),
-                        KMP_ERR( error ),
-                        __kmp_msg_null
-                    );
-                    KMP_INTERNAL_FREE( (void *) result );
-                    result = NULL;
-                }; // if
-            }; // if
-        }; // if
-    #else
-        #error Unknown or unsupported OS.
-    #endif
-
-    return result;
+  return result;
 
 } // func __kmp_env_get
 
-
 // TODO: Find and replace all regular free() with __kmp_env_free().
 
-void
-__kmp_env_free( char const * * value ) {
+void __kmp_env_free(char const **value) {
 
-    KMP_DEBUG_ASSERT( value != NULL );
-    KMP_INTERNAL_FREE( (void *) * value );
-    * value = NULL;
+  KMP_DEBUG_ASSERT(value != NULL);
+  KMP_INTERNAL_FREE(CCAST(char *, *value));
+  *value = NULL;
 
 } // func __kmp_env_free
 
+int __kmp_env_exists(char const *name) {
 
-
-int
-__kmp_env_exists( char const * name ) {
-
-    #if KMP_OS_UNIX
-        char const * value = getenv( name );
-        return ( ( value == NULL ) ? ( 0 ) : ( 1 ) );
-    #elif KMP_OS_WINDOWS
-        DWORD rc;
-        rc = GetEnvironmentVariable( name, NULL, 0 );
-        if ( rc == 0 ) {
-            DWORD error = GetLastError();
-            if ( error != ERROR_ENVVAR_NOT_FOUND ) {
-                __kmp_msg(
-                    kmp_ms_fatal,
-                    KMP_MSG( CantGetEnvVar, name ),
-                    KMP_ERR( error ),
-                    __kmp_msg_null
-                );
-            }; // if
-            return 0;
-        }; // if
-        return 1;
-    #else
-        #error Unknown or unsupported OS.
-    #endif
+#if KMP_OS_UNIX
+  char const *value = getenv(name);
+  return ((value == NULL) ? (0) : (1));
+#elif KMP_OS_WINDOWS
+  DWORD rc;
+  rc = GetEnvironmentVariable(name, NULL, 0);
+  if (rc == 0) {
+    DWORD error = GetLastError();
+    if (error != ERROR_ENVVAR_NOT_FOUND) {
+      __kmp_msg(kmp_ms_fatal, KMP_MSG(CantGetEnvVar, name), KMP_ERR(error),
+                __kmp_msg_null);
+    }; // if
+    return 0;
+  }; // if
+  return 1;
+#else
+#error Unknown or unsupported OS.
+#endif
 
 } // func __kmp_env_exists
 
+void __kmp_env_set(char const *name, char const *value, int overwrite) {
 
-
-void
-__kmp_env_set( char const * name, char const * value, int overwrite ) {
-
-    #if KMP_OS_UNIX
-        int rc = setenv( name, value, overwrite );
-        if ( rc != 0 ) {
-            // Dead code. I tried to put too many variables into Linux* OS
-            // environment on IA-32 architecture. When application consumes
-            // more than ~2.5 GB of memory, entire system feels bad. Sometimes
-            // application is killed (by OS?), sometimes system stops
-            // responding... But this error message never appears. --ln
-            __kmp_msg(
-                kmp_ms_fatal,
-                KMP_MSG( CantSetEnvVar, name ),
-                KMP_HNT( NotEnoughMemory ),
-                __kmp_msg_null
-            );
-        }; // if
-    #elif KMP_OS_WINDOWS
-        BOOL rc;
-        if ( ! overwrite ) {
-            rc = GetEnvironmentVariable( name, NULL, 0 );
-            if ( rc ) {
-                // Variable exists, do not overwrite.
-                return;
-            }; // if
-            DWORD error = GetLastError();
-            if ( error != ERROR_ENVVAR_NOT_FOUND ) {
-                __kmp_msg(
-                    kmp_ms_fatal,
-                    KMP_MSG( CantGetEnvVar, name ),
-                    KMP_ERR( error ),
-                    __kmp_msg_null
-                );
-            }; // if
-        }; // if
-        rc = SetEnvironmentVariable( name, value );
-        if ( ! rc ) {
-            DWORD error = GetLastError();
-            __kmp_msg(
-                kmp_ms_fatal,
-                KMP_MSG( CantSetEnvVar, name ),
-                KMP_ERR( error ),
-                __kmp_msg_null
-            );
-        }; // if
-    #else
-        #error Unknown or unsupported OS.
-    #endif
+#if KMP_OS_UNIX
+  int rc = setenv(name, value, overwrite);
+  if (rc != 0) {
+    // Dead code. I tried to put too many variables into Linux* OS
+    // environment on IA-32 architecture. When application consumes
+    // more than ~2.5 GB of memory, entire system feels bad. Sometimes
+    // application is killed (by OS?), sometimes system stops
+    // responding... But this error message never appears. --ln
+    __kmp_msg(kmp_ms_fatal, KMP_MSG(CantSetEnvVar, name),
+              KMP_HNT(NotEnoughMemory), __kmp_msg_null);
+  }; // if
+#elif KMP_OS_WINDOWS
+  BOOL rc;
+  if (!overwrite) {
+    rc = GetEnvironmentVariable(name, NULL, 0);
+    if (rc) {
+      // Variable exists, do not overwrite.
+      return;
+    }; // if
+    DWORD error = GetLastError();
+    if (error != ERROR_ENVVAR_NOT_FOUND) {
+      __kmp_msg(kmp_ms_fatal, KMP_MSG(CantGetEnvVar, name), KMP_ERR(error),
+                __kmp_msg_null);
+    }; // if
+  }; // if
+  rc = SetEnvironmentVariable(name, value);
+  if (!rc) {
+    DWORD error = GetLastError();
+    __kmp_msg(kmp_ms_fatal, KMP_MSG(CantSetEnvVar, name), KMP_ERR(error),
+              __kmp_msg_null);
+  }; // if
+#else
+#error Unknown or unsupported OS.
+#endif
 
 } // func __kmp_env_set
 
+void __kmp_env_unset(char const *name) {
 
-
-void
-__kmp_env_unset( char const * name ) {
-
-    #if KMP_OS_UNIX
-        unsetenv( name );
-    #elif KMP_OS_WINDOWS
-        BOOL rc = SetEnvironmentVariable( name, NULL );
-        if ( ! rc ) {
-            DWORD error = GetLastError();
-            __kmp_msg(
-                kmp_ms_fatal,
-                KMP_MSG( CantSetEnvVar, name ),
-                KMP_ERR( error ),
-                __kmp_msg_null
-            );
-        }; // if
-    #else
-        #error Unknown or unsupported OS.
-    #endif
+#if KMP_OS_UNIX
+  unsetenv(name);
+#elif KMP_OS_WINDOWS
+  BOOL rc = SetEnvironmentVariable(name, NULL);
+  if (!rc) {
+    DWORD error = GetLastError();
+    __kmp_msg(kmp_ms_fatal, KMP_MSG(CantSetEnvVar, name), KMP_ERR(error),
+              __kmp_msg_null);
+  }; // if
+#else
+#error Unknown or unsupported OS.
+#endif
 
 } // func __kmp_env_unset
 
-// -------------------------------------------------------------------------------------------------
-
-/*
-    Intel OpenMP RTL string representation of environment: just a string of characters, variables
-    are separated with vertical bars, e. g.:
+/* Intel OpenMP RTL string representation of environment: just a string of
+   characters, variables are separated with vertical bars, e. g.:
 
         "KMP_WARNINGS=0|KMP_AFFINITY=compact|"
 
     Empty variables are allowed and ignored:
 
         "||KMP_WARNINGS=1||"
-
 */
 
-static
-void
-___kmp_env_blk_parse_string(
-    kmp_env_blk_t * block,   // M: Env block to fill.
-    char const *    env      // I: String to parse.
-) {
+static void
+___kmp_env_blk_parse_string(kmp_env_blk_t *block, // M: Env block to fill.
+                            char const *env // I: String to parse.
+                            ) {
 
-    char const chr_delimiter   = '|';
-    char const str_delimiter[] = { chr_delimiter, 0 };
+  char const chr_delimiter = '|';
+  char const str_delimiter[] = {chr_delimiter, 0};
 
-    char *          bulk       = NULL;
-    kmp_env_var_t * vars       = NULL;
-    int             count      = 0;  // Number of used elements in vars array.
-    int             delimiters = 0;  // Number of delimiters in input string.
+  char *bulk = NULL;
+  kmp_env_var_t *vars = NULL;
+  int count = 0; // Number of used elements in vars array.
+  int delimiters = 0; // Number of delimiters in input string.
 
-    // Copy original string, we will modify the copy.
-    bulk = __kmp_str_format( "%s", env );
+  // Copy original string, we will modify the copy.
+  bulk = __kmp_str_format("%s", env);
 
-    // Loop thru all the vars in environment block. Count delimiters (maximum number of variables
-    // is number of delimiters plus one).
-    {
-        char const * ptr = bulk;
-        for ( ; ; ) {
-            ptr = strchr( ptr, chr_delimiter );
-            if ( ptr == NULL ) {
-                break;
-            }; // if
-            ++ delimiters;
-            ptr += 1;
-        }; // forever
-    }
+  // Loop thru all the vars in environment block. Count delimiters (maximum
+  // number of variables is number of delimiters plus one).
+  {
+    char const *ptr = bulk;
+    for (;;) {
+      ptr = strchr(ptr, chr_delimiter);
+      if (ptr == NULL) {
+        break;
+      }; // if
+      ++delimiters;
+      ptr += 1;
+    }; // forever
+  }
 
-    // Allocate vars array.
-    vars = (kmp_env_var_t *) allocate( ( delimiters + 1 ) * sizeof( kmp_env_var_t ) );
+  // Allocate vars array.
+  vars = (kmp_env_var_t *)allocate((delimiters + 1) * sizeof(kmp_env_var_t));
 
-    // Loop thru all the variables.
-    {
-        char * var;     // Pointer to variable (both name and value).
-        char * name;    // Pointer to name of variable.
-        char * value;   // Pointer to value.
-        char * buf;     // Buffer for __kmp_str_token() function.
-        var = __kmp_str_token( bulk, str_delimiter, & buf );      // Get the first var.
-        while ( var != NULL ) {
-            // Save found variable in vars array.
-            __kmp_str_split( var, '=', & name, & value );
-            KMP_DEBUG_ASSERT( count < delimiters + 1 );
-            vars[ count ].name  = name;
-            vars[ count ].value = value;
-            ++ count;
-            // Get the next var.
-            var = __kmp_str_token( NULL, str_delimiter, & buf );
-        }; // while
-    }
+  // Loop thru all the variables.
+  {
+    char *var; // Pointer to variable (both name and value).
+    char *name; // Pointer to name of variable.
+    char *value; // Pointer to value.
+    char *buf; // Buffer for __kmp_str_token() function.
+    var = __kmp_str_token(bulk, str_delimiter, &buf); // Get the first var.
+    while (var != NULL) {
+      // Save found variable in vars array.
+      __kmp_str_split(var, '=', &name, &value);
+      KMP_DEBUG_ASSERT(count < delimiters + 1);
+      vars[count].name = name;
+      vars[count].value = value;
+      ++count;
+      // Get the next var.
+      var = __kmp_str_token(NULL, str_delimiter, &buf);
+    }; // while
+  }
 
-    // Fill out result.
-    block->bulk  = bulk;
-    block->vars  = vars;
-    block->count = count;
+  // Fill out result.
+  block->bulk = bulk;
+  block->vars = vars;
+  block->count = count;
 
 }; // ___kmp_env_blk_parse_string
 
-
-
-/*
-    Windows* OS (actually, DOS) environment block is a piece of memory with environment variables. Each
-    variable is terminated with zero byte, entire block is terminated with one extra zero byte, so
-    we have two zero bytes at the end of environment block, e. g.:
+/* Windows* OS (actually, DOS) environment block is a piece of memory with
+   environment variables. Each variable is terminated with zero byte, entire
+   block is terminated with one extra zero byte, so we have two zero bytes at
+   the end of environment block, e. g.:
 
         "HOME=C:\\users\\lev\x00OS=Windows_NT\x00\x00"
 
@@ -369,227 +311,202 @@ ___kmp_env_blk_parse_string(
 */
 
 #if KMP_OS_WINDOWS
-static
-void
-___kmp_env_blk_parse_windows(
-    kmp_env_blk_t * block,   // M: Env block to fill.
-    char const *    env      // I: Pointer to Windows* OS (DOS) environment block.
-) {
+static void ___kmp_env_blk_parse_windows(
+    kmp_env_blk_t *block, // M: Env block to fill.
+    char const *env // I: Pointer to Windows* OS (DOS) environment block.
+    ) {
 
-    char *          bulk  = NULL;
-    kmp_env_var_t * vars  = NULL;
-    int             count = 0;     // Number of used elements in vars array.
-    int             size  = 0;     // Size of bulk.
+  char *bulk = NULL;
+  kmp_env_var_t *vars = NULL;
+  int count = 0; // Number of used elements in vars array.
+  int size = 0; // Size of bulk.
 
-    char * name;    // Pointer to name of variable.
-    char * value;   // Pointer to value.
+  char *name; // Pointer to name of variable.
+  char *value; // Pointer to value.
 
-    if ( env != NULL ) {
+  if (env != NULL) {
 
-        // Loop thru all the vars in environment block. Count variables, find size of block.
-        {
-            char const * var;     // Pointer to beginning of var.
-            int          len;     // Length of variable.
-            count = 0;
-            var = env;            // The first variable starts and beginning of environment block.
-            len = KMP_STRLEN( var );
-            while ( len != 0 ) {
-                ++ count;
-                size = size + len + 1;
-                var = var + len + 1; // Move pointer to the beginning of the next variable.
-                len = KMP_STRLEN( var );
-            }; // while
-            size = size + 1;         // Total size of env block, including terminating zero byte.
-        }
+    // Loop thru all the vars in environment block. Count variables, find size
+    // of block.
+    {
+      char const *var; // Pointer to beginning of var.
+      int len; // Length of variable.
+      count = 0;
+      var =
+          env; // The first variable starts and beginning of environment block.
+      len = KMP_STRLEN(var);
+      while (len != 0) {
+        ++count;
+        size = size + len + 1;
+        var = var + len +
+              1; // Move pointer to the beginning of the next variable.
+        len = KMP_STRLEN(var);
+      }; // while
+      size =
+          size + 1; // Total size of env block, including terminating zero byte.
+    }
 
-        // Copy original block to bulk, we will modify bulk, not original block.
-        bulk = (char *) allocate( size );
-        KMP_MEMCPY_S( bulk, size, env, size );
-        // Allocate vars array.
-        vars = (kmp_env_var_t *) allocate( count * sizeof( kmp_env_var_t ) );
+    // Copy original block to bulk, we will modify bulk, not original block.
+    bulk = (char *)allocate(size);
+    KMP_MEMCPY_S(bulk, size, env, size);
+    // Allocate vars array.
+    vars = (kmp_env_var_t *)allocate(count * sizeof(kmp_env_var_t));
 
-        // Loop thru all the vars, now in bulk.
-        {
-            char * var;     // Pointer to beginning of var.
-            int    len;     // Length of variable.
-            count = 0;
-            var = bulk;
-            len = KMP_STRLEN( var );
-            while ( len != 0 ) {
-                // Save variable in vars array.
-                __kmp_str_split( var, '=', & name, & value );
-                vars[ count ].name  = name;
-                vars[ count ].value = value;
-                ++ count;
-                // Get the next var.
-                var = var + len + 1;
-                len = KMP_STRLEN( var );
-            }; // while
-        }
+    // Loop thru all the vars, now in bulk.
+    {
+      char *var; // Pointer to beginning of var.
+      int len; // Length of variable.
+      count = 0;
+      var = bulk;
+      len = KMP_STRLEN(var);
+      while (len != 0) {
+        // Save variable in vars array.
+        __kmp_str_split(var, '=', &name, &value);
+        vars[count].name = name;
+        vars[count].value = value;
+        ++count;
+        // Get the next var.
+        var = var + len + 1;
+        len = KMP_STRLEN(var);
+      }; // while
+    }
 
-    }; // if
+  }; // if
 
-    // Fill out result.
-    block->bulk  = bulk;
-    block->vars  = vars;
-    block->count = count;
+  // Fill out result.
+  block->bulk = bulk;
+  block->vars = vars;
+  block->count = count;
 
 }; // ___kmp_env_blk_parse_windows
 #endif
 
-
-/*
-    Unix environment block is a array of pointers to variables, last pointer in array is NULL:
+/* Unix environment block is a array of pointers to variables, last pointer in
+   array is NULL:
 
         { "HOME=/home/lev", "TERM=xterm", NULL }
 */
 
-static
-void
-___kmp_env_blk_parse_unix(
-    kmp_env_blk_t * block,   // M: Env block to fill.
-    char * *        env      // I: Unix environment to parse.
-) {
+static void
+___kmp_env_blk_parse_unix(kmp_env_blk_t *block, // M: Env block to fill.
+                          char **env // I: Unix environment to parse.
+                          ) {
 
-    char *          bulk  = NULL;
-    kmp_env_var_t * vars  = NULL;
-    int             count = 0;
-    int             size  = 0;    // Size of bulk.
+  char *bulk = NULL;
+  kmp_env_var_t *vars = NULL;
+  int count = 0;
+  int size = 0; // Size of bulk.
 
-    // Count number of variables and length of required bulk.
-    {
-        count = 0;
-        size  = 0;
-        while ( env[ count ] != NULL ) {
-            size += KMP_STRLEN( env[ count ] ) + 1;
-            ++ count;
-        }; // while
-    }
+  // Count number of variables and length of required bulk.
+  {
+    count = 0;
+    size = 0;
+    while (env[count] != NULL) {
+      size += KMP_STRLEN(env[count]) + 1;
+      ++count;
+    }; // while
+  }
 
-    // Allocate memory.
-    bulk = (char *) allocate( size );
-    vars = (kmp_env_var_t *) allocate( count * sizeof( kmp_env_var_t ) );
+  // Allocate memory.
+  bulk = (char *)allocate(size);
+  vars = (kmp_env_var_t *)allocate(count * sizeof(kmp_env_var_t));
 
-    // Loop thru all the vars.
-    {
-        char * var;     // Pointer to beginning of var.
-        char * name;    // Pointer to name of variable.
-        char * value;   // Pointer to value.
-        int    len;     // Length of variable.
-        int    i;
-        var = bulk;
-        for ( i = 0; i < count; ++ i ) {
-            // Copy variable to bulk.
-            len = KMP_STRLEN( env[ i ] );
-            KMP_MEMCPY_S( var, size, env[ i ], len + 1 );
-            // Save found variable in vars array.
-            __kmp_str_split( var, '=', & name, & value );
-            vars[ i ].name  = name;
-            vars[ i ].value = value;
-            // Move pointer.
-            var += len + 1;
-        }; // for
-    }
+  // Loop thru all the vars.
+  {
+    char *var; // Pointer to beginning of var.
+    char *name; // Pointer to name of variable.
+    char *value; // Pointer to value.
+    int len; // Length of variable.
+    int i;
+    var = bulk;
+    for (i = 0; i < count; ++i) {
+      // Copy variable to bulk.
+      len = KMP_STRLEN(env[i]);
+      KMP_MEMCPY_S(var, size, env[i], len + 1);
+      // Save found variable in vars array.
+      __kmp_str_split(var, '=', &name, &value);
+      vars[i].name = name;
+      vars[i].value = value;
+      // Move pointer.
+      var += len + 1;
+    }; // for
+  }
 
-    // Fill out result.
-    block->bulk  = bulk;
-    block->vars  = vars;
-    block->count = count;
+  // Fill out result.
+  block->bulk = bulk;
+  block->vars = vars;
+  block->count = count;
 
 }; // ___kmp_env_blk_parse_unix
 
+void __kmp_env_blk_init(kmp_env_blk_t *block, // M: Block to initialize.
+                        char const *bulk // I: Initialization string, or NULL.
+                        ) {
 
-
-void
-__kmp_env_blk_init(
-    kmp_env_blk_t * block,  // M: Block to initialize.
-    char const *    bulk    // I: Initialization string, or NULL.
-) {
-
-    if ( bulk != NULL ) {
-        ___kmp_env_blk_parse_string( block, bulk );
-    } else {
-        #if KMP_OS_UNIX
-            ___kmp_env_blk_parse_unix( block, environ );
-        #elif KMP_OS_WINDOWS
-            {
-                char * mem = GetEnvironmentStrings();
-                if ( mem == NULL ) {
-                    DWORD error = GetLastError();
-                    __kmp_msg(
-                        kmp_ms_fatal,
-                        KMP_MSG( CantGetEnvironment ),
-                        KMP_ERR( error ),
-                        __kmp_msg_null
-                    );
-                }; // if
-                ___kmp_env_blk_parse_windows( block, mem );
-                FreeEnvironmentStrings( mem );
-            }
-        #else
-            #error Unknown or unsupported OS.
-        #endif
-    }; // if
+  if (bulk != NULL) {
+    ___kmp_env_blk_parse_string(block, bulk);
+  } else {
+#if KMP_OS_UNIX
+    ___kmp_env_blk_parse_unix(block, environ);
+#elif KMP_OS_WINDOWS
+    {
+      char *mem = GetEnvironmentStrings();
+      if (mem == NULL) {
+        DWORD error = GetLastError();
+        __kmp_msg(kmp_ms_fatal, KMP_MSG(CantGetEnvironment), KMP_ERR(error),
+                  __kmp_msg_null);
+      }; // if
+      ___kmp_env_blk_parse_windows(block, mem);
+      FreeEnvironmentStrings(mem);
+    }
+#else
+#error Unknown or unsupported OS.
+#endif
+  }; // if
 
 } // __kmp_env_blk_init
 
-
-
-static
-int
-___kmp_env_var_cmp(                              // Comparison function for qsort().
-    kmp_env_var_t const * lhs,
-    kmp_env_var_t const * rhs
-) {
-    return strcmp( lhs->name, rhs->name );
+static int ___kmp_env_var_cmp( // Comparison function for qsort().
+    kmp_env_var_t const *lhs, kmp_env_var_t const *rhs) {
+  return strcmp(lhs->name, rhs->name);
 }
 
-void
-__kmp_env_blk_sort(
-    kmp_env_blk_t * block  // M: Block of environment variables to sort.
-) {
+void __kmp_env_blk_sort(
+    kmp_env_blk_t *block // M: Block of environment variables to sort.
+    ) {
 
-    qsort(
-        (void *) block->vars,
-        block->count,
-        sizeof( kmp_env_var_t ),
-        ( int ( * )( void const *, void const * ) ) & ___kmp_env_var_cmp
-    );
+  qsort(CCAST(kmp_env_var_t *, block->vars), block->count,
+        sizeof(kmp_env_var_t),
+        (int (*)(void const *, void const *)) & ___kmp_env_var_cmp);
 
 } // __kmp_env_block_sort
 
+void __kmp_env_blk_free(
+    kmp_env_blk_t *block // M: Block of environment variables to free.
+    ) {
 
+  KMP_INTERNAL_FREE(CCAST(kmp_env_var_t *, block->vars));
+  __kmp_str_free(&(block->bulk));
 
-void
-__kmp_env_blk_free(
-    kmp_env_blk_t * block  // M: Block of environment variables to free.
-) {
-
-    KMP_INTERNAL_FREE( (void *) block->vars );
-    __kmp_str_free(&(block->bulk));
-
-    block->count = 0;
-    block->vars  = NULL;
+  block->count = 0;
+  block->vars = NULL;
 
 } // __kmp_env_blk_free
 
+char const * // R: Value of variable or NULL if variable does not exist.
+    __kmp_env_blk_var(
+        kmp_env_blk_t *block, // I: Block of environment variables.
+        char const *name // I: Name of variable to find.
+        ) {
 
-
-char const *               // R: Value of variable or NULL if variable does not exist.
-__kmp_env_blk_var(
-    kmp_env_blk_t * block, // I: Block of environment variables.
-    char const *    name   // I: Name of variable to find.
-) {
-
-    int i;
-    for ( i = 0; i < block->count; ++ i ) {
-        if ( strcmp( block->vars[ i ].name, name ) == 0 ) {
-            return block->vars[ i ].value;
-        }; // if
-    }; // for
-    return NULL;
+  int i;
+  for (i = 0; i < block->count; ++i) {
+    if (strcmp(block->vars[i].name, name) == 0) {
+      return block->vars[i].value;
+    }; // if
+  }; // for
+  return NULL;
 
 } // __kmp_env_block_var
 
-
 // end of file //

runtime/src/kmp_environment.h

@@ -20,56 +20,56 @@
 extern "C" {
 #endif
 
-// Return a copy of the value of environment variable or NULL if the variable does not exist.
+// Return a copy of the value of environment variable or NULL if the variable
+// does not exist.
 // *Note*: Returned pointed *must* be freed after use with __kmp_env_free().
-char * __kmp_env_get( char const * name );
-void   __kmp_env_free( char const * * value );
+char *__kmp_env_get(char const *name);
+void __kmp_env_free(char const **value);
 
 // Return 1 if the environment variable exists or 0 if does not exist.
-int __kmp_env_exists( char const * name );
+int __kmp_env_exists(char const *name);
 
 // Set the environment variable.
-void __kmp_env_set( char const * name, char const * value, int overwrite );
+void __kmp_env_set(char const *name, char const *value, int overwrite);
 
 // Unset (remove) environment variable.
-void __kmp_env_unset( char const * name );
+void __kmp_env_unset(char const *name);
 
-
-// -------------------------------------------------------------------------------------------------
+// -----------------------------------------------------------------------------
 //  Working with environment blocks.
-// -------------------------------------------------------------------------------------------------
 
-/*
-    kmp_env_blk_t is read-only collection of environment variables (or environment-like). Usage:
+/* kmp_env_blk_t is read-only collection of environment variables (or
+   environment-like). Usage:
 
-        kmp_env_blk_t block;
-        __kmp_env_blk_init( & block, NULL ); // Initialize block from process environment.
-        // or
-        __kmp_env_blk_init( & block, "KMP_WARNING=1|KMP_AFFINITY=none" ); // from string.
-        __kmp_env_blk_sort( & block ); // Optionally, sort list.
-        for ( i = 0; i < block.count; ++ i ) {
-            // Process block.vars[ i ].name and block.vars[ i ].value...
-        }; // for i
-        __kmp_env_block_free( & block );
+kmp_env_blk_t block;
+__kmp_env_blk_init( & block, NULL ); // Initialize block from process
+                                        // environment.
+// or
+__kmp_env_blk_init( & block, "KMP_WARNING=1|KMP_AFFINITY=none" ); // from string
+__kmp_env_blk_sort( & block ); // Optionally, sort list.
+for ( i = 0; i < block.count; ++ i ) {
+    // Process block.vars[ i ].name and block.vars[ i ].value...
+}; // for i
+__kmp_env_block_free( & block );
 */
 
 struct __kmp_env_var {
-    char const * name;
-    char const * value;
+  char const *name;
+  char const *value;
 };
 typedef struct __kmp_env_var kmp_env_var_t;
 
 struct __kmp_env_blk {
-    char const *          bulk;
-    kmp_env_var_t const * vars;
-    int                   count;
+  char const *bulk;
+  kmp_env_var_t const *vars;
+  int count;
 };
 typedef struct __kmp_env_blk kmp_env_blk_t;
 
-void         __kmp_env_blk_init( kmp_env_blk_t * block, char const * bulk );
-void         __kmp_env_blk_free( kmp_env_blk_t * block );
-void         __kmp_env_blk_sort( kmp_env_blk_t * block );
-char const * __kmp_env_blk_var(  kmp_env_blk_t * block, char const * name );
+void __kmp_env_blk_init(kmp_env_blk_t *block, char const *bulk);
+void __kmp_env_blk_free(kmp_env_blk_t *block);
+void __kmp_env_blk_sort(kmp_env_blk_t *block);
+char const *__kmp_env_blk_var(kmp_env_blk_t *block, char const *name);
 
 #ifdef __cplusplus
 }
@@ -78,4 +78,3 @@ char const * __kmp_env_blk_var(  kmp_env_blk_t * block, char const * name );
 #endif // KMP_ENVIRONMENT_H
 
 // end of file //
-

runtime/src/kmp_error.cpp

@@ -14,259 +14,237 @@
 
 
 #include "kmp.h"
+#include "kmp_error.h"
 #include "kmp_i18n.h"
 #include "kmp_str.h"
-#include "kmp_error.h"
 
-/* ------------------------------------------------------------------------ */
 /* ------------------------------------------------------------------------ */
 
-#define MIN_STACK       100
+#define MIN_STACK 100
 
-
-static char const * cons_text_c[] = {
-    "(none)",
-    "\"parallel\"",
-    "work-sharing",             /* this is not called "for" because of lowering of "sections" pragmas */
-    "\"ordered\" work-sharing", /* this is not called "for ordered" because of lowering of "sections" pragmas */
+static char const *cons_text_c[] = {
+    "(none)", "\"parallel\"", "work-sharing", /* this is not called "for"
+                                                 because of lowering of
+                                                 "sections" pragmas */
+    "\"ordered\" work-sharing", /* this is not called "for ordered" because of
+                                   lowering of "sections" pragmas */
     "\"sections\"",
-    "work-sharing",             /* this is not called "single" because of lowering of "sections" pragmas */
-    "\"taskq\"",
-    "\"taskq\"",
-    "\"taskq ordered\"",
-    "\"critical\"",
-    "\"ordered\"",              /* in PARALLEL */
-    "\"ordered\"",              /* in PDO */
-    "\"ordered\"",              /* in TASKQ */
-    "\"master\"",
-    "\"reduce\"",
-    "\"barrier\""
-};
+    "work-sharing", /* this is not called "single" because of lowering of
+                       "sections" pragmas */
+    "\"taskq\"", "\"taskq\"", "\"taskq ordered\"", "\"critical\"",
+    "\"ordered\"", /* in PARALLEL */
+    "\"ordered\"", /* in PDO */
+    "\"ordered\"", /* in TASKQ */
+    "\"master\"", "\"reduce\"", "\"barrier\""};
 
-#define get_src( ident )   ( (ident) == NULL ? NULL : (ident)->psource )
+#define get_src(ident) ((ident) == NULL ? NULL : (ident)->psource)
 
-#define PUSH_MSG( ct, ident ) \
-    "\tpushing on stack: %s (%s)\n", cons_text_c[ (ct) ], get_src( (ident) )
-#define POP_MSG( p )                                  \
-    "\tpopping off stack: %s (%s)\n",                 \
-    cons_text_c[ (p)->stack_data[ tos ].type ],       \
-    get_src( (p)->stack_data[ tos ].ident )
+#define PUSH_MSG(ct, ident)                                                    \
+  "\tpushing on stack: %s (%s)\n", cons_text_c[(ct)], get_src((ident))
+#define POP_MSG(p)                                                             \
+  "\tpopping off stack: %s (%s)\n", cons_text_c[(p)->stack_data[tos].type],    \
+      get_src((p)->stack_data[tos].ident)
 
-static int const cons_text_c_num    = sizeof( cons_text_c    ) / sizeof( char const * );
+static int const cons_text_c_num = sizeof(cons_text_c) / sizeof(char const *);
 
-/* ------------------------------------------------------------------------ */
 /* --------------- START OF STATIC LOCAL ROUTINES ------------------------- */
-/* ------------------------------------------------------------------------ */
 
-static void
-__kmp_check_null_func( void )
-{
-    /* nothing to do */
+static void __kmp_check_null_func(void) { /* nothing to do */
 }
 
-static void
-__kmp_expand_cons_stack( int gtid, struct cons_header *p )
-{
-    int    i;
-    struct cons_data *d;
+static void __kmp_expand_cons_stack(int gtid, struct cons_header *p) {
+  int i;
+  struct cons_data *d;
 
-    /* TODO for monitor perhaps? */
-    if (gtid < 0)
-        __kmp_check_null_func();
+  /* TODO for monitor perhaps? */
+  if (gtid < 0)
+    __kmp_check_null_func();
 
-    KE_TRACE( 10, ("expand cons_stack (%d %d)\n", gtid, __kmp_get_gtid() ) );
+  KE_TRACE(10, ("expand cons_stack (%d %d)\n", gtid, __kmp_get_gtid()));
 
-    d = p->stack_data;
+  d = p->stack_data;
 
-    p->stack_size = (p->stack_size * 2) + 100;
+  p->stack_size = (p->stack_size * 2) + 100;
 
-    /* TODO free the old data */
-    p->stack_data = (struct cons_data *) __kmp_allocate( sizeof( struct cons_data ) * (p->stack_size+1) );
+  /* TODO free the old data */
+  p->stack_data = (struct cons_data *)__kmp_allocate(sizeof(struct cons_data) *
+                                                     (p->stack_size + 1));
 
-    for (i = p->stack_top; i >= 0; --i)
-        p->stack_data[i] = d[i];
+  for (i = p->stack_top; i >= 0; --i)
+    p->stack_data[i] = d[i];
 
-    /* NOTE: we do not free the old stack_data */
+  /* NOTE: we do not free the old stack_data */
 }
 
 // NOTE: Function returns allocated memory, caller must free it!
-static char const *
-__kmp_pragma(
-    int              ct,
-    ident_t const *  ident
-) {
-    char const * cons = NULL;  // Construct name.
-    char * file = NULL;  // File name.
-    char * func = NULL;  // Function (routine) name.
-    char * line = NULL;  // Line number.
-    kmp_str_buf_t buffer;
-    kmp_msg_t     prgm;
-    __kmp_str_buf_init( & buffer );
-    if ( 0 < ct && ct < cons_text_c_num ) {
-        cons = cons_text_c[ ct ];
-    } else {
-        KMP_DEBUG_ASSERT( 0 );
-    };
-    if ( ident != NULL && ident->psource != NULL ) {
-        char * tail = NULL;
-        __kmp_str_buf_print( & buffer, "%s", ident->psource ); // Copy source to buffer.
-        // Split string in buffer to file, func, and line.
-        tail = buffer.str;
-        __kmp_str_split( tail, ';', NULL,   & tail );
-        __kmp_str_split( tail, ';', & file, & tail );
-        __kmp_str_split( tail, ';', & func, & tail );
-        __kmp_str_split( tail, ';', & line, & tail );
-    }; // if
-    prgm = __kmp_msg_format( kmp_i18n_fmt_Pragma, cons, file, func, line );
-    __kmp_str_buf_free( & buffer );
-    return prgm.str;
+static char const *__kmp_pragma(int ct, ident_t const *ident) {
+  char const *cons = NULL; // Construct name.
+  char *file = NULL; // File name.
+  char *func = NULL; // Function (routine) name.
+  char *line = NULL; // Line number.
+  kmp_str_buf_t buffer;
+  kmp_msg_t prgm;
+  __kmp_str_buf_init(&buffer);
+  if (0 < ct && ct < cons_text_c_num) {
+    cons = cons_text_c[ct];
+  } else {
+    KMP_DEBUG_ASSERT(0);
+  };
+  if (ident != NULL && ident->psource != NULL) {
+    char *tail = NULL;
+    __kmp_str_buf_print(&buffer, "%s",
+                        ident->psource); // Copy source to buffer.
+    // Split string in buffer to file, func, and line.
+    tail = buffer.str;
+    __kmp_str_split(tail, ';', NULL, &tail);
+    __kmp_str_split(tail, ';', &file, &tail);
+    __kmp_str_split(tail, ';', &func, &tail);
+    __kmp_str_split(tail, ';', &line, &tail);
+  }; // if
+  prgm = __kmp_msg_format(kmp_i18n_fmt_Pragma, cons, file, func, line);
+  __kmp_str_buf_free(&buffer);
+  return prgm.str;
 } // __kmp_pragma
 
-/* ------------------------------------------------------------------------ */
 /* ----------------- END OF STATIC LOCAL ROUTINES ------------------------- */
-/* ------------------------------------------------------------------------ */
 
-
-void
-__kmp_error_construct(
-    kmp_i18n_id_t    id,     // Message identifier.
-    enum cons_type   ct,     // Construct type.
-    ident_t const *  ident   // Construct ident.
-) {
-    char const * construct = __kmp_pragma( ct, ident );
-    __kmp_msg( kmp_ms_fatal, __kmp_msg_format( id, construct ), __kmp_msg_null );
-    KMP_INTERNAL_FREE( (void *) construct );
+void __kmp_error_construct(kmp_i18n_id_t id, // Message identifier.
+                           enum cons_type ct, // Construct type.
+                           ident_t const *ident // Construct ident.
+                           ) {
+  char const *construct = __kmp_pragma(ct, ident);
+  __kmp_msg(kmp_ms_fatal, __kmp_msg_format(id, construct), __kmp_msg_null);
+  KMP_INTERNAL_FREE(CCAST(char *, construct));
 }
 
-void
-__kmp_error_construct2(
-    kmp_i18n_id_t            id,     // Message identifier.
-    enum cons_type           ct,     // First construct type.
-    ident_t const *          ident,  // First construct ident.
-    struct cons_data const * cons    // Second construct.
-) {
-    char const * construct1 = __kmp_pragma( ct, ident );
-    char const * construct2 = __kmp_pragma( cons->type, cons->ident );
-    __kmp_msg( kmp_ms_fatal, __kmp_msg_format( id, construct1, construct2 ), __kmp_msg_null );
-    KMP_INTERNAL_FREE( (void *) construct1 );
-    KMP_INTERNAL_FREE( (void *) construct2 );
+void __kmp_error_construct2(kmp_i18n_id_t id, // Message identifier.
+                            enum cons_type ct, // First construct type.
+                            ident_t const *ident, // First construct ident.
+                            struct cons_data const *cons // Second construct.
+                            ) {
+  char const *construct1 = __kmp_pragma(ct, ident);
+  char const *construct2 = __kmp_pragma(cons->type, cons->ident);
+  __kmp_msg(kmp_ms_fatal, __kmp_msg_format(id, construct1, construct2),
+            __kmp_msg_null);
+  KMP_INTERNAL_FREE(CCAST(char *, construct1));
+  KMP_INTERNAL_FREE(CCAST(char *, construct2));
 }
 
+struct cons_header *__kmp_allocate_cons_stack(int gtid) {
+  struct cons_header *p;
 
-struct cons_header *
-__kmp_allocate_cons_stack( int gtid )
-{
-    struct cons_header *p;
+  /* TODO for monitor perhaps? */
+  if (gtid < 0) {
+    __kmp_check_null_func();
+  }; // if
+  KE_TRACE(10, ("allocate cons_stack (%d)\n", gtid));
+  p = (struct cons_header *)__kmp_allocate(sizeof(struct cons_header));
+  p->p_top = p->w_top = p->s_top = 0;
+  p->stack_data = (struct cons_data *)__kmp_allocate(sizeof(struct cons_data) *
+                                                     (MIN_STACK + 1));
+  p->stack_size = MIN_STACK;
+  p->stack_top = 0;
+  p->stack_data[0].type = ct_none;
+  p->stack_data[0].prev = 0;
+  p->stack_data[0].ident = NULL;
+  return p;
+}
 
-    /* TODO for monitor perhaps? */
-    if ( gtid < 0 ) {
-        __kmp_check_null_func();
+void __kmp_free_cons_stack(void *ptr) {
+  struct cons_header *p = (struct cons_header *)ptr;
+  if (p != NULL) {
+    if (p->stack_data != NULL) {
+      __kmp_free(p->stack_data);
+      p->stack_data = NULL;
     }; // if
-    KE_TRACE( 10, ("allocate cons_stack (%d)\n", gtid ) );
-    p = (struct cons_header *) __kmp_allocate( sizeof( struct cons_header ) );
-    p->p_top = p->w_top = p->s_top = 0;
-    p->stack_data = (struct cons_data *) __kmp_allocate( sizeof( struct cons_data ) * (MIN_STACK+1) );
-    p->stack_size = MIN_STACK;
-    p->stack_top  = 0;
-    p->stack_data[ 0 ].type = ct_none;
-    p->stack_data[ 0 ].prev = 0;
-    p->stack_data[ 0 ].ident = NULL;
-    return p;
+    __kmp_free(p);
+  }; // if
 }
 
-void
-__kmp_free_cons_stack( void * ptr ) {
-    struct cons_header * p = (struct cons_header *) ptr;
-    if ( p != NULL ) {
-        if ( p->stack_data != NULL ) {
-            __kmp_free( p->stack_data );
-            p->stack_data = NULL;
-        }; // if
-        __kmp_free( p );
-    }; // if
-}
-
-
 #if KMP_DEBUG
-static void
-dump_cons_stack( int gtid, struct cons_header * p ) {
-    int i;
-    int tos = p->stack_top;
-    kmp_str_buf_t buffer;
-    __kmp_str_buf_init( & buffer );
-    __kmp_str_buf_print( & buffer, "+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-\n" );
-    __kmp_str_buf_print( & buffer, "Begin construct stack with %d items for thread %d\n", tos, gtid );
-    __kmp_str_buf_print( & buffer, "     stack_top=%d { P=%d, W=%d, S=%d }\n", tos, p->p_top, p->w_top, p->s_top );
-    for ( i = tos; i > 0; i-- ) {
-        struct cons_data * c = & ( p->stack_data[ i ] );
-        __kmp_str_buf_print( & buffer, "        stack_data[%2d] = { %s (%s) %d %p }\n", i, cons_text_c[ c->type ], get_src( c->ident ), c->prev, c->name );
-    }; // for i
-    __kmp_str_buf_print( & buffer, "End construct stack for thread %d\n", gtid );
-    __kmp_str_buf_print( & buffer, "+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-\n" );
-    __kmp_debug_printf( "%s", buffer.str );
-    __kmp_str_buf_free( & buffer );
+static void dump_cons_stack(int gtid, struct cons_header *p) {
+  int i;
+  int tos = p->stack_top;
+  kmp_str_buf_t buffer;
+  __kmp_str_buf_init(&buffer);
+  __kmp_str_buf_print(
+      &buffer,
+      "+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-\n");
+  __kmp_str_buf_print(&buffer,
+                      "Begin construct stack with %d items for thread %d\n",
+                      tos, gtid);
+  __kmp_str_buf_print(&buffer, "     stack_top=%d { P=%d, W=%d, S=%d }\n", tos,
+                      p->p_top, p->w_top, p->s_top);
+  for (i = tos; i > 0; i--) {
+    struct cons_data *c = &(p->stack_data[i]);
+    __kmp_str_buf_print(
+        &buffer, "        stack_data[%2d] = { %s (%s) %d %p }\n", i,
+        cons_text_c[c->type], get_src(c->ident), c->prev, c->name);
+  }; // for i
+  __kmp_str_buf_print(&buffer, "End construct stack for thread %d\n", gtid);
+  __kmp_str_buf_print(
+      &buffer,
+      "+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-\n");
+  __kmp_debug_printf("%s", buffer.str);
+  __kmp_str_buf_free(&buffer);
 }
 #endif
 
-void
-__kmp_push_parallel( int gtid, ident_t const * ident )
-{
-    int tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
+void __kmp_push_parallel(int gtid, ident_t const *ident) {
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
 
-    KMP_DEBUG_ASSERT( __kmp_threads[ gtid ]-> th.th_cons );
-    KE_TRACE( 10, ("__kmp_push_parallel (%d %d)\n", gtid, __kmp_get_gtid() ) );
-    KE_TRACE( 100, ( PUSH_MSG( ct_parallel, ident ) ) );
-    if ( p->stack_top >= p->stack_size ) {
-        __kmp_expand_cons_stack( gtid, p );
-    }; // if
-    tos = ++p->stack_top;
-    p->stack_data[ tos ].type = ct_parallel;
-    p->stack_data[ tos ].prev = p->p_top;
-    p->stack_data[ tos ].ident = ident;
-    p->stack_data[ tos ].name = NULL;
-    p->p_top = tos;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
+  KMP_DEBUG_ASSERT(__kmp_threads[gtid]->th.th_cons);
+  KE_TRACE(10, ("__kmp_push_parallel (%d %d)\n", gtid, __kmp_get_gtid()));
+  KE_TRACE(100, (PUSH_MSG(ct_parallel, ident)));
+  if (p->stack_top >= p->stack_size) {
+    __kmp_expand_cons_stack(gtid, p);
+  }; // if
+  tos = ++p->stack_top;
+  p->stack_data[tos].type = ct_parallel;
+  p->stack_data[tos].prev = p->p_top;
+  p->stack_data[tos].ident = ident;
+  p->stack_data[tos].name = NULL;
+  p->p_top = tos;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
 }
 
-void
-__kmp_check_workshare( int gtid, enum cons_type ct, ident_t const * ident )
-{
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
+void __kmp_check_workshare(int gtid, enum cons_type ct, ident_t const *ident) {
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
 
-    KMP_DEBUG_ASSERT( __kmp_threads[ gtid ]-> th.th_cons );
-    KE_TRACE( 10, ("__kmp_check_workshare (%d %d)\n", gtid, __kmp_get_gtid() ) );
+  KMP_DEBUG_ASSERT(__kmp_threads[gtid]->th.th_cons);
+  KE_TRACE(10, ("__kmp_check_workshare (%d %d)\n", gtid, __kmp_get_gtid()));
 
-
-    if ( p->stack_top >= p->stack_size ) {
-        __kmp_expand_cons_stack( gtid, p );
-    }; // if
-    if ( p->w_top > p->p_top &&
-        !(IS_CONS_TYPE_TASKQ(p->stack_data[ p->w_top ].type) && IS_CONS_TYPE_TASKQ(ct))) {
-        // We are already in a WORKSHARE construct for this PARALLEL region.
-        __kmp_error_construct2( kmp_i18n_msg_CnsInvalidNesting, ct, ident, & p->stack_data[ p->w_top ] );
-    }; // if
-    if ( p->s_top > p->p_top ) {
-        // We are already in a SYNC construct for this PARALLEL region.
-        __kmp_error_construct2( kmp_i18n_msg_CnsInvalidNesting, ct, ident, & p->stack_data[ p->s_top ] );
-    }; // if
+  if (p->stack_top >= p->stack_size) {
+    __kmp_expand_cons_stack(gtid, p);
+  }; // if
+  if (p->w_top > p->p_top &&
+      !(IS_CONS_TYPE_TASKQ(p->stack_data[p->w_top].type) &&
+        IS_CONS_TYPE_TASKQ(ct))) {
+    // We are already in a WORKSHARE construct for this PARALLEL region.
+    __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                           &p->stack_data[p->w_top]);
+  }; // if
+  if (p->s_top > p->p_top) {
+    // We are already in a SYNC construct for this PARALLEL region.
+    __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                           &p->stack_data[p->s_top]);
+  }; // if
 }
 
-void
-__kmp_push_workshare( int gtid, enum cons_type ct, ident_t const * ident )
-{
-    int         tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
-    KE_TRACE( 10, ("__kmp_push_workshare (%d %d)\n", gtid, __kmp_get_gtid() ) );
-    __kmp_check_workshare( gtid, ct, ident );
-    KE_TRACE( 100, ( PUSH_MSG( ct, ident ) ) );
-    tos = ++p->stack_top;
-    p->stack_data[ tos ].type = ct;
-    p->stack_data[ tos ].prev = p->w_top;
-    p->stack_data[ tos ].ident = ident;
-    p->stack_data[ tos ].name = NULL;
-    p->w_top = tos;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
+void __kmp_push_workshare(int gtid, enum cons_type ct, ident_t const *ident) {
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
+  KE_TRACE(10, ("__kmp_push_workshare (%d %d)\n", gtid, __kmp_get_gtid()));
+  __kmp_check_workshare(gtid, ct, ident);
+  KE_TRACE(100, (PUSH_MSG(ct, ident)));
+  tos = ++p->stack_top;
+  p->stack_data[tos].type = ct;
+  p->stack_data[tos].prev = p->w_top;
+  p->stack_data[tos].ident = ident;
+  p->stack_data[tos].name = NULL;
+  p->w_top = tos;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
 }
 
 void
@@ -276,98 +254,91 @@ __kmp_check_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_l
 __kmp_check_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p lck )
 #endif
 {
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
 
-    KE_TRACE( 10, ("__kmp_check_sync (gtid=%d)\n", __kmp_get_gtid() ) );
+  KE_TRACE(10, ("__kmp_check_sync (gtid=%d)\n", __kmp_get_gtid()));
 
-    if (p->stack_top >= p->stack_size)
-       __kmp_expand_cons_stack( gtid, p );
+  if (p->stack_top >= p->stack_size)
+    __kmp_expand_cons_stack(gtid, p);
 
-    if (ct == ct_ordered_in_parallel || ct == ct_ordered_in_pdo || ct == ct_ordered_in_taskq ) {
-        if (p->w_top <= p->p_top) {
-            /* we are not in a worksharing construct */
-            #ifdef BUILD_PARALLEL_ORDERED
-                /* do not report error messages for PARALLEL ORDERED */
-                KMP_ASSERT( ct == ct_ordered_in_parallel );
-            #else
-                __kmp_error_construct( kmp_i18n_msg_CnsBoundToWorksharing, ct, ident );
-            #endif /* BUILD_PARALLEL_ORDERED */
-        } else {
-            /* inside a WORKSHARING construct for this PARALLEL region */
-            if (!IS_CONS_TYPE_ORDERED(p->stack_data[ p->w_top ].type)) {
-                if (p->stack_data[ p->w_top ].type == ct_taskq) {
-                    __kmp_error_construct2(
-                        kmp_i18n_msg_CnsNotInTaskConstruct,
-                        ct, ident,
-                        & p->stack_data[ p->w_top ]
-                    );
-                } else {
-                    __kmp_error_construct2(
-                        kmp_i18n_msg_CnsNoOrderedClause,
-                        ct, ident,
-                        & p->stack_data[ p->w_top ]
-                    );
-               }
-            }
-        }
-        if (p->s_top > p->p_top && p->s_top > p->w_top) {
-            /* inside a sync construct which is inside a worksharing construct */
-            int index = p->s_top;
-            enum cons_type stack_type;
-
-            stack_type = p->stack_data[ index ].type;
-
-            if (stack_type == ct_critical ||
-                ( ( stack_type == ct_ordered_in_parallel ||
-                    stack_type == ct_ordered_in_pdo      ||
-                    stack_type == ct_ordered_in_taskq  ) &&     /* C doesn't allow named ordered; ordered in ordered gets error */
-                 p->stack_data[ index ].ident != NULL &&
-                 (p->stack_data[ index ].ident->flags & KMP_IDENT_KMPC ))) {
-                /* we are in ORDERED which is inside an ORDERED or CRITICAL construct */
-                __kmp_error_construct2(
-                    kmp_i18n_msg_CnsInvalidNesting,
-                    ct, ident,
-                    & p->stack_data[ index ]
-                );
-            }
-        }
-    } else if ( ct == ct_critical ) {
-#if KMP_USE_DYNAMIC_LOCK
-        if ( lck != NULL && __kmp_get_user_lock_owner( lck, seq ) == gtid ) {    /* this same thread already has lock for this critical section */
+  if (ct == ct_ordered_in_parallel || ct == ct_ordered_in_pdo ||
+      ct == ct_ordered_in_taskq) {
+    if (p->w_top <= p->p_top) {
+/* we are not in a worksharing construct */
+#ifdef BUILD_PARALLEL_ORDERED
+      /* do not report error messages for PARALLEL ORDERED */
+      KMP_ASSERT(ct == ct_ordered_in_parallel);
 #else
-        if ( lck != NULL && __kmp_get_user_lock_owner( lck ) == gtid ) {    /* this same thread already has lock for this critical section */
+      __kmp_error_construct(kmp_i18n_msg_CnsBoundToWorksharing, ct, ident);
+#endif /* BUILD_PARALLEL_ORDERED */
+    } else {
+      /* inside a WORKSHARING construct for this PARALLEL region */
+      if (!IS_CONS_TYPE_ORDERED(p->stack_data[p->w_top].type)) {
+        if (p->stack_data[p->w_top].type == ct_taskq) {
+          __kmp_error_construct2(kmp_i18n_msg_CnsNotInTaskConstruct, ct, ident,
+                                 &p->stack_data[p->w_top]);
+        } else {
+          __kmp_error_construct2(kmp_i18n_msg_CnsNoOrderedClause, ct, ident,
+                                 &p->stack_data[p->w_top]);
+        }
+      }
+    }
+    if (p->s_top > p->p_top && p->s_top > p->w_top) {
+      /* inside a sync construct which is inside a worksharing construct */
+      int index = p->s_top;
+      enum cons_type stack_type;
+
+      stack_type = p->stack_data[index].type;
+
+      if (stack_type == ct_critical ||
+          ((stack_type == ct_ordered_in_parallel ||
+            stack_type == ct_ordered_in_pdo ||
+            stack_type ==
+                ct_ordered_in_taskq) && /* C doesn't allow named ordered;
+                                           ordered in ordered gets error */
+           p->stack_data[index].ident != NULL &&
+           (p->stack_data[index].ident->flags & KMP_IDENT_KMPC))) {
+        /* we are in ORDERED which is inside an ORDERED or CRITICAL construct */
+        __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                               &p->stack_data[index]);
+      }
+    }
+  } else if (ct == ct_critical) {
+#if KMP_USE_DYNAMIC_LOCK
+    if (lck != NULL &&
+        __kmp_get_user_lock_owner(lck, seq) ==
+            gtid) { /* this thread already has lock for this critical section */
+#else
+    if (lck != NULL &&
+        __kmp_get_user_lock_owner(lck) ==
+            gtid) { /* this thread already has lock for this critical section */
 #endif
-            int index = p->s_top;
-            struct cons_data cons = { NULL, ct_critical, 0, NULL };
-            /* walk up construct stack and try to find critical with matching name */
-            while ( index != 0 && p->stack_data[ index ].name != lck ) {
-                index = p->stack_data[ index ].prev;
-            }
-            if ( index != 0 ) {
-                /* found match on the stack (may not always because of interleaved critical for Fortran) */
-                cons = p->stack_data[ index ];
-            }
-            /* we are in CRITICAL which is inside a CRITICAL construct of the same name */
-            __kmp_error_construct2( kmp_i18n_msg_CnsNestingSameName, ct, ident, & cons );
-        }
-    } else if ( ct == ct_master || ct == ct_reduce ) {
-        if (p->w_top > p->p_top) {
-            /* inside a WORKSHARING construct for this PARALLEL region */
-           __kmp_error_construct2(
-               kmp_i18n_msg_CnsInvalidNesting,
-               ct, ident,
-               & p->stack_data[ p->w_top ]
-           );
-        }
-        if (ct == ct_reduce && p->s_top > p->p_top) {
-            /* inside a another SYNC construct for this PARALLEL region */
-            __kmp_error_construct2(
-                kmp_i18n_msg_CnsInvalidNesting,
-                ct, ident,
-                & p->stack_data[ p->s_top ]
-            );
-        }; // if
+      int index = p->s_top;
+      struct cons_data cons = {NULL, ct_critical, 0, NULL};
+      /* walk up construct stack and try to find critical with matching name */
+      while (index != 0 && p->stack_data[index].name != lck) {
+        index = p->stack_data[index].prev;
+      }
+      if (index != 0) {
+        /* found match on the stack (may not always because of interleaved
+         * critical for Fortran) */
+        cons = p->stack_data[index];
+      }
+      /* we are in CRITICAL which is inside a CRITICAL construct of same name */
+      __kmp_error_construct2(kmp_i18n_msg_CnsNestingSameName, ct, ident, &cons);
+    }
+  } else if (ct == ct_master || ct == ct_reduce) {
+    if (p->w_top > p->p_top) {
+      /* inside a WORKSHARING construct for this PARALLEL region */
+      __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                             &p->stack_data[p->w_top]);
+    }
+    if (ct == ct_reduce && p->s_top > p->p_top) {
+      /* inside a another SYNC construct for this PARALLEL region */
+      __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                             &p->stack_data[p->s_top]);
     }; // if
+  }; // if
 }
 
 void
@@ -377,147 +348,118 @@ __kmp_push_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lo
 __kmp_push_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p lck )
 #endif
 {
-    int         tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
 
-    KMP_ASSERT( gtid == __kmp_get_gtid() );
-    KE_TRACE( 10, ("__kmp_push_sync (gtid=%d)\n", gtid ) );
+  KMP_ASSERT(gtid == __kmp_get_gtid());
+  KE_TRACE(10, ("__kmp_push_sync (gtid=%d)\n", gtid));
 #if KMP_USE_DYNAMIC_LOCK
-    __kmp_check_sync( gtid, ct, ident, lck, seq );
+  __kmp_check_sync(gtid, ct, ident, lck, seq);
 #else
-    __kmp_check_sync( gtid, ct, ident, lck );
+  __kmp_check_sync(gtid, ct, ident, lck);
 #endif
-    KE_TRACE( 100, ( PUSH_MSG( ct, ident ) ) );
-    tos = ++ p->stack_top;
-    p->stack_data[ tos ].type  = ct;
-    p->stack_data[ tos ].prev  = p->s_top;
-    p->stack_data[ tos ].ident = ident;
-    p->stack_data[ tos ].name  = lck;
-    p->s_top = tos;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
+  KE_TRACE(100, (PUSH_MSG(ct, ident)));
+  tos = ++p->stack_top;
+  p->stack_data[tos].type = ct;
+  p->stack_data[tos].prev = p->s_top;
+  p->stack_data[tos].ident = ident;
+  p->stack_data[tos].name = lck;
+  p->s_top = tos;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
 }
 
 /* ------------------------------------------------------------------------ */
 
-void
-__kmp_pop_parallel( int gtid, ident_t const * ident )
-{
-    int tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
-    tos = p->stack_top;
-    KE_TRACE( 10, ("__kmp_pop_parallel (%d %d)\n", gtid, __kmp_get_gtid() ) );
-    if ( tos == 0 || p->p_top == 0 ) {
-        __kmp_error_construct( kmp_i18n_msg_CnsDetectedEnd, ct_parallel, ident );
-    }
-    if ( tos != p->p_top || p->stack_data[ tos ].type != ct_parallel ) {
-        __kmp_error_construct2(
-            kmp_i18n_msg_CnsExpectedEnd,
-            ct_parallel, ident,
-            & p->stack_data[ tos ]
-        );
-    }
-    KE_TRACE( 100, ( POP_MSG( p ) ) );
-    p->p_top = p->stack_data[ tos ].prev;
-    p->stack_data[ tos ].type = ct_none;
-    p->stack_data[ tos ].ident = NULL;
-    p->stack_top = tos - 1;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
+void __kmp_pop_parallel(int gtid, ident_t const *ident) {
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
+  tos = p->stack_top;
+  KE_TRACE(10, ("__kmp_pop_parallel (%d %d)\n", gtid, __kmp_get_gtid()));
+  if (tos == 0 || p->p_top == 0) {
+    __kmp_error_construct(kmp_i18n_msg_CnsDetectedEnd, ct_parallel, ident);
+  }
+  if (tos != p->p_top || p->stack_data[tos].type != ct_parallel) {
+    __kmp_error_construct2(kmp_i18n_msg_CnsExpectedEnd, ct_parallel, ident,
+                           &p->stack_data[tos]);
+  }
+  KE_TRACE(100, (POP_MSG(p)));
+  p->p_top = p->stack_data[tos].prev;
+  p->stack_data[tos].type = ct_none;
+  p->stack_data[tos].ident = NULL;
+  p->stack_top = tos - 1;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
 }
 
-enum cons_type
-__kmp_pop_workshare( int gtid, enum cons_type ct, ident_t const * ident )
-{
-    int tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
+enum cons_type __kmp_pop_workshare(int gtid, enum cons_type ct,
+                                   ident_t const *ident) {
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
 
-    tos = p->stack_top;
-    KE_TRACE( 10, ("__kmp_pop_workshare (%d %d)\n", gtid, __kmp_get_gtid() ) );
-    if ( tos == 0 || p->w_top == 0 ) {
-        __kmp_error_construct( kmp_i18n_msg_CnsDetectedEnd, ct, ident );
-    }
+  tos = p->stack_top;
+  KE_TRACE(10, ("__kmp_pop_workshare (%d %d)\n", gtid, __kmp_get_gtid()));
+  if (tos == 0 || p->w_top == 0) {
+    __kmp_error_construct(kmp_i18n_msg_CnsDetectedEnd, ct, ident);
+  }
 
-    if ( tos != p->w_top ||
-         ( p->stack_data[ tos ].type != ct &&
-          /* below are two exceptions to the rule that construct types must match */
-          ! ( p->stack_data[ tos ].type == ct_pdo_ordered && ct == ct_pdo ) &&
-          ! ( p->stack_data[ tos ].type == ct_task_ordered && ct == ct_task )
-         )
-       ) {
-        __kmp_check_null_func();
-        __kmp_error_construct2(
-            kmp_i18n_msg_CnsExpectedEnd,
-            ct, ident,
-            & p->stack_data[ tos ]
-        );
-    }
-    KE_TRACE( 100, ( POP_MSG( p ) ) );
-    p->w_top = p->stack_data[ tos ].prev;
-    p->stack_data[ tos ].type = ct_none;
-    p->stack_data[ tos ].ident = NULL;
-    p->stack_top = tos - 1;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
-    return p->stack_data[ p->w_top ].type;
+  if (tos != p->w_top ||
+      (p->stack_data[tos].type != ct &&
+       // below are two exceptions to the rule that construct types must match
+       !(p->stack_data[tos].type == ct_pdo_ordered && ct == ct_pdo) &&
+       !(p->stack_data[tos].type == ct_task_ordered && ct == ct_task))) {
+    __kmp_check_null_func();
+    __kmp_error_construct2(kmp_i18n_msg_CnsExpectedEnd, ct, ident,
+                           &p->stack_data[tos]);
+  }
+  KE_TRACE(100, (POP_MSG(p)));
+  p->w_top = p->stack_data[tos].prev;
+  p->stack_data[tos].type = ct_none;
+  p->stack_data[tos].ident = NULL;
+  p->stack_top = tos - 1;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
+  return p->stack_data[p->w_top].type;
 }
 
-void
-__kmp_pop_sync( int gtid, enum cons_type ct, ident_t const * ident )
-{
-    int tos;
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
-    tos = p->stack_top;
-    KE_TRACE( 10, ("__kmp_pop_sync (%d %d)\n", gtid, __kmp_get_gtid() ) );
-    if ( tos == 0 || p->s_top == 0 ) {
-        __kmp_error_construct( kmp_i18n_msg_CnsDetectedEnd, ct, ident );
-    };
-    if ( tos != p->s_top || p->stack_data[ tos ].type != ct ) {
-        __kmp_check_null_func();
-        __kmp_error_construct2(
-            kmp_i18n_msg_CnsExpectedEnd,
-            ct, ident,
-            & p->stack_data[ tos ]
-        );
-    };
-    if ( gtid < 0 ) {
-        __kmp_check_null_func();
-    };
-    KE_TRACE( 100, ( POP_MSG( p ) ) );
-    p->s_top = p->stack_data[ tos ].prev;
-    p->stack_data[ tos ].type = ct_none;
-    p->stack_data[ tos ].ident = NULL;
-    p->stack_top = tos - 1;
-    KE_DUMP( 1000, dump_cons_stack( gtid, p ) );
+void __kmp_pop_sync(int gtid, enum cons_type ct, ident_t const *ident) {
+  int tos;
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
+  tos = p->stack_top;
+  KE_TRACE(10, ("__kmp_pop_sync (%d %d)\n", gtid, __kmp_get_gtid()));
+  if (tos == 0 || p->s_top == 0) {
+    __kmp_error_construct(kmp_i18n_msg_CnsDetectedEnd, ct, ident);
+  };
+  if (tos != p->s_top || p->stack_data[tos].type != ct) {
+    __kmp_check_null_func();
+    __kmp_error_construct2(kmp_i18n_msg_CnsExpectedEnd, ct, ident,
+                           &p->stack_data[tos]);
+  };
+  if (gtid < 0) {
+    __kmp_check_null_func();
+  };
+  KE_TRACE(100, (POP_MSG(p)));
+  p->s_top = p->stack_data[tos].prev;
+  p->stack_data[tos].type = ct_none;
+  p->stack_data[tos].ident = NULL;
+  p->stack_top = tos - 1;
+  KE_DUMP(1000, dump_cons_stack(gtid, p));
 }
 
 /* ------------------------------------------------------------------------ */
 
-void
-__kmp_check_barrier( int gtid, enum cons_type ct, ident_t const * ident )
-{
-    struct cons_header *p = __kmp_threads[ gtid ]->th.th_cons;
-    KE_TRACE( 10, ("__kmp_check_barrier (loc: %p, gtid: %d %d)\n", ident, gtid, __kmp_get_gtid() ) );
-    if ( ident != 0 ) {
-        __kmp_check_null_func();
-    }
-    if ( p->w_top > p->p_top ) {
-        /* we are already in a WORKSHARING construct for this PARALLEL region */
-        __kmp_error_construct2(
-            kmp_i18n_msg_CnsInvalidNesting,
-            ct, ident,
-            & p->stack_data[ p->w_top ]
-        );
-    }
-    if (p->s_top > p->p_top) {
-        /* we are already in a SYNC construct for this PARALLEL region */
-        __kmp_error_construct2(
-            kmp_i18n_msg_CnsInvalidNesting,
-            ct, ident,
-            & p->stack_data[ p->s_top ]
-        );
-    }
+void __kmp_check_barrier(int gtid, enum cons_type ct, ident_t const *ident) {
+  struct cons_header *p = __kmp_threads[gtid]->th.th_cons;
+  KE_TRACE(10, ("__kmp_check_barrier (loc: %p, gtid: %d %d)\n", ident, gtid,
+                __kmp_get_gtid()));
+  if (ident != 0) {
+    __kmp_check_null_func();
+  }
+  if (p->w_top > p->p_top) {
+    /* we are already in a WORKSHARING construct for this PARALLEL region */
+    __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                           &p->stack_data[p->w_top]);
+  }
+  if (p->s_top > p->p_top) {
+    /* we are already in a SYNC construct for this PARALLEL region */
+    __kmp_error_construct2(kmp_i18n_msg_CnsInvalidNesting, ct, ident,
+                           &p->stack_data[p->s_top]);
+  }
 }
-
-/* ------------------------------------------------------------------------ */
-
-
-/* ------------------------------------------------------------------------ */
-/* ------------------------------------------------------------------------ */

runtime/src/kmp_error.h

@@ -20,38 +20,44 @@
 
 /* ------------------------------------------------------------------------ */
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif
 
-void __kmp_error_construct(  kmp_i18n_id_t id, enum cons_type ct, ident_t const * ident );
-void __kmp_error_construct2( kmp_i18n_id_t id, enum cons_type ct, ident_t const * ident, struct cons_data const * cons );
+void __kmp_error_construct(kmp_i18n_id_t id, enum cons_type ct,
+                           ident_t const *ident);
+void __kmp_error_construct2(kmp_i18n_id_t id, enum cons_type ct,
+                            ident_t const *ident, struct cons_data const *cons);
 
-struct cons_header * __kmp_allocate_cons_stack( int gtid );
-void                 __kmp_free_cons_stack( void * ptr );
+struct cons_header *__kmp_allocate_cons_stack(int gtid);
+void __kmp_free_cons_stack(void *ptr);
 
-void __kmp_push_parallel( int gtid, ident_t const * ident );
-void __kmp_push_workshare( int gtid, enum cons_type ct, ident_t const * ident );
+void __kmp_push_parallel(int gtid, ident_t const *ident);
+void __kmp_push_workshare(int gtid, enum cons_type ct, ident_t const *ident);
 #if KMP_USE_DYNAMIC_LOCK
-void __kmp_push_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p name, kmp_uint32 );
+void __kmp_push_sync(int gtid, enum cons_type ct, ident_t const *ident,
+                     kmp_user_lock_p name, kmp_uint32);
 #else
-void __kmp_push_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p name );
+void __kmp_push_sync(int gtid, enum cons_type ct, ident_t const *ident,
+                     kmp_user_lock_p name);
 #endif
 
-void __kmp_check_workshare( int gtid, enum cons_type ct, ident_t const * ident );
+void __kmp_check_workshare(int gtid, enum cons_type ct, ident_t const *ident);
 #if KMP_USE_DYNAMIC_LOCK
-void __kmp_check_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p name, kmp_uint32 );
+void __kmp_check_sync(int gtid, enum cons_type ct, ident_t const *ident,
+                      kmp_user_lock_p name, kmp_uint32);
 #else
-void __kmp_check_sync( int gtid, enum cons_type ct, ident_t const * ident, kmp_user_lock_p name );
+void __kmp_check_sync(int gtid, enum cons_type ct, ident_t const *ident,
+                      kmp_user_lock_p name);
 #endif
 
-void __kmp_pop_parallel( int gtid, ident_t const * ident );
-enum cons_type __kmp_pop_workshare( int gtid, enum cons_type ct, ident_t const * ident );
-void __kmp_pop_sync( int gtid, enum cons_type ct, ident_t const * ident );
-void __kmp_check_barrier( int gtid, enum cons_type ct, ident_t const * ident );
+void __kmp_pop_parallel(int gtid, ident_t const *ident);
+enum cons_type __kmp_pop_workshare(int gtid, enum cons_type ct,
+                                   ident_t const *ident);
+void __kmp_pop_sync(int gtid, enum cons_type ct, ident_t const *ident);
+void __kmp_check_barrier(int gtid, enum cons_type ct, ident_t const *ident);
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif
 
 #endif // KMP_ERROR_H
-

runtime/src/kmp_ftn_cdecl.cpp

@@ -17,20 +17,21 @@
 #include "kmp_affinity.h"
 
 #if KMP_OS_WINDOWS
-#   if defined  KMP_WIN_CDECL ||  !defined KMP_DYNAMIC_LIB
-#       define KMP_FTN_ENTRIES      KMP_FTN_UPPER
-#   endif
+#if defined KMP_WIN_CDECL || !defined KMP_DYNAMIC_LIB
+#define KMP_FTN_ENTRIES KMP_FTN_UPPER
+#endif
 #elif KMP_OS_UNIX
-#   define KMP_FTN_ENTRIES  KMP_FTN_PLAIN
+#define KMP_FTN_ENTRIES KMP_FTN_PLAIN
 #endif
 
 // Note: This string is not printed when KMP_VERSION=1.
-char const __kmp_version_ftncdecl[] = KMP_VERSION_PREFIX "Fortran __cdecl OMP support: "
+char const __kmp_version_ftncdecl[] =
+    KMP_VERSION_PREFIX "Fortran __cdecl OMP support: "
 #ifdef KMP_FTN_ENTRIES
-    "yes";
-#   define FTN_STDCALL 	/* no stdcall */
-#   include "kmp_ftn_os.h"
-#   include "kmp_ftn_entry.h"
+                       "yes";
+#define FTN_STDCALL /* no stdcall */
+#include "kmp_ftn_os.h"
+#include "kmp_ftn_entry.h"
 #else
-    "no";
+                       "no";
 #endif /* KMP_FTN_ENTRIES */

runtime/src/kmp_ftn_extra.cpp

@@ -17,18 +17,19 @@
 #include "kmp_affinity.h"
 
 #if KMP_OS_WINDOWS
-#   define KMP_FTN_ENTRIES KMP_FTN_PLAIN
+#define KMP_FTN_ENTRIES KMP_FTN_PLAIN
 #elif KMP_OS_UNIX
-#   define KMP_FTN_ENTRIES KMP_FTN_APPEND
+#define KMP_FTN_ENTRIES KMP_FTN_APPEND
 #endif
 
 // Note: This string is not printed when KMP_VERSION=1.
-char const __kmp_version_ftnextra[] = KMP_VERSION_PREFIX "Fortran \"extra\" OMP support: "
+char const __kmp_version_ftnextra[] =
+    KMP_VERSION_PREFIX "Fortran \"extra\" OMP support: "
 #ifdef KMP_FTN_ENTRIES
-    "yes";
-#   define FTN_STDCALL /* nothing to do */
-#   include "kmp_ftn_os.h"
-#   include "kmp_ftn_entry.h"
+                       "yes";
+#define FTN_STDCALL /* nothing to do */
+#include "kmp_ftn_os.h"
+#include "kmp_ftn_entry.h"
 #else
-    "no";
+                       "no";
 #endif /* KMP_FTN_ENTRIES */

runtime/src/kmp_ftn_stdcall.cpp

@@ -16,20 +16,20 @@
 #include "kmp.h"
 
 // Note: This string is not printed when KMP_VERSION=1.
-char const __kmp_version_ftnstdcall[] = KMP_VERSION_PREFIX "Fortran __stdcall OMP support: "
+char const __kmp_version_ftnstdcall[] =
+    KMP_VERSION_PREFIX "Fortran __stdcall OMP support: "
 #ifdef USE_FTN_STDCALL
-    "yes";
+                       "yes";
 #else
-    "no";
+                       "no";
 #endif
 
 #ifdef USE_FTN_STDCALL
 
-#define FTN_STDCALL 	KMP_STDCALL
-#define KMP_FTN_ENTRIES	USE_FTN_STDCALL
+#define FTN_STDCALL KMP_STDCALL
+#define KMP_FTN_ENTRIES USE_FTN_STDCALL
 
-#include "kmp_ftn_os.h"
 #include "kmp_ftn_entry.h"
+#include "kmp_ftn_os.h"
 
 #endif /* USE_FTN_STDCALL */
-

runtime/src/kmp_global.cpp

@@ -19,7 +19,7 @@
 kmp_key_t __kmp_gtid_threadprivate_key;
 
 #if KMP_ARCH_X86 || KMP_ARCH_X86_64
-kmp_cpuinfo_t   __kmp_cpuinfo = { 0 }; // Not initialized
+kmp_cpuinfo_t __kmp_cpuinfo = {0}; // Not initialized
 #endif
 
 #if KMP_STATS_ENABLED
@@ -27,11 +27,12 @@ kmp_cpuinfo_t   __kmp_cpuinfo = { 0 }; // Not initialized
 // lock for modifying the global __kmp_stats_list
 kmp_tas_lock_t __kmp_stats_lock;
 
-// global list of per thread stats, the head is a sentinel node which accumulates all stats produced before __kmp_create_worker is called.
-kmp_stats_list* __kmp_stats_list;
+// global list of per thread stats, the head is a sentinel node which
+// accumulates all stats produced before __kmp_create_worker is called.
+kmp_stats_list *__kmp_stats_list;
 
 // thread local pointer to stats node within list
-__thread kmp_stats_list* __kmp_stats_thread_ptr = NULL;
+__thread kmp_stats_list *__kmp_stats_thread_ptr = NULL;
 
 // gives reference tick for all events (considered the 0 tick)
 tsc_tick_count __kmp_stats_start_time;
@@ -40,176 +41,196 @@ tsc_tick_count __kmp_stats_start_time;
 /* ----------------------------------------------------- */
 /* INITIALIZATION VARIABLES */
 /* they are syncronized to write during init, but read anytime */
-volatile int        __kmp_init_serial     = FALSE;
-volatile int        __kmp_init_gtid       = FALSE;
-volatile int        __kmp_init_common     = FALSE;
-volatile int        __kmp_init_middle     = FALSE;
-volatile int        __kmp_init_parallel   = FALSE;
+volatile int __kmp_init_serial = FALSE;
+volatile int __kmp_init_gtid = FALSE;
+volatile int __kmp_init_common = FALSE;
+volatile int __kmp_init_middle = FALSE;
+volatile int __kmp_init_parallel = FALSE;
 #if KMP_USE_MONITOR
-volatile int        __kmp_init_monitor    = 0;  /* 1 - launched, 2 - actually started (Windows* OS only) */
+volatile int __kmp_init_monitor =
+    0; /* 1 - launched, 2 - actually started (Windows* OS only) */
 #endif
-volatile int        __kmp_init_user_locks = FALSE;
+volatile int __kmp_init_user_locks = FALSE;
 
 /* list of address of allocated caches for commons */
-kmp_cached_addr_t  *__kmp_threadpriv_cache_list = NULL;
+kmp_cached_addr_t *__kmp_threadpriv_cache_list = NULL;
 
-int                 __kmp_init_counter  = 0;
-int                 __kmp_root_counter  = 0;
-int                 __kmp_version       = 0;
+int __kmp_init_counter = 0;
+int __kmp_root_counter = 0;
+int __kmp_version = 0;
 
-volatile kmp_uint32 __kmp_team_counter  = 0;
-volatile kmp_uint32 __kmp_task_counter  = 0;
+volatile kmp_uint32 __kmp_team_counter = 0;
+volatile kmp_uint32 __kmp_task_counter = 0;
 
-unsigned int __kmp_init_wait = KMP_DEFAULT_INIT_WAIT;   /* initial number of spin-tests   */
-unsigned int __kmp_next_wait = KMP_DEFAULT_NEXT_WAIT;   /* susequent number of spin-tests */
+unsigned int __kmp_init_wait =
+    KMP_DEFAULT_INIT_WAIT; /* initial number of spin-tests   */
+unsigned int __kmp_next_wait =
+    KMP_DEFAULT_NEXT_WAIT; /* susequent number of spin-tests */
 
-size_t      __kmp_stksize         = KMP_DEFAULT_STKSIZE;
+size_t __kmp_stksize = KMP_DEFAULT_STKSIZE;
 #if KMP_USE_MONITOR
-size_t      __kmp_monitor_stksize = 0;  // auto adjust
+size_t __kmp_monitor_stksize = 0; // auto adjust
 #endif
-size_t      __kmp_stkoffset       = KMP_DEFAULT_STKOFFSET;
-int         __kmp_stkpadding      = KMP_MIN_STKPADDING;
+size_t __kmp_stkoffset = KMP_DEFAULT_STKOFFSET;
+int __kmp_stkpadding = KMP_MIN_STKPADDING;
 
-size_t    __kmp_malloc_pool_incr  = KMP_DEFAULT_MALLOC_POOL_INCR;
+size_t __kmp_malloc_pool_incr = KMP_DEFAULT_MALLOC_POOL_INCR;
 
-/* Barrier method defaults, settings, and strings */
-/* branch factor = 2^branch_bits (only relevant for tree and hyper barrier types) */
+// Barrier method defaults, settings, and strings.
+// branch factor = 2^branch_bits (only relevant for tree & hyper barrier types)
 #if KMP_ARCH_X86_64
-kmp_uint32 __kmp_barrier_gather_bb_dflt      = 2;  /* branch_factor = 4 */ /* hyper2: C78980 */
-kmp_uint32 __kmp_barrier_release_bb_dflt     = 2;  /* branch_factor = 4 */ /* hyper2: C78980 */
+kmp_uint32 __kmp_barrier_gather_bb_dflt = 2;
+/* branch_factor = 4 */ /* hyper2: C78980 */
+kmp_uint32 __kmp_barrier_release_bb_dflt = 2;
+/* branch_factor = 4 */ /* hyper2: C78980 */
 #else
-kmp_uint32 __kmp_barrier_gather_bb_dflt      = 2;  /* branch_factor = 4 */ /* communication in core for MIC */
-kmp_uint32 __kmp_barrier_release_bb_dflt     = 2;  /* branch_factor = 4 */ /* communication in core for MIC */
+kmp_uint32 __kmp_barrier_gather_bb_dflt = 2;
+/* branch_factor = 4 */ /* communication in core for MIC */
+kmp_uint32 __kmp_barrier_release_bb_dflt = 2;
+/* branch_factor = 4 */ /* communication in core for MIC */
 #endif // KMP_ARCH_X86_64
 #if KMP_ARCH_X86_64
-kmp_bar_pat_e __kmp_barrier_gather_pat_dflt  = bp_hyper_bar;  /* hyper2: C78980 */
-kmp_bar_pat_e __kmp_barrier_release_pat_dflt = bp_hyper_bar;  /* hyper2: C78980 */
+kmp_bar_pat_e __kmp_barrier_gather_pat_dflt = bp_hyper_bar; /* hyper2: C78980 */
+kmp_bar_pat_e __kmp_barrier_release_pat_dflt =
+    bp_hyper_bar; /* hyper2: C78980 */
 #else
-kmp_bar_pat_e __kmp_barrier_gather_pat_dflt  = bp_linear_bar;
+kmp_bar_pat_e __kmp_barrier_gather_pat_dflt = bp_linear_bar;
 kmp_bar_pat_e __kmp_barrier_release_pat_dflt = bp_linear_bar;
 #endif
-kmp_uint32 __kmp_barrier_gather_branch_bits  [ bs_last_barrier ] = { 0 };
-kmp_uint32 __kmp_barrier_release_branch_bits [ bs_last_barrier ] = { 0 };
-kmp_bar_pat_e __kmp_barrier_gather_pattern   [ bs_last_barrier ] = { bp_linear_bar };
-kmp_bar_pat_e __kmp_barrier_release_pattern  [ bs_last_barrier ] = { bp_linear_bar };
-char const *__kmp_barrier_branch_bit_env_name [ bs_last_barrier ] =
-                            { "KMP_PLAIN_BARRIER", "KMP_FORKJOIN_BARRIER"
-                                #if KMP_FAST_REDUCTION_BARRIER
-                                    , "KMP_REDUCTION_BARRIER"
-                                #endif // KMP_FAST_REDUCTION_BARRIER
-                            };
-char const *__kmp_barrier_pattern_env_name    [ bs_last_barrier ] =
-                            { "KMP_PLAIN_BARRIER_PATTERN", "KMP_FORKJOIN_BARRIER_PATTERN"
-                                #if KMP_FAST_REDUCTION_BARRIER
-                                    , "KMP_REDUCTION_BARRIER_PATTERN"
-                                #endif // KMP_FAST_REDUCTION_BARRIER
-                            };
-char const *__kmp_barrier_type_name           [ bs_last_barrier ] =
-                            { "plain", "forkjoin"
-                                #if KMP_FAST_REDUCTION_BARRIER
-                                    , "reduction"
-                                #endif // KMP_FAST_REDUCTION_BARRIER
-                            };
-char const *__kmp_barrier_pattern_name[bp_last_bar] = {"linear","tree","hyper","hierarchical"};
+kmp_uint32 __kmp_barrier_gather_branch_bits[bs_last_barrier] = {0};
+kmp_uint32 __kmp_barrier_release_branch_bits[bs_last_barrier] = {0};
+kmp_bar_pat_e __kmp_barrier_gather_pattern[bs_last_barrier] = {bp_linear_bar};
+kmp_bar_pat_e __kmp_barrier_release_pattern[bs_last_barrier] = {bp_linear_bar};
+char const *__kmp_barrier_branch_bit_env_name[bs_last_barrier] = {
+    "KMP_PLAIN_BARRIER", "KMP_FORKJOIN_BARRIER"
+#if KMP_FAST_REDUCTION_BARRIER
+    ,
+    "KMP_REDUCTION_BARRIER"
+#endif // KMP_FAST_REDUCTION_BARRIER
+};
+char const *__kmp_barrier_pattern_env_name[bs_last_barrier] = {
+    "KMP_PLAIN_BARRIER_PATTERN", "KMP_FORKJOIN_BARRIER_PATTERN"
+#if KMP_FAST_REDUCTION_BARRIER
+    ,
+    "KMP_REDUCTION_BARRIER_PATTERN"
+#endif // KMP_FAST_REDUCTION_BARRIER
+};
+char const *__kmp_barrier_type_name[bs_last_barrier] = {"plain", "forkjoin"
+#if KMP_FAST_REDUCTION_BARRIER
+                                                        ,
+                                                        "reduction"
+#endif // KMP_FAST_REDUCTION_BARRIER
+};
+char const *__kmp_barrier_pattern_name[bp_last_bar] = {"linear", "tree",
+                                                       "hyper", "hierarchical"};
 
-int       __kmp_allThreadsSpecified = 0;
-size_t    __kmp_align_alloc = CACHE_LINE;
+int __kmp_allThreadsSpecified = 0;
+size_t __kmp_align_alloc = CACHE_LINE;
 
 
-int     __kmp_generate_warnings = kmp_warnings_low;
-int          __kmp_reserve_warn = 0;
-int                 __kmp_xproc = 0;
-int            __kmp_avail_proc = 0;
-size_t    __kmp_sys_min_stksize = KMP_MIN_STKSIZE;
-int           __kmp_sys_max_nth = KMP_MAX_NTH;
-int               __kmp_max_nth = 0;
-int      __kmp_threads_capacity = 0;
-int         __kmp_dflt_team_nth = 0;
-int      __kmp_dflt_team_nth_ub = 0;
-int           __kmp_tp_capacity = 0;
-int             __kmp_tp_cached = 0;
-int           __kmp_dflt_nested = FALSE;
-int  __kmp_dispatch_num_buffers = KMP_DFLT_DISP_NUM_BUFF;
-int __kmp_dflt_max_active_levels = KMP_MAX_ACTIVE_LEVELS_LIMIT; /* max_active_levels limit */
+int __kmp_generate_warnings = kmp_warnings_low;
+int __kmp_reserve_warn = 0;
+int __kmp_xproc = 0;
+int __kmp_avail_proc = 0;
+size_t __kmp_sys_min_stksize = KMP_MIN_STKSIZE;
+int __kmp_sys_max_nth = KMP_MAX_NTH;
+int __kmp_max_nth = 0;
+int __kmp_threads_capacity = 0;
+int __kmp_dflt_team_nth = 0;
+int __kmp_dflt_team_nth_ub = 0;
+int __kmp_tp_capacity = 0;
+int __kmp_tp_cached = 0;
+int __kmp_dflt_nested = FALSE;
+int __kmp_dispatch_num_buffers = KMP_DFLT_DISP_NUM_BUFF;
+int __kmp_dflt_max_active_levels =
+    KMP_MAX_ACTIVE_LEVELS_LIMIT; /* max_active_levels limit */
 #if KMP_NESTED_HOT_TEAMS
-int __kmp_hot_teams_mode         = 0; /* 0 - free extra threads when reduced */
-                                      /* 1 - keep extra threads when reduced */
-int __kmp_hot_teams_max_level    = 1; /* nesting level of hot teams */
+int __kmp_hot_teams_mode = 0; /* 0 - free extra threads when reduced */
+/* 1 - keep extra threads when reduced */
+int __kmp_hot_teams_max_level = 1; /* nesting level of hot teams */
 #endif
 enum library_type __kmp_library = library_none;
-enum sched_type     __kmp_sched = kmp_sch_default;  /* scheduling method for runtime scheduling */
-enum sched_type    __kmp_static = kmp_sch_static_greedy; /* default static scheduling method */
-enum sched_type    __kmp_guided = kmp_sch_guided_iterative_chunked; /* default guided scheduling method */
-enum sched_type      __kmp_auto = kmp_sch_guided_analytical_chunked; /* default auto scheduling method */
-int        __kmp_dflt_blocktime = KMP_DEFAULT_BLOCKTIME;
+enum sched_type __kmp_sched =
+    kmp_sch_default; /* scheduling method for runtime scheduling */
+enum sched_type __kmp_static =
+    kmp_sch_static_greedy; /* default static scheduling method */
+enum sched_type __kmp_guided =
+    kmp_sch_guided_iterative_chunked; /* default guided scheduling method */
+enum sched_type __kmp_auto =
+    kmp_sch_guided_analytical_chunked; /* default auto scheduling method */
+int __kmp_dflt_blocktime = KMP_DEFAULT_BLOCKTIME;
 #if KMP_USE_MONITOR
-int       __kmp_monitor_wakeups = KMP_MIN_MONITOR_WAKEUPS;
-int          __kmp_bt_intervals = KMP_INTERVALS_FROM_BLOCKTIME( KMP_DEFAULT_BLOCKTIME, KMP_MIN_MONITOR_WAKEUPS );
+int __kmp_monitor_wakeups = KMP_MIN_MONITOR_WAKEUPS;
+int __kmp_bt_intervals = KMP_INTERVALS_FROM_BLOCKTIME(KMP_DEFAULT_BLOCKTIME,
+                                                      KMP_MIN_MONITOR_WAKEUPS);
 #endif
 #ifdef KMP_ADJUST_BLOCKTIME
-int               __kmp_zero_bt = FALSE;
+int __kmp_zero_bt = FALSE;
 #endif /* KMP_ADJUST_BLOCKTIME */
 #ifdef KMP_DFLT_NTH_CORES
-int                __kmp_ncores = 0;
+int __kmp_ncores = 0;
 #endif
-int                 __kmp_chunk = 0;
-int           __kmp_abort_delay = 0;
+int __kmp_chunk = 0;
+int __kmp_abort_delay = 0;
 #if KMP_OS_LINUX && defined(KMP_TDATA_GTID)
-int             __kmp_gtid_mode = 3; /* use __declspec(thread) TLS to store gtid */
-int      __kmp_adjust_gtid_mode = FALSE;
+int __kmp_gtid_mode = 3; /* use __declspec(thread) TLS to store gtid */
+int __kmp_adjust_gtid_mode = FALSE;
 #elif KMP_OS_WINDOWS
-int             __kmp_gtid_mode = 2; /* use TLS functions to store gtid */
-int      __kmp_adjust_gtid_mode = FALSE;
+int __kmp_gtid_mode = 2; /* use TLS functions to store gtid */
+int __kmp_adjust_gtid_mode = FALSE;
 #else
-int             __kmp_gtid_mode = 0; /* select method to get gtid based on #threads */
-int      __kmp_adjust_gtid_mode = TRUE;
+int __kmp_gtid_mode = 0; /* select method to get gtid based on #threads */
+int __kmp_adjust_gtid_mode = TRUE;
 #endif /* KMP_OS_LINUX && defined(KMP_TDATA_GTID) */
 #ifdef KMP_TDATA_GTID
 #if KMP_OS_WINDOWS
 __declspec(thread) int __kmp_gtid = KMP_GTID_DNE;
 #else
 __thread int __kmp_gtid = KMP_GTID_DNE;
-#endif /* KMP_OS_WINDOWS - workaround because Intel(R) Many Integrated Core compiler 20110316 doesn't accept __declspec */
+#endif /* KMP_OS_WINDOWS - workaround because Intel(R) Many Integrated Core    \
+          compiler 20110316 doesn't accept __declspec */
 #endif /* KMP_TDATA_GTID */
-int          __kmp_tls_gtid_min = INT_MAX;
-int            __kmp_foreign_tp = TRUE;
+int __kmp_tls_gtid_min = INT_MAX;
+int __kmp_foreign_tp = TRUE;
 #if KMP_ARCH_X86 || KMP_ARCH_X86_64
-int    __kmp_inherit_fp_control = TRUE;
-kmp_int16  __kmp_init_x87_fpu_control_word = 0;
-kmp_uint32     __kmp_init_mxcsr = 0;
+int __kmp_inherit_fp_control = TRUE;
+kmp_int16 __kmp_init_x87_fpu_control_word = 0;
+kmp_uint32 __kmp_init_mxcsr = 0;
 #endif /* KMP_ARCH_X86 || KMP_ARCH_X86_64 */
 
 #ifdef USE_LOAD_BALANCE
-double  __kmp_load_balance_interval   = 1.0;
+double __kmp_load_balance_interval = 1.0;
 #endif /* USE_LOAD_BALANCE */
 
-kmp_nested_nthreads_t __kmp_nested_nth  = { NULL, 0, 0 };
+kmp_nested_nthreads_t __kmp_nested_nth = {NULL, 0, 0};
 
 #if KMP_USE_ADAPTIVE_LOCKS
 
-kmp_adaptive_backoff_params_t __kmp_adaptive_backoff_params = { 1, 1024 }; // TODO: tune it!
+kmp_adaptive_backoff_params_t __kmp_adaptive_backoff_params = {
+    1, 1024}; // TODO: tune it!
 
 #if KMP_DEBUG_ADAPTIVE_LOCKS
-char * __kmp_speculative_statsfile = "-";
+char *__kmp_speculative_statsfile = "-";
 #endif
 
 #endif // KMP_USE_ADAPTIVE_LOCKS
 
 #if OMP_40_ENABLED
-int __kmp_display_env           = FALSE;
-int __kmp_display_env_verbose   = FALSE;
-int __kmp_omp_cancellation      = FALSE;
+int __kmp_display_env = FALSE;
+int __kmp_display_env_verbose = FALSE;
+int __kmp_omp_cancellation = FALSE;
 #endif
 
 /* map OMP 3.0 schedule types with our internal schedule types */
-enum sched_type __kmp_sch_map[ kmp_sched_upper - kmp_sched_lower_ext + kmp_sched_upper_std - kmp_sched_lower - 2 ] = {
-    kmp_sch_static_chunked,     // ==> kmp_sched_static            = 1
-    kmp_sch_dynamic_chunked,    // ==> kmp_sched_dynamic           = 2
-    kmp_sch_guided_chunked,     // ==> kmp_sched_guided            = 3
-    kmp_sch_auto,               // ==> kmp_sched_auto              = 4
-    kmp_sch_trapezoidal         // ==> kmp_sched_trapezoidal       = 101
-                                // will likely not used, introduced here just to debug the code
-                                // of public intel extension schedules
+enum sched_type __kmp_sch_map[kmp_sched_upper - kmp_sched_lower_ext +
+                              kmp_sched_upper_std - kmp_sched_lower - 2] = {
+    kmp_sch_static_chunked, // ==> kmp_sched_static            = 1
+    kmp_sch_dynamic_chunked, // ==> kmp_sched_dynamic           = 2
+    kmp_sch_guided_chunked, // ==> kmp_sched_guided            = 3
+    kmp_sch_auto, // ==> kmp_sched_auto              = 4
+    kmp_sch_trapezoidal // ==> kmp_sched_trapezoidal       = 101
+    // will likely not be used, introduced here just to debug the code
+    // of public intel extension schedules
 };
 
 #if KMP_OS_LINUX
@@ -217,58 +238,61 @@ enum clock_function_type __kmp_clock_function;
 int __kmp_clock_function_param;
 #endif /* KMP_OS_LINUX */
 
-#if KMP_ARCH_X86_64 && (KMP_OS_LINUX || KMP_OS_WINDOWS)
+#if KMP_MIC_SUPPORTED
 enum mic_type __kmp_mic_type = non_mic;
 #endif
 
 #if KMP_AFFINITY_SUPPORTED
 
-KMPAffinity* __kmp_affinity_dispatch = NULL;
+KMPAffinity *__kmp_affinity_dispatch = NULL;
 
-# if KMP_USE_HWLOC
+#if KMP_USE_HWLOC
 int __kmp_hwloc_error = FALSE;
 hwloc_topology_t __kmp_hwloc_topology = NULL;
-# endif
+#endif
 
-# if KMP_OS_WINDOWS
-#  if KMP_GROUP_AFFINITY
+#if KMP_OS_WINDOWS
+#if KMP_GROUP_AFFINITY
 int __kmp_num_proc_groups = 1;
-#  endif /* KMP_GROUP_AFFINITY */
+#endif /* KMP_GROUP_AFFINITY */
 kmp_GetActiveProcessorCount_t __kmp_GetActiveProcessorCount = NULL;
 kmp_GetActiveProcessorGroupCount_t __kmp_GetActiveProcessorGroupCount = NULL;
 kmp_GetThreadGroupAffinity_t __kmp_GetThreadGroupAffinity = NULL;
 kmp_SetThreadGroupAffinity_t __kmp_SetThreadGroupAffinity = NULL;
-# endif /* KMP_OS_WINDOWS */
+#endif /* KMP_OS_WINDOWS */
 
-size_t   __kmp_affin_mask_size = 0;
+size_t __kmp_affin_mask_size = 0;
 enum affinity_type __kmp_affinity_type = affinity_default;
 enum affinity_gran __kmp_affinity_gran = affinity_gran_default;
-int __kmp_affinity_gran_levels  = -1;
+int __kmp_affinity_gran_levels = -1;
 int __kmp_affinity_dups = TRUE;
-enum affinity_top_method __kmp_affinity_top_method = affinity_top_method_default;
-int      __kmp_affinity_compact      = 0;
-int      __kmp_affinity_offset       = 0;
-int      __kmp_affinity_verbose      = FALSE;
-int      __kmp_affinity_warnings     = TRUE;
-int      __kmp_affinity_respect_mask = affinity_respect_mask_default;
-char *   __kmp_affinity_proclist     = NULL;
+enum affinity_top_method __kmp_affinity_top_method =
+    affinity_top_method_default;
+int __kmp_affinity_compact = 0;
+int __kmp_affinity_offset = 0;
+int __kmp_affinity_verbose = FALSE;
+int __kmp_affinity_warnings = TRUE;
+int __kmp_affinity_respect_mask = affinity_respect_mask_default;
+char *__kmp_affinity_proclist = NULL;
 kmp_affin_mask_t *__kmp_affinity_masks = NULL;
-unsigned __kmp_affinity_num_masks    = 0;
+unsigned __kmp_affinity_num_masks = 0;
 
-char const *  __kmp_cpuinfo_file     = NULL;
+char const *__kmp_cpuinfo_file = NULL;
 
 #endif /* KMP_AFFINITY_SUPPORTED */
 
 #if OMP_40_ENABLED
-kmp_nested_proc_bind_t __kmp_nested_proc_bind = { NULL, 0, 0 };
+kmp_nested_proc_bind_t __kmp_nested_proc_bind = {NULL, 0, 0};
 int __kmp_affinity_num_places = 0;
 #endif
 
-int __kmp_place_num_sockets = 0;
-int __kmp_place_socket_offset = 0;
-int __kmp_place_num_cores = 0;
-int __kmp_place_core_offset = 0;
-int __kmp_place_num_threads_per_core = 0;
+kmp_hws_item_t __kmp_hws_socket = {0, 0};
+kmp_hws_item_t __kmp_hws_node = {0, 0};
+kmp_hws_item_t __kmp_hws_tile = {0, 0};
+kmp_hws_item_t __kmp_hws_core = {0, 0};
+kmp_hws_item_t __kmp_hws_proc = {0, 0};
+int __kmp_hws_requested = 0;
+int __kmp_hws_abs_flag = 0; // absolute or per-item number requested
 
 #if OMP_40_ENABLED
 kmp_int32 __kmp_default_device = 0;
@@ -277,123 +301,132 @@ kmp_int32 __kmp_default_device = 0;
 kmp_tasking_mode_t __kmp_tasking_mode = tskm_task_teams;
 #if OMP_45_ENABLED
 kmp_int32 __kmp_max_task_priority = 0;
+kmp_uint64 __kmp_taskloop_min_tasks = 0;
 #endif
 
-/* This check ensures that the compiler is passing the correct data type
- * for the flags formal parameter of the function kmpc_omp_task_alloc().
- * If the type is not a 4-byte type, then give an error message about
- * a non-positive length array pointing here.  If that happens, the
- * kmp_tasking_flags_t structure must be redefined to have exactly 32 bits.
- */
-KMP_BUILD_ASSERT( sizeof(kmp_tasking_flags_t) == 4 );
+/* This check ensures that the compiler is passing the correct data type for the
+   flags formal parameter of the function kmpc_omp_task_alloc(). If the type is
+   not a 4-byte type, then give an error message about a non-positive length
+   array pointing here.  If that happens, the kmp_tasking_flags_t structure must
+   be redefined to have exactly 32 bits. */
+KMP_BUILD_ASSERT(sizeof(kmp_tasking_flags_t) == 4);
 
-kmp_int32 __kmp_task_stealing_constraint = 1;   /* Constrain task stealing by default */
+kmp_int32 __kmp_task_stealing_constraint =
+    1; /* Constrain task stealing by default */
 
 #ifdef DEBUG_SUSPEND
-int         __kmp_suspend_count = 0;
+int __kmp_suspend_count = 0;
 #endif
 
-int     __kmp_settings = FALSE;
-int     __kmp_duplicate_library_ok = 0;
+int __kmp_settings = FALSE;
+int __kmp_duplicate_library_ok = 0;
 #if USE_ITT_BUILD
-int     __kmp_forkjoin_frames = 1;
-int     __kmp_forkjoin_frames_mode = 3;
+int __kmp_forkjoin_frames = 1;
+int __kmp_forkjoin_frames_mode = 3;
 #endif
-PACKED_REDUCTION_METHOD_T __kmp_force_reduction_method = reduction_method_not_defined;
-int     __kmp_determ_red = FALSE;
+PACKED_REDUCTION_METHOD_T __kmp_force_reduction_method =
+    reduction_method_not_defined;
+int __kmp_determ_red = FALSE;
 
 #ifdef KMP_DEBUG
-int     kmp_a_debug = 0;
-int     kmp_b_debug = 0;
-int     kmp_c_debug = 0;
-int     kmp_d_debug = 0;
-int     kmp_e_debug = 0;
-int     kmp_f_debug = 0;
-int     kmp_diag    = 0;
+int kmp_a_debug = 0;
+int kmp_b_debug = 0;
+int kmp_c_debug = 0;
+int kmp_d_debug = 0;
+int kmp_e_debug = 0;
+int kmp_f_debug = 0;
+int kmp_diag = 0;
 #endif
 
 /* For debug information logging using rotating buffer */
-int     __kmp_debug_buf = FALSE;        /* TRUE means use buffer, FALSE means print to stderr */
-int     __kmp_debug_buf_lines = KMP_DEBUG_BUF_LINES_INIT; /* Lines of debug stored in buffer */
-int     __kmp_debug_buf_chars = KMP_DEBUG_BUF_CHARS_INIT; /* Characters allowed per line in buffer */
-int     __kmp_debug_buf_atomic = FALSE; /* TRUE means use atomic update of buffer entry pointer */
+int __kmp_debug_buf =
+    FALSE; /* TRUE means use buffer, FALSE means print to stderr */
+int __kmp_debug_buf_lines =
+    KMP_DEBUG_BUF_LINES_INIT; /* Lines of debug stored in buffer */
+int __kmp_debug_buf_chars =
+    KMP_DEBUG_BUF_CHARS_INIT; /* Characters allowed per line in buffer */
+int __kmp_debug_buf_atomic =
+    FALSE; /* TRUE means use atomic update of buffer entry pointer */
 
-char   *__kmp_debug_buffer = NULL;      /* Debug buffer itself */
-int     __kmp_debug_count = 0;          /* Counter for number of lines printed in buffer so far */
-int     __kmp_debug_buf_warn_chars = 0; /* Keep track of char increase recommended in warnings */
+char *__kmp_debug_buffer = NULL; /* Debug buffer itself */
+int __kmp_debug_count =
+    0; /* Counter for number of lines printed in buffer so far */
+int __kmp_debug_buf_warn_chars =
+    0; /* Keep track of char increase recommended in warnings */
 /* end rotating debug buffer */
 
 #ifdef KMP_DEBUG
-int     __kmp_par_range;           /* +1 => only go par for constructs in range */
-                                           /* -1 => only go par for constructs outside range */
-char    __kmp_par_range_routine[KMP_PAR_RANGE_ROUTINE_LEN] = { '\0' };
-char    __kmp_par_range_filename[KMP_PAR_RANGE_FILENAME_LEN] = { '\0' };
-int     __kmp_par_range_lb = 0;
-int     __kmp_par_range_ub = INT_MAX;
+int __kmp_par_range; /* +1 => only go par for constructs in range */
+/* -1 => only go par for constructs outside range */
+char __kmp_par_range_routine[KMP_PAR_RANGE_ROUTINE_LEN] = {'\0'};
+char __kmp_par_range_filename[KMP_PAR_RANGE_FILENAME_LEN] = {'\0'};
+int __kmp_par_range_lb = 0;
+int __kmp_par_range_ub = INT_MAX;
 #endif /* KMP_DEBUG */
 
 /* For printing out dynamic storage map for threads and teams */
-int     __kmp_storage_map = FALSE;         /* True means print storage map for threads and teams */
-int     __kmp_storage_map_verbose = FALSE; /* True means storage map includes placement info */
-int     __kmp_storage_map_verbose_specified = FALSE;
-/* Initialize the library data structures when we fork a child process, defaults to TRUE */
-int     __kmp_need_register_atfork = TRUE; /* At initialization, call pthread_atfork to install fork handler */
-int     __kmp_need_register_atfork_specified = TRUE;
+int __kmp_storage_map =
+    FALSE; /* True means print storage map for threads and teams */
+int __kmp_storage_map_verbose =
+    FALSE; /* True means storage map includes placement info */
+int __kmp_storage_map_verbose_specified = FALSE;
+/* Initialize the library data structures when we fork a child process, defaults
+ * to TRUE */
+int __kmp_need_register_atfork =
+    TRUE; /* At initialization, call pthread_atfork to install fork handler */
+int __kmp_need_register_atfork_specified = TRUE;
 
-int        __kmp_env_chunk       = FALSE;  /* KMP_CHUNK specified?     */
-int        __kmp_env_stksize     = FALSE;  /* KMP_STACKSIZE specified? */
-int        __kmp_env_omp_stksize = FALSE;  /* OMP_STACKSIZE specified? */
-int        __kmp_env_all_threads     = FALSE;/* KMP_ALL_THREADS or KMP_MAX_THREADS specified? */
-int        __kmp_env_omp_all_threads = FALSE;/* OMP_THREAD_LIMIT specified? */
-int        __kmp_env_blocktime   = FALSE;  /* KMP_BLOCKTIME specified? */
-int        __kmp_env_checks      = FALSE;  /* KMP_CHECKS specified?    */
-int        __kmp_env_consistency_check  = FALSE;  /* KMP_CONSISTENCY_CHECK specified? */
+int __kmp_env_chunk = FALSE; /* KMP_CHUNK specified?     */
+int __kmp_env_stksize = FALSE; /* KMP_STACKSIZE specified? */
+int __kmp_env_omp_stksize = FALSE; /* OMP_STACKSIZE specified? */
+int __kmp_env_all_threads =
+    FALSE; /* KMP_ALL_THREADS or KMP_MAX_THREADS specified? */
+int __kmp_env_omp_all_threads = FALSE; /* OMP_THREAD_LIMIT specified? */
+int __kmp_env_blocktime = FALSE; /* KMP_BLOCKTIME specified? */
+int __kmp_env_checks = FALSE; /* KMP_CHECKS specified?    */
+int __kmp_env_consistency_check = FALSE; /* KMP_CONSISTENCY_CHECK specified? */
 
 kmp_uint32 __kmp_yield_init = KMP_INIT_WAIT;
 kmp_uint32 __kmp_yield_next = KMP_NEXT_WAIT;
 
 #if KMP_USE_MONITOR
 kmp_uint32 __kmp_yielding_on = 1;
+#endif
 #if KMP_OS_CNK
 kmp_uint32 __kmp_yield_cycle = 0;
 #else
-kmp_uint32 __kmp_yield_cycle = 1;     /* Yield-cycle is on by default */
+kmp_uint32 __kmp_yield_cycle = 1; /* Yield-cycle is on by default */
 #endif
-kmp_int32  __kmp_yield_on_count = 10; /* By default, yielding is on for 10 monitor periods. */
-kmp_int32  __kmp_yield_off_count = 1; /* By default, yielding is off for 1 monitor periods. */
-#endif
-/* ----------------------------------------------------- */
-
+kmp_int32 __kmp_yield_on_count =
+    10; /* By default, yielding is on for 10 monitor periods. */
+kmp_int32 __kmp_yield_off_count =
+    1; /* By default, yielding is off for 1 monitor periods. */
 
 /* ------------------------------------------------------ */
 /* STATE mostly syncronized with global lock */
 /* data written to rarely by masters, read often by workers */
-/*
- * SHALL WE EDIT THE COMMENT BELOW IN SOME WAY?
- * TODO:  None of this global padding stuff works consistently because
- * the order of declaration is not necessarily correlated to storage order.
- * To fix this, all the important globals must be put in a big structure
- * instead.
- */
+/* TODO: None of this global padding stuff works consistently because the order
+   of declaration is not necessarily correlated to storage order. To fix this,
+   all the important globals must be put in a big structure instead. */
 KMP_ALIGN_CACHE
-         kmp_info_t **__kmp_threads     = NULL;
-         kmp_root_t **__kmp_root        = NULL;
+kmp_info_t **__kmp_threads = NULL;
+kmp_root_t **__kmp_root = NULL;
 
 /* data read/written to often by masters */
 KMP_ALIGN_CACHE
-volatile int          __kmp_nth                    = 0;
-volatile int          __kmp_all_nth                = 0;
-int                   __kmp_thread_pool_nth        = 0;
-volatile kmp_info_t  *__kmp_thread_pool            = NULL;
-volatile kmp_team_t  *__kmp_team_pool              = NULL;
+volatile int __kmp_nth = 0;
+volatile int __kmp_all_nth = 0;
+int __kmp_thread_pool_nth = 0;
+volatile kmp_info_t *__kmp_thread_pool = NULL;
+volatile kmp_team_t *__kmp_team_pool = NULL;
 
 KMP_ALIGN_CACHE
-volatile int          __kmp_thread_pool_active_nth = 0;
+volatile int __kmp_thread_pool_active_nth = 0;
 
 /* -------------------------------------------------
  * GLOBAL/ROOT STATE */
 KMP_ALIGN_CACHE
-kmp_global_t __kmp_global = {{ 0 }};
+kmp_global_t __kmp_global = {{0}};
 
 /* ----------------------------------------------- */
 /* GLOBAL SYNCHRONIZATION LOCKS */
@@ -404,66 +437,72 @@ kmp_global_t __kmp_global = {{ 0 }};
  * false sharing if the alignment is not large enough for these locks */
 KMP_ALIGN_CACHE_INTERNODE
 
-kmp_bootstrap_lock_t __kmp_initz_lock   = KMP_BOOTSTRAP_LOCK_INITIALIZER( __kmp_initz_lock   ); /* Control initializations */
+kmp_bootstrap_lock_t __kmp_initz_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER(
+    __kmp_initz_lock); /* Control initializations */
 KMP_ALIGN_CACHE_INTERNODE
 kmp_bootstrap_lock_t __kmp_forkjoin_lock; /* control fork/join access */
 KMP_ALIGN_CACHE_INTERNODE
-kmp_bootstrap_lock_t __kmp_exit_lock;   /* exit() is not always thread-safe */
+kmp_bootstrap_lock_t __kmp_exit_lock; /* exit() is not always thread-safe */
 #if KMP_USE_MONITOR
 KMP_ALIGN_CACHE_INTERNODE
 kmp_bootstrap_lock_t __kmp_monitor_lock; /* control monitor thread creation */
 #endif
+/* used for the hack to allow threadprivate cache and __kmp_threads expansion
+   to co-exist */
 KMP_ALIGN_CACHE_INTERNODE
-kmp_bootstrap_lock_t __kmp_tp_cached_lock; /* used for the hack to allow threadprivate cache and __kmp_threads expansion to co-exist */
+kmp_bootstrap_lock_t __kmp_tp_cached_lock;
 
 KMP_ALIGN_CACHE_INTERNODE
-kmp_lock_t __kmp_global_lock;           /* Control OS/global access */
+kmp_lock_t __kmp_global_lock; /* Control OS/global access */
 KMP_ALIGN_CACHE_INTERNODE
-kmp_queuing_lock_t __kmp_dispatch_lock;         /* Control dispatch access  */
+kmp_queuing_lock_t __kmp_dispatch_lock; /* Control dispatch access  */
 KMP_ALIGN_CACHE_INTERNODE
-kmp_lock_t __kmp_debug_lock;            /* Control I/O access for KMP_DEBUG */
+kmp_lock_t __kmp_debug_lock; /* Control I/O access for KMP_DEBUG */
 #else
 KMP_ALIGN_CACHE
 
-kmp_bootstrap_lock_t __kmp_initz_lock   = KMP_BOOTSTRAP_LOCK_INITIALIZER( __kmp_initz_lock   ); /* Control initializations */
+kmp_bootstrap_lock_t __kmp_initz_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER(
+    __kmp_initz_lock); /* Control initializations */
 kmp_bootstrap_lock_t __kmp_forkjoin_lock; /* control fork/join access */
-kmp_bootstrap_lock_t __kmp_exit_lock;   /* exit() is not always thread-safe */
+kmp_bootstrap_lock_t __kmp_exit_lock; /* exit() is not always thread-safe */
 #if KMP_USE_MONITOR
 kmp_bootstrap_lock_t __kmp_monitor_lock; /* control monitor thread creation */
 #endif
-kmp_bootstrap_lock_t __kmp_tp_cached_lock; /* used for the hack to allow threadprivate cache and __kmp_threads expansion to co-exist */
+/* used for the hack to allow threadprivate cache and __kmp_threads expansion
+   to co-exist */
+kmp_bootstrap_lock_t __kmp_tp_cached_lock;
 
 KMP_ALIGN(128)
-kmp_lock_t __kmp_global_lock;           /* Control OS/global access */
+kmp_lock_t __kmp_global_lock; /* Control OS/global access */
 KMP_ALIGN(128)
-kmp_queuing_lock_t __kmp_dispatch_lock;         /* Control dispatch access  */
+kmp_queuing_lock_t __kmp_dispatch_lock; /* Control dispatch access  */
 KMP_ALIGN(128)
-kmp_lock_t __kmp_debug_lock;            /* Control I/O access for KMP_DEBUG */
+kmp_lock_t __kmp_debug_lock; /* Control I/O access for KMP_DEBUG */
 #endif
 
 /* ----------------------------------------------- */
 
 #if KMP_HANDLE_SIGNALS
-    /*
-        Signal handling is disabled by default, because it confuses users: In case of sigsegv
-        (or other trouble) in user code signal handler catches the signal, which then "appears" in
-        the monitor thread (when the monitor executes raise() function). Users see signal in the
-        monitor thread and blame OpenMP RTL.
+/* Signal handling is disabled by default, because it confuses users: In case of
+   sigsegv (or other trouble) in user code signal handler catches the signal,
+   which then "appears" in the monitor thread (when the monitor executes raise()
+   function). Users see signal in the monitor thread and blame OpenMP RTL.
 
-        Grant said signal handling required on some older OSes (Irix?) supported by KAI, because
-        bad applications hung but not aborted. Currently it is not a problem for Linux* OS, OS X* and
-        Windows* OS.
+   Grant said signal handling required on some older OSes (Irix?) supported by
+   KAI, because bad applications hung but not aborted. Currently it is not a
+   problem for Linux* OS, OS X* and Windows* OS.
 
-        Grant: Found new hangs for EL4, EL5, and a Fedora Core machine.  So I'm putting
-        the default back for now to see if that fixes hangs on those machines.
+   Grant: Found new hangs for EL4, EL5, and a Fedora Core machine.  So I'm
+   putting the default back for now to see if that fixes hangs on those
+   machines.
 
-        2010-04013 Lev: It was a bug in Fortran RTL. Fortran RTL prints a kind of stack backtrace
-        when program is aborting, but the code is not signal-safe. When multiple signals raised at
-        the same time (which occurs in dynamic negative tests because all the worker threads detects
-        the same error), Fortran RTL may hang. The bug finally fixed in Fortran RTL library provided
-        by Steve R., and will be available soon.
-    */
-    int __kmp_handle_signals = FALSE;
+   2010-04013 Lev: It was a bug in Fortran RTL. Fortran RTL prints a kind of
+   stack backtrace when program is aborting, but the code is not signal-safe.
+   When multiple signals raised at the same time (which occurs in dynamic
+   negative tests because all the worker threads detects the same error),
+   Fortran RTL may hang. The bug finally fixed in Fortran RTL library provided
+   by Steve R., and will be available soon. */
+int __kmp_handle_signals = FALSE;
 #endif
 
 /* ----------------------------------------------- */
@@ -471,27 +510,22 @@ kmp_lock_t __kmp_debug_lock;            /* Control I/O access for KMP_DEBUG */
 kmp_key_t __kmp_tv_key = 0;
 #endif
 
-/* ------------------------------------------------------------------------ */
 /* ------------------------------------------------------------------------ */
 
 #ifdef DEBUG_SUSPEND
-int
-get_suspend_count_( void ) {
-    int count = __kmp_suspend_count;
-    __kmp_suspend_count = 0;
-    return count;
-}
-void
-set_suspend_count_( int * value ) {
-    __kmp_suspend_count = *value;
+int get_suspend_count_(void) {
+  int count = __kmp_suspend_count;
+  __kmp_suspend_count = 0;
+  return count;
 }
+void set_suspend_count_(int *value) { __kmp_suspend_count = *value; }
 #endif
 
 // Symbols for MS mutual detection.
 int _You_must_link_with_exactly_one_OpenMP_library = 1;
-int _You_must_link_with_Intel_OpenMP_library       = 1;
-#if KMP_OS_WINDOWS && ( KMP_VERSION_MAJOR > 4 )
-    int _You_must_link_with_Microsoft_OpenMP_library = 1;
+int _You_must_link_with_Intel_OpenMP_library = 1;
+#if KMP_OS_WINDOWS && (KMP_VERSION_MAJOR > 4)
+int _You_must_link_with_Microsoft_OpenMP_library = 1;
 #endif
 
 // end of file //

runtime/src/kmp_i18n.h

@@ -19,173 +19,164 @@
 #include "kmp_str.h"
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
-/*
-    kmp_i18n_id.inc defines kmp_i18n_id_t type. It is an enumeration with identifiers of all the
-    messages in the catalog. There is one special identifier: kmp_i18n_null, which denotes absence
-    of message.
-*/
+/* kmp_i18n_id.inc defines kmp_i18n_id_t type. It is an enumeration with
+   identifiers of all the messages in the catalog. There is one special
+   identifier: kmp_i18n_null, which denotes absence of message. */
 #include "kmp_i18n_id.inc" // Generated file. Do not edit it manually.
 
-/*
-    Low-level functions handling message catalog. __kmp_i18n_open() opens message catalog,
-    __kmp_i18n_closes() it. Explicit opening is not required: if message catalog is not yet open,
-    __kmp_i18n_catgets() will open it implicitly. However, catalog should be explicitly closed,
-    otherwise resources (mamory, handles) may leak.
+/* Low-level functions handling message catalog. __kmp_i18n_open() opens message
+   catalog, __kmp_i18n_closes() it. Explicit opening is not required: if message
+   catalog is not yet open, __kmp_i18n_catgets() will open it implicitly.
+   However, catalog should be explicitly closed, otherwise resources (mamory,
+   handles) may leak.
 
-    __kmp_i18n_catgets() returns read-only string. It should not be freed.
+   __kmp_i18n_catgets() returns read-only string. It should not be freed.
 
-    KMP_I18N_STR macro simplifies acces to strings in message catalog a bit. Following two lines are
-    equivalent:
+   KMP_I18N_STR macro simplifies acces to strings in message catalog a bit.
+   Following two lines are equivalent:
 
-        __kmp_i18n_catgets( kmp_i18n_str_Warning )
-        KMP_I18N_STR( Warning )
+   __kmp_i18n_catgets( kmp_i18n_str_Warning )
+   KMP_I18N_STR( Warning )
 */
 
-void            __kmp_i18n_catopen();
-void            __kmp_i18n_catclose();
-char const *    __kmp_i18n_catgets( kmp_i18n_id_t id );
+void __kmp_i18n_catopen();
+void __kmp_i18n_catclose();
+char const *__kmp_i18n_catgets(kmp_i18n_id_t id);
 
-#define KMP_I18N_STR( id )    __kmp_i18n_catgets( kmp_i18n_str_ ## id )
+#define KMP_I18N_STR(id) __kmp_i18n_catgets(kmp_i18n_str_##id)
 
+/* High-level interface for printing strings targeted to the user.
 
-/*
-    ------------------------------------------------------------------------------------------------
+   All the strings are divided into 3 types:
+   * messages,
+   * hints,
+   * system errors.
 
-    High-level interface for printing strings targeted to the user.
+   There are 3 kind of message severities:
+   * informational messages,
+   * warnings (non-fatal errors),
+   * fatal errors.
 
-    All the strings are divided into 3 types:
+   For example:
+     OMP: Warning #2: Cannot open message catalog "libguide.cat":   (1)
+     OMP: System error #2: No such file or directory                (2)
+     OMP: Hint: Please check NLSPATH environment variable.          (3)
+     OMP: Info #3: Default messages will be used.                   (4)
 
-        * messages,
-        * hints,
-        * system errors.
-
-    There are 3 kind of message severities:
-
-        * informational messages,
-        * warnings (non-fatal errors),
-        * fatal errors.
-
-    For example:
-
-        OMP: Warning #2: Cannot open message catalog "libguide.cat":   (1)
-        OMP: System error #2: No such file or directory                (2)
-        OMP: Hint: Please check NLSPATH environment variable.          (3)
-        OMP: Info #3: Default messages will be used.                   (4)
-
-    where
-
-        (1) is a message of warning severity,
-        (2) is a system error caused the previous warning,
-        (3) is a hint for the user how to fix the problem,
-        (4) is a message of informational severity.
+   where
+   (1) is a message of warning severity,
+   (2) is a system error caused the previous warning,
+   (3) is a hint for the user how to fix the problem,
+   (4) is a message of informational severity.
 
    Usage in complex cases (message is accompanied with hints and system errors):
 
-       int error = errno;   // We need save errno immediately, because it may be changed.
-       __kmp_msg(
-           kmp_ms_warning,                            // Severity
-           KMP_MSG( CantOpenMessageCatalog, name ),   // Primary message
-           KMP_ERR( error ),                          // System error
-           KMP_HNT( CheckNLSPATH ),                   // Hint
-           __kmp_msg_null                             // Variadic argument list finisher
-       );
+   int error = errno; // We need save errno immediately, because it may
+                      // be changed.
+   __kmp_msg(
+       kmp_ms_warning,                        // Severity
+       KMP_MSG( CantOpenMessageCatalog, name ), // Primary message
+       KMP_ERR( error ),                      // System error
+       KMP_HNT( CheckNLSPATH ),               // Hint
+       __kmp_msg_null                         // Variadic argument list finisher
+   );
 
-    Usage in simple cases (just a message, no system errors or hints):
-
-        KMP_INFORM( WillUseDefaultMessages );
-        KMP_WARNING( CantOpenMessageCatalog, name );
-        KMP_FATAL( StackOverlap );
-        KMP_SYSFAIL( "pthread_create", status );
-        KMP_CHECK_SYSFAIL( "pthread_create", status );
-        KMP_CHECK_SYSFAIL_ERRNO( "gettimeofday", status );
-
-    ------------------------------------------------------------------------------------------------
+   Usage in simple cases (just a message, no system errors or hints):
+   KMP_INFORM( WillUseDefaultMessages );
+   KMP_WARNING( CantOpenMessageCatalog, name );
+   KMP_FATAL( StackOverlap );
+   KMP_SYSFAIL( "pthread_create", status );
+   KMP_CHECK_SYSFAIL( "pthread_create", status );
+   KMP_CHECK_SYSFAIL_ERRNO( "gettimeofday", status );
 */
 
 enum kmp_msg_type {
-    kmp_mt_dummy  =  0, // Special type for internal purposes.
-    kmp_mt_mesg   =  4, // Primary OpenMP message, could be information, warning, or fatal.
-    kmp_mt_hint   =  5, // Hint to the user.
-    kmp_mt_syserr = -1  // System error message.
+  kmp_mt_dummy = 0, // Special type for internal purposes.
+  kmp_mt_mesg =
+      4, // Primary OpenMP message, could be information, warning, or fatal.
+  kmp_mt_hint = 5, // Hint to the user.
+  kmp_mt_syserr = -1 // System error message.
 }; // enum kmp_msg_type
-typedef enum kmp_msg_type  kmp_msg_type_t;
+typedef enum kmp_msg_type kmp_msg_type_t;
 
 struct kmp_msg {
-    kmp_msg_type_t  type;
-    int             num;
-    char const *    str;
-    int             len;
+  kmp_msg_type_t type;
+  int num;
+  char const *str;
+  int len;
 }; // struct kmp_message
-typedef struct kmp_msg  kmp_msg_t;
+typedef struct kmp_msg kmp_msg_t;
 
 // Two special messages.
-extern kmp_msg_t __kmp_msg_empty;  // Can be used in place where message is required syntactically.
-extern kmp_msg_t __kmp_msg_null;   // Denotes the end of variadic list of arguments.
+extern kmp_msg_t __kmp_msg_empty; // Can be used in place where message is
+// required syntactically.
+extern kmp_msg_t
+    __kmp_msg_null; // Denotes the end of variadic list of arguments.
 
-// Helper functions. Creates messages either from message catalog or from system. Note: these
-// functions allocate memory. You should pass created messages to __kmp_msg() function, it will
-// print messages and destroy them.
-kmp_msg_t  __kmp_msg_format( unsigned id_arg, ... );
-kmp_msg_t  __kmp_msg_error_code( int code );
-kmp_msg_t  __kmp_msg_error_mesg( char const * mesg );
+// Helper functions. Creates messages either from message catalog or from
+// system. Note: these functions allocate memory. You should pass created
+// messages to __kmp_msg() function, it will print messages and destroy them.
+kmp_msg_t __kmp_msg_format(unsigned id_arg, ...);
+kmp_msg_t __kmp_msg_error_code(int code);
+kmp_msg_t __kmp_msg_error_mesg(char const *mesg);
 
 // Helper macros to make calls shorter.
-#define KMP_MSG( ...  )   __kmp_msg_format( kmp_i18n_msg_ ## __VA_ARGS__ )
-#define KMP_HNT( ...  )   __kmp_msg_format( kmp_i18n_hnt_ ## __VA_ARGS__ )
-#define KMP_SYSERRCODE( code )  __kmp_msg_error_code( code )
-#define KMP_SYSERRMESG( mesg )  __kmp_msg_error_mesg( mesg )
+#define KMP_MSG(...) __kmp_msg_format(kmp_i18n_msg_##__VA_ARGS__)
+#define KMP_HNT(...) __kmp_msg_format(kmp_i18n_hnt_##__VA_ARGS__)
+#define KMP_SYSERRCODE(code) __kmp_msg_error_code(code)
+#define KMP_SYSERRMESG(mesg) __kmp_msg_error_mesg(mesg)
 #define KMP_ERR KMP_SYSERRCODE
 
 // Message severity.
 enum kmp_msg_severity {
-    kmp_ms_inform,      // Just information for the user.
-    kmp_ms_warning,     // Non-fatal error, execution continues.
-    kmp_ms_fatal        // Fatal error, program aborts.
+  kmp_ms_inform, // Just information for the user.
+  kmp_ms_warning, // Non-fatal error, execution continues.
+  kmp_ms_fatal // Fatal error, program aborts.
 }; // enum kmp_msg_severity
-typedef enum kmp_msg_severity  kmp_msg_severity_t;
+typedef enum kmp_msg_severity kmp_msg_severity_t;
 
-// Primary function for printing messages for the user. The first message is mandatory. Any number
-// of system errors and hints may be specified. Argument list must be finished with __kmp_msg_null.
-void    __kmp_msg( kmp_msg_severity_t severity, kmp_msg_t message, ... );
+// Primary function for printing messages for the user. The first message is
+// mandatory. Any number of system errors and hints may be specified. Argument
+// list must be finished with __kmp_msg_null.
+void __kmp_msg(kmp_msg_severity_t severity, kmp_msg_t message, ...);
 
 // Helper macros to make calls shorter in simple cases.
-#define KMP_INFORM( ...  ) __kmp_msg( kmp_ms_inform,  KMP_MSG( __VA_ARGS__ ), __kmp_msg_null )
-#define KMP_WARNING( ... ) __kmp_msg( kmp_ms_warning, KMP_MSG( __VA_ARGS__ ), __kmp_msg_null )
-#define KMP_FATAL(   ... ) __kmp_msg( kmp_ms_fatal,   KMP_MSG( __VA_ARGS__ ), __kmp_msg_null )
-#define KMP_SYSFAIL( func, error )                                                                 \
-    __kmp_msg(                                                                                     \
-        kmp_ms_fatal,                                                                              \
-        KMP_MSG( FunctionError, func ),                                                            \
-        KMP_SYSERRCODE( error ),                                                                   \
-        __kmp_msg_null                                                                             \
-    )
+#define KMP_INFORM(...)                                                        \
+  __kmp_msg(kmp_ms_inform, KMP_MSG(__VA_ARGS__), __kmp_msg_null)
+#define KMP_WARNING(...)                                                       \
+  __kmp_msg(kmp_ms_warning, KMP_MSG(__VA_ARGS__), __kmp_msg_null)
+#define KMP_FATAL(...)                                                         \
+  __kmp_msg(kmp_ms_fatal, KMP_MSG(__VA_ARGS__), __kmp_msg_null)
+#define KMP_SYSFAIL(func, error)                                               \
+  __kmp_msg(kmp_ms_fatal, KMP_MSG(FunctionError, func), KMP_SYSERRCODE(error), \
+            __kmp_msg_null)
 
 // Check error, if not zero, generate fatal error message.
-#define KMP_CHECK_SYSFAIL( func, error )                                                           \
-    {                                                                                              \
-        if ( error ) {                                                                             \
-            KMP_SYSFAIL( func, error );                                                            \
-        };                                                                                         \
-    }
+#define KMP_CHECK_SYSFAIL(func, error)                                         \
+  {                                                                            \
+    if (error) {                                                               \
+      KMP_SYSFAIL(func, error);                                                \
+    };                                                                         \
+  }
 
 // Check status, if not zero, generate fatal error message using errno.
-#define KMP_CHECK_SYSFAIL_ERRNO( func, status )                                                    \
-    {                                                                                              \
-        if ( status != 0 ) {                                                                       \
-            int error = errno;                                                                     \
-            KMP_SYSFAIL( func, error );                                                            \
-        };                                                                                         \
-    }
+#define KMP_CHECK_SYSFAIL_ERRNO(func, status)                                  \
+  {                                                                            \
+    if (status != 0) {                                                         \
+      int error = errno;                                                       \
+      KMP_SYSFAIL(func, error);                                                \
+    };                                                                         \
+  }
 
 #ifdef KMP_DEBUG
-    void __kmp_i18n_dump_catalog( kmp_str_buf_t * buffer );
+void __kmp_i18n_dump_catalog(kmp_str_buf_t *buffer);
 #endif // KMP_DEBUG
 
 #ifdef __cplusplus
-    }; // extern "C"
+}; // extern "C"
 #endif // __cplusplus
 
 #endif // KMP_I18N_H

runtime/src/kmp_import.cpp

@@ -13,26 +13,20 @@
 //===----------------------------------------------------------------------===//
 
 
-/*
-    ------------------------------------------------------------------------------------------------
-    Object generated from this source file is linked to Windows* OS DLL import library (libompmd.lib)
-    only! It is not a part of regular static or dynamic OpenMP RTL. Any code that just needs to go
-    in the libompmd.lib (but not in libompmt.lib and libompmd.dll) should be placed in this
-    file.
-    ------------------------------------------------------------------------------------------------
-*/
+/* Object generated from this source file is linked to Windows* OS DLL import
+   library (libompmd.lib) only! It is not a part of regular static or dynamic
+   OpenMP RTL. Any code that just needs to go in the libompmd.lib (but not in
+   libompmt.lib and libompmd.dll) should be placed in this file. */
 
 #ifdef __cplusplus
 extern "C" {
 #endif
 
-/*
-    These symbols are required for mutual exclusion with Microsoft OpenMP RTL (and compatibility
-    with MS Compiler).
-*/
+/*These symbols are required for mutual exclusion with Microsoft OpenMP RTL
+  (and compatibility with MS Compiler). */
 
 int _You_must_link_with_exactly_one_OpenMP_library = 1;
-int _You_must_link_with_Intel_OpenMP_library       = 1;
+int _You_must_link_with_Intel_OpenMP_library = 1;
 int _You_must_link_with_Microsoft_OpenMP_library = 1;
 
 #ifdef __cplusplus

runtime/src/kmp_io.cpp

@@ -13,236 +13,218 @@
 //===----------------------------------------------------------------------===//
 
 
+#include <stdarg.h>
+#include <stddef.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <stddef.h>
-#include <stdarg.h>
 #include <string.h>
 #ifndef __ABSOFT_WIN
-# include <sys/types.h>
+#include <sys/types.h>
 #endif
 
-#include "kmp_os.h"
-#include "kmp_lock.h"
-#include "kmp_str.h"
-#include "kmp_io.h"
 #include "kmp.h" // KMP_GTID_DNE, __kmp_debug_buf, etc
+#include "kmp_io.h"
+#include "kmp_lock.h"
+#include "kmp_os.h"
+#include "kmp_str.h"
 
 #if KMP_OS_WINDOWS
-# pragma warning( push )
-# pragma warning( disable: 271 310 )
-# include <windows.h>
-# pragma warning( pop )
+#pragma warning(push)
+#pragma warning(disable : 271 310)
+#include <windows.h>
+#pragma warning(pop)
 #endif
 
-/* ------------------------------------------------------------------------ */
 /* ------------------------------------------------------------------------ */
 
-kmp_bootstrap_lock_t __kmp_stdio_lock   = KMP_BOOTSTRAP_LOCK_INITIALIZER( __kmp_stdio_lock   ); /* Control stdio functions */
-kmp_bootstrap_lock_t __kmp_console_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER( __kmp_console_lock ); /* Control console initialization */
+kmp_bootstrap_lock_t __kmp_stdio_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER(
+    __kmp_stdio_lock); /* Control stdio functions */
+kmp_bootstrap_lock_t __kmp_console_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER(
+    __kmp_console_lock); /* Control console initialization */
 
 #if KMP_OS_WINDOWS
 
-    # ifdef KMP_DEBUG
-    /* __kmp_stdout is used only for dev build */
-    static HANDLE    __kmp_stdout = NULL;
-    # endif
-    static HANDLE        __kmp_stderr = NULL;
-    static int           __kmp_console_exists = FALSE;
-    static kmp_str_buf_t __kmp_console_buf;
+#ifdef KMP_DEBUG
+/* __kmp_stdout is used only for dev build */
+static HANDLE __kmp_stdout = NULL;
+#endif
+static HANDLE __kmp_stderr = NULL;
+static int __kmp_console_exists = FALSE;
+static kmp_str_buf_t __kmp_console_buf;
 
-    static int
-    is_console( void )
-    {
-        char buffer[ 128 ];
-        DWORD rc  = 0;
-        DWORD err = 0;
-        // Try to get console title.
-        SetLastError( 0 );
-            // GetConsoleTitle does not reset last error in case of success or short buffer,
-            // so we need to clear it explicitly.
-        rc = GetConsoleTitle( buffer, sizeof( buffer ) );
-        if ( rc == 0 ) {
-            // rc == 0 means getting console title failed. Let us find out why.
-            err = GetLastError();
-            // err == 0 means buffer too short (we suppose console exists).
-            // In Window applications we usually have err == 6 (invalid handle).
-        }; // if
-        return rc > 0 || err == 0;
+static int is_console(void) {
+  char buffer[128];
+  DWORD rc = 0;
+  DWORD err = 0;
+  // Try to get console title.
+  SetLastError(0);
+  // GetConsoleTitle does not reset last error in case of success or short
+  // buffer, so we need to clear it explicitly.
+  rc = GetConsoleTitle(buffer, sizeof(buffer));
+  if (rc == 0) {
+    // rc == 0 means getting console title failed. Let us find out why.
+    err = GetLastError();
+    // err == 0 means buffer too short (we suppose console exists).
+    // In Window applications we usually have err == 6 (invalid handle).
+  }; // if
+  return rc > 0 || err == 0;
+}
+
+void __kmp_close_console(void) {
+  /* wait until user presses return before closing window */
+  /* TODO only close if a window was opened */
+  if (__kmp_console_exists) {
+#ifdef KMP_DEBUG
+    /* standard out is used only in dev build */
+    __kmp_stdout = NULL;
+#endif
+    __kmp_stderr = NULL;
+    __kmp_str_buf_free(&__kmp_console_buf);
+    __kmp_console_exists = FALSE;
+  }
+}
+
+/* For windows, call this before stdout, stderr, or stdin are used.
+   It opens a console window and starts processing */
+static void __kmp_redirect_output(void) {
+  __kmp_acquire_bootstrap_lock(&__kmp_console_lock);
+
+  if (!__kmp_console_exists) {
+#ifdef KMP_DEBUG
+    /* standard out is used only in dev build */
+    HANDLE ho;
+#endif
+    HANDLE he;
+
+    __kmp_str_buf_init(&__kmp_console_buf);
+
+    AllocConsole();
+// We do not check the result of AllocConsole because
+//  1. the call is harmless
+//  2. it is not clear how to communicate failue
+//  3. we will detect failure later when we get handle(s)
+
+#ifdef KMP_DEBUG
+    ho = GetStdHandle(STD_OUTPUT_HANDLE);
+    if (ho == INVALID_HANDLE_VALUE || ho == NULL) {
+
+      DWORD err = GetLastError();
+      // TODO: output error somehow (maybe message box)
+      __kmp_stdout = NULL;
+
+    } else {
+
+      __kmp_stdout = ho; // temporary code, need new global for ho
     }
+#endif
+    he = GetStdHandle(STD_ERROR_HANDLE);
+    if (he == INVALID_HANDLE_VALUE || he == NULL) {
 
-    void
-    __kmp_close_console( void )
-    {
-        /* wait until user presses return before closing window */
-        /* TODO only close if a window was opened */
-        if( __kmp_console_exists ) {
-            #ifdef KMP_DEBUG
-            /* standard out is used only in dev build */
-            __kmp_stdout = NULL;
-            #endif
-            __kmp_stderr = NULL;
-            __kmp_str_buf_free( &__kmp_console_buf );
-            __kmp_console_exists = FALSE;
-        }
-    }
-
-    /* For windows, call this before stdout, stderr, or stdin are used.
-     * It opens a console window and starts processing */
-    static void
-    __kmp_redirect_output( void )
-    {
-        __kmp_acquire_bootstrap_lock( &__kmp_console_lock );
-
-        if( ! __kmp_console_exists ) {
-            #ifdef KMP_DEBUG
-            /* standard out is used only in dev build */
-            HANDLE ho;
-            #endif
-            HANDLE he;
-
-            __kmp_str_buf_init( &__kmp_console_buf );
-
-            AllocConsole();
-            // We do not check the result of AllocConsole because
-            //  1. the call is harmless
-            //  2. it is not clear how to communicate failue
-            //  3. we will detect failure later when we get handle(s)
-
-            #ifdef KMP_DEBUG
-                ho = GetStdHandle( STD_OUTPUT_HANDLE );
-                if ( ho == INVALID_HANDLE_VALUE || ho == NULL ) {
-
-                    DWORD  err = GetLastError();
-                    // TODO: output error somehow (maybe message box)
-                    __kmp_stdout = NULL;
-
-                } else {
-
-                    __kmp_stdout = ho; // temporary code, need new global for ho
-
-                }
-            #endif
-            he = GetStdHandle( STD_ERROR_HANDLE );
-            if ( he == INVALID_HANDLE_VALUE || he == NULL ) {
-
-                DWORD  err = GetLastError();
-                // TODO: output error somehow (maybe message box)
-                __kmp_stderr = NULL;
-
-            } else {
-
-                __kmp_stderr = he; // temporary code, need new global
-            }
-            __kmp_console_exists = TRUE;
-        }
-        __kmp_release_bootstrap_lock( &__kmp_console_lock );
+      DWORD err = GetLastError();
+      // TODO: output error somehow (maybe message box)
+      __kmp_stderr = NULL;
+
+    } else {
+
+      __kmp_stderr = he; // temporary code, need new global
     }
+    __kmp_console_exists = TRUE;
+  }
+  __kmp_release_bootstrap_lock(&__kmp_console_lock);
+}
 
 #else
-    #define       __kmp_stderr     (stderr)
+#define __kmp_stderr (stderr)
 #endif /* KMP_OS_WINDOWS */
 
-void
-__kmp_vprintf( enum kmp_io __kmp_io, char const * format, va_list ap )
-{
-    #if KMP_OS_WINDOWS
-        if( !__kmp_console_exists ) {
-            __kmp_redirect_output();
-        }
-            if( ! __kmp_stderr && __kmp_io == kmp_err ) {
-            return;
-        }
-        #ifdef KMP_DEBUG
-            if( ! __kmp_stdout && __kmp_io == kmp_out ) {
-                return;
-            }
-        #endif
-    #endif /* KMP_OS_WINDOWS */
+void __kmp_vprintf(enum kmp_io __kmp_io, char const *format, va_list ap) {
+#if KMP_OS_WINDOWS
+  if (!__kmp_console_exists) {
+    __kmp_redirect_output();
+  }
+  if (!__kmp_stderr && __kmp_io == kmp_err) {
+    return;
+  }
+#ifdef KMP_DEBUG
+  if (!__kmp_stdout && __kmp_io == kmp_out) {
+    return;
+  }
+#endif
+#endif /* KMP_OS_WINDOWS */
 
-    if ( __kmp_debug_buf && __kmp_debug_buffer != NULL ) {
+  if (__kmp_debug_buf && __kmp_debug_buffer != NULL) {
 
-        int dc = ( __kmp_debug_buf_atomic ?
-                   KMP_TEST_THEN_INC32( & __kmp_debug_count) : __kmp_debug_count++ )
-                   % __kmp_debug_buf_lines;
-        char *db = & __kmp_debug_buffer[ dc * __kmp_debug_buf_chars ];
-        int chars = 0;
+    int dc = (__kmp_debug_buf_atomic ? KMP_TEST_THEN_INC32(&__kmp_debug_count)
+                                     : __kmp_debug_count++) %
+             __kmp_debug_buf_lines;
+    char *db = &__kmp_debug_buffer[dc * __kmp_debug_buf_chars];
+    int chars = 0;
 
-        #ifdef KMP_DEBUG_PIDS
-            chars = KMP_SNPRINTF( db, __kmp_debug_buf_chars, "pid=%d: ", (kmp_int32)getpid() );
-        #endif
-        chars += KMP_VSNPRINTF( db, __kmp_debug_buf_chars, format, ap );
+#ifdef KMP_DEBUG_PIDS
+    chars = KMP_SNPRINTF(db, __kmp_debug_buf_chars, "pid=%d: ",
+                         (kmp_int32)getpid());
+#endif
+    chars += KMP_VSNPRINTF(db, __kmp_debug_buf_chars, format, ap);
 
-        if ( chars + 1 > __kmp_debug_buf_chars ) {
-            if ( chars + 1 > __kmp_debug_buf_warn_chars ) {
-                #if KMP_OS_WINDOWS
-                    DWORD count;
-                    __kmp_str_buf_print( &__kmp_console_buf,
-                        "OMP warning: Debugging buffer overflow; increase KMP_DEBUG_BUF_CHARS to %d\n",
-                        chars + 1 );
-                    WriteFile( __kmp_stderr, __kmp_console_buf.str, __kmp_console_buf.used, &count, NULL );
-                    __kmp_str_buf_clear( &__kmp_console_buf );
-                #else
-                    fprintf( __kmp_stderr,
-                         "OMP warning: Debugging buffer overflow; increase KMP_DEBUG_BUF_CHARS to %d\n",
-                         chars + 1 );
-                    fflush( __kmp_stderr );
-                #endif
-                __kmp_debug_buf_warn_chars = chars + 1;
-            }
-            /* terminate string if overflow occurred */
-            db[ __kmp_debug_buf_chars - 2 ] = '\n';
-            db[ __kmp_debug_buf_chars - 1 ] = '\0';
-        }
-    } else {
-        #if KMP_OS_WINDOWS
-            DWORD count;
-            #ifdef KMP_DEBUG_PIDS
-                __kmp_str_buf_print( &__kmp_console_buf, "pid=%d: ",
-                  (kmp_int32)getpid() );
-            #endif
-            __kmp_str_buf_vprint( &__kmp_console_buf, format, ap );
-            WriteFile(
-                __kmp_stderr,
-                __kmp_console_buf.str,
-                __kmp_console_buf.used,
-                &count,
-                NULL
-            );
-            __kmp_str_buf_clear( &__kmp_console_buf );
-        #else
-            #ifdef KMP_DEBUG_PIDS
-                fprintf( __kmp_stderr, "pid=%d: ", (kmp_int32)getpid() );
-            #endif
-            vfprintf( __kmp_stderr, format, ap );
-            fflush( __kmp_stderr );
-        #endif
+    if (chars + 1 > __kmp_debug_buf_chars) {
+      if (chars + 1 > __kmp_debug_buf_warn_chars) {
+#if KMP_OS_WINDOWS
+        DWORD count;
+        __kmp_str_buf_print(&__kmp_console_buf, "OMP warning: Debugging buffer "
+                                                "overflow; increase "
+                                                "KMP_DEBUG_BUF_CHARS to %d\n",
+                            chars + 1);
+        WriteFile(__kmp_stderr, __kmp_console_buf.str, __kmp_console_buf.used,
+                  &count, NULL);
+        __kmp_str_buf_clear(&__kmp_console_buf);
+#else
+        fprintf(__kmp_stderr, "OMP warning: Debugging buffer overflow; "
+                              "increase KMP_DEBUG_BUF_CHARS to %d\n",
+                chars + 1);
+        fflush(__kmp_stderr);
+#endif
+        __kmp_debug_buf_warn_chars = chars + 1;
+      }
+      /* terminate string if overflow occurred */
+      db[__kmp_debug_buf_chars - 2] = '\n';
+      db[__kmp_debug_buf_chars - 1] = '\0';
     }
+  } else {
+#if KMP_OS_WINDOWS
+    DWORD count;
+#ifdef KMP_DEBUG_PIDS
+    __kmp_str_buf_print(&__kmp_console_buf, "pid=%d: ", (kmp_int32)getpid());
+#endif
+    __kmp_str_buf_vprint(&__kmp_console_buf, format, ap);
+    WriteFile(__kmp_stderr, __kmp_console_buf.str, __kmp_console_buf.used,
+              &count, NULL);
+    __kmp_str_buf_clear(&__kmp_console_buf);
+#else
+#ifdef KMP_DEBUG_PIDS
+    fprintf(__kmp_stderr, "pid=%d: ", (kmp_int32)getpid());
+#endif
+    vfprintf(__kmp_stderr, format, ap);
+    fflush(__kmp_stderr);
+#endif
+  }
 }
 
-void
-__kmp_printf( char const * format, ... )
-{
-    va_list ap;
-    va_start( ap, format );
+void __kmp_printf(char const *format, ...) {
+  va_list ap;
+  va_start(ap, format);
 
-    __kmp_acquire_bootstrap_lock( & __kmp_stdio_lock );
-    __kmp_vprintf( kmp_err, format, ap );
-    __kmp_release_bootstrap_lock( & __kmp_stdio_lock );
+  __kmp_acquire_bootstrap_lock(&__kmp_stdio_lock);
+  __kmp_vprintf(kmp_err, format, ap);
+  __kmp_release_bootstrap_lock(&__kmp_stdio_lock);
 
-    va_end( ap );
+  va_end(ap);
 }
 
-void
-__kmp_printf_no_lock( char const * format, ... )
-{
-    va_list ap;
-    va_start( ap, format );
+void __kmp_printf_no_lock(char const *format, ...) {
+  va_list ap;
+  va_start(ap, format);
 
-    __kmp_vprintf( kmp_err, format, ap );
+  __kmp_vprintf(kmp_err, format, ap);
 
-    va_end( ap );
+  va_end(ap);
 }
-
-/* ------------------------------------------------------------------------ */
-/* ------------------------------------------------------------------------ */

runtime/src/kmp_io.h

@@ -20,25 +20,21 @@
 extern "C" {
 #endif
 
-/* ------------------------------------------------------------------------ */
 /* ------------------------------------------------------------------------ */
 
-enum kmp_io {
-    kmp_out = 0,
-    kmp_err
-};
+enum kmp_io { kmp_out = 0, kmp_err };
 
-extern kmp_bootstrap_lock_t __kmp_stdio_lock;     /* Control stdio functions */
-extern kmp_bootstrap_lock_t __kmp_console_lock;   /* Control console initialization */
+extern kmp_bootstrap_lock_t __kmp_stdio_lock; /* Control stdio functions */
+extern kmp_bootstrap_lock_t
+    __kmp_console_lock; /* Control console initialization */
 
-extern void __kmp_vprintf( enum kmp_io __kmp_io, char const * format, va_list ap );
-extern void __kmp_printf( char const * format, ... );
-extern void __kmp_printf_no_lock( char const * format, ... );
-extern void __kmp_close_console( void );
+extern void __kmp_vprintf(enum kmp_io __kmp_io, char const *format, va_list ap);
+extern void __kmp_printf(char const *format, ...);
+extern void __kmp_printf_no_lock(char const *format, ...);
+extern void __kmp_close_console(void);
 
 #ifdef __cplusplus
 }
 #endif
 
 #endif /* KMP_IO_H */
-

runtime/src/kmp_itt.cpp

@@ -19,145 +19,133 @@
 #include "kmp_itt.h"
 
 #if KMP_DEBUG
-    #include "kmp_itt.inl"
+#include "kmp_itt.inl"
 #endif
 
-
 #if USE_ITT_NOTIFY
 
-    kmp_int32 __kmp_barrier_domain_count;
-    kmp_int32 __kmp_region_domain_count;
-    __itt_domain* __kmp_itt_barrier_domains[KMP_MAX_FRAME_DOMAINS];
-    __itt_domain* __kmp_itt_region_domains[KMP_MAX_FRAME_DOMAINS];
-    __itt_domain* __kmp_itt_imbalance_domains[KMP_MAX_FRAME_DOMAINS];
-    kmp_int32 __kmp_itt_region_team_size[KMP_MAX_FRAME_DOMAINS];
-    __itt_domain * metadata_domain = NULL;
-    __itt_string_handle * string_handle_imbl = NULL;
-    __itt_string_handle * string_handle_loop = NULL;
-    __itt_string_handle * string_handle_sngl = NULL;
+kmp_int32 __kmp_barrier_domain_count;
+kmp_int32 __kmp_region_domain_count;
+__itt_domain *__kmp_itt_barrier_domains[KMP_MAX_FRAME_DOMAINS];
+__itt_domain *__kmp_itt_region_domains[KMP_MAX_FRAME_DOMAINS];
+__itt_domain *__kmp_itt_imbalance_domains[KMP_MAX_FRAME_DOMAINS];
+kmp_int32 __kmp_itt_region_team_size[KMP_MAX_FRAME_DOMAINS];
+__itt_domain *metadata_domain = NULL;
+__itt_string_handle *string_handle_imbl = NULL;
+__itt_string_handle *string_handle_loop = NULL;
+__itt_string_handle *string_handle_sngl = NULL;
 
-    #include "kmp_version.h"
-    #include "kmp_i18n.h"
-    #include "kmp_str.h"
+#include "kmp_i18n.h"
+#include "kmp_str.h"
+#include "kmp_version.h"
 
-    KMP_BUILD_ASSERT( sizeof( kmp_itt_mark_t ) == sizeof( __itt_mark_type ) );
+KMP_BUILD_ASSERT(sizeof(kmp_itt_mark_t) == sizeof(__itt_mark_type));
 
-    /*
-        Previously used warnings:
+/* Previously used warnings:
 
-        KMP_WARNING( IttAllNotifDisabled );
-        KMP_WARNING( IttObjNotifDisabled );
-        KMP_WARNING( IttMarkNotifDisabled );
-        KMP_WARNING( IttUnloadLibFailed, libittnotify );
-    */
+   KMP_WARNING( IttAllNotifDisabled );
+   KMP_WARNING( IttObjNotifDisabled );
+   KMP_WARNING( IttMarkNotifDisabled );
+   KMP_WARNING( IttUnloadLibFailed, libittnotify );
+*/
 
-
-    kmp_int32 __kmp_itt_prepare_delay = 0;
-    kmp_bootstrap_lock_t __kmp_itt_debug_lock = KMP_BOOTSTRAP_LOCK_INITIALIZER( __kmp_itt_debug_lock );
+kmp_int32 __kmp_itt_prepare_delay = 0;
+kmp_bootstrap_lock_t __kmp_itt_debug_lock =
+    KMP_BOOTSTRAP_LOCK_INITIALIZER(__kmp_itt_debug_lock);
 
 #endif // USE_ITT_NOTIFY
 
 void __kmp_itt_initialize() {
 
-    // ITTNotify library is loaded and initialized at first call to any ittnotify function,
-    // so we do not need to explicitly load it any more.
-    // Jusr report OMP RTL version to ITTNotify.
+// ITTNotify library is loaded and initialized at first call to any ittnotify
+// function, so we do not need to explicitly load it any more. Just report OMP
+// RTL version to ITTNotify.
 
-    #if USE_ITT_NOTIFY
-        // Report OpenMP RTL version.
-        kmp_str_buf_t       buf;
-        __itt_mark_type     version;
-        __kmp_str_buf_init( & buf );
-        __kmp_str_buf_print(
-            & buf,
-            "OMP RTL Version %d.%d.%d",
-            __kmp_version_major,
-            __kmp_version_minor,
-            __kmp_version_build
-        );
-        if ( __itt_api_version_ptr != NULL ) {
-            __kmp_str_buf_print( & buf, ":%s", __itt_api_version() );
-        }; // if
-        version = __itt_mark_create( buf.str );
-        __itt_mark( version, NULL );
-        __kmp_str_buf_free( & buf );
-    #endif
+#if USE_ITT_NOTIFY
+  // Report OpenMP RTL version.
+  kmp_str_buf_t buf;
+  __itt_mark_type version;
+  __kmp_str_buf_init(&buf);
+  __kmp_str_buf_print(&buf, "OMP RTL Version %d.%d.%d", __kmp_version_major,
+                      __kmp_version_minor, __kmp_version_build);
+  if (__itt_api_version_ptr != NULL) {
+    __kmp_str_buf_print(&buf, ":%s", __itt_api_version());
+  }; // if
+  version = __itt_mark_create(buf.str);
+  __itt_mark(version, NULL);
+  __kmp_str_buf_free(&buf);
+#endif
 
 } // __kmp_itt_initialize
 
-
 void __kmp_itt_destroy() {
-    #if USE_ITT_NOTIFY
-        __kmp_itt_fini_ittlib();
-    #endif
+#if USE_ITT_NOTIFY
+  __kmp_itt_fini_ittlib();
+#endif
 } // __kmp_itt_destroy
 
+extern "C" void __itt_error_handler(__itt_error_code err, va_list args) {
 
-extern "C"
-void
-__itt_error_handler(
-    __itt_error_code err,
-    va_list args
-) {
-
-    switch ( err ) {
-        case __itt_error_no_module : {
-            char const * library = va_arg( args, char const * );
+  switch (err) {
+  case __itt_error_no_module: {
+    char const *library = va_arg(args, char const *);
 #if KMP_OS_WINDOWS
-            int sys_err = va_arg( args, int );
-            kmp_msg_t err_code = KMP_SYSERRCODE( sys_err );
-            __kmp_msg( kmp_ms_warning, KMP_MSG( IttLoadLibFailed, library ), err_code, __kmp_msg_null );
-            if (__kmp_generate_warnings == kmp_warnings_off) {
-              __kmp_str_free(&err_code.str);
-            }
+    int sys_err = va_arg(args, int);
+    kmp_msg_t err_code = KMP_SYSERRCODE(sys_err);
+    __kmp_msg(kmp_ms_warning, KMP_MSG(IttLoadLibFailed, library), err_code,
+              __kmp_msg_null);
+    if (__kmp_generate_warnings == kmp_warnings_off) {
+      __kmp_str_free(&err_code.str);
+    }
 #else
-            char const * sys_err = va_arg( args, char const * );
-            kmp_msg_t err_code = KMP_SYSERRMESG( sys_err );
-            __kmp_msg( kmp_ms_warning, KMP_MSG( IttLoadLibFailed, library ), err_code, __kmp_msg_null );
-            if (__kmp_generate_warnings == kmp_warnings_off) {
-              __kmp_str_free(&err_code.str);
-            }
+    char const *sys_err = va_arg(args, char const *);
+    kmp_msg_t err_code = KMP_SYSERRMESG(sys_err);
+    __kmp_msg(kmp_ms_warning, KMP_MSG(IttLoadLibFailed, library), err_code,
+              __kmp_msg_null);
+    if (__kmp_generate_warnings == kmp_warnings_off) {
+      __kmp_str_free(&err_code.str);
+    }
 #endif
-        } break;
-        case __itt_error_no_symbol : {
-            char const * library = va_arg( args, char const * );
-            char const * symbol  = va_arg( args, char const * );
-            KMP_WARNING( IttLookupFailed, symbol, library );
-        } break;
-        case __itt_error_unknown_group : {
-            char const * var   = va_arg( args, char const * );
-            char const * group = va_arg( args, char const * );
-            KMP_WARNING( IttUnknownGroup, var, group );
-        } break;
-        case __itt_error_env_too_long : {
-            char const * var     = va_arg( args, char const * );
-            size_t       act_len = va_arg( args, size_t );
-            size_t       max_len = va_arg( args, size_t );
-            KMP_WARNING( IttEnvVarTooLong, var, (unsigned long) act_len, (unsigned long) max_len );
-        } break;
-        case __itt_error_cant_read_env : {
-            char const * var     = va_arg( args, char const * );
-            int          sys_err = va_arg( args, int );
-            kmp_msg_t err_code = KMP_ERR( sys_err );
-            __kmp_msg( kmp_ms_warning, KMP_MSG( CantGetEnvVar, var ), err_code, __kmp_msg_null );
-            if (__kmp_generate_warnings == kmp_warnings_off) {
-              __kmp_str_free(&err_code.str);
-            }
-        } break;
-        case __itt_error_system : {
-            char const * func    = va_arg( args, char const * );
-            int          sys_err = va_arg( args, int );
-            kmp_msg_t err_code = KMP_SYSERRCODE( sys_err );
-            __kmp_msg( kmp_ms_warning, KMP_MSG( IttFunctionError, func ), err_code, __kmp_msg_null );
-            if (__kmp_generate_warnings == kmp_warnings_off) {
-              __kmp_str_free(&err_code.str);
-            }
-        } break;
-        default : {
-            KMP_WARNING( IttUnknownError, err );
-        };
-    }; // switch
-
+  } break;
+  case __itt_error_no_symbol: {
+    char const *library = va_arg(args, char const *);
+    char const *symbol = va_arg(args, char const *);
+    KMP_WARNING(IttLookupFailed, symbol, library);
+  } break;
+  case __itt_error_unknown_group: {
+    char const *var = va_arg(args, char const *);
+    char const *group = va_arg(args, char const *);
+    KMP_WARNING(IttUnknownGroup, var, group);
+  } break;
+  case __itt_error_env_too_long: {
+    char const *var = va_arg(args, char const *);
+    size_t act_len = va_arg(args, size_t);
+    size_t max_len = va_arg(args, size_t);
+    KMP_WARNING(IttEnvVarTooLong, var, (unsigned long)act_len,
+                (unsigned long)max_len);
+  } break;
+  case __itt_error_cant_read_env: {
+    char const *var = va_arg(args, char const *);
+    int sys_err = va_arg(args, int);
+    kmp_msg_t err_code = KMP_ERR(sys_err);
+    __kmp_msg(kmp_ms_warning, KMP_MSG(CantGetEnvVar, var), err_code,
+              __kmp_msg_null);
+    if (__kmp_generate_warnings == kmp_warnings_off) {
+      __kmp_str_free(&err_code.str);
+    }
+  } break;
+  case __itt_error_system: {
+    char const *func = va_arg(args, char const *);
+    int sys_err = va_arg(args, int);
+    kmp_msg_t err_code = KMP_SYSERRCODE(sys_err);
+    __kmp_msg(kmp_ms_warning, KMP_MSG(IttFunctionError, func), err_code,
+              __kmp_msg_null);
+    if (__kmp_generate_warnings == kmp_warnings_off) {
+      __kmp_str_free(&err_code.str);
+    }
+  } break;
+  default: { KMP_WARNING(IttUnknownError, err); };
+  }; // switch
 } // __itt_error_handler
 
 #endif /* USE_ITT_BUILD */

runtime/src/kmp_itt.h

@@ -24,104 +24,121 @@
 #include "legacy/ittnotify.h"
 
 #if KMP_DEBUG
-    #define __kmp_inline           // Turn off inlining in debug mode.
+#define __kmp_inline // Turn off inlining in debug mode.
 #else
-    #define __kmp_inline static inline
+#define __kmp_inline static inline
 #endif
 
 #if USE_ITT_NOTIFY
-    extern kmp_int32  __kmp_itt_prepare_delay;
-# ifdef __cplusplus
-    extern "C" void __kmp_itt_fini_ittlib(void);
-# else
-    extern void __kmp_itt_fini_ittlib(void);
-# endif
+extern kmp_int32 __kmp_itt_prepare_delay;
+#ifdef __cplusplus
+extern "C" void __kmp_itt_fini_ittlib(void);
+#else
+extern void __kmp_itt_fini_ittlib(void);
+#endif
 #endif
 
-// Simplify the handling of an argument that is only required when USE_ITT_BUILD is enabled.
-#define USE_ITT_BUILD_ARG(x) ,x
+// Simplify the handling of an argument that is only required when USE_ITT_BUILD
+// is enabled.
+#define USE_ITT_BUILD_ARG(x) , x
 
 void __kmp_itt_initialize();
 void __kmp_itt_destroy();
 
-// -------------------------------------------------------------------------------------------------
+// -----------------------------------------------------------------------------
 // New stuff for reporting high-level constructs.
-// -------------------------------------------------------------------------------------------------
 
 // Note the naming convention:
 //     __kmp_itt_xxxing() function should be called before action, while
 //     __kmp_itt_xxxed()  function should be called after action.
 
 // --- Parallel region reporting ---
-__kmp_inline void __kmp_itt_region_forking(  int gtid, int team_size, int barriers ); // Master only, before forking threads.
-__kmp_inline void __kmp_itt_region_joined(   int gtid ); // Master only, after joining threads.
-    // (*) Note: A thread may execute tasks after this point, though.
+__kmp_inline void
+__kmp_itt_region_forking(int gtid, int team_size,
+                         int barriers); // Master only, before forking threads.
+__kmp_inline void
+__kmp_itt_region_joined(int gtid); // Master only, after joining threads.
+// (*) Note: A thread may execute tasks after this point, though.
 
 // --- Frame reporting ---
-// region = 0 - no regions, region = 1 - parallel, region = 2 - serialized parallel
-__kmp_inline void __kmp_itt_frame_submit( int gtid, __itt_timestamp begin, __itt_timestamp end, int imbalance, ident_t *loc, int team_size, int region = 0 );
+// region=0: no regions, region=1: parallel, region=2: serialized parallel
+__kmp_inline void __kmp_itt_frame_submit(int gtid, __itt_timestamp begin,
+                                         __itt_timestamp end, int imbalance,
+                                         ident_t *loc, int team_size,
+                                         int region = 0);
 
 // --- Metadata reporting ---
-// begin/end - begin/end timestamps of a barrier frame, imbalance - aggregated wait time value, reduction -if this is a reduction barrier
-__kmp_inline void __kmp_itt_metadata_imbalance( int gtid, kmp_uint64 begin, kmp_uint64 end, kmp_uint64 imbalance, kmp_uint64 reduction );
-// sched_type: 0 - static, 1 - dynamic, 2 - guided, 3 - custom (all others); iterations - loop trip count, chunk - chunk size
-__kmp_inline void __kmp_itt_metadata_loop( ident_t * loc, kmp_uint64 sched_type, kmp_uint64 iterations, kmp_uint64 chunk );
-__kmp_inline void __kmp_itt_metadata_single( ident_t * loc );
+// begin/end - begin/end timestamps of a barrier frame, imbalance - aggregated
+// wait time value, reduction -if this is a reduction barrier
+__kmp_inline void __kmp_itt_metadata_imbalance(int gtid, kmp_uint64 begin,
+                                               kmp_uint64 end,
+                                               kmp_uint64 imbalance,
+                                               kmp_uint64 reduction);
+// sched_type: 0 - static, 1 - dynamic, 2 - guided, 3 - custom (all others);
+// iterations - loop trip count, chunk - chunk size
+__kmp_inline void __kmp_itt_metadata_loop(ident_t *loc, kmp_uint64 sched_type,
+                                          kmp_uint64 iterations,
+                                          kmp_uint64 chunk);
+__kmp_inline void __kmp_itt_metadata_single(ident_t *loc);
 
 // --- Barrier reporting ---
-__kmp_inline void * __kmp_itt_barrier_object( int gtid, int bt, int set_name = 0, int delta = 0 );
-__kmp_inline void   __kmp_itt_barrier_starting( int gtid, void * object );
-__kmp_inline void   __kmp_itt_barrier_middle(   int gtid, void * object );
-__kmp_inline void   __kmp_itt_barrier_finished( int gtid, void * object );
+__kmp_inline void *__kmp_itt_barrier_object(int gtid, int bt, int set_name = 0,
+                                            int delta = 0);
+__kmp_inline void __kmp_itt_barrier_starting(int gtid, void *object);
+__kmp_inline void __kmp_itt_barrier_middle(int gtid, void *object);
+__kmp_inline void __kmp_itt_barrier_finished(int gtid, void *object);
 
 // --- Taskwait reporting ---
-__kmp_inline void * __kmp_itt_taskwait_object( int gtid );
-__kmp_inline void   __kmp_itt_taskwait_starting( int gtid, void * object );
-__kmp_inline void   __kmp_itt_taskwait_finished(   int gtid, void * object );
+__kmp_inline void *__kmp_itt_taskwait_object(int gtid);
+__kmp_inline void __kmp_itt_taskwait_starting(int gtid, void *object);
+__kmp_inline void __kmp_itt_taskwait_finished(int gtid, void *object);
 
 // --- Task reporting ---
-__kmp_inline void   __kmp_itt_task_starting( void * object );
-__kmp_inline void   __kmp_itt_task_finished( void * object );
+__kmp_inline void __kmp_itt_task_starting(void *object);
+__kmp_inline void __kmp_itt_task_finished(void *object);
 
 // --- Lock reporting ---
 #if KMP_USE_DYNAMIC_LOCK
-__kmp_inline void   __kmp_itt_lock_creating(  kmp_user_lock_p lock, const ident_t * );
+__kmp_inline void __kmp_itt_lock_creating(kmp_user_lock_p lock,
+                                          const ident_t *);
 #else
-__kmp_inline void   __kmp_itt_lock_creating(  kmp_user_lock_p lock );
+__kmp_inline void __kmp_itt_lock_creating(kmp_user_lock_p lock);
 #endif
-__kmp_inline void   __kmp_itt_lock_acquiring( kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_lock_acquired(  kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_lock_releasing( kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_lock_cancelled( kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_lock_destroyed( kmp_user_lock_p lock );
+__kmp_inline void __kmp_itt_lock_acquiring(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_lock_acquired(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_lock_releasing(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_lock_cancelled(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_lock_destroyed(kmp_user_lock_p lock);
 
 // --- Critical reporting ---
 #if KMP_USE_DYNAMIC_LOCK
-__kmp_inline void   __kmp_itt_critical_creating(  kmp_user_lock_p lock, const ident_t * );
+__kmp_inline void __kmp_itt_critical_creating(kmp_user_lock_p lock,
+                                              const ident_t *);
 #else
-__kmp_inline void   __kmp_itt_critical_creating(  kmp_user_lock_p lock );
+__kmp_inline void __kmp_itt_critical_creating(kmp_user_lock_p lock);
 #endif
-__kmp_inline void   __kmp_itt_critical_acquiring( kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_critical_acquired(  kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_critical_releasing( kmp_user_lock_p lock );
-__kmp_inline void   __kmp_itt_critical_destroyed( kmp_user_lock_p lock );
+__kmp_inline void __kmp_itt_critical_acquiring(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_critical_acquired(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_critical_releasing(kmp_user_lock_p lock);
+__kmp_inline void __kmp_itt_critical_destroyed(kmp_user_lock_p lock);
 
 // --- Single reporting ---
-__kmp_inline void   __kmp_itt_single_start( int gtid );
-__kmp_inline void   __kmp_itt_single_end(   int gtid );
+__kmp_inline void __kmp_itt_single_start(int gtid);
+__kmp_inline void __kmp_itt_single_end(int gtid);
 
 // --- Ordered reporting ---
-__kmp_inline void   __kmp_itt_ordered_init(  int gtid );
-__kmp_inline void   __kmp_itt_ordered_prep(  int gtid );
-__kmp_inline void   __kmp_itt_ordered_start( int gtid );
-__kmp_inline void   __kmp_itt_ordered_end(   int gtid );
+__kmp_inline void __kmp_itt_ordered_init(int gtid);
+__kmp_inline void __kmp_itt_ordered_prep(int gtid);
+__kmp_inline void __kmp_itt_ordered_start(int gtid);
+__kmp_inline void __kmp_itt_ordered_end(int gtid);
 
 // --- Threads reporting ---
-__kmp_inline void  __kmp_itt_thread_ignore();
-__kmp_inline void  __kmp_itt_thread_name( int gtid );
+__kmp_inline void __kmp_itt_thread_ignore();
+__kmp_inline void __kmp_itt_thread_name(int gtid);
 
 // --- System objects ---
-__kmp_inline void   __kmp_itt_system_object_created( void * object, char const * name );
+__kmp_inline void __kmp_itt_system_object_created(void *object,
+                                                  char const *name);
 
 // --- Stack stitching ---
 __kmp_inline __itt_caller __kmp_itt_stack_caller_create(void);
@@ -129,184 +146,189 @@ __kmp_inline void __kmp_itt_stack_caller_destroy(__itt_caller);
 __kmp_inline void __kmp_itt_stack_callee_enter(__itt_caller);
 __kmp_inline void __kmp_itt_stack_callee_leave(__itt_caller);
 
-// -------------------------------------------------------------------------------------------------
+// -----------------------------------------------------------------------------
 // Old stuff for reporting low-level internal synchronization.
-// -------------------------------------------------------------------------------------------------
 
 #if USE_ITT_NOTIFY
 
-    /*
-     * Support for SSC marks, which are used by SDE
-     * http://software.intel.com/en-us/articles/intel-software-development-emulator
-     * to mark points in instruction traces that represent spin-loops and are
-     * therefore uninteresting when collecting traces for architecture simulation.
-     */
-    #ifndef INCLUDE_SSC_MARKS
-    # define INCLUDE_SSC_MARKS (KMP_OS_LINUX && KMP_ARCH_X86_64)
-    #endif
+/* Support for SSC marks, which are used by SDE
+   http://software.intel.com/en-us/articles/intel-software-development-emulator
+   to mark points in instruction traces that represent spin-loops and are
+   therefore uninteresting when collecting traces for architecture simulation.
+ */
+#ifndef INCLUDE_SSC_MARKS
+#define INCLUDE_SSC_MARKS (KMP_OS_LINUX && KMP_ARCH_X86_64)
+#endif
 
-    /* Linux 64 only for now */
-    #if (INCLUDE_SSC_MARKS && KMP_OS_LINUX && KMP_ARCH_X86_64)
-    // Portable (at least for gcc and icc) code to insert the necessary instructions
-    // to set %ebx and execute the unlikely no-op.
-      #if defined( __INTEL_COMPILER )
-      # define INSERT_SSC_MARK(tag) __SSC_MARK(tag)
-      #else
-      # define INSERT_SSC_MARK(tag)                                          \
-      __asm__ __volatile__ ("movl %0, %%ebx; .byte 0x64, 0x67, 0x90 " ::"i"(tag):"%ebx")
-      #endif
-    #else
-    # define INSERT_SSC_MARK(tag) ((void)0)
-    #endif
+/* Linux 64 only for now */
+#if (INCLUDE_SSC_MARKS && KMP_OS_LINUX && KMP_ARCH_X86_64)
+// Portable (at least for gcc and icc) code to insert the necessary instructions
+// to set %ebx and execute the unlikely no-op.
+#if defined(__INTEL_COMPILER)
+#define INSERT_SSC_MARK(tag) __SSC_MARK(tag)
+#else
+#define INSERT_SSC_MARK(tag)                                                   \
+  __asm__ __volatile__("movl %0, %%ebx; .byte 0x64, 0x67, 0x90 " ::"i"(tag)    \
+                       : "%ebx")
+#endif
+#else
+#define INSERT_SSC_MARK(tag) ((void)0)
+#endif
 
-    /* Markers for the start and end of regions that represent polling and
-     * are therefore uninteresting to architectural simulations 0x4376 and
-     * 0x4377 are arbitrary numbers that should be unique in the space of
-     * SSC tags, but there is no central issuing authority rather
-     * randomness is expected to work.
-     */
-    #define SSC_MARK_SPIN_START() INSERT_SSC_MARK(0x4376)
-    #define SSC_MARK_SPIN_END()   INSERT_SSC_MARK(0x4377)
+/* Markers for the start and end of regions that represent polling and are
+   therefore uninteresting to architectural simulations 0x4376 and 0x4377 are
+   arbitrary numbers that should be unique in the space of SSC tags, but there
+   is no central issuing authority rather randomness is expected to work. */
+#define SSC_MARK_SPIN_START() INSERT_SSC_MARK(0x4376)
+#define SSC_MARK_SPIN_END() INSERT_SSC_MARK(0x4377)
 
-    // Markers for architecture simulation.
-    // FORKING      : Before the master thread forks.
-    // JOINING      : At the start of the join.
-    // INVOKING     : Before the threads invoke microtasks.
-    // DISPATCH_INIT: At the start of dynamically scheduled loop.
-    // DISPATCH_NEXT: After claming next iteration of dynamically scheduled loop.
-    #define SSC_MARK_FORKING()          INSERT_SSC_MARK(0xd693)
-    #define SSC_MARK_JOINING()          INSERT_SSC_MARK(0xd694)
-    #define SSC_MARK_INVOKING()         INSERT_SSC_MARK(0xd695)
-    #define SSC_MARK_DISPATCH_INIT()    INSERT_SSC_MARK(0xd696)
-    #define SSC_MARK_DISPATCH_NEXT()    INSERT_SSC_MARK(0xd697)
+// Markers for architecture simulation.
+// FORKING      : Before the master thread forks.
+// JOINING      : At the start of the join.
+// INVOKING     : Before the threads invoke microtasks.
+// DISPATCH_INIT: At the start of dynamically scheduled loop.
+// DISPATCH_NEXT: After claming next iteration of dynamically scheduled loop.
+#define SSC_MARK_FORKING() INSERT_SSC_MARK(0xd693)
+#define SSC_MARK_JOINING() INSERT_SSC_MARK(0xd694)
+#define SSC_MARK_INVOKING() INSERT_SSC_MARK(0xd695)
+#define SSC_MARK_DISPATCH_INIT() INSERT_SSC_MARK(0xd696)
+#define SSC_MARK_DISPATCH_NEXT() INSERT_SSC_MARK(0xd697)
 
-    // The object is an address that associates a specific set of the prepare, acquire, release,
-    // and cancel operations.
+// The object is an address that associates a specific set of the prepare,
+// acquire, release, and cancel operations.
 
-    /* Sync prepare indicates a thread is going to start waiting for another thread
-       to send a release event.  This operation should be done just before the thread
-       begins checking for the existence of the release event */
+/* Sync prepare indicates a thread is going to start waiting for another thread
+   to send a release event.  This operation should be done just before the
+   thread begins checking for the existence of the release event */
 
-    /* Sync cancel indicates a thread is cancelling a wait on another thread anc
-       continuing execution without waiting for the other thread to release it */
+/* Sync cancel indicates a thread is cancelling a wait on another thread and
+   continuing execution without waiting for the other thread to release it */
 
-    /* Sync acquired indicates a thread has received a release event from another
-       thread and has stopped waiting.  This operation must occur only after the release
-       event is received. */
+/* Sync acquired indicates a thread has received a release event from another
+   thread and has stopped waiting.  This operation must occur only after the
+   release event is received. */
 
-    /* Sync release indicates a thread is going to send a release event to another thread
-       so it will stop waiting and continue execution. This operation must just happen before
-       the release event. */
+/* Sync release indicates a thread is going to send a release event to another
+   thread so it will stop waiting and continue execution. This operation must
+   just happen before the release event. */
 
-    #define KMP_FSYNC_PREPARE(   obj )  __itt_fsync_prepare(   (void *)( obj ) )
-    #define KMP_FSYNC_CANCEL(    obj )  __itt_fsync_cancel(    (void *)( obj ) )
-    #define KMP_FSYNC_ACQUIRED(  obj )  __itt_fsync_acquired(  (void *)( obj ) )
-    #define KMP_FSYNC_RELEASING( obj )  __itt_fsync_releasing( (void *)( obj ) )
+#define KMP_FSYNC_PREPARE(obj) __itt_fsync_prepare((void *)(obj))
+#define KMP_FSYNC_CANCEL(obj) __itt_fsync_cancel((void *)(obj))
+#define KMP_FSYNC_ACQUIRED(obj) __itt_fsync_acquired((void *)(obj))
+#define KMP_FSYNC_RELEASING(obj) __itt_fsync_releasing((void *)(obj))
 
-    /*
-        In case of waiting in a spin loop, ITT wants KMP_FSYNC_PREPARE() to be called with a delay
-        (and not called at all if waiting time is small). So, in spin loops, do not use
-        KMP_FSYNC_PREPARE(), but use KMP_FSYNC_SPIN_INIT() (before spin loop),
-        KMP_FSYNC_SPIN_PREPARE() (whithin the spin loop), and KMP_FSYNC_SPIN_ACQUIRED().
-        See KMP_WAIT_YIELD() for example.
-    */
+/* In case of waiting in a spin loop, ITT wants KMP_FSYNC_PREPARE() to be called
+   with a delay (and not called at all if waiting time is small). So, in spin
+   loops, do not use KMP_FSYNC_PREPARE(), but use KMP_FSYNC_SPIN_INIT() (before
+   spin loop), KMP_FSYNC_SPIN_PREPARE() (whithin the spin loop), and
+   KMP_FSYNC_SPIN_ACQUIRED(). See KMP_WAIT_YIELD() for example. */
 
-    #undef  KMP_FSYNC_SPIN_INIT
-    #define KMP_FSYNC_SPIN_INIT( obj, spin )    \
-        int sync_iters = 0;                     \
-        if ( __itt_fsync_prepare_ptr ) {        \
-            if ( obj == NULL ) {                \
-                obj = spin;                     \
-            } /* if */                          \
-        } /* if */                              \
-        SSC_MARK_SPIN_START()
+#undef KMP_FSYNC_SPIN_INIT
+#define KMP_FSYNC_SPIN_INIT(obj, spin)                                         \
+  int sync_iters = 0;                                                          \
+  if (__itt_fsync_prepare_ptr) {                                               \
+    if (obj == NULL) {                                                         \
+      obj = spin;                                                              \
+    } /* if */                                                                 \
+  } /* if */                                                                   \
+  SSC_MARK_SPIN_START()
 
-    #undef  KMP_FSYNC_SPIN_PREPARE
-    #define KMP_FSYNC_SPIN_PREPARE( obj ) do {                          \
-        if ( __itt_fsync_prepare_ptr && sync_iters < __kmp_itt_prepare_delay ) { \
-            ++ sync_iters;                                              \
-            if ( sync_iters >= __kmp_itt_prepare_delay ) {              \
-                KMP_FSYNC_PREPARE( (void*) obj );                       \
-            } /* if */                                                  \
-        } /* if */                                                      \
-     } while (0)
-    #undef  KMP_FSYNC_SPIN_ACQUIRED
-    #define KMP_FSYNC_SPIN_ACQUIRED( obj ) do {         \
-        SSC_MARK_SPIN_END();                            \
-        if ( sync_iters >= __kmp_itt_prepare_delay ) {  \
-            KMP_FSYNC_ACQUIRED( (void*) obj );          \
-        } /* if */                                      \
-     } while (0)
+#undef KMP_FSYNC_SPIN_PREPARE
+#define KMP_FSYNC_SPIN_PREPARE(obj)                                            \
+  do {                                                                         \
+    if (__itt_fsync_prepare_ptr && sync_iters < __kmp_itt_prepare_delay) {     \
+      ++sync_iters;                                                            \
+      if (sync_iters >= __kmp_itt_prepare_delay) {                             \
+        KMP_FSYNC_PREPARE((void *)obj);                                        \
+      } /* if */                                                               \
+    } /* if */                                                                 \
+  } while (0)
+#undef KMP_FSYNC_SPIN_ACQUIRED
+#define KMP_FSYNC_SPIN_ACQUIRED(obj)                                           \
+  do {                                                                         \
+    SSC_MARK_SPIN_END();                                                       \
+    if (sync_iters >= __kmp_itt_prepare_delay) {                               \
+      KMP_FSYNC_ACQUIRED((void *)obj);                                         \
+    } /* if */                                                                 \
+  } while (0)
 
-    /* ITT will not report objects created within KMP_ITT_IGNORE(), e. g.:
-           KMP_ITT_IGNORE(
-               ptr = malloc( size );
-           );
-    */
-    #define KMP_ITT_IGNORE( statement ) do {                            \
-            __itt_state_t __itt_state_;                                 \
-            if ( __itt_state_get_ptr ) {                                \
-                __itt_state_ = __itt_state_get();                       \
-                __itt_obj_mode_set( __itt_obj_prop_ignore, __itt_obj_state_set ); \
-            }  /* if */                                                 \
-            { statement }                                               \
-            if ( __itt_state_get_ptr ) {                                \
-                __itt_state_set( __itt_state_ );                        \
-            }  /* if */                                                 \
-    } while (0)
+/* ITT will not report objects created within KMP_ITT_IGNORE(), e. g.:
+       KMP_ITT_IGNORE(
+           ptr = malloc( size );
+       );
+*/
+#define KMP_ITT_IGNORE(statement)                                              \
+  do {                                                                         \
+    __itt_state_t __itt_state_;                                                \
+    if (__itt_state_get_ptr) {                                                 \
+      __itt_state_ = __itt_state_get();                                        \
+      __itt_obj_mode_set(__itt_obj_prop_ignore, __itt_obj_state_set);          \
+    } /* if */                                                                 \
+    { statement }                                                              \
+    if (__itt_state_get_ptr) {                                                 \
+      __itt_state_set(__itt_state_);                                           \
+    } /* if */                                                                 \
+  } while (0)
 
-    const int KMP_MAX_FRAME_DOMAINS = 512; // Maximum number of frame domains to use (maps to
-                                           // different OpenMP regions in the user source code).
-    extern kmp_int32 __kmp_barrier_domain_count;
-    extern kmp_int32 __kmp_region_domain_count;
-    extern __itt_domain* __kmp_itt_barrier_domains[KMP_MAX_FRAME_DOMAINS];
-    extern __itt_domain* __kmp_itt_region_domains[KMP_MAX_FRAME_DOMAINS];
-    extern __itt_domain* __kmp_itt_imbalance_domains[KMP_MAX_FRAME_DOMAINS];
-    extern kmp_int32 __kmp_itt_region_team_size[KMP_MAX_FRAME_DOMAINS];
-    extern __itt_domain * metadata_domain;
-    extern __itt_string_handle * string_handle_imbl;
-    extern __itt_string_handle * string_handle_loop;
-    extern __itt_string_handle * string_handle_sngl;
+const int KMP_MAX_FRAME_DOMAINS =
+    512; // Maximum number of frame domains to use (maps to
+// different OpenMP regions in the user source code).
+extern kmp_int32 __kmp_barrier_domain_count;
+extern kmp_int32 __kmp_region_domain_count;
+extern __itt_domain *__kmp_itt_barrier_domains[KMP_MAX_FRAME_DOMAINS];
+extern __itt_domain *__kmp_itt_region_domains[KMP_MAX_FRAME_DOMAINS];
+extern __itt_domain *__kmp_itt_imbalance_domains[KMP_MAX_FRAME_DOMAINS];
+extern kmp_int32 __kmp_itt_region_team_size[KMP_MAX_FRAME_DOMAINS];
+extern __itt_domain *metadata_domain;
+extern __itt_string_handle *string_handle_imbl;
+extern __itt_string_handle *string_handle_loop;
+extern __itt_string_handle *string_handle_sngl;
 
 #else
 
 // Null definitions of the synchronization tracing functions.
-# define KMP_FSYNC_PREPARE(   obj )        ((void)0)
-# define KMP_FSYNC_CANCEL(    obj )        ((void)0)
-# define KMP_FSYNC_ACQUIRED(  obj )        ((void)0)
-# define KMP_FSYNC_RELEASING( obj )        ((void)0)
+#define KMP_FSYNC_PREPARE(obj) ((void)0)
+#define KMP_FSYNC_CANCEL(obj) ((void)0)
+#define KMP_FSYNC_ACQUIRED(obj) ((void)0)
+#define KMP_FSYNC_RELEASING(obj) ((void)0)
 
-# define KMP_FSYNC_SPIN_INIT( obj, spin )  ((void)0)
-# define KMP_FSYNC_SPIN_PREPARE(  obj )    ((void)0)
-# define KMP_FSYNC_SPIN_ACQUIRED( obj )    ((void)0)
+#define KMP_FSYNC_SPIN_INIT(obj, spin) ((void)0)
+#define KMP_FSYNC_SPIN_PREPARE(obj) ((void)0)
+#define KMP_FSYNC_SPIN_ACQUIRED(obj) ((void)0)
 
-# define KMP_ITT_IGNORE(stmt ) do { stmt } while (0)
+#define KMP_ITT_IGNORE(stmt)                                                   \
+  do {                                                                         \
+    stmt                                                                       \
+  } while (0)
 
 #endif // USE_ITT_NOTIFY
 
-#if ! KMP_DEBUG
-    // In release mode include definitions of inline functions.
-    #include "kmp_itt.inl"
+#if !KMP_DEBUG
+// In release mode include definitions of inline functions.
+#include "kmp_itt.inl"
 #endif
 
 #endif // KMP_ITT_H
 
-#else  /* USE_ITT_BUILD */
+#else /* USE_ITT_BUILD */
 
 // Null definitions of the synchronization tracing functions.
 // If USE_ITT_BULID is not enabled, USE_ITT_NOTIFY cannot be either.
 // By defining these we avoid unpleasant ifdef tests in many places.
-# define KMP_FSYNC_PREPARE(   obj )        ((void)0)
-# define KMP_FSYNC_CANCEL(    obj )        ((void)0)
-# define KMP_FSYNC_ACQUIRED(  obj )        ((void)0)
-# define KMP_FSYNC_RELEASING( obj )        ((void)0)
+#define KMP_FSYNC_PREPARE(obj) ((void)0)
+#define KMP_FSYNC_CANCEL(obj) ((void)0)
+#define KMP_FSYNC_ACQUIRED(obj) ((void)0)
+#define KMP_FSYNC_RELEASING(obj) ((void)0)
 
-# define KMP_FSYNC_SPIN_INIT( obj, spin )  ((void)0)
-# define KMP_FSYNC_SPIN_PREPARE(  obj )    ((void)0)
-# define KMP_FSYNC_SPIN_ACQUIRED( obj )    ((void)0)
+#define KMP_FSYNC_SPIN_INIT(obj, spin) ((void)0)
+#define KMP_FSYNC_SPIN_PREPARE(obj) ((void)0)
+#define KMP_FSYNC_SPIN_ACQUIRED(obj) ((void)0)
 
-# define KMP_ITT_IGNORE(stmt ) do { stmt } while (0)
+#define KMP_ITT_IGNORE(stmt)                                                   \
+  do {                                                                         \
+    stmt                                                                       \
+  } while (0)
 
-# define USE_ITT_BUILD_ARG(x)
+#define USE_ITT_BUILD_ARG(x)
 
 #endif /* USE_ITT_BUILD */

runtime/src/kmp_omp.h

@@ -16,216 +16,224 @@
 
 
 /* THIS FILE SHOULD NOT BE MODIFIED IN IDB INTERFACE LIBRARY CODE
- * It should instead be modified in the OpenMP runtime and copied
- * to the interface library code.  This way we can minimize the
- * problems that this is sure to cause having two copies of the
- * same file.
- *
- * files live in libomp and libomp_db/src/include
- */
+   It should instead be modified in the OpenMP runtime and copied to the
+   interface library code.  This way we can minimize the problems that this is
+   sure to cause having two copies of the same file.
+
+   Files live in libomp and libomp_db/src/include  */
 
 /* CHANGE THIS WHEN STRUCTURES BELOW CHANGE
- * Before we release this to a customer, please don't change this value.  After it is released and
- * stable, then any new updates to the structures or data structure traversal algorithms need to
- * change this value.
- */
+   Before we release this to a customer, please don't change this value.  After
+   it is released and stable, then any new updates to the structures or data
+   structure traversal algorithms need to change this value. */
 #define KMP_OMP_VERSION 9
 
 typedef struct {
-    kmp_int32  offset;
-    kmp_int32  size;
+  kmp_int32 offset;
+  kmp_int32 size;
 } offset_and_size_t;
 
 typedef struct {
-    kmp_uint64    addr;
-    kmp_int32     size;
-    kmp_int32     padding;
+  kmp_uint64 addr;
+  kmp_int32 size;
+  kmp_int32 padding;
 } addr_and_size_t;
 
 typedef struct {
-    kmp_uint64   flags;         // Flags for future extensions.
-    kmp_uint64   file;          // Pointer to name of source file where the parallel region is.
-    kmp_uint64   func;          // Pointer to name of routine where the parallel region is.
-    kmp_int32    begin;         // Beginning of source line range.
-    kmp_int32    end;           // End of source line range.
-    kmp_int32    num_threads;   // Specified number of threads.
+  kmp_uint64 flags; // Flags for future extensions.
+  kmp_uint64
+      file; // Pointer to name of source file where the parallel region is.
+  kmp_uint64 func; // Pointer to name of routine where the parallel region is.
+  kmp_int32 begin; // Beginning of source line range.
+  kmp_int32 end; // End of source line range.
+  kmp_int32 num_threads; // Specified number of threads.
 } kmp_omp_nthr_item_t;
 
 typedef struct {
-    kmp_int32     num;          // Number of items in the arrray.
-    kmp_uint64    array;        // Address of array of kmp_omp_num_threads_item_t.
+  kmp_int32 num; // Number of items in the arrray.
+  kmp_uint64 array; // Address of array of kmp_omp_num_threads_item_t.
 } kmp_omp_nthr_info_t;
 
-
 /* This structure is known to the idb interface library */
 typedef struct {
 
-    /* Change this only if you make a fundamental data structure change here */
-    kmp_int32          lib_version;
+  /* Change this only if you make a fundamental data structure change here */
+  kmp_int32 lib_version;
 
-    /* sanity check.  Only should be checked if versions are identical
-     * This is also used for backward compatibility to get the runtime
-     * structure size if it the runtime is older than the interface */
-    kmp_int32          sizeof_this_structure;
+  /* sanity check.  Only should be checked if versions are identical
+   * This is also used for backward compatibility to get the runtime
+   * structure size if it the runtime is older than the interface */
+  kmp_int32 sizeof_this_structure;
 
-    /* OpenMP RTL version info. */
-    addr_and_size_t    major;
-    addr_and_size_t    minor;
-    addr_and_size_t    build;
-    addr_and_size_t    openmp_version;
-    addr_and_size_t    banner;
+  /* OpenMP RTL version info. */
+  addr_and_size_t major;
+  addr_and_size_t minor;
+  addr_and_size_t build;
+  addr_and_size_t openmp_version;
+  addr_and_size_t banner;
 
-    /* Various globals. */
-    addr_and_size_t  threads;            // Pointer to __kmp_threads.
-    addr_and_size_t  roots;              // Pointer to __kmp_root.
-    addr_and_size_t  capacity;           // Pointer to __kmp_threads_capacity.
-    addr_and_size_t  monitor;            // Pointer to __kmp_monitor.
-#if ! KMP_USE_DYNAMIC_LOCK
-    addr_and_size_t  lock_table;         // Pointer to __kmp_lock_table.
+  /* Various globals. */
+  addr_and_size_t threads; // Pointer to __kmp_threads.
+  addr_and_size_t roots; // Pointer to __kmp_root.
+  addr_and_size_t capacity; // Pointer to __kmp_threads_capacity.
+  addr_and_size_t monitor; // Pointer to __kmp_monitor.
+#if !KMP_USE_DYNAMIC_LOCK
+  addr_and_size_t lock_table; // Pointer to __kmp_lock_table.
 #endif
-    addr_and_size_t  func_microtask;
-    addr_and_size_t  func_fork;
-    addr_and_size_t  func_fork_teams;
-    addr_and_size_t  team_counter;
-    addr_and_size_t  task_counter;
-    addr_and_size_t  nthr_info;
-    kmp_int32        address_width;
-    kmp_int32        indexed_locks;
-    kmp_int32        last_barrier;       // The end in enum barrier_type
-    kmp_int32        deque_size;         // TASK_DEQUE_SIZE
+  addr_and_size_t func_microtask;
+  addr_and_size_t func_fork;
+  addr_and_size_t func_fork_teams;
+  addr_and_size_t team_counter;
+  addr_and_size_t task_counter;
+  addr_and_size_t nthr_info;
+  kmp_int32 address_width;
+  kmp_int32 indexed_locks;
+  kmp_int32 last_barrier; // The end in enum barrier_type
+  kmp_int32 deque_size; // TASK_DEQUE_SIZE
 
-    /* thread structure information. */
-    kmp_int32          th_sizeof_struct;
-    offset_and_size_t  th_info;          // descriptor for thread
-    offset_and_size_t  th_team;          // team for this thread
-    offset_and_size_t  th_root;          // root for this thread
-    offset_and_size_t  th_serial_team;   // serial team under this thread
-    offset_and_size_t  th_ident;         // location for this thread (if available)
-    offset_and_size_t  th_spin_here;     // is thread waiting for lock (if available)
-    offset_and_size_t  th_next_waiting;  // next thread waiting for lock (if available)
-    offset_and_size_t  th_task_team;     // task team struct
-    offset_and_size_t  th_current_task;  // innermost task being executed
-    offset_and_size_t  th_task_state;    // alternating 0/1 for task team identification
-    offset_and_size_t  th_bar;
-    offset_and_size_t  th_b_worker_arrived; // the worker increases it by 1 when it arrives to the barrier
+  /* thread structure information. */
+  kmp_int32 th_sizeof_struct;
+  offset_and_size_t th_info; // descriptor for thread
+  offset_and_size_t th_team; // team for this thread
+  offset_and_size_t th_root; // root for this thread
+  offset_and_size_t th_serial_team; // serial team under this thread
+  offset_and_size_t th_ident; // location for this thread (if available)
+  offset_and_size_t th_spin_here; // is thread waiting for lock (if available)
+  offset_and_size_t
+      th_next_waiting; // next thread waiting for lock (if available)
+  offset_and_size_t th_task_team; // task team struct
+  offset_and_size_t th_current_task; // innermost task being executed
+  offset_and_size_t
+      th_task_state; // alternating 0/1 for task team identification
+  offset_and_size_t th_bar;
+  offset_and_size_t th_b_worker_arrived; // the worker increases it by 1 when it
+// arrives to the barrier
 
 #if OMP_40_ENABLED
-    /* teams information */
-    offset_and_size_t th_teams_microtask;// entry address for teams construct
-    offset_and_size_t th_teams_level;    // initial level of teams construct
-    offset_and_size_t th_teams_nteams;   // number of teams in a league
-    offset_and_size_t th_teams_nth;      // number of threads in each team of the league
+  /* teams information */
+  offset_and_size_t th_teams_microtask; // entry address for teams construct
+  offset_and_size_t th_teams_level; // initial level of teams construct
+  offset_and_size_t th_teams_nteams; // number of teams in a league
+  offset_and_size_t
+      th_teams_nth; // number of threads in each team of the league
 #endif
 
-    /* kmp_desc structure (for info field above) */
-    kmp_int32          ds_sizeof_struct;
-    offset_and_size_t  ds_tid;           // team thread id
-    offset_and_size_t  ds_gtid;          // global thread id
-    offset_and_size_t  ds_thread;        // native thread id
+  /* kmp_desc structure (for info field above) */
+  kmp_int32 ds_sizeof_struct;
+  offset_and_size_t ds_tid; // team thread id
+  offset_and_size_t ds_gtid; // global thread id
+  offset_and_size_t ds_thread; // native thread id
 
-    /* team structure information */
-    kmp_int32          t_sizeof_struct;
-    offset_and_size_t  t_master_tid;     // tid of master in parent team
-    offset_and_size_t  t_ident;          // location of parallel region
-    offset_and_size_t  t_parent;         // parent team
-    offset_and_size_t  t_nproc;          // # team threads
-    offset_and_size_t  t_threads;        // array of threads
-    offset_and_size_t  t_serialized;     // # levels of serialized teams
-    offset_and_size_t  t_id;             // unique team id
-    offset_and_size_t  t_pkfn;
-    offset_and_size_t  t_task_team;      // task team structure
-    offset_and_size_t  t_implicit_task;  // taskdata for the thread's implicit task
+  /* team structure information */
+  kmp_int32 t_sizeof_struct;
+  offset_and_size_t t_master_tid; // tid of master in parent team
+  offset_and_size_t t_ident; // location of parallel region
+  offset_and_size_t t_parent; // parent team
+  offset_and_size_t t_nproc; // # team threads
+  offset_and_size_t t_threads; // array of threads
+  offset_and_size_t t_serialized; // # levels of serialized teams
+  offset_and_size_t t_id; // unique team id
+  offset_and_size_t t_pkfn;
+  offset_and_size_t t_task_team; // task team structure
+  offset_and_size_t t_implicit_task; // taskdata for the thread's implicit task
 #if OMP_40_ENABLED
-    offset_and_size_t  t_cancel_request;
+  offset_and_size_t t_cancel_request;
 #endif
-    offset_and_size_t  t_bar;
-    offset_and_size_t  t_b_master_arrived; // increased by 1 when master arrives to a barrier
-    offset_and_size_t  t_b_team_arrived;   // increased by one when all the threads arrived
+  offset_and_size_t t_bar;
+  offset_and_size_t
+      t_b_master_arrived; // increased by 1 when master arrives to a barrier
+  offset_and_size_t
+      t_b_team_arrived; // increased by one when all the threads arrived
 
-    /* root structure information */
-    kmp_int32          r_sizeof_struct;
-    offset_and_size_t  r_root_team;      // team at root
-    offset_and_size_t  r_hot_team;       // hot team for this root
-    offset_and_size_t  r_uber_thread;    // root thread
-    offset_and_size_t  r_root_id;        // unique root id (if available)
+  /* root structure information */
+  kmp_int32 r_sizeof_struct;
+  offset_and_size_t r_root_team; // team at root
+  offset_and_size_t r_hot_team; // hot team for this root
+  offset_and_size_t r_uber_thread; // root thread
+  offset_and_size_t r_root_id; // unique root id (if available)
 
-    /* ident structure information */
-    kmp_int32          id_sizeof_struct;
-    offset_and_size_t  id_psource;       /* address of string ";file;func;line1;line2;;". */
-    offset_and_size_t  id_flags;
+  /* ident structure information */
+  kmp_int32 id_sizeof_struct;
+  offset_and_size_t
+      id_psource; /* address of string ";file;func;line1;line2;;". */
+  offset_and_size_t id_flags;
 
-    /* lock structure information */
-    kmp_int32          lk_sizeof_struct;
-    offset_and_size_t  lk_initialized;
-    offset_and_size_t  lk_location;
-    offset_and_size_t  lk_tail_id;
-    offset_and_size_t  lk_head_id;
-    offset_and_size_t  lk_next_ticket;
-    offset_and_size_t  lk_now_serving;
-    offset_and_size_t  lk_owner_id;
-    offset_and_size_t  lk_depth_locked;
-    offset_and_size_t  lk_lock_flags;
+  /* lock structure information */
+  kmp_int32 lk_sizeof_struct;
+  offset_and_size_t lk_initialized;
+  offset_and_size_t lk_location;
+  offset_and_size_t lk_tail_id;
+  offset_and_size_t lk_head_id;
+  offset_and_size_t lk_next_ticket;
+  offset_and_size_t lk_now_serving;
+  offset_and_size_t lk_owner_id;
+  offset_and_size_t lk_depth_locked;
+  offset_and_size_t lk_lock_flags;
 
-#if ! KMP_USE_DYNAMIC_LOCK
-    /* lock_table_t */
-    kmp_int32          lt_size_of_struct;    /* Size and layout of kmp_lock_table_t. */
-    offset_and_size_t  lt_used;
-    offset_and_size_t  lt_allocated;
-    offset_and_size_t  lt_table;
+#if !KMP_USE_DYNAMIC_LOCK
+  /* lock_table_t */
+  kmp_int32 lt_size_of_struct; /* Size and layout of kmp_lock_table_t. */
+  offset_and_size_t lt_used;
+  offset_and_size_t lt_allocated;
+  offset_and_size_t lt_table;
 #endif
 
-    /* task_team_t */
-    kmp_int32          tt_sizeof_struct;
-    offset_and_size_t  tt_threads_data;
-    offset_and_size_t  tt_found_tasks;
-    offset_and_size_t  tt_nproc;
-    offset_and_size_t  tt_unfinished_threads;
-    offset_and_size_t  tt_active;
+  /* task_team_t */
+  kmp_int32 tt_sizeof_struct;
+  offset_and_size_t tt_threads_data;
+  offset_and_size_t tt_found_tasks;
+  offset_and_size_t tt_nproc;
+  offset_and_size_t tt_unfinished_threads;
+  offset_and_size_t tt_active;
 
-    /* kmp_taskdata_t */
-    kmp_int32          td_sizeof_struct;
-    offset_and_size_t  td_task_id;                  // task id
-    offset_and_size_t  td_flags;                    // task flags
-    offset_and_size_t  td_team;                     // team for this task
-    offset_and_size_t  td_parent;                   // parent task
-    offset_and_size_t  td_level;                    // task testing level
-    offset_and_size_t  td_ident;                    // task identifier
-    offset_and_size_t  td_allocated_child_tasks;    // child tasks (+ current task) not yet deallocated
-    offset_and_size_t  td_incomplete_child_tasks;   // child tasks not yet complete
+  /* kmp_taskdata_t */
+  kmp_int32 td_sizeof_struct;
+  offset_and_size_t td_task_id; // task id
+  offset_and_size_t td_flags; // task flags
+  offset_and_size_t td_team; // team for this task
+  offset_and_size_t td_parent; // parent task
+  offset_and_size_t td_level; // task testing level
+  offset_and_size_t td_ident; // task identifier
+  offset_and_size_t td_allocated_child_tasks; // child tasks (+ current task)
+  // not yet deallocated
+  offset_and_size_t td_incomplete_child_tasks; // child tasks not yet complete
 
-    /* Taskwait */
-    offset_and_size_t  td_taskwait_ident;
-    offset_and_size_t  td_taskwait_counter;
-    offset_and_size_t  td_taskwait_thread;          // gtid + 1 of thread encountered taskwait
+  /* Taskwait */
+  offset_and_size_t td_taskwait_ident;
+  offset_and_size_t td_taskwait_counter;
+  offset_and_size_t
+      td_taskwait_thread; // gtid + 1 of thread encountered taskwait
 
 #if OMP_40_ENABLED
-    /* Taskgroup */
-    offset_and_size_t  td_taskgroup;                // pointer to the current taskgroup
-    offset_and_size_t  td_task_count;               // number of allocated and not yet complete tasks
-    offset_and_size_t  td_cancel;                   // request for cancellation of this taskgroup
+  /* Taskgroup */
+  offset_and_size_t td_taskgroup; // pointer to the current taskgroup
+  offset_and_size_t
+      td_task_count; // number of allocated and not yet complete tasks
+  offset_and_size_t td_cancel; // request for cancellation of this taskgroup
 
-    /* Task dependency */
-    offset_and_size_t  td_depnode;                  // pointer to graph node if the task has dependencies
-    offset_and_size_t  dn_node;
-    offset_and_size_t  dn_next;
-    offset_and_size_t  dn_successors;
-    offset_and_size_t  dn_task;
-    offset_and_size_t  dn_npredecessors;
-    offset_and_size_t  dn_nrefs;
+  /* Task dependency */
+  offset_and_size_t
+      td_depnode; // pointer to graph node if the task has dependencies
+  offset_and_size_t dn_node;
+  offset_and_size_t dn_next;
+  offset_and_size_t dn_successors;
+  offset_and_size_t dn_task;
+  offset_and_size_t dn_npredecessors;
+  offset_and_size_t dn_nrefs;
 #endif
-    offset_and_size_t  dn_routine;
+  offset_and_size_t dn_routine;
 
-    /* kmp_thread_data_t */
-    kmp_int32          hd_sizeof_struct;
-    offset_and_size_t  hd_deque;
-    offset_and_size_t  hd_deque_size;
-    offset_and_size_t  hd_deque_head;
-    offset_and_size_t  hd_deque_tail;
-    offset_and_size_t  hd_deque_ntasks;
-    offset_and_size_t  hd_deque_last_stolen;
+  /* kmp_thread_data_t */
+  kmp_int32 hd_sizeof_struct;
+  offset_and_size_t hd_deque;
+  offset_and_size_t hd_deque_size;
+  offset_and_size_t hd_deque_head;
+  offset_and_size_t hd_deque_tail;
+  offset_and_size_t hd_deque_ntasks;
+  offset_and_size_t hd_deque_last_stolen;
 
-    // The last field of stable version.
-    kmp_uint64         last_field;
+  // The last field of stable version.
+  kmp_uint64 last_field;
 
 } kmp_omp_struct_info_t;
 

runtime/src/kmp_platform.h

@@ -2,6 +2,7 @@
  * kmp_platform.h -- header for determining operating system and architecture
  */
 
+
 //===----------------------------------------------------------------------===//
 //
 //                     The LLVM Compiler Infrastructure
@@ -11,171 +12,179 @@
 //
 //===----------------------------------------------------------------------===//
 
+
 #ifndef KMP_PLATFORM_H
 #define KMP_PLATFORM_H
 
 /* ---------------------- Operating system recognition ------------------- */
 
-#define KMP_OS_LINUX    0
-#define KMP_OS_FREEBSD  0
-#define KMP_OS_NETBSD   0
-#define KMP_OS_DARWIN   0
-#define KMP_OS_WINDOWS  0
-#define KMP_OS_CNK      0
-#define KMP_OS_UNIX     0  /* disjunction of KMP_OS_LINUX, KMP_OS_DARWIN etc. */
-
+#define KMP_OS_LINUX 0
+#define KMP_OS_FREEBSD 0
+#define KMP_OS_NETBSD 0
+#define KMP_OS_DARWIN 0
+#define KMP_OS_WINDOWS 0
+#define KMP_OS_CNK 0
+#define KMP_OS_UNIX 0 /* disjunction of KMP_OS_LINUX, KMP_OS_DARWIN etc. */
 
 #ifdef _WIN32
-# undef KMP_OS_WINDOWS
-# define KMP_OS_WINDOWS 1
+#undef KMP_OS_WINDOWS
+#define KMP_OS_WINDOWS 1
 #endif
 
-#if ( defined __APPLE__ && defined __MACH__ )
-# undef KMP_OS_DARWIN
-# define KMP_OS_DARWIN 1
+#if (defined __APPLE__ && defined __MACH__)
+#undef KMP_OS_DARWIN
+#define KMP_OS_DARWIN 1
 #endif
 
 // in some ppc64 linux installations, only the second condition is met
-#if ( defined __linux )
-# undef KMP_OS_LINUX
-# define KMP_OS_LINUX 1
-#elif ( defined __linux__)
-# undef KMP_OS_LINUX
-# define KMP_OS_LINUX 1
+#if (defined __linux)
+#undef KMP_OS_LINUX
+#define KMP_OS_LINUX 1
+#elif (defined __linux__)
+#undef KMP_OS_LINUX
+#define KMP_OS_LINUX 1
 #else
 #endif
 
-#if ( defined __FreeBSD__ )
-# undef KMP_OS_FREEBSD
-# define KMP_OS_FREEBSD 1
+#if (defined __FreeBSD__)
+#undef KMP_OS_FREEBSD
+#define KMP_OS_FREEBSD 1
 #endif
 
-#if ( defined __NetBSD__ )
-# undef KMP_OS_NETBSD
-# define KMP_OS_NETBSD 1
+#if (defined __NetBSD__)
+#undef KMP_OS_NETBSD
+#define KMP_OS_NETBSD 1
 #endif
 
-#if ( defined __bgq__ )
-# undef KMP_OS_CNK
-# define KMP_OS_CNK 1
+#if (defined __bgq__)
+#undef KMP_OS_CNK
+#define KMP_OS_CNK 1
 #endif
 
-#if (1 != KMP_OS_LINUX + KMP_OS_FREEBSD + KMP_OS_NETBSD + KMP_OS_DARWIN + KMP_OS_WINDOWS)
-# error Unknown OS
+#if (1 !=                                                                      \
+     KMP_OS_LINUX + KMP_OS_FREEBSD + KMP_OS_NETBSD + KMP_OS_DARWIN +           \
+         KMP_OS_WINDOWS)
+#error Unknown OS
 #endif
 
 #if KMP_OS_LINUX || KMP_OS_FREEBSD || KMP_OS_NETBSD || KMP_OS_DARWIN
-# undef KMP_OS_UNIX
-# define KMP_OS_UNIX 1
+#undef KMP_OS_UNIX
+#define KMP_OS_UNIX 1
 #endif
 
 /* ---------------------- Architecture recognition ------------------- */
 
-#define KMP_ARCH_X86        0
-#define KMP_ARCH_X86_64     0
-#define KMP_ARCH_AARCH64    0
-#define KMP_ARCH_PPC64_BE   0
-#define KMP_ARCH_PPC64_LE   0
+#define KMP_ARCH_X86 0
+#define KMP_ARCH_X86_64 0
+#define KMP_ARCH_AARCH64 0
+#define KMP_ARCH_PPC64_BE 0
+#define KMP_ARCH_PPC64_LE 0
 #define KMP_ARCH_PPC64 (KMP_ARCH_PPC64_LE || KMP_ARCH_PPC64_BE)
-#define KMP_ARCH_MIPS        0
-#define KMP_ARCH_MIPS64      0
+#define KMP_ARCH_MIPS 0
+#define KMP_ARCH_MIPS64 0
 
 #if KMP_OS_WINDOWS
-# if defined _M_AMD64
-#  undef KMP_ARCH_X86_64
-#  define KMP_ARCH_X86_64 1
-# else
-#  undef KMP_ARCH_X86
-#  define KMP_ARCH_X86 1
-# endif
+#if defined _M_AMD64
+#undef KMP_ARCH_X86_64
+#define KMP_ARCH_X86_64 1
+#else
+#undef KMP_ARCH_X86
+#define KMP_ARCH_X86 1
+#endif
 #endif
 
 #if KMP_OS_UNIX
-# if defined __x86_64
-#  undef KMP_ARCH_X86_64
-#  define KMP_ARCH_X86_64 1
-# elif defined __i386
-#  undef KMP_ARCH_X86
-#  define KMP_ARCH_X86 1
-# elif defined __powerpc64__
-#  if defined __LITTLE_ENDIAN__
-#   undef KMP_ARCH_PPC64_LE
-#   define KMP_ARCH_PPC64_LE 1
-#  else
-#   undef KMP_ARCH_PPC64_BE
-#   define KMP_ARCH_PPC64_BE 1
-#  endif
-# elif defined __aarch64__
-#  undef KMP_ARCH_AARCH64
-#  define KMP_ARCH_AARCH64 1
-# elif defined __mips__
-#  if defined __mips64
-#   undef KMP_ARCH_MIPS64
-#   define KMP_ARCH_MIPS64 1
-#  else
-#   undef KMP_ARCH_MIPS
-#   define KMP_ARCH_MIPS 1
-#  endif
-# endif
+#if defined __x86_64
+#undef KMP_ARCH_X86_64
+#define KMP_ARCH_X86_64 1
+#elif defined __i386
+#undef KMP_ARCH_X86
+#define KMP_ARCH_X86 1
+#elif defined __powerpc64__
+#if defined __LITTLE_ENDIAN__
+#undef KMP_ARCH_PPC64_LE
+#define KMP_ARCH_PPC64_LE 1
+#else
+#undef KMP_ARCH_PPC64_BE
+#define KMP_ARCH_PPC64_BE 1
+#endif
+#elif defined __aarch64__
+#undef KMP_ARCH_AARCH64
+#define KMP_ARCH_AARCH64 1
+#elif defined __mips__
+#if defined __mips64
+#undef KMP_ARCH_MIPS64
+#define KMP_ARCH_MIPS64 1
+#else
+#undef KMP_ARCH_MIPS
+#define KMP_ARCH_MIPS 1
+#endif
+#endif
 #endif
 
-#if defined(__ARM_ARCH_7__)   || defined(__ARM_ARCH_7R__)  || \
+#if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7R__) ||                     \
     defined(__ARM_ARCH_7A__)
-# define KMP_ARCH_ARMV7 1
+#define KMP_ARCH_ARMV7 1
 #endif
 
-#if defined(KMP_ARCH_ARMV7)   || defined(__ARM_ARCH_6__)   || \
-    defined(__ARM_ARCH_6J__)  || defined(__ARM_ARCH_6K__)  || \
-    defined(__ARM_ARCH_6Z__)  || defined(__ARM_ARCH_6T2__) || \
+#if defined(KMP_ARCH_ARMV7) || defined(__ARM_ARCH_6__) ||                      \
+    defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) ||                    \
+    defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6T2__) ||                   \
     defined(__ARM_ARCH_6ZK__)
-# define KMP_ARCH_ARMV6 1
+#define KMP_ARCH_ARMV6 1
 #endif
 
-#if defined(KMP_ARCH_ARMV6)   || defined(__ARM_ARCH_5T__)  || \
-    defined(__ARM_ARCH_5E__)  || defined(__ARM_ARCH_5TE__) || \
+#if defined(KMP_ARCH_ARMV6) || defined(__ARM_ARCH_5T__) ||                     \
+    defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__) ||                   \
     defined(__ARM_ARCH_5TEJ__)
-# define KMP_ARCH_ARMV5 1
+#define KMP_ARCH_ARMV5 1
 #endif
 
-#if defined(KMP_ARCH_ARMV5)   || defined(__ARM_ARCH_4__)   || \
+#if defined(KMP_ARCH_ARMV5) || defined(__ARM_ARCH_4__) ||                      \
     defined(__ARM_ARCH_4T__)
-# define KMP_ARCH_ARMV4 1
+#define KMP_ARCH_ARMV4 1
 #endif
 
-#if defined(KMP_ARCH_ARMV4)   || defined(__ARM_ARCH_3__)   || \
+#if defined(KMP_ARCH_ARMV4) || defined(__ARM_ARCH_3__) ||                      \
     defined(__ARM_ARCH_3M__)
-# define KMP_ARCH_ARMV3 1
+#define KMP_ARCH_ARMV3 1
 #endif
 
-#if defined(KMP_ARCH_ARMV3)   || defined(__ARM_ARCH_2__)
-# define KMP_ARCH_ARMV2 1
+#if defined(KMP_ARCH_ARMV3) || defined(__ARM_ARCH_2__)
+#define KMP_ARCH_ARMV2 1
 #endif
 
 #if defined(KMP_ARCH_ARMV2)
-# define KMP_ARCH_ARM 1
+#define KMP_ARCH_ARM 1
 #endif
 
 #if defined(__MIC__) || defined(__MIC2__)
-# define KMP_MIC  1
-# if __MIC2__ || __KNC__
-#  define KMP_MIC1 0
-#  define KMP_MIC2 1
-# else
-#  define KMP_MIC1 1
-#  define KMP_MIC2 0
-# endif
+#define KMP_MIC 1
+#if __MIC2__ || __KNC__
+#define KMP_MIC1 0
+#define KMP_MIC2 1
 #else
-# define KMP_MIC  0
-# define KMP_MIC1 0
-# define KMP_MIC2 0
+#define KMP_MIC1 1
+#define KMP_MIC2 0
+#endif
+#else
+#define KMP_MIC 0
+#define KMP_MIC1 0
+#define KMP_MIC2 0
 #endif
 
 /* Specify 32 bit architectures here */
 #define KMP_32_BIT_ARCH (KMP_ARCH_X86 || KMP_ARCH_ARM || KMP_ARCH_MIPS)
 
+// Platforms which support Intel(R) Many Integrated Core Architecture
+#define KMP_MIC_SUPPORTED                                                      \
+  ((KMP_ARCH_X86 || KMP_ARCH_X86_64) && (KMP_OS_LINUX || KMP_OS_WINDOWS))
+
 // TODO: Fixme - This is clever, but really fugly
-#if (1 != KMP_ARCH_X86 + KMP_ARCH_X86_64 + KMP_ARCH_ARM + KMP_ARCH_PPC64 + KMP_ARCH_AARCH64 + KMP_ARCH_MIPS + KMP_ARCH_MIPS64)
-# error Unknown or unsupported architecture
+#if (1 !=                                                                      \
+     KMP_ARCH_X86 + KMP_ARCH_X86_64 + KMP_ARCH_ARM + KMP_ARCH_PPC64 +          \
+         KMP_ARCH_AARCH64 + KMP_ARCH_MIPS + KMP_ARCH_MIPS64)
+#error Unknown or unsupported architecture
 #endif
 
 #endif // KMP_PLATFORM_H

runtime/src/kmp_safe_c_api.h

@@ -12,50 +12,49 @@
 #ifndef KMP_SAFE_C_API_H
 #define KMP_SAFE_C_API_H
 
-//
 // Replacement for banned C API
-//
 
 // Not every unsafe call listed here is handled now, but keeping everything
 // in one place should be handy for future maintenance.
 #if KMP_OS_WINDOWS
 
-# define RSIZE_MAX_STR ( 4UL << 10 ) // 4KB
+#define RSIZE_MAX_STR (4UL << 10) // 4KB
 
 // _malloca was suggested, but it is not a drop-in replacement for _alloca
-# define KMP_ALLOCA                  _alloca
+#define KMP_ALLOCA _alloca
 
-# define KMP_MEMCPY_S                memcpy_s
-# define KMP_SNPRINTF                sprintf_s
-# define KMP_SSCANF                  sscanf_s
-# define KMP_STRCPY_S                strcpy_s
-# define KMP_STRNCPY_S               strncpy_s
+#define KMP_MEMCPY_S memcpy_s
+#define KMP_SNPRINTF sprintf_s
+#define KMP_SSCANF sscanf_s
+#define KMP_STRCPY_S strcpy_s
+#define KMP_STRNCPY_S strncpy_s
 
 // Use this only when buffer size is unknown
-# define KMP_MEMCPY(dst, src, cnt)   memcpy_s(dst, cnt, src, cnt)
+#define KMP_MEMCPY(dst, src, cnt) memcpy_s(dst, cnt, src, cnt)
 
-# define KMP_STRLEN(str)             strnlen_s(str, RSIZE_MAX_STR)
+#define KMP_STRLEN(str) strnlen_s(str, RSIZE_MAX_STR)
 
 // Use this only when buffer size is unknown
-# define KMP_STRNCPY(dst, src, cnt)  strncpy_s(dst, cnt, src, cnt)
+#define KMP_STRNCPY(dst, src, cnt) strncpy_s(dst, cnt, src, cnt)
 
 // _TRUNCATE insures buffer size > max string to print.
-# define KMP_VSNPRINTF(dst, cnt, fmt, arg)  vsnprintf_s(dst, cnt, _TRUNCATE, fmt, arg)
+#define KMP_VSNPRINTF(dst, cnt, fmt, arg)                                      \
+  vsnprintf_s(dst, cnt, _TRUNCATE, fmt, arg)
 
 #else // KMP_OS_WINDOWS
 
 // For now, these macros use the existing API.
 
-# define KMP_ALLOCA                         alloca
-# define KMP_MEMCPY_S(dst, bsz, src, cnt)   memcpy(dst, src, cnt)
-# define KMP_SNPRINTF                       snprintf
-# define KMP_SSCANF                         sscanf
-# define KMP_STRCPY_S(dst, bsz, src)        strcpy(dst, src)
-# define KMP_STRNCPY_S(dst, bsz, src, cnt)  strncpy(dst, src, cnt)
-# define KMP_VSNPRINTF                      vsnprintf
-# define KMP_STRNCPY                        strncpy
-# define KMP_STRLEN                         strlen
-# define KMP_MEMCPY                         memcpy
+#define KMP_ALLOCA alloca
+#define KMP_MEMCPY_S(dst, bsz, src, cnt) memcpy(dst, src, cnt)
+#define KMP_SNPRINTF snprintf
+#define KMP_SSCANF sscanf
+#define KMP_STRCPY_S(dst, bsz, src) strcpy(dst, src)
+#define KMP_STRNCPY_S(dst, bsz, src, cnt) strncpy(dst, src, cnt)
+#define KMP_VSNPRINTF vsnprintf
+#define KMP_STRNCPY strncpy
+#define KMP_STRLEN strlen
+#define KMP_MEMCPY memcpy
 
 #endif // KMP_OS_WINDOWS
 

runtime/src/kmp_settings.h

@@ -16,35 +16,52 @@
 #ifndef KMP_SETTINGS_H
 #define KMP_SETTINGS_H
 
-void __kmp_reset_global_vars( void );
-void __kmp_env_initialize( char const * );
+void __kmp_reset_global_vars(void);
+void __kmp_env_initialize(char const *);
 void __kmp_env_print();
 #if OMP_40_ENABLED
 void __kmp_env_print_2();
 #endif // OMP_40_ENABLED
 
-int __kmp_initial_threads_capacity( int req_nproc );
+int __kmp_initial_threads_capacity(int req_nproc);
 void __kmp_init_dflt_team_nth();
-int __kmp_convert_to_milliseconds( char const * );
-int __kmp_default_tp_capacity( int, int, int);
+int __kmp_convert_to_milliseconds(char const *);
+int __kmp_default_tp_capacity(int, int, int);
 
 #if KMP_MIC
-#define KMP_STR_BUF_PRINT_NAME          __kmp_str_buf_print( buffer, "  %s %s", KMP_I18N_STR(Device), name )
-#define KMP_STR_BUF_PRINT_NAME_EX(x)    __kmp_str_buf_print( buffer, "  %s %s='", KMP_I18N_STR(Device), x )
-#define KMP_STR_BUF_PRINT_BOOL          __kmp_str_buf_print( buffer, "  %s %s='%s'\n", KMP_I18N_STR(Device), name, value ? "TRUE" : "FALSE" );
-#define KMP_STR_BUF_PRINT_INT           __kmp_str_buf_print( buffer, "  %s %s='%d'\n", KMP_I18N_STR(Device), name, value )
-#define KMP_STR_BUF_PRINT_UINT64        __kmp_str_buf_print( buffer, "  %s %s='%" KMP_UINT64_SPEC "'\n", KMP_I18N_STR(Device), name, value );
-#define KMP_STR_BUF_PRINT_STR           __kmp_str_buf_print( buffer, "  %s %s='%s'\n", KMP_I18N_STR(Device), name, value )
+#define KMP_STR_BUF_PRINT_NAME                                                 \
+  __kmp_str_buf_print(buffer, "  %s %s", KMP_I18N_STR(Device), name)
+#define KMP_STR_BUF_PRINT_NAME_EX(x)                                           \
+  __kmp_str_buf_print(buffer, "  %s %s='", KMP_I18N_STR(Device), x)
+#define KMP_STR_BUF_PRINT_BOOL                                                 \
+  __kmp_str_buf_print(buffer, "  %s %s='%s'\n", KMP_I18N_STR(Device), name,    \
+                      value ? "TRUE" : "FALSE");
+#define KMP_STR_BUF_PRINT_INT                                                  \
+  __kmp_str_buf_print(buffer, "  %s %s='%d'\n", KMP_I18N_STR(Device), name,    \
+                      value)
+#define KMP_STR_BUF_PRINT_UINT64                                               \
+  __kmp_str_buf_print(buffer, "  %s %s='%" KMP_UINT64_SPEC "'\n",              \
+                      KMP_I18N_STR(Device), name, value);
+#define KMP_STR_BUF_PRINT_STR                                                  \
+  __kmp_str_buf_print(buffer, "  %s %s='%s'\n", KMP_I18N_STR(Device), name,    \
+                      value)
 #else
-#define KMP_STR_BUF_PRINT_NAME          __kmp_str_buf_print( buffer, "  %s %s", KMP_I18N_STR(Host), name )
-#define KMP_STR_BUF_PRINT_NAME_EX(x)    __kmp_str_buf_print( buffer, "  %s %s='", KMP_I18N_STR(Host), x )
-#define KMP_STR_BUF_PRINT_BOOL          __kmp_str_buf_print( buffer, "  %s %s='%s'\n", KMP_I18N_STR(Host), name, value ? "TRUE" : "FALSE" );
-#define KMP_STR_BUF_PRINT_INT           __kmp_str_buf_print( buffer, "  %s %s='%d'\n", KMP_I18N_STR(Host), name, value )
-#define KMP_STR_BUF_PRINT_UINT64        __kmp_str_buf_print( buffer, "  %s %s='%" KMP_UINT64_SPEC "'\n", KMP_I18N_STR(Host), name, value );
-#define KMP_STR_BUF_PRINT_STR           __kmp_str_buf_print( buffer, "  %s %s='%s'\n", KMP_I18N_STR(Host), name, value )
+#define KMP_STR_BUF_PRINT_NAME                                                 \
+  __kmp_str_buf_print(buffer, "  %s %s", KMP_I18N_STR(Host), name)
+#define KMP_STR_BUF_PRINT_NAME_EX(x)                                           \
+  __kmp_str_buf_print(buffer, "  %s %s='", KMP_I18N_STR(Host), x)
+#define KMP_STR_BUF_PRINT_BOOL                                                 \
+  __kmp_str_buf_print(buffer, "  %s %s='%s'\n", KMP_I18N_STR(Host), name,      \
+                      value ? "TRUE" : "FALSE");
+#define KMP_STR_BUF_PRINT_INT                                                  \
+  __kmp_str_buf_print(buffer, "  %s %s='%d'\n", KMP_I18N_STR(Host), name, value)
+#define KMP_STR_BUF_PRINT_UINT64                                               \
+  __kmp_str_buf_print(buffer, "  %s %s='%" KMP_UINT64_SPEC "'\n",              \
+                      KMP_I18N_STR(Host), name, value);
+#define KMP_STR_BUF_PRINT_STR                                                  \
+  __kmp_str_buf_print(buffer, "  %s %s='%s'\n", KMP_I18N_STR(Host), name, value)
 #endif
 
 #endif // KMP_SETTINGS_H
 
 // end of file //
-

runtime/src/kmp_stats_timing.cpp

@@ -16,8 +16,8 @@
 #include <stdlib.h>
 #include <unistd.h>
 
-#include <iostream>
 #include <iomanip>
+#include <iostream>
 #include <sstream>
 
 #include "kmp.h"
@@ -26,119 +26,107 @@
 using namespace std;
 
 #if KMP_HAVE_TICK_TIME
-# if KMP_MIC
-double tsc_tick_count::tick_time()
-{
-    // pretty bad assumption of 1GHz clock for MIC
-    return 1/((double)1000*1.e6);
+#if KMP_MIC
+double tsc_tick_count::tick_time() {
+  // pretty bad assumption of 1GHz clock for MIC
+  return 1 / ((double)1000 * 1.e6);
 }
-# elif KMP_ARCH_X86 || KMP_ARCH_X86_64
-#  include <string.h>
+#elif KMP_ARCH_X86 || KMP_ARCH_X86_64
+#include <string.h>
 // Extract the value from the CPUID information
-double tsc_tick_count::tick_time()
-{
-    static double result = 0.0;
+double tsc_tick_count::tick_time() {
+  static double result = 0.0;
 
-    if (result == 0.0)
-    {
-        kmp_cpuid_t cpuinfo;
-        char brand[256];
+  if (result == 0.0) {
+    kmp_cpuid_t cpuinfo;
+    char brand[256];
 
-        __kmp_x86_cpuid(0x80000000, 0, &cpuinfo);
-        memset(brand, 0, sizeof(brand));
-        int ids = cpuinfo.eax;
+    __kmp_x86_cpuid(0x80000000, 0, &cpuinfo);
+    memset(brand, 0, sizeof(brand));
+    int ids = cpuinfo.eax;
 
-        for (unsigned int i=2; i<(ids^0x80000000)+2; i++)
-            __kmp_x86_cpuid(i | 0x80000000, 0, (kmp_cpuid_t*)(brand+(i-2)*sizeof(kmp_cpuid_t)));
+    for (unsigned int i = 2; i < (ids ^ 0x80000000) + 2; i++)
+      __kmp_x86_cpuid(i | 0x80000000, 0,
+                      (kmp_cpuid_t *)(brand + (i - 2) * sizeof(kmp_cpuid_t)));
 
-        char * start = &brand[0];
-        for (;*start == ' '; start++)
-            ;
+    char *start = &brand[0];
+    for (; *start == ' '; start++)
+      ;
 
-        char * end = brand + KMP_STRLEN(brand) - 3;
-        uint64_t multiplier;
+    char *end = brand + KMP_STRLEN(brand) - 3;
+    uint64_t multiplier;
 
-        if (*end == 'M') multiplier = 1000LL*1000LL;
-        else if (*end == 'G') multiplier = 1000LL*1000LL*1000LL;
-        else if (*end == 'T') multiplier = 1000LL*1000LL*1000LL*1000LL;
-        else
-        {
-            cout << "Error determining multiplier '" << *end << "'\n";
-            exit (-1);
-        }
-        *end = 0;
-        while (*end != ' ') end--;
-        end++;
-
-        double freq = strtod(end, &start);
-        if (freq == 0.0)
-        {
-            cout << "Error calculating frequency " <<  end << "\n";
-            exit (-1);
-        }
-
-        result = ((double)1.0)/(freq * multiplier);
+    if (*end == 'M')
+      multiplier = 1000LL * 1000LL;
+    else if (*end == 'G')
+      multiplier = 1000LL * 1000LL * 1000LL;
+    else if (*end == 'T')
+      multiplier = 1000LL * 1000LL * 1000LL * 1000LL;
+    else {
+      cout << "Error determining multiplier '" << *end << "'\n";
+      exit(-1);
     }
-    return result;
+    *end = 0;
+    while (*end != ' ')
+      end--;
+    end++;
+
+    double freq = strtod(end, &start);
+    if (freq == 0.0) {
+      cout << "Error calculating frequency " << end << "\n";
+      exit(-1);
+    }
+
+    result = ((double)1.0) / (freq * multiplier);
+  }
+  return result;
 }
-# endif
+#endif
 #endif
 
 static bool useSI = true;
 
 // Return a formatted string after normalising the value into
 // engineering style and using a suitable unit prefix (e.g. ms, us, ns).
-std::string formatSI(double interval, int width, char unit)
-{
-    std::stringstream os;
+std::string formatSI(double interval, int width, char unit) {
+  std::stringstream os;
 
-    if (useSI)
-    {
-        // Preserve accuracy for small numbers, since we only multiply and the positive powers
-        // of ten are precisely representable.
-        static struct { double scale; char prefix; } ranges[] = {
-            {1.e12,'f'},
-            {1.e9, 'p'},
-            {1.e6, 'n'},
-            {1.e3, 'u'},
-            {1.0,  'm'},
-            {1.e-3,' '},
-            {1.e-6,'k'},
-            {1.e-9,'M'},
-            {1.e-12,'G'},
-            {1.e-15,'T'},
-            {1.e-18,'P'},
-            {1.e-21,'E'},
-            {1.e-24,'Z'},
-            {1.e-27,'Y'}
-        };
+  if (useSI) {
+    // Preserve accuracy for small numbers, since we only multiply and the
+    // positive powers of ten are precisely representable.
+    static struct {
+      double scale;
+      char prefix;
+    } ranges[] = {{1.e12, 'f'},  {1.e9, 'p'},   {1.e6, 'n'},   {1.e3, 'u'},
+                  {1.0, 'm'},    {1.e-3, ' '},  {1.e-6, 'k'},  {1.e-9, 'M'},
+                  {1.e-12, 'G'}, {1.e-15, 'T'}, {1.e-18, 'P'}, {1.e-21, 'E'},
+                  {1.e-24, 'Z'}, {1.e-27, 'Y'}};
 
-        if (interval == 0.0)
-        {
-            os << std::setw(width-3) << std::right << "0.00" << std::setw(3) << unit;
-            return os.str();
-        }
-
-        bool negative = false;
-        if (interval < 0.0)
-        {
-            negative = true;
-            interval = -interval;
-        }
-
-        for (int i=0; i<(int)(sizeof(ranges)/sizeof(ranges[0])); i++)
-        {
-            if (interval*ranges[i].scale < 1.e0)
-            {
-                interval = interval * 1000.e0 * ranges[i].scale;
-                os << std::fixed << std::setprecision(2) << std::setw(width-3) << std::right <<
-                    (negative ? -interval : interval) << std::setw(2) << ranges[i].prefix << std::setw(1) << unit;
-
-                return os.str();
-            }
-        }
+    if (interval == 0.0) {
+      os << std::setw(width - 3) << std::right << "0.00" << std::setw(3)
+         << unit;
+      return os.str();
     }
-    os << std::setprecision(2) << std::fixed << std::right << std::setw(width-3) << interval << std::setw(3) << unit;
 
-    return os.str();
+    bool negative = false;
+    if (interval < 0.0) {
+      negative = true;
+      interval = -interval;
+    }
+
+    for (int i = 0; i < (int)(sizeof(ranges) / sizeof(ranges[0])); i++) {
+      if (interval * ranges[i].scale < 1.e0) {
+        interval = interval * 1000.e0 * ranges[i].scale;
+        os << std::fixed << std::setprecision(2) << std::setw(width - 3)
+           << std::right << (negative ? -interval : interval) << std::setw(2)
+           << ranges[i].prefix << std::setw(1) << unit;
+
+        return os.str();
+      }
+    }
+  }
+  os << std::setprecision(2) << std::fixed << std::right << std::setw(width - 3)
+     << interval << std::setw(3) << unit;
+
+  return os.str();
 }

runtime/src/kmp_stats_timing.h

@@ -16,97 +16,103 @@
 //===----------------------------------------------------------------------===//
 
 
-
+#include "kmp_os.h"
+#include <limits>
 #include <stdint.h>
 #include <string>
-#include <limits>
-#include "kmp_os.h"
 #if KMP_HAVE_X86INTRIN_H
-# include <x86intrin.h>
+#include <x86intrin.h>
 #endif
 
 class tsc_tick_count {
-  private:
-    int64_t my_count;
+private:
+  int64_t my_count;
+
+public:
+  class tsc_interval_t {
+    int64_t value;
+    explicit tsc_interval_t(int64_t _value) : value(_value) {}
 
   public:
-    class tsc_interval_t {
-        int64_t value;
-        explicit tsc_interval_t(int64_t _value) : value(_value) {}
-     public:
-        tsc_interval_t() : value(0) {}; // Construct 0 time duration
+    tsc_interval_t() : value(0){}; // Construct 0 time duration
 #if KMP_HAVE_TICK_TIME
-        double seconds() const; // Return the length of a time interval in seconds
+    double seconds() const; // Return the length of a time interval in seconds
 #endif
-        double ticks() const { return double(value); }
-        int64_t getValue() const { return value; }
-        tsc_interval_t& operator=(int64_t nvalue) { value = nvalue; return *this; }
+    double ticks() const { return double(value); }
+    int64_t getValue() const { return value; }
+    tsc_interval_t &operator=(int64_t nvalue) {
+      value = nvalue;
+      return *this;
+    }
 
-        friend class tsc_tick_count;
+    friend class tsc_tick_count;
 
-        friend tsc_interval_t operator-(const tsc_tick_count& t1,
-                                        const tsc_tick_count& t0);
-        friend tsc_interval_t operator-(const tsc_tick_count::tsc_interval_t& i1,
-                                        const tsc_tick_count::tsc_interval_t& i0);
-        friend tsc_interval_t& operator+=(tsc_tick_count::tsc_interval_t& i1,
-                                         const tsc_tick_count::tsc_interval_t& i0);
-    };
+    friend tsc_interval_t operator-(const tsc_tick_count &t1,
+                                    const tsc_tick_count &t0);
+    friend tsc_interval_t operator-(const tsc_tick_count::tsc_interval_t &i1,
+                                    const tsc_tick_count::tsc_interval_t &i0);
+    friend tsc_interval_t &operator+=(tsc_tick_count::tsc_interval_t &i1,
+                                      const tsc_tick_count::tsc_interval_t &i0);
+  };
 
 #if KMP_HAVE___BUILTIN_READCYCLECOUNTER
-    tsc_tick_count() : my_count(static_cast<int64_t>(__builtin_readcyclecounter())) {}
+  tsc_tick_count()
+      : my_count(static_cast<int64_t>(__builtin_readcyclecounter())) {}
 #elif KMP_HAVE___RDTSC
-    tsc_tick_count() : my_count(static_cast<int64_t>(__rdtsc())) {};
+  tsc_tick_count() : my_count(static_cast<int64_t>(__rdtsc())){};
 #else
-# error Must have high resolution timer defined
+#error Must have high resolution timer defined
 #endif
-    tsc_tick_count(int64_t value) : my_count(value) {};
-    int64_t getValue() const { return my_count; }
-    tsc_tick_count later (tsc_tick_count const other) const {
-        return my_count > other.my_count ? (*this) : other;
-    }
-    tsc_tick_count earlier(tsc_tick_count const other) const {
-        return my_count < other.my_count ? (*this) : other;
-    }
+  tsc_tick_count(int64_t value) : my_count(value){};
+  int64_t getValue() const { return my_count; }
+  tsc_tick_count later(tsc_tick_count const other) const {
+    return my_count > other.my_count ? (*this) : other;
+  }
+  tsc_tick_count earlier(tsc_tick_count const other) const {
+    return my_count < other.my_count ? (*this) : other;
+  }
 #if KMP_HAVE_TICK_TIME
-    static double tick_time(); // returns seconds per cycle (period) of clock
+  static double tick_time(); // returns seconds per cycle (period) of clock
 #endif
-    static tsc_tick_count now() { return tsc_tick_count(); } // returns the rdtsc register value
-    friend tsc_tick_count::tsc_interval_t operator-(const tsc_tick_count& t1, const tsc_tick_count& t0);
+  static tsc_tick_count now() {
+    return tsc_tick_count();
+  } // returns the rdtsc register value
+  friend tsc_tick_count::tsc_interval_t operator-(const tsc_tick_count &t1,
+                                                  const tsc_tick_count &t0);
 };
 
-inline tsc_tick_count::tsc_interval_t operator-(const tsc_tick_count& t1, const tsc_tick_count& t0)
-{
-    return tsc_tick_count::tsc_interval_t( t1.my_count-t0.my_count );
+inline tsc_tick_count::tsc_interval_t operator-(const tsc_tick_count &t1,
+                                                const tsc_tick_count &t0) {
+  return tsc_tick_count::tsc_interval_t(t1.my_count - t0.my_count);
 }
 
-inline tsc_tick_count::tsc_interval_t operator-(const tsc_tick_count::tsc_interval_t& i1, const tsc_tick_count::tsc_interval_t& i0)
-{
-    return tsc_tick_count::tsc_interval_t( i1.value-i0.value );
+inline tsc_tick_count::tsc_interval_t
+operator-(const tsc_tick_count::tsc_interval_t &i1,
+          const tsc_tick_count::tsc_interval_t &i0) {
+  return tsc_tick_count::tsc_interval_t(i1.value - i0.value);
 }
 
-inline tsc_tick_count::tsc_interval_t& operator+=(tsc_tick_count::tsc_interval_t& i1, const tsc_tick_count::tsc_interval_t& i0)
-{
-    i1.value += i0.value;
-    return i1;
+inline tsc_tick_count::tsc_interval_t &
+operator+=(tsc_tick_count::tsc_interval_t &i1,
+           const tsc_tick_count::tsc_interval_t &i0) {
+  i1.value += i0.value;
+  return i1;
 }
 
 #if KMP_HAVE_TICK_TIME
-inline double tsc_tick_count::tsc_interval_t::seconds() const
-{
-    return value*tick_time();
+inline double tsc_tick_count::tsc_interval_t::seconds() const {
+  return value * tick_time();
 }
 #endif
 
 extern std::string formatSI(double interval, int width, char unit);
 
-inline std::string formatSeconds(double interval, int width)
-{
-    return formatSI(interval, width, 'S');
+inline std::string formatSeconds(double interval, int width) {
+  return formatSI(interval, width, 'S');
 }
 
-inline std::string formatTicks(double interval, int width)
-{
-    return formatSI(interval, width, 'T');
+inline std::string formatTicks(double interval, int width) {
+  return formatSI(interval, width, 'T');
 }
 
 #endif // KMP_STATS_TIMING_H

runtime/src/kmp_str.h

@@ -16,104 +16,112 @@
 #ifndef KMP_STR_H
 #define KMP_STR_H
 
-#include <string.h>
 #include <stdarg.h>
+#include <string.h>
 
 #include "kmp_os.h"
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
 #if KMP_OS_WINDOWS
-# define strdup    _strdup
+#define strdup _strdup
 #endif
 
 /*  some macros to replace ctype.h functions  */
-#define TOLOWER(c)	((((c) >= 'A') && ((c) <= 'Z')) ? ((c) + 'a' - 'A') : (c))
+#define TOLOWER(c) ((((c) >= 'A') && ((c) <= 'Z')) ? ((c) + 'a' - 'A') : (c))
 
 struct kmp_str_buf {
-    char       * str;         // Pointer to buffer content, read only.
-    unsigned int size;        // Do not change this field!
-    int          used;        // Number of characters printed to buffer, read only.
-    char         bulk[ 512 ]; // Do not use this field!
+  char *str; // Pointer to buffer content, read only.
+  unsigned int size; // Do not change this field!
+  int used; // Number of characters printed to buffer, read only.
+  char bulk[512]; // Do not use this field!
 }; // struct kmp_str_buf
-typedef struct kmp_str_buf  kmp_str_buf_t;
+typedef struct kmp_str_buf kmp_str_buf_t;
 
-#define __kmp_str_buf_init( b )   { (b)->str = (b)->bulk; (b)->size = sizeof( (b)->bulk ); (b)->used = 0; (b)->bulk[ 0 ] = 0; }
+#define __kmp_str_buf_init(b)                                                  \
+  {                                                                            \
+    (b)->str = (b)->bulk;                                                      \
+    (b)->size = sizeof((b)->bulk);                                             \
+    (b)->used = 0;                                                             \
+    (b)->bulk[0] = 0;                                                          \
+  }
 
-void   __kmp_str_buf_clear( kmp_str_buf_t * buffer );
-void   __kmp_str_buf_reserve( kmp_str_buf_t * buffer, int size );
-void   __kmp_str_buf_detach( kmp_str_buf_t * buffer );
-void   __kmp_str_buf_free( kmp_str_buf_t * buffer );
-void   __kmp_str_buf_cat( kmp_str_buf_t * buffer, char const * str, int len );
-void   __kmp_str_buf_vprint( kmp_str_buf_t * buffer, char const * format, va_list args );
-void   __kmp_str_buf_print( kmp_str_buf_t * buffer, char const * format, ... );
-void   __kmp_str_buf_print_size( kmp_str_buf_t * buffer, size_t size );
+void __kmp_str_buf_clear(kmp_str_buf_t *buffer);
+void __kmp_str_buf_reserve(kmp_str_buf_t *buffer, int size);
+void __kmp_str_buf_detach(kmp_str_buf_t *buffer);
+void __kmp_str_buf_free(kmp_str_buf_t *buffer);
+void __kmp_str_buf_cat(kmp_str_buf_t *buffer, char const *str, int len);
+void __kmp_str_buf_vprint(kmp_str_buf_t *buffer, char const *format,
+                          va_list args);
+void __kmp_str_buf_print(kmp_str_buf_t *buffer, char const *format, ...);
+void __kmp_str_buf_print_size(kmp_str_buf_t *buffer, size_t size);
 
-/*
-    File name parser. Usage:
-
-        kmp_str_fname_t fname = __kmp_str_fname_init( path );
-        // Use fname.path (copy of original path ), fname.dir, fname.base.
-        // Note fname.dir concatenated with fname.base gives exact copy of path.
-        __kmp_str_fname_free( & fname );
+/* File name parser.
+   Usage:
 
+   kmp_str_fname_t fname = __kmp_str_fname_init( path );
+   // Use fname.path (copy of original path ), fname.dir, fname.base.
+   // Note fname.dir concatenated with fname.base gives exact copy of path.
+   __kmp_str_fname_free( & fname );
 */
 struct kmp_str_fname {
-    char * path;
-    char * dir;
-    char * base;
+  char *path;
+  char *dir;
+  char *base;
 }; // struct kmp_str_fname
 typedef struct kmp_str_fname kmp_str_fname_t;
-void __kmp_str_fname_init( kmp_str_fname_t * fname, char const * path );
-void __kmp_str_fname_free( kmp_str_fname_t * fname );
-// Compares file name with specified patern. If pattern is NULL, any fname matched.
-int __kmp_str_fname_match( kmp_str_fname_t const * fname, char const * pattern );
+void __kmp_str_fname_init(kmp_str_fname_t *fname, char const *path);
+void __kmp_str_fname_free(kmp_str_fname_t *fname);
+// Compares file name with specified patern. If pattern is NULL, any fname
+// matched.
+int __kmp_str_fname_match(kmp_str_fname_t const *fname, char const *pattern);
 
-/*
-    The compiler provides source locations in string form ";file;func;line;col;;". It not not
-    convenient for manupulation. These structure keeps source location in more convenient form.
-    Usage:
+/* The compiler provides source locations in string form
+   ";file;func;line;col;;". It is not convenient for manupulation. This
+   structure keeps source location in more convenient form.
+   Usage:
 
-        kmp_str_loc_t loc = __kmp_str_loc_init( ident->psource, 0 );
-        // use loc.file, loc.func, loc.line, loc.col.
-        // loc.fname is available if the second argument of __kmp_str_loc_init is true.
-        __kmp_str_loc_free( & loc );
+   kmp_str_loc_t loc = __kmp_str_loc_init( ident->psource, 0 );
+   // use loc.file, loc.func, loc.line, loc.col.
+   // loc.fname is available if second argument of __kmp_str_loc_init is true.
+   __kmp_str_loc_free( & loc );
 
-    If psource is NULL or does not follow format above, file and/or func may be NULL pointers.
+   If psource is NULL or does not follow format above, file and/or func may be
+   NULL pointers.
 */
 struct kmp_str_loc {
-    char *          _bulk;  // Do not use thid field.
-    kmp_str_fname_t fname;  // Will be initialized if init_fname is true.
-    char *          file;
-    char *          func;
-    int             line;
-    int             col;
+  char *_bulk; // Do not use thid field.
+  kmp_str_fname_t fname; // Will be initialized if init_fname is true.
+  char *file;
+  char *func;
+  int line;
+  int col;
 }; // struct kmp_str_loc
 typedef struct kmp_str_loc kmp_str_loc_t;
-kmp_str_loc_t __kmp_str_loc_init( char const * psource, int init_fname );
-void __kmp_str_loc_free( kmp_str_loc_t * loc );
+kmp_str_loc_t __kmp_str_loc_init(char const *psource, int init_fname);
+void __kmp_str_loc_free(kmp_str_loc_t *loc);
 
-int    __kmp_str_eqf( char const * lhs, char const * rhs );
-char * __kmp_str_format( char const * format, ... );
-void   __kmp_str_free( char const * * str );
-int    __kmp_str_match( char const * target, int len, char const * data );
-int    __kmp_str_match_false( char const * data );
-int    __kmp_str_match_true( char const * data );
-void   __kmp_str_replace( char * str, char search_for, char replace_with );
-void   __kmp_str_split( char * str, char delim, char ** head, char ** tail );
-char * __kmp_str_token( char * str, char const * delim, char ** buf );
-int    __kmp_str_to_int( char const * str, char sentinel );
+int __kmp_str_eqf(char const *lhs, char const *rhs);
+char *__kmp_str_format(char const *format, ...);
+void __kmp_str_free(char const **str);
+int __kmp_str_match(char const *target, int len, char const *data);
+int __kmp_str_match_false(char const *data);
+int __kmp_str_match_true(char const *data);
+void __kmp_str_replace(char *str, char search_for, char replace_with);
+void __kmp_str_split(char *str, char delim, char **head, char **tail);
+char *__kmp_str_token(char *str, char const *delim, char **buf);
+int __kmp_str_to_int(char const *str, char sentinel);
 
-void __kmp_str_to_size( char const * str, size_t * out, size_t dfactor, char const * * error );
-void __kmp_str_to_uint( char const * str, kmp_uint64 * out, char const * * error );
+void __kmp_str_to_size(char const *str, size_t *out, size_t dfactor,
+                       char const **error);
+void __kmp_str_to_uint(char const *str, kmp_uint64 *out, char const **error);
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif // __cplusplus
 
 #endif // KMP_STR_H
 
 // end of file //
-

runtime/src/kmp_stub.cpp

@@ -13,258 +13,304 @@
 //===----------------------------------------------------------------------===//
 
 
-#include <stdlib.h>
-#include <limits.h>
 #include <errno.h>
+#include <limits.h>
+#include <stdlib.h>
 
-#include "omp.h"                // Function renamings.
-#include "kmp.h"                // KMP_DEFAULT_STKSIZE
+#include "kmp.h" // KMP_DEFAULT_STKSIZE
 #include "kmp_stub.h"
+#include "omp.h" // Function renamings.
 
 #if KMP_OS_WINDOWS
-    #include <windows.h>
+#include <windows.h>
 #else
-    #include <sys/time.h>
+#include <sys/time.h>
 #endif
 
 // Moved from omp.h
-#define omp_set_max_active_levels    ompc_set_max_active_levels
-#define omp_set_schedule             ompc_set_schedule
-#define omp_get_ancestor_thread_num  ompc_get_ancestor_thread_num
-#define omp_get_team_size            ompc_get_team_size
+#define omp_set_max_active_levels ompc_set_max_active_levels
+#define omp_set_schedule ompc_set_schedule
+#define omp_get_ancestor_thread_num ompc_get_ancestor_thread_num
+#define omp_get_team_size ompc_get_team_size
 
-#define omp_set_num_threads          ompc_set_num_threads
-#define omp_set_dynamic              ompc_set_dynamic
-#define omp_set_nested               ompc_set_nested
-#define kmp_set_stacksize            kmpc_set_stacksize
-#define kmp_set_stacksize_s          kmpc_set_stacksize_s
-#define kmp_set_blocktime            kmpc_set_blocktime
-#define kmp_set_library              kmpc_set_library
-#define kmp_set_defaults             kmpc_set_defaults
-#define kmp_set_disp_num_buffers     kmpc_set_disp_num_buffers
-#define kmp_malloc                   kmpc_malloc
-#define kmp_aligned_malloc           kmpc_aligned_malloc
-#define kmp_calloc                   kmpc_calloc
-#define kmp_realloc                  kmpc_realloc
-#define kmp_free                     kmpc_free
+#define omp_set_num_threads ompc_set_num_threads
+#define omp_set_dynamic ompc_set_dynamic
+#define omp_set_nested ompc_set_nested
+#define kmp_set_stacksize kmpc_set_stacksize
+#define kmp_set_stacksize_s kmpc_set_stacksize_s
+#define kmp_set_blocktime kmpc_set_blocktime
+#define kmp_set_library kmpc_set_library
+#define kmp_set_defaults kmpc_set_defaults
+#define kmp_set_disp_num_buffers kmpc_set_disp_num_buffers
+#define kmp_malloc kmpc_malloc
+#define kmp_aligned_malloc kmpc_aligned_malloc
+#define kmp_calloc kmpc_calloc
+#define kmp_realloc kmpc_realloc
+#define kmp_free kmpc_free
 
 static double frequency = 0.0;
 
 // Helper functions.
 static size_t __kmps_init() {
-    static int    initialized = 0;
-    static size_t dummy = 0;
-    if ( ! initialized ) {
+  static int initialized = 0;
+  static size_t dummy = 0;
+  if (!initialized) {
+    // TODO: Analyze KMP_VERSION environment variable, print
+    // __kmp_version_copyright and __kmp_version_build_time.
+    // WARNING: Do not use "fprintf(stderr, ...)" because it will cause
+    // unresolved "__iob" symbol (see C70080). We need to extract __kmp_printf()
+    // stuff from kmp_runtime.cpp and use it.
 
-        // TODO: Analyze KMP_VERSION environment variable, print
-        // __kmp_version_copyright and __kmp_version_build_time.
-        // WARNING: Do not use "fprintf( stderr, ... )" because it will cause
-        // unresolved "__iob" symbol (see C70080). We need to extract
-        // __kmp_printf() stuff from kmp_runtime.cpp and use it.
+    // Trick with dummy variable forces linker to keep __kmp_version_copyright
+    // and __kmp_version_build_time strings in executable file (in case of
+    // static linkage). When KMP_VERSION analysis is implemented, dummy
+    // variable should be deleted, function should return void.
+    dummy = __kmp_version_copyright - __kmp_version_build_time;
 
-        // Trick with dummy variable forces linker to keep __kmp_version_copyright
-        // and __kmp_version_build_time strings in executable file (in case of
-        // static linkage). When KMP_VERSION analysis is implemented, dummy
-        // variable should be deleted, function should return void.
-        dummy = __kmp_version_copyright - __kmp_version_build_time;
-
-        #if KMP_OS_WINDOWS
-            LARGE_INTEGER freq;
-            BOOL status = QueryPerformanceFrequency( & freq );
-            if ( status ) {
-                frequency = double( freq.QuadPart );
-            }; // if
-        #endif
-
-        initialized = 1;
+#if KMP_OS_WINDOWS
+    LARGE_INTEGER freq;
+    BOOL status = QueryPerformanceFrequency(&freq);
+    if (status) {
+      frequency = double(freq.QuadPart);
     }; // if
-    return dummy;
+#endif
+
+    initialized = 1;
+  }; // if
+  return dummy;
 }; // __kmps_init
 
 #define i __kmps_init();
 
 /* set API functions */
-void omp_set_num_threads( omp_int_t num_threads ) { i; }
-void omp_set_dynamic( omp_int_t dynamic )         { i; __kmps_set_dynamic( dynamic ); }
-void omp_set_nested( omp_int_t nested )           { i; __kmps_set_nested( nested );   }
-void omp_set_max_active_levels( omp_int_t max_active_levels ) { i; }
-void omp_set_schedule( omp_sched_t kind, omp_int_t modifier ) { i; __kmps_set_schedule( (kmp_sched_t)kind, modifier ); }
-int omp_get_ancestor_thread_num( omp_int_t level ) { i; return ( level ) ? ( -1 ) : ( 0 ); }
-int omp_get_team_size( omp_int_t level ) { i; return ( level ) ? ( -1 ) : ( 1 ); }
-int kmpc_set_affinity_mask_proc( int proc, void **mask ) { i; return -1; }
-int kmpc_unset_affinity_mask_proc( int proc, void **mask ) { i; return -1; }
-int kmpc_get_affinity_mask_proc( int proc, void **mask ) { i; return -1; }
+void omp_set_num_threads(omp_int_t num_threads) { i; }
+void omp_set_dynamic(omp_int_t dynamic) {
+  i;
+  __kmps_set_dynamic(dynamic);
+}
+void omp_set_nested(omp_int_t nested) {
+  i;
+  __kmps_set_nested(nested);
+}
+void omp_set_max_active_levels(omp_int_t max_active_levels) { i; }
+void omp_set_schedule(omp_sched_t kind, omp_int_t modifier) {
+  i;
+  __kmps_set_schedule((kmp_sched_t)kind, modifier);
+}
+int omp_get_ancestor_thread_num(omp_int_t level) {
+  i;
+  return (level) ? (-1) : (0);
+}
+int omp_get_team_size(omp_int_t level) {
+  i;
+  return (level) ? (-1) : (1);
+}
+int kmpc_set_affinity_mask_proc(int proc, void **mask) {
+  i;
+  return -1;
+}
+int kmpc_unset_affinity_mask_proc(int proc, void **mask) {
+  i;
+  return -1;
+}
+int kmpc_get_affinity_mask_proc(int proc, void **mask) {
+  i;
+  return -1;
+}
 
 /* kmp API functions */
-void kmp_set_stacksize( omp_int_t arg )   { i; __kmps_set_stacksize( arg ); }
-void kmp_set_stacksize_s( size_t arg )    { i; __kmps_set_stacksize( arg ); }
-void kmp_set_blocktime( omp_int_t arg )   { i; __kmps_set_blocktime( arg ); }
-void kmp_set_library( omp_int_t arg )     { i; __kmps_set_library( arg ); }
-void kmp_set_defaults( char const * str ) { i; }
-void kmp_set_disp_num_buffers( omp_int_t arg ) { i; }
+void kmp_set_stacksize(omp_int_t arg) {
+  i;
+  __kmps_set_stacksize(arg);
+}
+void kmp_set_stacksize_s(size_t arg) {
+  i;
+  __kmps_set_stacksize(arg);
+}
+void kmp_set_blocktime(omp_int_t arg) {
+  i;
+  __kmps_set_blocktime(arg);
+}
+void kmp_set_library(omp_int_t arg) {
+  i;
+  __kmps_set_library(arg);
+}
+void kmp_set_defaults(char const *str) { i; }
+void kmp_set_disp_num_buffers(omp_int_t arg) { i; }
 
 /* KMP memory management functions. */
-void * kmp_malloc( size_t size )                 { i; return malloc( size ); }
-void * kmp_aligned_malloc( size_t sz, size_t a ) {
-    i;
+void *kmp_malloc(size_t size) {
+  i;
+  return malloc(size);
+}
+void *kmp_aligned_malloc(size_t sz, size_t a) {
+  i;
 #if KMP_OS_WINDOWS
-    errno = ENOSYS; // not supported
-    return NULL;    // no standard aligned allocator on Windows (pre - C11)
+  errno = ENOSYS; // not supported
+  return NULL; // no standard aligned allocator on Windows (pre - C11)
 #else
-    void *res;
-    int err;
-    if( err = posix_memalign( &res, a, sz ) ) {
-        errno = err; // can be EINVAL or ENOMEM
-        return NULL;
-    }
-    return res;
+  void *res;
+  int err;
+  if (err = posix_memalign(&res, a, sz)) {
+    errno = err; // can be EINVAL or ENOMEM
+    return NULL;
+  }
+  return res;
 #endif
 }
-void * kmp_calloc( size_t nelem, size_t elsize ) { i; return calloc( nelem, elsize ); }
-void * kmp_realloc( void *ptr, size_t size )     { i; return realloc( ptr, size ); }
-void   kmp_free( void * ptr )                    { i; free( ptr ); }
+void *kmp_calloc(size_t nelem, size_t elsize) {
+  i;
+  return calloc(nelem, elsize);
+}
+void *kmp_realloc(void *ptr, size_t size) {
+  i;
+  return realloc(ptr, size);
+}
+void kmp_free(void *ptr) {
+  i;
+  free(ptr);
+}
 
 static int __kmps_blocktime = INT_MAX;
 
-void __kmps_set_blocktime( int arg ) {
-    i;
-    __kmps_blocktime = arg;
+void __kmps_set_blocktime(int arg) {
+  i;
+  __kmps_blocktime = arg;
 } // __kmps_set_blocktime
 
-int __kmps_get_blocktime( void ) {
-    i;
-    return __kmps_blocktime;
+int __kmps_get_blocktime(void) {
+  i;
+  return __kmps_blocktime;
 } // __kmps_get_blocktime
 
 static int __kmps_dynamic = 0;
 
-void __kmps_set_dynamic( int arg ) {
-    i;
-    __kmps_dynamic = arg;
+void __kmps_set_dynamic(int arg) {
+  i;
+  __kmps_dynamic = arg;
 } // __kmps_set_dynamic
 
-int __kmps_get_dynamic( void ) {
-    i;
-    return __kmps_dynamic;
+int __kmps_get_dynamic(void) {
+  i;
+  return __kmps_dynamic;
 } // __kmps_get_dynamic
 
 static int __kmps_library = 1000;
 
-void __kmps_set_library( int arg ) {
-    i;
-    __kmps_library = arg;
+void __kmps_set_library(int arg) {
+  i;
+  __kmps_library = arg;
 } // __kmps_set_library
 
-int __kmps_get_library( void ) {
-    i;
-    return __kmps_library;
+int __kmps_get_library(void) {
+  i;
+  return __kmps_library;
 } // __kmps_get_library
 
 static int __kmps_nested = 0;
 
-void __kmps_set_nested( int arg ) {
-    i;
-    __kmps_nested = arg;
+void __kmps_set_nested(int arg) {
+  i;
+  __kmps_nested = arg;
 } // __kmps_set_nested
 
-int __kmps_get_nested( void ) {
-    i;
-    return __kmps_nested;
+int __kmps_get_nested(void) {
+  i;
+  return __kmps_nested;
 } // __kmps_get_nested
 
 static size_t __kmps_stacksize = KMP_DEFAULT_STKSIZE;
 
-void __kmps_set_stacksize( int arg ) {
-    i;
-    __kmps_stacksize = arg;
+void __kmps_set_stacksize(int arg) {
+  i;
+  __kmps_stacksize = arg;
 } // __kmps_set_stacksize
 
-int __kmps_get_stacksize( void ) {
-    i;
-    return __kmps_stacksize;
+int __kmps_get_stacksize(void) {
+  i;
+  return __kmps_stacksize;
 } // __kmps_get_stacksize
 
-static kmp_sched_t __kmps_sched_kind     = kmp_sched_default;
-static int         __kmps_sched_modifier = 0;
+static kmp_sched_t __kmps_sched_kind = kmp_sched_default;
+static int __kmps_sched_modifier = 0;
 
-    void __kmps_set_schedule( kmp_sched_t kind, int modifier ) {
-        i;
-        __kmps_sched_kind     = kind;
-        __kmps_sched_modifier = modifier;
-    } // __kmps_set_schedule
+void __kmps_set_schedule(kmp_sched_t kind, int modifier) {
+  i;
+  __kmps_sched_kind = kind;
+  __kmps_sched_modifier = modifier;
+} // __kmps_set_schedule
 
-    void __kmps_get_schedule( kmp_sched_t *kind, int *modifier ) {
-        i;
-        *kind     = __kmps_sched_kind;
-        *modifier = __kmps_sched_modifier;
-    } // __kmps_get_schedule
+void __kmps_get_schedule(kmp_sched_t *kind, int *modifier) {
+  i;
+  *kind = __kmps_sched_kind;
+  *modifier = __kmps_sched_modifier;
+} // __kmps_get_schedule
 
 #if OMP_40_ENABLED
 
 static kmp_proc_bind_t __kmps_proc_bind = proc_bind_false;
 
-void __kmps_set_proc_bind( kmp_proc_bind_t arg ) {
-    i;
-    __kmps_proc_bind = arg;
+void __kmps_set_proc_bind(kmp_proc_bind_t arg) {
+  i;
+  __kmps_proc_bind = arg;
 } // __kmps_set_proc_bind
 
-kmp_proc_bind_t __kmps_get_proc_bind( void ) {
-    i;
-    return __kmps_proc_bind;
+kmp_proc_bind_t __kmps_get_proc_bind(void) {
+  i;
+  return __kmps_proc_bind;
 } // __kmps_get_proc_bind
 
 #endif /* OMP_40_ENABLED */
 
-double __kmps_get_wtime( void ) {
-    // Elapsed wall clock time (in second) from "sometime in the past".
-    double wtime = 0.0;
-    i;
-    #if KMP_OS_WINDOWS
-        if ( frequency > 0.0 ) {
-            LARGE_INTEGER now;
-            BOOL status = QueryPerformanceCounter( & now );
-            if ( status ) {
-                wtime = double( now.QuadPart ) / frequency;
-            }; // if
-        }; // if
-    #else
-        // gettimeofday() returns seconds and microseconds since the Epoch.
-        struct timeval  tval;
-        int             rc;
-        rc = gettimeofday( & tval, NULL );
-        if ( rc == 0 ) {
-            wtime = (double)( tval.tv_sec ) + 1.0E-06 * (double)( tval.tv_usec );
-        } else {
-            // TODO: Assert or abort here.
-        }; // if
-    #endif
-    return wtime;
+double __kmps_get_wtime(void) {
+  // Elapsed wall clock time (in second) from "sometime in the past".
+  double wtime = 0.0;
+  i;
+#if KMP_OS_WINDOWS
+  if (frequency > 0.0) {
+    LARGE_INTEGER now;
+    BOOL status = QueryPerformanceCounter(&now);
+    if (status) {
+      wtime = double(now.QuadPart) / frequency;
+    }; // if
+  }; // if
+#else
+  // gettimeofday() returns seconds and microseconds since the Epoch.
+  struct timeval tval;
+  int rc;
+  rc = gettimeofday(&tval, NULL);
+  if (rc == 0) {
+    wtime = (double)(tval.tv_sec) + 1.0E-06 * (double)(tval.tv_usec);
+  } else {
+    // TODO: Assert or abort here.
+  }; // if
+#endif
+  return wtime;
 }; // __kmps_get_wtime
 
-double __kmps_get_wtick( void ) {
-    // Number of seconds between successive clock ticks.
-    double wtick = 0.0;
-    i;
-    #if KMP_OS_WINDOWS
-        {
-            DWORD increment;
-            DWORD adjustment;
-            BOOL  disabled;
-            BOOL  rc;
-            rc = GetSystemTimeAdjustment( & adjustment, & increment, & disabled );
-            if ( rc ) {
-                wtick = 1.0E-07 * (double)( disabled ? increment : adjustment );
-            } else {
-                // TODO: Assert or abort here.
-                wtick = 1.0E-03;
-            }; // if
-        }
-    #else
-        // TODO: gettimeofday() returns in microseconds, but what the precision?
-        wtick = 1.0E-06;
-    #endif
-    return wtick;
+double __kmps_get_wtick(void) {
+  // Number of seconds between successive clock ticks.
+  double wtick = 0.0;
+  i;
+#if KMP_OS_WINDOWS
+  {
+    DWORD increment;
+    DWORD adjustment;
+    BOOL disabled;
+    BOOL rc;
+    rc = GetSystemTimeAdjustment(&adjustment, &increment, &disabled);
+    if (rc) {
+      wtick = 1.0E-07 * (double)(disabled ? increment : adjustment);
+    } else {
+      // TODO: Assert or abort here.
+      wtick = 1.0E-03;
+    }; // if
+  }
+#else
+  // TODO: gettimeofday() returns in microseconds, but what the precision?
+  wtick = 1.0E-06;
+#endif
+  return wtick;
 }; // __kmps_get_wtick
 
 // end of file //
-

runtime/src/kmp_stub.h

@@ -17,43 +17,43 @@
 #define KMP_STUB_H
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
-void __kmps_set_blocktime( int arg );
-int  __kmps_get_blocktime( void );
-void __kmps_set_dynamic( int arg );
-int  __kmps_get_dynamic( void );
-void __kmps_set_library( int arg );
-int  __kmps_get_library( void );
-void __kmps_set_nested( int arg );
-int  __kmps_get_nested( void );
-void __kmps_set_stacksize( int arg );
-int  __kmps_get_stacksize();
+void __kmps_set_blocktime(int arg);
+int __kmps_get_blocktime(void);
+void __kmps_set_dynamic(int arg);
+int __kmps_get_dynamic(void);
+void __kmps_set_library(int arg);
+int __kmps_get_library(void);
+void __kmps_set_nested(int arg);
+int __kmps_get_nested(void);
+void __kmps_set_stacksize(int arg);
+int __kmps_get_stacksize();
 
 #ifndef KMP_SCHED_TYPE_DEFINED
 #define KMP_SCHED_TYPE_DEFINED
 typedef enum kmp_sched {
-    kmp_sched_static            = 1, // mapped to kmp_sch_static_chunked           (33)
-    kmp_sched_dynamic           = 2, // mapped to kmp_sch_dynamic_chunked          (35)
-    kmp_sched_guided            = 3, // mapped to kmp_sch_guided_chunked           (36)
-    kmp_sched_auto              = 4, // mapped to kmp_sch_auto                     (38)
-    kmp_sched_default = kmp_sched_static   // default scheduling
+  kmp_sched_static = 1, // mapped to kmp_sch_static_chunked           (33)
+  kmp_sched_dynamic = 2, // mapped to kmp_sch_dynamic_chunked          (35)
+  kmp_sched_guided = 3, // mapped to kmp_sch_guided_chunked           (36)
+  kmp_sched_auto = 4, // mapped to kmp_sch_auto                     (38)
+  kmp_sched_default = kmp_sched_static // default scheduling
 } kmp_sched_t;
 #endif
-void __kmps_set_schedule( kmp_sched_t kind, int modifier );
-void __kmps_get_schedule( kmp_sched_t *kind, int *modifier );
+void __kmps_set_schedule(kmp_sched_t kind, int modifier);
+void __kmps_get_schedule(kmp_sched_t *kind, int *modifier);
 
 #if OMP_40_ENABLED
-void __kmps_set_proc_bind( kmp_proc_bind_t arg );
-kmp_proc_bind_t __kmps_get_proc_bind( void );
+void __kmps_set_proc_bind(kmp_proc_bind_t arg);
+kmp_proc_bind_t __kmps_get_proc_bind(void);
 #endif /* OMP_40_ENABLED */
 
 double __kmps_get_wtime();
 double __kmps_get_wtick();
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif // __cplusplus
 
 #endif // KMP_STUB_H

runtime/src/kmp_taskdeps.cpp

@@ -21,511 +21,545 @@
 
 #if OMP_40_ENABLED
 
-//TODO: Improve memory allocation? keep a list of pre-allocated structures? allocate in blocks? re-use list finished list entries?
-//TODO: don't use atomic ref counters for stack-allocated nodes.
-//TODO: find an alternate to atomic refs for heap-allocated nodes?
-//TODO: Finish graph output support
-//TODO: kmp_lock_t seems a tad to big (and heavy weight) for this. Check other runtime locks
-//TODO: Any ITT support needed?
+// TODO: Improve memory allocation? keep a list of pre-allocated structures?
+// allocate in blocks? re-use list finished list entries?
+// TODO: don't use atomic ref counters for stack-allocated nodes.
+// TODO: find an alternate to atomic refs for heap-allocated nodes?
+// TODO: Finish graph output support
+// TODO: kmp_lock_t seems a tad to big (and heavy weight) for this. Check other
+// runtime locks
+// TODO: Any ITT support needed?
 
 #ifdef KMP_SUPPORT_GRAPH_OUTPUT
 static kmp_int32 kmp_node_id_seed = 0;
 #endif
 
-static void
-__kmp_init_node ( kmp_depnode_t *node )
-{
-    node->dn.task = NULL; // set to null initially, it will point to the right task once dependences have been processed
-    node->dn.successors = NULL;
-    __kmp_init_lock(&node->dn.lock);
-    node->dn.nrefs = 1; // init creates the first reference to the node
+static void __kmp_init_node(kmp_depnode_t *node) {
+  node->dn.task = NULL; // set to null initially, it will point to the right
+  // task once dependences have been processed
+  node->dn.successors = NULL;
+  __kmp_init_lock(&node->dn.lock);
+  node->dn.nrefs = 1; // init creates the first reference to the node
 #ifdef KMP_SUPPORT_GRAPH_OUTPUT
-    node->dn.id = KMP_TEST_THEN_INC32(&kmp_node_id_seed);
+  node->dn.id = KMP_TEST_THEN_INC32(&kmp_node_id_seed);
 #endif
 }
 
-static inline kmp_depnode_t *
-__kmp_node_ref ( kmp_depnode_t *node )
-{
-    KMP_TEST_THEN_INC32(&node->dn.nrefs);
-    return node;
+static inline kmp_depnode_t *__kmp_node_ref(kmp_depnode_t *node) {
+  KMP_TEST_THEN_INC32(CCAST(kmp_int32 *, &node->dn.nrefs));
+  return node;
 }
 
-static inline void
-__kmp_node_deref ( kmp_info_t *thread, kmp_depnode_t *node )
-{
-    if (!node) return;
+static inline void __kmp_node_deref(kmp_info_t *thread, kmp_depnode_t *node) {
+  if (!node)
+    return;
 
-    kmp_int32 n = KMP_TEST_THEN_DEC32(&node->dn.nrefs) - 1;
-    if ( n == 0 ) {
-        KMP_ASSERT(node->dn.nrefs == 0);
+  kmp_int32 n = KMP_TEST_THEN_DEC32(CCAST(kmp_int32 *, &node->dn.nrefs)) - 1;
+  if (n == 0) {
+    KMP_ASSERT(node->dn.nrefs == 0);
 #if USE_FAST_MEMORY
-        __kmp_fast_free(thread,node);
+    __kmp_fast_free(thread, node);
 #else
-        __kmp_thread_free(thread,node);
+    __kmp_thread_free(thread, node);
 #endif
-    }
+  }
 }
 
-#define KMP_ACQUIRE_DEPNODE(gtid,n) __kmp_acquire_lock(&(n)->dn.lock,(gtid))
-#define KMP_RELEASE_DEPNODE(gtid,n) __kmp_release_lock(&(n)->dn.lock,(gtid))
+#define KMP_ACQUIRE_DEPNODE(gtid, n) __kmp_acquire_lock(&(n)->dn.lock, (gtid))
+#define KMP_RELEASE_DEPNODE(gtid, n) __kmp_release_lock(&(n)->dn.lock, (gtid))
 
-static void
-__kmp_depnode_list_free ( kmp_info_t *thread, kmp_depnode_list *list );
+static void __kmp_depnode_list_free(kmp_info_t *thread, kmp_depnode_list *list);
 
-enum {
-    KMP_DEPHASH_OTHER_SIZE = 97,
-    KMP_DEPHASH_MASTER_SIZE = 997
-};
+enum { KMP_DEPHASH_OTHER_SIZE = 97, KMP_DEPHASH_MASTER_SIZE = 997 };
 
-static inline kmp_int32
-__kmp_dephash_hash ( kmp_intptr_t addr, size_t hsize )
-{
-    //TODO alternate to try: set = (((Addr64)(addrUsefulBits * 9.618)) % m_num_sets );
-    return ((addr >> 6) ^ (addr >> 2)) % hsize;
+static inline kmp_int32 __kmp_dephash_hash(kmp_intptr_t addr, size_t hsize) {
+  // TODO alternate to try: set = (((Addr64)(addrUsefulBits * 9.618)) %
+  // m_num_sets );
+  return ((addr >> 6) ^ (addr >> 2)) % hsize;
 }
 
-static kmp_dephash_t *
-__kmp_dephash_create ( kmp_info_t *thread, kmp_taskdata_t *current_task )
-{
-    kmp_dephash_t *h;
+static kmp_dephash_t *__kmp_dephash_create(kmp_info_t *thread,
+                                           kmp_taskdata_t *current_task) {
+  kmp_dephash_t *h;
 
-    size_t h_size;
+  size_t h_size;
 
-    if ( current_task->td_flags.tasktype == TASK_IMPLICIT )
-        h_size = KMP_DEPHASH_MASTER_SIZE;
-    else
-        h_size = KMP_DEPHASH_OTHER_SIZE;
+  if (current_task->td_flags.tasktype == TASK_IMPLICIT)
+    h_size = KMP_DEPHASH_MASTER_SIZE;
+  else
+    h_size = KMP_DEPHASH_OTHER_SIZE;
 
-    kmp_int32 size =
-        h_size * sizeof(kmp_dephash_entry_t *) + sizeof(kmp_dephash_t);
+  kmp_int32 size =
+      h_size * sizeof(kmp_dephash_entry_t *) + sizeof(kmp_dephash_t);
 
 #if USE_FAST_MEMORY
-    h = (kmp_dephash_t *) __kmp_fast_allocate( thread, size );
+  h = (kmp_dephash_t *)__kmp_fast_allocate(thread, size);
 #else
-    h = (kmp_dephash_t *) __kmp_thread_malloc( thread, size );
+  h = (kmp_dephash_t *)__kmp_thread_malloc(thread, size);
 #endif
-    h->size = h_size;
+  h->size = h_size;
 
 #ifdef KMP_DEBUG
-    h->nelements = 0;
-    h->nconflicts = 0;
+  h->nelements = 0;
+  h->nconflicts = 0;
 #endif
-    h->buckets = (kmp_dephash_entry **)(h+1);
+  h->buckets = (kmp_dephash_entry **)(h + 1);
 
-    for ( size_t i = 0; i < h_size; i++ )
-        h->buckets[i] = 0;
+  for (size_t i = 0; i < h_size; i++)
+    h->buckets[i] = 0;
 
-    return h;
+  return h;
 }
 
-void
-__kmp_dephash_free_entries(kmp_info_t *thread, kmp_dephash_t *h)
-{
-    for (size_t i = 0; i < h->size; i++) {
-        if (h->buckets[i]) {
-            kmp_dephash_entry_t *next;
-            for (kmp_dephash_entry_t *entry = h->buckets[i]; entry; entry = next) {
-                next = entry->next_in_bucket;
-                __kmp_depnode_list_free(thread,entry->last_ins);
-                __kmp_node_deref(thread,entry->last_out);
+void __kmp_dephash_free_entries(kmp_info_t *thread, kmp_dephash_t *h) {
+  for (size_t i = 0; i < h->size; i++) {
+    if (h->buckets[i]) {
+      kmp_dephash_entry_t *next;
+      for (kmp_dephash_entry_t *entry = h->buckets[i]; entry; entry = next) {
+        next = entry->next_in_bucket;
+        __kmp_depnode_list_free(thread, entry->last_ins);
+        __kmp_node_deref(thread, entry->last_out);
 #if USE_FAST_MEMORY
-                __kmp_fast_free(thread,entry);
+        __kmp_fast_free(thread, entry);
 #else
-                __kmp_thread_free(thread,entry);
+        __kmp_thread_free(thread, entry);
 #endif
-            }
-            h->buckets[i] = 0;
-        }
+      }
+      h->buckets[i] = 0;
     }
+  }
 }
 
-void
-__kmp_dephash_free(kmp_info_t *thread, kmp_dephash_t *h)
-{
-    __kmp_dephash_free_entries(thread, h);
+void __kmp_dephash_free(kmp_info_t *thread, kmp_dephash_t *h) {
+  __kmp_dephash_free_entries(thread, h);
 #if USE_FAST_MEMORY
-    __kmp_fast_free(thread,h);
+  __kmp_fast_free(thread, h);
 #else
-    __kmp_thread_free(thread,h);
+  __kmp_thread_free(thread, h);
 #endif
 }
 
 static kmp_dephash_entry *
-__kmp_dephash_find ( kmp_info_t *thread, kmp_dephash_t *h, kmp_intptr_t addr )
-{
-    kmp_int32 bucket = __kmp_dephash_hash(addr,h->size);
+__kmp_dephash_find(kmp_info_t *thread, kmp_dephash_t *h, kmp_intptr_t addr) {
+  kmp_int32 bucket = __kmp_dephash_hash(addr, h->size);
 
-    kmp_dephash_entry_t *entry;
-    for ( entry = h->buckets[bucket]; entry; entry = entry->next_in_bucket )
-        if ( entry->addr == addr ) break;
+  kmp_dephash_entry_t *entry;
+  for (entry = h->buckets[bucket]; entry; entry = entry->next_in_bucket)
+    if (entry->addr == addr)
+      break;
 
-    if ( entry == NULL ) {
-        // create entry. This is only done by one thread so no locking required
+  if (entry == NULL) {
+// create entry. This is only done by one thread so no locking required
 #if USE_FAST_MEMORY
-        entry = (kmp_dephash_entry_t *) __kmp_fast_allocate( thread, sizeof(kmp_dephash_entry_t) );
+    entry = (kmp_dephash_entry_t *)__kmp_fast_allocate(
+        thread, sizeof(kmp_dephash_entry_t));
 #else
-        entry = (kmp_dephash_entry_t *) __kmp_thread_malloc( thread, sizeof(kmp_dephash_entry_t) );
+    entry = (kmp_dephash_entry_t *)__kmp_thread_malloc(
+        thread, sizeof(kmp_dephash_entry_t));
 #endif
-        entry->addr = addr;
-        entry->last_out = NULL;
-        entry->last_ins = NULL;
-        entry->next_in_bucket = h->buckets[bucket];
-        h->buckets[bucket] = entry;
+    entry->addr = addr;
+    entry->last_out = NULL;
+    entry->last_ins = NULL;
+    entry->next_in_bucket = h->buckets[bucket];
+    h->buckets[bucket] = entry;
 #ifdef KMP_DEBUG
-        h->nelements++;
-        if ( entry->next_in_bucket ) h->nconflicts++;
+    h->nelements++;
+    if (entry->next_in_bucket)
+      h->nconflicts++;
 #endif
-    }
-    return entry;
+  }
+  return entry;
 }
 
-static kmp_depnode_list_t *
-__kmp_add_node ( kmp_info_t *thread, kmp_depnode_list_t *list, kmp_depnode_t *node )
-{
-    kmp_depnode_list_t *new_head;
+static kmp_depnode_list_t *__kmp_add_node(kmp_info_t *thread,
+                                          kmp_depnode_list_t *list,
+                                          kmp_depnode_t *node) {
+  kmp_depnode_list_t *new_head;
 
 #if USE_FAST_MEMORY
-    new_head = (kmp_depnode_list_t *) __kmp_fast_allocate(thread,sizeof(kmp_depnode_list_t));
+  new_head = (kmp_depnode_list_t *)__kmp_fast_allocate(
+      thread, sizeof(kmp_depnode_list_t));
 #else
-    new_head = (kmp_depnode_list_t *) __kmp_thread_malloc(thread,sizeof(kmp_depnode_list_t));
+  new_head = (kmp_depnode_list_t *)__kmp_thread_malloc(
+      thread, sizeof(kmp_depnode_list_t));
 #endif
 
-    new_head->node = __kmp_node_ref(node);
-    new_head->next = list;
+  new_head->node = __kmp_node_ref(node);
+  new_head->next = list;
 
-    return new_head;
+  return new_head;
 }
 
-static void
-__kmp_depnode_list_free ( kmp_info_t *thread, kmp_depnode_list *list )
-{
-    kmp_depnode_list *next;
+static void __kmp_depnode_list_free(kmp_info_t *thread,
+                                    kmp_depnode_list *list) {
+  kmp_depnode_list *next;
 
-    for ( ; list ; list = next ) {
-        next = list->next;
+  for (; list; list = next) {
+    next = list->next;
 
-        __kmp_node_deref(thread,list->node);
+    __kmp_node_deref(thread, list->node);
 #if USE_FAST_MEMORY
-        __kmp_fast_free(thread,list);
+    __kmp_fast_free(thread, list);
 #else
-        __kmp_thread_free(thread,list);
+    __kmp_thread_free(thread, list);
 #endif
-    }
+  }
 }
 
-static inline void
-__kmp_track_dependence ( kmp_depnode_t *source, kmp_depnode_t *sink,
-                         kmp_task_t *sink_task )
-{
+static inline void __kmp_track_dependence(kmp_depnode_t *source,
+                                          kmp_depnode_t *sink,
+                                          kmp_task_t *sink_task) {
 #ifdef KMP_SUPPORT_GRAPH_OUTPUT
-    kmp_taskdata_t * task_source = KMP_TASK_TO_TASKDATA(source->dn.task);
-    // do not use sink->dn.task as that is only filled after the dependencies
-    // are already processed!
-    kmp_taskdata_t * task_sink = KMP_TASK_TO_TASKDATA(sink_task);
+  kmp_taskdata_t *task_source = KMP_TASK_TO_TASKDATA(source->dn.task);
+  // do not use sink->dn.task as that is only filled after the dependencies
+  // are already processed!
+  kmp_taskdata_t *task_sink = KMP_TASK_TO_TASKDATA(sink_task);
 
-    __kmp_printf("%d(%s) -> %d(%s)\n", source->dn.id, task_source->td_ident->psource, sink->dn.id, task_sink->td_ident->psource);
+  __kmp_printf("%d(%s) -> %d(%s)\n", source->dn.id,
+               task_source->td_ident->psource, sink->dn.id,
+               task_sink->td_ident->psource);
 #endif
 #if OMPT_SUPPORT && OMPT_TRACE
-    /* OMPT tracks dependences between task (a=source, b=sink) in which
-       task a blocks the execution of b through the ompt_new_dependence_callback */
-    if (ompt_enabled &&
-        ompt_callbacks.ompt_callback(ompt_event_task_dependence_pair))
-    {
-        kmp_taskdata_t * task_source = KMP_TASK_TO_TASKDATA(source->dn.task);
-        kmp_taskdata_t * task_sink = KMP_TASK_TO_TASKDATA(sink_task);
+  // OMPT tracks dependences between task (a=source, b=sink) in which
+  // task a blocks the execution of b through the ompt_new_dependence_callback
+  if (ompt_enabled &&
+      ompt_callbacks.ompt_callback(ompt_event_task_dependence_pair)) {
+    kmp_taskdata_t *task_source = KMP_TASK_TO_TASKDATA(source->dn.task);
+    kmp_taskdata_t *task_sink = KMP_TASK_TO_TASKDATA(sink_task);
 
-        ompt_callbacks.ompt_callback(ompt_event_task_dependence_pair)(
-          task_source->ompt_task_info.task_id,
-          task_sink->ompt_task_info.task_id);
-    }
+    ompt_callbacks.ompt_callback(ompt_event_task_dependence_pair)(
+        task_source->ompt_task_info.task_id, task_sink->ompt_task_info.task_id);
+  }
 #endif /* OMPT_SUPPORT && OMPT_TRACE */
 }
 
-template< bool filter >
+template <bool filter>
 static inline kmp_int32
-__kmp_process_deps ( kmp_int32 gtid, kmp_depnode_t *node, kmp_dephash_t *hash,
-                     bool dep_barrier,kmp_int32 ndeps, kmp_depend_info_t *dep_list,
-                     kmp_task_t *task )
-{
-    KA_TRACE(30, ("__kmp_process_deps<%d>: T#%d processing %d dependencies : dep_barrier = %d\n", filter, gtid, ndeps, dep_barrier ) );
+__kmp_process_deps(kmp_int32 gtid, kmp_depnode_t *node, kmp_dephash_t *hash,
+                   bool dep_barrier, kmp_int32 ndeps,
+                   kmp_depend_info_t *dep_list, kmp_task_t *task) {
+  KA_TRACE(30, ("__kmp_process_deps<%d>: T#%d processing %d dependencies : "
+                "dep_barrier = %d\n",
+                filter, gtid, ndeps, dep_barrier));
 
-    kmp_info_t *thread = __kmp_threads[ gtid ];
-    kmp_int32 npredecessors=0;
-    for ( kmp_int32 i = 0; i < ndeps ; i++ ) {
-        const kmp_depend_info_t * dep = &dep_list[i];
+  kmp_info_t *thread = __kmp_threads[gtid];
+  kmp_int32 npredecessors = 0;
+  for (kmp_int32 i = 0; i < ndeps; i++) {
+    const kmp_depend_info_t *dep = &dep_list[i];
 
-        KMP_DEBUG_ASSERT(dep->flags.in);
+    KMP_DEBUG_ASSERT(dep->flags.in);
 
-        if ( filter && dep->base_addr == 0 ) continue; // skip filtered entries
+    if (filter && dep->base_addr == 0)
+      continue; // skip filtered entries
 
-        kmp_dephash_entry_t *info = __kmp_dephash_find(thread,hash,dep->base_addr);
-        kmp_depnode_t *last_out = info->last_out;
+    kmp_dephash_entry_t *info =
+        __kmp_dephash_find(thread, hash, dep->base_addr);
+    kmp_depnode_t *last_out = info->last_out;
 
-        if ( dep->flags.out && info->last_ins ) {
-            for ( kmp_depnode_list_t * p = info->last_ins; p; p = p->next ) {
-                kmp_depnode_t * indep = p->node;
-                if ( indep->dn.task ) {
-                    KMP_ACQUIRE_DEPNODE(gtid,indep);
-                    if ( indep->dn.task ) {
-                        __kmp_track_dependence(indep,node,task);
-                        indep->dn.successors = __kmp_add_node(thread, indep->dn.successors, node);
-                        KA_TRACE(40,("__kmp_process_deps<%d>: T#%d adding dependence from %p to %p\n",
-                                 filter,gtid, KMP_TASK_TO_TASKDATA(indep->dn.task), KMP_TASK_TO_TASKDATA(task)));
-                        npredecessors++;
-                    }
-                    KMP_RELEASE_DEPNODE(gtid,indep);
-                }
-            }
-
-            __kmp_depnode_list_free(thread,info->last_ins);
-            info->last_ins = NULL;
-
-        } else if ( last_out && last_out->dn.task ) {
-            KMP_ACQUIRE_DEPNODE(gtid,last_out);
-            if ( last_out->dn.task ) {
-                __kmp_track_dependence(last_out,node,task);
-                last_out->dn.successors = __kmp_add_node(thread, last_out->dn.successors, node);
-                KA_TRACE(40,("__kmp_process_deps<%d>: T#%d adding dependence from %p to %p\n",
-                             filter,gtid, KMP_TASK_TO_TASKDATA(last_out->dn.task), KMP_TASK_TO_TASKDATA(task)));
-
-                npredecessors++;
-            }
-            KMP_RELEASE_DEPNODE(gtid,last_out);
+    if (dep->flags.out && info->last_ins) {
+      for (kmp_depnode_list_t *p = info->last_ins; p; p = p->next) {
+        kmp_depnode_t *indep = p->node;
+        if (indep->dn.task) {
+          KMP_ACQUIRE_DEPNODE(gtid, indep);
+          if (indep->dn.task) {
+            __kmp_track_dependence(indep, node, task);
+            indep->dn.successors =
+                __kmp_add_node(thread, indep->dn.successors, node);
+            KA_TRACE(40, ("__kmp_process_deps<%d>: T#%d adding dependence from "
+                          "%p to %p\n",
+                          filter, gtid, KMP_TASK_TO_TASKDATA(indep->dn.task),
+                          KMP_TASK_TO_TASKDATA(task)));
+            npredecessors++;
+          }
+          KMP_RELEASE_DEPNODE(gtid, indep);
         }
+      }
 
-        if ( dep_barrier ) {
-            // if this is a sync point in the serial sequence, then the previous outputs are guaranteed to be completed after
-            // the execution of this task so the previous output nodes can be cleared.
-            __kmp_node_deref(thread,last_out);
-            info->last_out = NULL;
-        } else {
-            if ( dep->flags.out ) {
-                __kmp_node_deref(thread,last_out);
-                info->last_out = __kmp_node_ref(node);
-            } else
-                info->last_ins = __kmp_add_node(thread, info->last_ins, node);
-        }
+      __kmp_depnode_list_free(thread, info->last_ins);
+      info->last_ins = NULL;
 
+    } else if (last_out && last_out->dn.task) {
+      KMP_ACQUIRE_DEPNODE(gtid, last_out);
+      if (last_out->dn.task) {
+        __kmp_track_dependence(last_out, node, task);
+        last_out->dn.successors =
+            __kmp_add_node(thread, last_out->dn.successors, node);
+        KA_TRACE(
+            40,
+            ("__kmp_process_deps<%d>: T#%d adding dependence from %p to %p\n",
+             filter, gtid, KMP_TASK_TO_TASKDATA(last_out->dn.task),
+             KMP_TASK_TO_TASKDATA(task)));
+
+        npredecessors++;
+      }
+      KMP_RELEASE_DEPNODE(gtid, last_out);
     }
 
-    KA_TRACE(30, ("__kmp_process_deps<%d>: T#%d found %d predecessors\n", filter, gtid, npredecessors ) );
+    if (dep_barrier) {
+      // if this is a sync point in the serial sequence, then the previous
+      // outputs are guaranteed to be completed after
+      // the execution of this task so the previous output nodes can be cleared.
+      __kmp_node_deref(thread, last_out);
+      info->last_out = NULL;
+    } else {
+      if (dep->flags.out) {
+        __kmp_node_deref(thread, last_out);
+        info->last_out = __kmp_node_ref(node);
+      } else
+        info->last_ins = __kmp_add_node(thread, info->last_ins, node);
+    }
+  }
 
-    return npredecessors;
+  KA_TRACE(30, ("__kmp_process_deps<%d>: T#%d found %d predecessors\n", filter,
+                gtid, npredecessors));
+
+  return npredecessors;
 }
 
 #define NO_DEP_BARRIER (false)
 #define DEP_BARRIER (true)
 
 // returns true if the task has any outstanding dependence
-static bool
-__kmp_check_deps ( kmp_int32 gtid, kmp_depnode_t *node, kmp_task_t *task, kmp_dephash_t *hash, bool dep_barrier,
-                   kmp_int32 ndeps, kmp_depend_info_t *dep_list,
-                   kmp_int32 ndeps_noalias, kmp_depend_info_t *noalias_dep_list )
-{
-    int i;
+static bool __kmp_check_deps(kmp_int32 gtid, kmp_depnode_t *node,
+                             kmp_task_t *task, kmp_dephash_t *hash,
+                             bool dep_barrier, kmp_int32 ndeps,
+                             kmp_depend_info_t *dep_list,
+                             kmp_int32 ndeps_noalias,
+                             kmp_depend_info_t *noalias_dep_list) {
+  int i;
 
 #if KMP_DEBUG
-    kmp_taskdata_t * taskdata = KMP_TASK_TO_TASKDATA(task);
+  kmp_taskdata_t *taskdata = KMP_TASK_TO_TASKDATA(task);
 #endif
-    KA_TRACE(20, ("__kmp_check_deps: T#%d checking dependencies for task %p : %d possibly aliased dependencies, %d non-aliased depedencies : dep_barrier=%d .\n", gtid, taskdata, ndeps, ndeps_noalias, dep_barrier ) );
+  KA_TRACE(20, ("__kmp_check_deps: T#%d checking dependencies for task %p : %d "
+                "possibly aliased dependencies, %d non-aliased depedencies : "
+                "dep_barrier=%d .\n",
+                gtid, taskdata, ndeps, ndeps_noalias, dep_barrier));
 
-    // Filter deps in dep_list
-    // TODO: Different algorithm for large dep_list ( > 10 ? )
-    for ( i = 0; i < ndeps; i ++ ) {
-        if ( dep_list[i].base_addr != 0 )
-            for ( int j = i+1; j < ndeps; j++ )
-                if ( dep_list[i].base_addr == dep_list[j].base_addr ) {
-                    dep_list[i].flags.in |= dep_list[j].flags.in;
-                    dep_list[i].flags.out |= dep_list[j].flags.out;
-                    dep_list[j].base_addr = 0; // Mark j element as void
-                }
-    }
+  // Filter deps in dep_list
+  // TODO: Different algorithm for large dep_list ( > 10 ? )
+  for (i = 0; i < ndeps; i++) {
+    if (dep_list[i].base_addr != 0)
+      for (int j = i + 1; j < ndeps; j++)
+        if (dep_list[i].base_addr == dep_list[j].base_addr) {
+          dep_list[i].flags.in |= dep_list[j].flags.in;
+          dep_list[i].flags.out |= dep_list[j].flags.out;
+          dep_list[j].base_addr = 0; // Mark j element as void
+        }
+  }
 
-    // doesn't need to be atomic as no other thread is going to be accessing this node just yet
-    // npredecessors is set -1 to ensure that none of the releasing tasks queues this task before we have finished processing all the dependencies
-    node->dn.npredecessors = -1;
+  // doesn't need to be atomic as no other thread is going to be accessing this
+  // node just yet.
+  // npredecessors is set -1 to ensure that none of the releasing tasks queues
+  // this task before we have finished processing all the dependencies
+  node->dn.npredecessors = -1;
 
-    // used to pack all npredecessors additions into a single atomic operation at the end
-    int npredecessors;
+  // used to pack all npredecessors additions into a single atomic operation at
+  // the end
+  int npredecessors;
 
-    npredecessors = __kmp_process_deps<true>(gtid, node, hash, dep_barrier,
-      ndeps, dep_list, task);
-    npredecessors += __kmp_process_deps<false>(gtid, node, hash, dep_barrier,
-      ndeps_noalias, noalias_dep_list, task);
+  npredecessors = __kmp_process_deps<true>(gtid, node, hash, dep_barrier, ndeps,
+                                           dep_list, task);
+  npredecessors += __kmp_process_deps<false>(
+      gtid, node, hash, dep_barrier, ndeps_noalias, noalias_dep_list, task);
 
-    node->dn.task = task;
-    KMP_MB();
+  node->dn.task = task;
+  KMP_MB();
 
-    // Account for our initial fake value
-    npredecessors++;
+  // Account for our initial fake value
+  npredecessors++;
 
-    // Update predecessors and obtain current value to check if there are still any outstandig dependences (some tasks may have finished while we processed the dependences)
-    npredecessors = KMP_TEST_THEN_ADD32(&node->dn.npredecessors, npredecessors) + npredecessors;
+  // Update predecessors and obtain current value to check if there are still
+  // any outstandig dependences (some tasks may have finished while we processed
+  // the dependences)
+  npredecessors =
+      KMP_TEST_THEN_ADD32(CCAST(kmp_int32 *, &node->dn.npredecessors),
+                          npredecessors) +
+      npredecessors;
 
-    KA_TRACE(20, ("__kmp_check_deps: T#%d found %d predecessors for task %p \n", gtid, npredecessors, taskdata ) );
+  KA_TRACE(20, ("__kmp_check_deps: T#%d found %d predecessors for task %p \n",
+                gtid, npredecessors, taskdata));
 
-    // beyond this point the task could be queued (and executed) by a releasing task...
-    return npredecessors > 0 ? true : false;
+  // beyond this point the task could be queued (and executed) by a releasing
+  // task...
+  return npredecessors > 0 ? true : false;
 }
 
-void
-__kmp_release_deps ( kmp_int32 gtid, kmp_taskdata_t *task )
-{
-    kmp_info_t *thread = __kmp_threads[ gtid ];
-    kmp_depnode_t *node = task->td_depnode;
+void __kmp_release_deps(kmp_int32 gtid, kmp_taskdata_t *task) {
+  kmp_info_t *thread = __kmp_threads[gtid];
+  kmp_depnode_t *node = task->td_depnode;
 
-    if ( task->td_dephash ) {
-        KA_TRACE(40, ("__kmp_release_deps: T#%d freeing dependencies hash of task %p.\n", gtid, task ) );
-        __kmp_dephash_free(thread,task->td_dephash);
-        task->td_dephash = NULL;
+  if (task->td_dephash) {
+    KA_TRACE(
+        40, ("__kmp_release_deps: T#%d freeing dependencies hash of task %p.\n",
+             gtid, task));
+    __kmp_dephash_free(thread, task->td_dephash);
+    task->td_dephash = NULL;
+  }
+
+  if (!node)
+    return;
+
+  KA_TRACE(20, ("__kmp_release_deps: T#%d notifying successors of task %p.\n",
+                gtid, task));
+
+  KMP_ACQUIRE_DEPNODE(gtid, node);
+  node->dn.task =
+      NULL; // mark this task as finished, so no new dependencies are generated
+  KMP_RELEASE_DEPNODE(gtid, node);
+
+  kmp_depnode_list_t *next;
+  for (kmp_depnode_list_t *p = node->dn.successors; p; p = next) {
+    kmp_depnode_t *successor = p->node;
+    kmp_int32 npredecessors =
+        KMP_TEST_THEN_DEC32(CCAST(kmp_int32 *, &successor->dn.npredecessors)) -
+        1;
+    // successor task can be NULL for wait_depends or because deps are still
+    // being processed
+    if (npredecessors == 0) {
+      KMP_MB();
+      if (successor->dn.task) {
+        KA_TRACE(20, ("__kmp_release_deps: T#%d successor %p of %p scheduled "
+                      "for execution.\n",
+                      gtid, successor->dn.task, task));
+        __kmp_omp_task(gtid, successor->dn.task, false);
+      }
     }
 
-    if ( !node ) return;
-
-    KA_TRACE(20, ("__kmp_release_deps: T#%d notifying successors of task %p.\n", gtid, task ) );
-
-    KMP_ACQUIRE_DEPNODE(gtid,node);
-    node->dn.task = NULL; // mark this task as finished, so no new dependencies are generated
-    KMP_RELEASE_DEPNODE(gtid,node);
-
-    kmp_depnode_list_t *next;
-    for ( kmp_depnode_list_t *p = node->dn.successors; p; p = next ) {
-        kmp_depnode_t *successor = p->node;
-        kmp_int32 npredecessors = KMP_TEST_THEN_DEC32(&successor->dn.npredecessors) - 1;
-
-        // successor task can be NULL for wait_depends or because deps are still being processed
-        if ( npredecessors == 0 ) {
-            KMP_MB();
-            if ( successor->dn.task ) {
-                KA_TRACE(20, ("__kmp_release_deps: T#%d successor %p of %p scheduled for execution.\n", gtid, successor->dn.task, task ) );
-                __kmp_omp_task(gtid,successor->dn.task,false);
-            }
-        }
-
-        next = p->next;
-        __kmp_node_deref(thread,p->node);
+    next = p->next;
+    __kmp_node_deref(thread, p->node);
 #if USE_FAST_MEMORY
-        __kmp_fast_free(thread,p);
+    __kmp_fast_free(thread, p);
 #else
-        __kmp_thread_free(thread,p);
+    __kmp_thread_free(thread, p);
 #endif
-    }
+  }
 
-    __kmp_node_deref(thread,node);
+  __kmp_node_deref(thread, node);
 
-    KA_TRACE(20, ("__kmp_release_deps: T#%d all successors of %p notified of completion\n", gtid, task ) );
+  KA_TRACE(
+      20,
+      ("__kmp_release_deps: T#%d all successors of %p notified of completion\n",
+       gtid, task));
 }
 
 /*!
 @ingroup TASKING
 @param loc_ref location of the original task directive
 @param gtid Global Thread ID of encountering thread
-@param new_task task thunk allocated by __kmp_omp_task_alloc() for the ''new task''
+@param new_task task thunk allocated by __kmp_omp_task_alloc() for the ''new
+task''
 @param ndeps Number of depend items with possible aliasing
 @param dep_list List of depend items with possible aliasing
 @param ndeps_noalias Number of depend items with no aliasing
 @param noalias_dep_list List of depend items with no aliasing
 
-@return Returns either TASK_CURRENT_NOT_QUEUED if the current task was not suspendend and queued, or TASK_CURRENT_QUEUED if it was suspended and queued
+@return Returns either TASK_CURRENT_NOT_QUEUED if the current task was not
+suspendend and queued, or TASK_CURRENT_QUEUED if it was suspended and queued
 
 Schedule a non-thread-switchable task with dependences for execution
 */
-kmp_int32
-__kmpc_omp_task_with_deps( ident_t *loc_ref, kmp_int32 gtid, kmp_task_t * new_task,
-                            kmp_int32 ndeps, kmp_depend_info_t *dep_list,
-                            kmp_int32 ndeps_noalias, kmp_depend_info_t *noalias_dep_list )
-{
+kmp_int32 __kmpc_omp_task_with_deps(ident_t *loc_ref, kmp_int32 gtid,
+                                    kmp_task_t *new_task, kmp_int32 ndeps,
+                                    kmp_depend_info_t *dep_list,
+                                    kmp_int32 ndeps_noalias,
+                                    kmp_depend_info_t *noalias_dep_list) {
 
-    kmp_taskdata_t * new_taskdata = KMP_TASK_TO_TASKDATA(new_task);
-    KA_TRACE(10, ("__kmpc_omp_task_with_deps(enter): T#%d loc=%p task=%p\n",
-                  gtid, loc_ref, new_taskdata ) );
+  kmp_taskdata_t *new_taskdata = KMP_TASK_TO_TASKDATA(new_task);
+  KA_TRACE(10, ("__kmpc_omp_task_with_deps(enter): T#%d loc=%p task=%p\n", gtid,
+                loc_ref, new_taskdata));
 
-    kmp_info_t *thread = __kmp_threads[ gtid ];
-    kmp_taskdata_t * current_task = thread->th.th_current_task;
+  kmp_info_t *thread = __kmp_threads[gtid];
+  kmp_taskdata_t *current_task = thread->th.th_current_task;
 
 #if OMPT_SUPPORT && OMPT_TRACE
-    /* OMPT grab all dependences if requested by the tool */
-    if (ompt_enabled && ndeps+ndeps_noalias > 0 &&
-        ompt_callbacks.ompt_callback(ompt_event_task_dependences))
-	{
-        kmp_int32 i;
+  /* OMPT grab all dependences if requested by the tool */
+  if (ompt_enabled && ndeps + ndeps_noalias > 0 &&
+      ompt_callbacks.ompt_callback(ompt_event_task_dependences)) {
+    kmp_int32 i;
 
-        new_taskdata->ompt_task_info.ndeps = ndeps+ndeps_noalias;
-        new_taskdata->ompt_task_info.deps = (ompt_task_dependence_t *)
-          KMP_OMPT_DEPS_ALLOC(thread,
-             (ndeps+ndeps_noalias)*sizeof(ompt_task_dependence_t));
+    new_taskdata->ompt_task_info.ndeps = ndeps + ndeps_noalias;
+    new_taskdata->ompt_task_info.deps =
+        (ompt_task_dependence_t *)KMP_OMPT_DEPS_ALLOC(
+            thread, (ndeps + ndeps_noalias) * sizeof(ompt_task_dependence_t));
 
-        KMP_ASSERT(new_taskdata->ompt_task_info.deps != NULL);
+    KMP_ASSERT(new_taskdata->ompt_task_info.deps != NULL);
 
-        for (i = 0; i < ndeps; i++)
-        {
-            new_taskdata->ompt_task_info.deps[i].variable_addr =
-              (void*) dep_list[i].base_addr;
-            if (dep_list[i].flags.in && dep_list[i].flags.out)
-                new_taskdata->ompt_task_info.deps[i].dependence_flags =
-                  ompt_task_dependence_type_inout;
-            else if (dep_list[i].flags.out)
-                new_taskdata->ompt_task_info.deps[i].dependence_flags =
-                  ompt_task_dependence_type_out;
-            else if (dep_list[i].flags.in)
-                new_taskdata->ompt_task_info.deps[i].dependence_flags =
-                  ompt_task_dependence_type_in;
-        }
-        for (i = 0; i < ndeps_noalias; i++)
-        {
-            new_taskdata->ompt_task_info.deps[ndeps+i].variable_addr =
-              (void*) noalias_dep_list[i].base_addr;
-            if (noalias_dep_list[i].flags.in && noalias_dep_list[i].flags.out)
-                new_taskdata->ompt_task_info.deps[ndeps+i].dependence_flags =
-                  ompt_task_dependence_type_inout;
-            else if (noalias_dep_list[i].flags.out)
-                new_taskdata->ompt_task_info.deps[ndeps+i].dependence_flags =
-                  ompt_task_dependence_type_out;
-            else if (noalias_dep_list[i].flags.in)
-                new_taskdata->ompt_task_info.deps[ndeps+i].dependence_flags =
-                  ompt_task_dependence_type_in;
-        }
+    for (i = 0; i < ndeps; i++) {
+      new_taskdata->ompt_task_info.deps[i].variable_addr =
+          (void *)dep_list[i].base_addr;
+      if (dep_list[i].flags.in && dep_list[i].flags.out)
+        new_taskdata->ompt_task_info.deps[i].dependence_flags =
+            ompt_task_dependence_type_inout;
+      else if (dep_list[i].flags.out)
+        new_taskdata->ompt_task_info.deps[i].dependence_flags =
+            ompt_task_dependence_type_out;
+      else if (dep_list[i].flags.in)
+        new_taskdata->ompt_task_info.deps[i].dependence_flags =
+            ompt_task_dependence_type_in;
     }
+    for (i = 0; i < ndeps_noalias; i++) {
+      new_taskdata->ompt_task_info.deps[ndeps + i].variable_addr =
+          (void *)noalias_dep_list[i].base_addr;
+      if (noalias_dep_list[i].flags.in && noalias_dep_list[i].flags.out)
+        new_taskdata->ompt_task_info.deps[ndeps + i].dependence_flags =
+            ompt_task_dependence_type_inout;
+      else if (noalias_dep_list[i].flags.out)
+        new_taskdata->ompt_task_info.deps[ndeps + i].dependence_flags =
+            ompt_task_dependence_type_out;
+      else if (noalias_dep_list[i].flags.in)
+        new_taskdata->ompt_task_info.deps[ndeps + i].dependence_flags =
+            ompt_task_dependence_type_in;
+    }
+  }
 #endif /* OMPT_SUPPORT && OMPT_TRACE */
 
-    bool serial = current_task->td_flags.team_serial || current_task->td_flags.tasking_ser || current_task->td_flags.final;
+  bool serial = current_task->td_flags.team_serial ||
+                current_task->td_flags.tasking_ser ||
+                current_task->td_flags.final;
 #if OMP_45_ENABLED
-    kmp_task_team_t * task_team = thread->th.th_task_team;
-    serial = serial && !(task_team && task_team->tt.tt_found_proxy_tasks);
+  kmp_task_team_t *task_team = thread->th.th_task_team;
+  serial = serial && !(task_team && task_team->tt.tt_found_proxy_tasks);
 #endif
 
-    if ( !serial && ( ndeps > 0 || ndeps_noalias > 0 )) {
-        /* if no dependencies have been tracked yet, create the dependence hash */
-        if ( current_task->td_dephash == NULL )
-            current_task->td_dephash = __kmp_dephash_create(thread, current_task);
+  if (!serial && (ndeps > 0 || ndeps_noalias > 0)) {
+    /* if no dependencies have been tracked yet, create the dependence hash */
+    if (current_task->td_dephash == NULL)
+      current_task->td_dephash = __kmp_dephash_create(thread, current_task);
 
 #if USE_FAST_MEMORY
-        kmp_depnode_t *node = (kmp_depnode_t *) __kmp_fast_allocate(thread,sizeof(kmp_depnode_t));
+    kmp_depnode_t *node =
+        (kmp_depnode_t *)__kmp_fast_allocate(thread, sizeof(kmp_depnode_t));
 #else
-        kmp_depnode_t *node = (kmp_depnode_t *) __kmp_thread_malloc(thread,sizeof(kmp_depnode_t));
+    kmp_depnode_t *node =
+        (kmp_depnode_t *)__kmp_thread_malloc(thread, sizeof(kmp_depnode_t));
 #endif
 
-        __kmp_init_node(node);
-        new_taskdata->td_depnode = node;
+    __kmp_init_node(node);
+    new_taskdata->td_depnode = node;
 
-        if ( __kmp_check_deps( gtid, node, new_task, current_task->td_dephash, NO_DEP_BARRIER,
-                               ndeps, dep_list, ndeps_noalias,noalias_dep_list ) ) {
-            KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d task had blocking dependencies: "
-                  "loc=%p task=%p, return: TASK_CURRENT_NOT_QUEUED\n", gtid, loc_ref,
-                  new_taskdata ) );
-            return TASK_CURRENT_NOT_QUEUED;
-        }
-    } else {
-        KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d ignored dependencies for task (serialized)"
-                      "loc=%p task=%p\n", gtid, loc_ref, new_taskdata ) );
+    if (__kmp_check_deps(gtid, node, new_task, current_task->td_dephash,
+                         NO_DEP_BARRIER, ndeps, dep_list, ndeps_noalias,
+                         noalias_dep_list)) {
+      KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d task had blocking "
+                    "dependencies: "
+                    "loc=%p task=%p, return: TASK_CURRENT_NOT_QUEUED\n",
+                    gtid, loc_ref, new_taskdata));
+      return TASK_CURRENT_NOT_QUEUED;
     }
+  } else {
+    KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d ignored dependencies "
+                  "for task (serialized)"
+                  "loc=%p task=%p\n",
+                  gtid, loc_ref, new_taskdata));
+  }
 
-    KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d task had no blocking dependencies : "
-                  "loc=%p task=%p, transferring to __kmpc_omp_task\n", gtid, loc_ref,
-                  new_taskdata ) );
+  KA_TRACE(10, ("__kmpc_omp_task_with_deps(exit): T#%d task had no blocking "
+                "dependencies : "
+                "loc=%p task=%p, transferring to __kmpc_omp_task\n",
+                gtid, loc_ref, new_taskdata));
 
-    return __kmpc_omp_task(loc_ref,gtid,new_task);
+  return __kmpc_omp_task(loc_ref, gtid, new_task);
 }
 
 /*!
@@ -539,55 +573,64 @@ __kmpc_omp_task_with_deps( ident_t *loc_ref, kmp_int32 gtid, kmp_task_t * new_ta
 
 Blocks the current task until all specifies dependencies have been fulfilled.
 */
-void
-__kmpc_omp_wait_deps ( ident_t *loc_ref, kmp_int32 gtid, kmp_int32 ndeps, kmp_depend_info_t *dep_list,
-                       kmp_int32 ndeps_noalias, kmp_depend_info_t *noalias_dep_list )
-{
-    KA_TRACE(10, ("__kmpc_omp_wait_deps(enter): T#%d loc=%p\n", gtid, loc_ref) );
+void __kmpc_omp_wait_deps(ident_t *loc_ref, kmp_int32 gtid, kmp_int32 ndeps,
+                          kmp_depend_info_t *dep_list, kmp_int32 ndeps_noalias,
+                          kmp_depend_info_t *noalias_dep_list) {
+  KA_TRACE(10, ("__kmpc_omp_wait_deps(enter): T#%d loc=%p\n", gtid, loc_ref));
 
-    if ( ndeps == 0 && ndeps_noalias == 0 ) {
-        KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no dependencies to wait upon : loc=%p\n", gtid, loc_ref) );
-        return;
-    }
+  if (ndeps == 0 && ndeps_noalias == 0) {
+    KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no dependencies to "
+                  "wait upon : loc=%p\n",
+                  gtid, loc_ref));
+    return;
+  }
 
-    kmp_info_t *thread = __kmp_threads[ gtid ];
-    kmp_taskdata_t * current_task = thread->th.th_current_task;
+  kmp_info_t *thread = __kmp_threads[gtid];
+  kmp_taskdata_t *current_task = thread->th.th_current_task;
 
-    // We can return immediately as:
-    //   - dependences are not computed in serial teams (except if we have proxy tasks)
-    //   - if the dephash is not yet created it means we have nothing to wait for
-    bool ignore = current_task->td_flags.team_serial || current_task->td_flags.tasking_ser || current_task->td_flags.final;
+  // We can return immediately as:
+  // - dependences are not computed in serial teams (except with proxy tasks)
+  // - if the dephash is not yet created it means we have nothing to wait for
+  bool ignore = current_task->td_flags.team_serial ||
+                current_task->td_flags.tasking_ser ||
+                current_task->td_flags.final;
 #if OMP_45_ENABLED
-    ignore = ignore && thread->th.th_task_team != NULL && thread->th.th_task_team->tt.tt_found_proxy_tasks == FALSE;
+  ignore = ignore && thread->th.th_task_team != NULL &&
+           thread->th.th_task_team->tt.tt_found_proxy_tasks == FALSE;
 #endif
-    ignore = ignore || current_task->td_dephash == NULL;
+  ignore = ignore || current_task->td_dephash == NULL;
 
-    if ( ignore ) {
-        KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no blocking dependencies : loc=%p\n", gtid, loc_ref) );
-        return;
-    }
+  if (ignore) {
+    KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no blocking "
+                  "dependencies : loc=%p\n",
+                  gtid, loc_ref));
+    return;
+  }
 
-    kmp_depnode_t node;
-    __kmp_init_node(&node);
+  kmp_depnode_t node;
+  __kmp_init_node(&node);
 
-    if (!__kmp_check_deps( gtid, &node, NULL, current_task->td_dephash, DEP_BARRIER,
-                           ndeps, dep_list, ndeps_noalias, noalias_dep_list )) {
-        KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no blocking dependencies : loc=%p\n", gtid, loc_ref) );
-        return;
-    }
+  if (!__kmp_check_deps(gtid, &node, NULL, current_task->td_dephash,
+                        DEP_BARRIER, ndeps, dep_list, ndeps_noalias,
+                        noalias_dep_list)) {
+    KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d has no blocking "
+                  "dependencies : loc=%p\n",
+                  gtid, loc_ref));
+    return;
+  }
 
-    int thread_finished = FALSE;
-    kmp_flag_32 flag((volatile kmp_uint32 *)&(node.dn.npredecessors), 0U);
-    while ( node.dn.npredecessors > 0 ) {
-        flag.execute_tasks(thread, gtid, FALSE, &thread_finished,
+  int thread_finished = FALSE;
+  kmp_flag_32 flag((volatile kmp_uint32 *)&(node.dn.npredecessors), 0U);
+  while (node.dn.npredecessors > 0) {
+    flag.execute_tasks(thread, gtid, FALSE, &thread_finished,
 #if USE_ITT_BUILD
-                           NULL,
+                       NULL,
 #endif
-                           __kmp_task_stealing_constraint );
-    }
+                       __kmp_task_stealing_constraint);
+  }
 
-    KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d finished waiting : loc=%p\n", gtid, loc_ref) );
+  KA_TRACE(10, ("__kmpc_omp_wait_deps(exit): T#%d finished waiting : loc=%p\n",
+                gtid, loc_ref));
 }
 
 #endif /* OMP_40_ENABLED */
-

runtime/src/kmp_utility.cpp

@@ -14,416 +14,396 @@
 
 
 #include "kmp.h"
-#include "kmp_wrapper_getpid.h"
-#include "kmp_str.h"
-#include <float.h>
 #include "kmp_i18n.h"
-
-/* ------------------------------------------------------------------------ */
-/* ------------------------------------------------------------------------ */
+#include "kmp_str.h"
+#include "kmp_wrapper_getpid.h"
+#include <float.h>
 
 static const char *unknown = "unknown";
 
 #if KMP_ARCH_X86 || KMP_ARCH_X86_64
 
-/* NOTE: If called before serial_initialize (i.e. from runtime_initialize), then */
-/* the debugging package has not been initialized yet, and only "0" will print   */
-/* debugging output since the environment variables have not been read.          */
+/* NOTE: If called before serial_initialize (i.e. from runtime_initialize), then
+   the debugging package has not been initialized yet, and only "0" will print
+   debugging output since the environment variables have not been read. */
 
 #ifdef KMP_DEBUG
 static int trace_level = 5;
 #endif
 
-/*
- * LOG_ID_BITS  = ( 1 + floor( log_2( max( log_per_phy - 1, 1 ))))
+/* LOG_ID_BITS  = ( 1 + floor( log_2( max( log_per_phy - 1, 1 ))))
  * APIC_ID      = (PHY_ID << LOG_ID_BITS) | LOG_ID
  * PHY_ID       = APIC_ID >> LOG_ID_BITS
  */
-int
-__kmp_get_physical_id( int log_per_phy, int apic_id )
-{
-   int index_lsb, index_msb, temp;
+int __kmp_get_physical_id(int log_per_phy, int apic_id) {
+  int index_lsb, index_msb, temp;
 
-   if (log_per_phy > 1) {
-	index_lsb = 0;
-	index_msb = 31;
+  if (log_per_phy > 1) {
+    index_lsb = 0;
+    index_msb = 31;
 
-	temp = log_per_phy;
-        while ( (temp & 1) == 0 ) {
-	    temp  >>= 1;
-	    index_lsb++;
-	}
+    temp = log_per_phy;
+    while ((temp & 1) == 0) {
+      temp >>= 1;
+      index_lsb++;
+    }
 
-	temp = log_per_phy;
-	while ( (temp & 0x80000000)==0 ) {
-	    temp <<= 1;
-	    index_msb--;
-	}
+    temp = log_per_phy;
+    while ((temp & 0x80000000) == 0) {
+      temp <<= 1;
+      index_msb--;
+    }
 
-	/* If >1 bits were set in log_per_phy, choose next higher power of 2 */
-	if (index_lsb != index_msb) index_msb++;
+    /* If >1 bits were set in log_per_phy, choose next higher power of 2 */
+    if (index_lsb != index_msb)
+      index_msb++;
 
-	return ( (int) (apic_id >> index_msb) );
-   }
+    return ((int)(apic_id >> index_msb));
+  }
 
-   return apic_id;
+  return apic_id;
 }
 
-
 /*
  * LOG_ID_BITS  = ( 1 + floor( log_2( max( log_per_phy - 1, 1 ))))
  * APIC_ID      = (PHY_ID << LOG_ID_BITS) | LOG_ID
  * LOG_ID       = APIC_ID & (( 1 << LOG_ID_BITS ) - 1 )
  */
-int
-__kmp_get_logical_id( int log_per_phy, int apic_id )
-{
-   unsigned current_bit;
-   int bits_seen;
+int __kmp_get_logical_id(int log_per_phy, int apic_id) {
+  unsigned current_bit;
+  int bits_seen;
 
-   if (log_per_phy <= 1) return ( 0 );
+  if (log_per_phy <= 1)
+    return (0);
 
-   bits_seen = 0;
+  bits_seen = 0;
 
-   for (current_bit = 1; log_per_phy != 0; current_bit <<= 1) {
-	if ( log_per_phy & current_bit ) {
-	    log_per_phy &= ~current_bit;
-	    bits_seen++;
-	}
-   }
+  for (current_bit = 1; log_per_phy != 0; current_bit <<= 1) {
+    if (log_per_phy & current_bit) {
+      log_per_phy &= ~current_bit;
+      bits_seen++;
+    }
+  }
 
-   /* If exactly 1 bit was set in log_per_phy, choose next lower power of 2 */
-   if (bits_seen == 1) {
-	current_bit >>= 1;
-   }
+  /* If exactly 1 bit was set in log_per_phy, choose next lower power of 2 */
+  if (bits_seen == 1) {
+    current_bit >>= 1;
+  }
 
-   return ( (int) ((current_bit - 1) & apic_id) );
+  return ((int)((current_bit - 1) & apic_id));
 }
 
+static kmp_uint64 __kmp_parse_frequency( // R: Frequency in Hz.
+    char const *frequency // I: Float number and unit: MHz, GHz, or TGz.
+    ) {
 
-static
-kmp_uint64
-__kmp_parse_frequency(        // R: Frequency in Hz.
-    char const * frequency    // I: Float number and unit: MHz, GHz, or TGz.
-) {
+  double value = 0.0;
+  char const *unit = NULL;
+  kmp_uint64 result = 0; /* Zero is a better unknown value than all ones. */
 
-    double       value  = 0.0;
-    char const * unit   = NULL;
-    kmp_uint64   result = 0;                    /* Zero is a better unknown value than all ones. */
-
-    if ( frequency == NULL ) {
-        return result;
-    }; // if
-    value = strtod( frequency, (char * *) & unit ); // strtod() does not like "char const *".
-    if ( 0 < value && value <= DBL_MAX ) {          // Good value (not overflow, underflow, etc).
-        if ( strcmp( unit, "MHz" ) == 0 ) {
-            value = value * 1.0E+6;
-        } else if ( strcmp( unit, "GHz" ) == 0 ) {
-            value = value * 1.0E+9;
-        } else if ( strcmp( unit, "THz" ) == 0 ) {
-            value = value * 1.0E+12;
-        } else {                      // Wrong unit.
-            return result;
-        }; // if
-        result = value;
-    }; // if
+  if (frequency == NULL) {
     return result;
+  }; // if
+  value = strtod(frequency,
+                 CCAST(char **, &unit)); // strtod() does not like "const"
+  if (0 < value &&
+      value <= DBL_MAX) { // Good value (not overflow, underflow, etc).
+    if (strcmp(unit, "MHz") == 0) {
+      value = value * 1.0E+6;
+    } else if (strcmp(unit, "GHz") == 0) {
+      value = value * 1.0E+9;
+    } else if (strcmp(unit, "THz") == 0) {
+      value = value * 1.0E+12;
+    } else { // Wrong unit.
+      return result;
+    }; // if
+    result = value;
+  }; // if
+  return result;
 
 }; // func __kmp_parse_cpu_frequency
 
-void
-__kmp_query_cpuid( kmp_cpuinfo_t *p )
-{
-    struct kmp_cpuid buf;
-    int max_arg;
-    int log_per_phy;
+void __kmp_query_cpuid(kmp_cpuinfo_t *p) {
+  struct kmp_cpuid buf;
+  int max_arg;
+  int log_per_phy;
 #ifdef KMP_DEBUG
-    int cflush_size;
+  int cflush_size;
 #endif
 
-    p->initialized = 1;
+  p->initialized = 1;
 
-    p->sse2 = 1; // Assume SSE2 by default.
+  p->sse2 = 1; // Assume SSE2 by default.
 
-    __kmp_x86_cpuid( 0, 0, &buf );
+  __kmp_x86_cpuid(0, 0, &buf);
 
-    KA_TRACE( trace_level, ("INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n",
-        0, buf.eax, buf.ebx, buf.ecx, buf.edx ) );
+  KA_TRACE(trace_level,
+           ("INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n", 0,
+            buf.eax, buf.ebx, buf.ecx, buf.edx));
 
-    max_arg = buf.eax;
+  max_arg = buf.eax;
 
-    p->apic_id = -1;
+  p->apic_id = -1;
 
-    if (max_arg >= 1) {
-        int i;
-        kmp_uint32 t, data[ 4 ];
+  if (max_arg >= 1) {
+    int i;
+    kmp_uint32 t, data[4];
 
-        __kmp_x86_cpuid( 1, 0, &buf );
-        KA_TRACE( trace_level, ("INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n",
-                                1, buf.eax, buf.ebx, buf.ecx, buf.edx ) );
+    __kmp_x86_cpuid(1, 0, &buf);
+    KA_TRACE(trace_level,
+             ("INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n",
+              1, buf.eax, buf.ebx, buf.ecx, buf.edx));
 
-        {
-#define get_value(reg,lo,mask) ( ( ( reg ) >> ( lo ) ) & ( mask  ) )
+    {
+#define get_value(reg, lo, mask) (((reg) >> (lo)) & (mask))
 
-            p->signature = buf.eax;
-            p->family    =   get_value( buf.eax, 20, 0xff )        + get_value( buf.eax, 8, 0x0f );
-            p->model     = ( get_value( buf.eax, 16, 0x0f ) << 4 ) + get_value( buf.eax, 4, 0x0f );
-            p->stepping  =   get_value( buf.eax,  0, 0x0f );
+      p->signature = buf.eax;
+      p->family = get_value(buf.eax, 20, 0xff) + get_value(buf.eax, 8, 0x0f);
+      p->model =
+          (get_value(buf.eax, 16, 0x0f) << 4) + get_value(buf.eax, 4, 0x0f);
+      p->stepping = get_value(buf.eax, 0, 0x0f);
 
 #undef get_value
 
-            KA_TRACE( trace_level, (" family = %d, model = %d, stepping = %d\n", p->family, p->model, p->stepping ) );
-        }
+      KA_TRACE(trace_level, (" family = %d, model = %d, stepping = %d\n",
+                             p->family, p->model, p->stepping));
+    }
 
-        for ( t = buf.ebx, i = 0; i < 4; t >>= 8, ++i ) {
-            data[ i ] = (t & 0xff);
-        }; // for
+    for (t = buf.ebx, i = 0; i < 4; t >>= 8, ++i) {
+      data[i] = (t & 0xff);
+    }; // for
 
-        p->sse2 = ( buf.edx >> 26 ) & 1;
+    p->sse2 = (buf.edx >> 26) & 1;
 
 #ifdef KMP_DEBUG
 
-        if ( (buf.edx >> 4) & 1 ) {
-            /* TSC - Timestamp Counter Available */
-            KA_TRACE( trace_level, (" TSC" ) );
-        }
-        if ( (buf.edx >> 8) & 1 ) {
-            /* CX8 - CMPXCHG8B Instruction Available */
-            KA_TRACE( trace_level, (" CX8" ) );
-        }
-        if ( (buf.edx >> 9) & 1 ) {
-            /* APIC - Local APIC Present (multi-processor operation support */
-            KA_TRACE( trace_level, (" APIC" ) );
-        }
-        if ( (buf.edx >> 15) & 1 ) {
-            /* CMOV - Conditional MOVe Instruction Available */
-            KA_TRACE( trace_level, (" CMOV" ) );
-        }
-        if ( (buf.edx >> 18) & 1 ) {
-            /* PSN - Processor Serial Number Available */
-            KA_TRACE( trace_level, (" PSN" ) );
-        }
-        if ( (buf.edx >> 19) & 1 ) {
-            /* CLFULSH - Cache Flush Instruction Available */
-            cflush_size = data[ 1 ] * 8;    /* Bits 15-08: CLFLUSH line size = 8 (64 bytes) */
-            KA_TRACE( trace_level, (" CLFLUSH(%db)", cflush_size ) );
-
-        }
-        if ( (buf.edx >> 21) & 1 ) {
-            /* DTES - Debug Trace & EMON Store */
-            KA_TRACE( trace_level, (" DTES" ) );
-        }
-        if ( (buf.edx >> 22) & 1 ) {
-            /* ACPI - ACPI Support Available */
-            KA_TRACE( trace_level, (" ACPI" ) );
-        }
-        if ( (buf.edx >> 23) & 1 ) {
-            /* MMX - Multimedia Extensions */
-            KA_TRACE( trace_level, (" MMX" ) );
-        }
-        if ( (buf.edx >> 25) & 1 ) {
-            /* SSE - SSE Instructions */
-            KA_TRACE( trace_level, (" SSE" ) );
-        }
-        if ( (buf.edx >> 26) & 1 ) {
-            /* SSE2 - SSE2 Instructions */
-            KA_TRACE( trace_level, (" SSE2" ) );
-        }
-        if ( (buf.edx >> 27) & 1 ) {
-            /* SLFSNP - Self-Snooping Cache */
-            KA_TRACE( trace_level, (" SLFSNP" ) );
-        }
+    if ((buf.edx >> 4) & 1) {
+      /* TSC - Timestamp Counter Available */
+      KA_TRACE(trace_level, (" TSC"));
+    }
+    if ((buf.edx >> 8) & 1) {
+      /* CX8 - CMPXCHG8B Instruction Available */
+      KA_TRACE(trace_level, (" CX8"));
+    }
+    if ((buf.edx >> 9) & 1) {
+      /* APIC - Local APIC Present (multi-processor operation support */
+      KA_TRACE(trace_level, (" APIC"));
+    }
+    if ((buf.edx >> 15) & 1) {
+      /* CMOV - Conditional MOVe Instruction Available */
+      KA_TRACE(trace_level, (" CMOV"));
+    }
+    if ((buf.edx >> 18) & 1) {
+      /* PSN - Processor Serial Number Available */
+      KA_TRACE(trace_level, (" PSN"));
+    }
+    if ((buf.edx >> 19) & 1) {
+      /* CLFULSH - Cache Flush Instruction Available */
+      cflush_size =
+          data[1] * 8; /* Bits 15-08: CLFLUSH line size = 8 (64 bytes) */
+      KA_TRACE(trace_level, (" CLFLUSH(%db)", cflush_size));
+    }
+    if ((buf.edx >> 21) & 1) {
+      /* DTES - Debug Trace & EMON Store */
+      KA_TRACE(trace_level, (" DTES"));
+    }
+    if ((buf.edx >> 22) & 1) {
+      /* ACPI - ACPI Support Available */
+      KA_TRACE(trace_level, (" ACPI"));
+    }
+    if ((buf.edx >> 23) & 1) {
+      /* MMX - Multimedia Extensions */
+      KA_TRACE(trace_level, (" MMX"));
+    }
+    if ((buf.edx >> 25) & 1) {
+      /* SSE - SSE Instructions */
+      KA_TRACE(trace_level, (" SSE"));
+    }
+    if ((buf.edx >> 26) & 1) {
+      /* SSE2 - SSE2 Instructions */
+      KA_TRACE(trace_level, (" SSE2"));
+    }
+    if ((buf.edx >> 27) & 1) {
+      /* SLFSNP - Self-Snooping Cache */
+      KA_TRACE(trace_level, (" SLFSNP"));
+    }
 #endif /* KMP_DEBUG */
 
-        if ( (buf.edx >> 28) & 1 ) {
-            /* Bits 23-16: Logical Processors per Physical Processor (1 for P4) */
-            log_per_phy = data[ 2 ];
-            p->apic_id     = data[ 3 ]; /* Bits 31-24: Processor Initial APIC ID (X) */
-            KA_TRACE( trace_level, (" HT(%d TPUs)", log_per_phy ) );
+    if ((buf.edx >> 28) & 1) {
+      /* Bits 23-16: Logical Processors per Physical Processor (1 for P4) */
+      log_per_phy = data[2];
+      p->apic_id = data[3]; /* Bits 31-24: Processor Initial APIC ID (X) */
+      KA_TRACE(trace_level, (" HT(%d TPUs)", log_per_phy));
 
-            if( log_per_phy > 1 ) {
-                /* default to 1k FOR JT-enabled processors (4k on OS X*) */
+      if (log_per_phy > 1) {
+/* default to 1k FOR JT-enabled processors (4k on OS X*) */
 #if KMP_OS_DARWIN
-                p->cpu_stackoffset = 4 * 1024;
+        p->cpu_stackoffset = 4 * 1024;
 #else
-                p->cpu_stackoffset = 1 * 1024;
+        p->cpu_stackoffset = 1 * 1024;
 #endif
-            }
+      }
 
-            p->physical_id = __kmp_get_physical_id( log_per_phy, p->apic_id );
-            p->logical_id  = __kmp_get_logical_id( log_per_phy, p->apic_id );
-        }
+      p->physical_id = __kmp_get_physical_id(log_per_phy, p->apic_id);
+      p->logical_id = __kmp_get_logical_id(log_per_phy, p->apic_id);
+    }
 #ifdef KMP_DEBUG
-        if ( (buf.edx >> 29) & 1 ) {
-            /* ATHROTL - Automatic Throttle Control */
-            KA_TRACE( trace_level, (" ATHROTL" ) );
-        }
-        KA_TRACE( trace_level, (" ]\n" ) );
+    if ((buf.edx >> 29) & 1) {
+      /* ATHROTL - Automatic Throttle Control */
+      KA_TRACE(trace_level, (" ATHROTL"));
+    }
+    KA_TRACE(trace_level, (" ]\n"));
 
-        for (i = 2; i <= max_arg; ++i) {
-            __kmp_x86_cpuid( i, 0, &buf );
-            KA_TRACE( trace_level,
-                      ( "INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n",
-                        i, buf.eax, buf.ebx, buf.ecx, buf.edx ) );
-        }
+    for (i = 2; i <= max_arg; ++i) {
+      __kmp_x86_cpuid(i, 0, &buf);
+      KA_TRACE(trace_level,
+               ("INFO: CPUID %d: EAX=0x%08X EBX=0x%08X ECX=0x%08X EDX=0x%08X\n",
+                i, buf.eax, buf.ebx, buf.ecx, buf.edx));
+    }
 #endif
 #if KMP_USE_ADAPTIVE_LOCKS
-        p->rtm = 0;
-        if (max_arg > 7)
-        {
-            /* RTM bit CPUID.07:EBX, bit 11 */
-            __kmp_x86_cpuid(7, 0, &buf);
-            p->rtm = (buf.ebx >> 11) & 1;
-            KA_TRACE( trace_level, (" RTM" ) );
-        }
-#endif
-    }; // if
-
-    { // Parse CPU brand string for frequency, saving the string for later.
-        int i;
-        kmp_cpuid_t * base = (kmp_cpuid_t *)&p->name[0];
-
-        // Get CPU brand string.
-        for ( i = 0; i < 3; ++ i ) {
-            __kmp_x86_cpuid( 0x80000002 + i, 0, base+i );
-        }; // for
-        p->name[ sizeof(p->name) - 1 ] = 0; // Just in case. ;-)
-        KA_TRACE( trace_level, ( "cpu brand string: \"%s\"\n", &p->name[0] ) );
-
-        // Parse frequency.
-        p->frequency = __kmp_parse_frequency( strrchr( &p->name[0], ' ' ) );
-        KA_TRACE( trace_level, ( "cpu frequency from brand string: %" KMP_UINT64_SPEC "\n", p->frequency ) );
+    p->rtm = 0;
+    if (max_arg > 7) {
+      /* RTM bit CPUID.07:EBX, bit 11 */
+      __kmp_x86_cpuid(7, 0, &buf);
+      p->rtm = (buf.ebx >> 11) & 1;
+      KA_TRACE(trace_level, (" RTM"));
     }
+#endif
+  }; // if
+
+  { // Parse CPU brand string for frequency, saving the string for later.
+    int i;
+    kmp_cpuid_t *base = (kmp_cpuid_t *)&p->name[0];
+
+    // Get CPU brand string.
+    for (i = 0; i < 3; ++i) {
+      __kmp_x86_cpuid(0x80000002 + i, 0, base + i);
+    }; // for
+    p->name[sizeof(p->name) - 1] = 0; // Just in case. ;-)
+    KA_TRACE(trace_level, ("cpu brand string: \"%s\"\n", &p->name[0]));
+
+    // Parse frequency.
+    p->frequency = __kmp_parse_frequency(strrchr(&p->name[0], ' '));
+    KA_TRACE(trace_level,
+             ("cpu frequency from brand string: %" KMP_UINT64_SPEC "\n",
+              p->frequency));
+  }
 }
 
 #endif /* KMP_ARCH_X86 || KMP_ARCH_X86_64 */
 
-/* ------------------------------------------------------------------------------------ */
-/* ------------------------------------------------------------------------------------ */
-
-void
-__kmp_expand_host_name( char *buffer, size_t size )
-{
-    KMP_DEBUG_ASSERT(size >= sizeof(unknown));
+void __kmp_expand_host_name(char *buffer, size_t size) {
+  KMP_DEBUG_ASSERT(size >= sizeof(unknown));
 #if KMP_OS_WINDOWS
-    {
-	DWORD	s = size;
+  {
+    DWORD s = size;
 
-	if (! GetComputerNameA( buffer, & s ))
-	    KMP_STRCPY_S( buffer, size, unknown );
-    }
+    if (!GetComputerNameA(buffer, &s))
+      KMP_STRCPY_S(buffer, size, unknown);
+  }
 #else
-    buffer[size - 2] = 0;
-    if (gethostname( buffer, size ) || buffer[size - 2] != 0)
-	KMP_STRCPY_S( buffer, size, unknown );
+  buffer[size - 2] = 0;
+  if (gethostname(buffer, size) || buffer[size - 2] != 0)
+    KMP_STRCPY_S(buffer, size, unknown);
 #endif
 }
 
 /* Expand the meta characters in the filename:
- *
  * Currently defined characters are:
- *
  * %H the hostname
  * %P the number of threads used.
  * %I the unique identifier for this run.
  */
 
-void
-__kmp_expand_file_name( char *result, size_t rlen, char *pattern )
-{
-    char	*pos = result, *end = result + rlen - 1;
-    char	 buffer[256];
-    int		 default_cpu_width = 1;
-    int          snp_result;
+void __kmp_expand_file_name(char *result, size_t rlen, char *pattern) {
+  char *pos = result, *end = result + rlen - 1;
+  char buffer[256];
+  int default_cpu_width = 1;
+  int snp_result;
 
-    KMP_DEBUG_ASSERT(rlen > 0);
-    *end = 0;
-    {
-	int i;
-	for(i = __kmp_xproc; i >= 10; i /= 10, ++default_cpu_width);
+  KMP_DEBUG_ASSERT(rlen > 0);
+  *end = 0;
+  {
+    int i;
+    for (i = __kmp_xproc; i >= 10; i /= 10, ++default_cpu_width)
+      ;
+  }
+
+  if (pattern != NULL) {
+    while (*pattern != '\0' && pos < end) {
+      if (*pattern != '%') {
+        *pos++ = *pattern++;
+      } else {
+        char *old_pattern = pattern;
+        int width = 1;
+        int cpu_width = default_cpu_width;
+
+        ++pattern;
+
+        if (*pattern >= '0' && *pattern <= '9') {
+          width = 0;
+          do {
+            width = (width * 10) + *pattern++ - '0';
+          } while (*pattern >= '0' && *pattern <= '9');
+          if (width < 0 || width > 1024)
+            width = 1;
+
+          cpu_width = width;
+        }
+
+        switch (*pattern) {
+        case 'H':
+        case 'h': {
+          __kmp_expand_host_name(buffer, sizeof(buffer));
+          KMP_STRNCPY(pos, buffer, end - pos + 1);
+          if (*end == 0) {
+            while (*pos)
+              ++pos;
+            ++pattern;
+          } else
+            pos = end;
+        } break;
+        case 'P':
+        case 'p': {
+          snp_result = KMP_SNPRINTF(pos, end - pos + 1, "%0*d", cpu_width,
+                                    __kmp_dflt_team_nth);
+          if (snp_result >= 0 && snp_result <= end - pos) {
+            while (*pos)
+              ++pos;
+            ++pattern;
+          } else
+            pos = end;
+        } break;
+        case 'I':
+        case 'i': {
+          pid_t id = getpid();
+          snp_result = KMP_SNPRINTF(pos, end - pos + 1, "%0*d", width, id);
+          if (snp_result >= 0 && snp_result <= end - pos) {
+            while (*pos)
+              ++pos;
+            ++pattern;
+          } else
+            pos = end;
+          break;
+        }
+        case '%': {
+          *pos++ = '%';
+          ++pattern;
+          break;
+        }
+        default: {
+          *pos++ = '%';
+          pattern = old_pattern + 1;
+          break;
+        }
+        }
+      }
     }
+    /* TODO: How do we get rid of this? */
+    if (*pattern != '\0')
+      KMP_FATAL(FileNameTooLong);
+  }
 
-    if (pattern != NULL) {
-	while (*pattern != '\0' && pos < end) {
-	    if (*pattern != '%') {
-		*pos++ = *pattern++;
-	    } else {
-		char *old_pattern = pattern;
-		int width = 1;
-		int cpu_width = default_cpu_width;
-
-		++pattern;
-
-		if (*pattern >= '0' && *pattern <= '9') {
-		    width = 0;
-		    do {
-			width = (width * 10) + *pattern++ - '0';
-		    } while (*pattern >= '0' && *pattern <= '9');
-		    if (width < 0 || width > 1024)
-			width = 1;
-
-		    cpu_width = width;
-		}
-
-		switch (*pattern) {
-		case 'H':
-		case 'h':
-		    {
-			__kmp_expand_host_name( buffer, sizeof( buffer ) );
-			KMP_STRNCPY( pos,  buffer, end - pos + 1);
-			if(*end == 0) {
-			    while ( *pos )
-				++pos;
-			    ++pattern;
-			} else
-			    pos = end;
-		    }
-		    break;
-		case 'P':
-		case 'p':
-		    {
-			snp_result = KMP_SNPRINTF( pos, end - pos + 1, "%0*d", cpu_width, __kmp_dflt_team_nth );
-			if(snp_result >= 0 && snp_result <= end - pos) {
-			    while ( *pos )
-				++pos;
-			    ++pattern;
-			} else
-			    pos = end;
-		    }
-		    break;
-		case 'I':
-		case 'i':
-		    {
-			pid_t id = getpid();
-			snp_result = KMP_SNPRINTF( pos, end - pos + 1, "%0*d", width, id );
-			if(snp_result >= 0 && snp_result <= end - pos) {
-			    while ( *pos )
-				++pos;
-			    ++pattern;
-			} else
-			    pos = end;
-			break;
-		    }
-		case '%':
-		    {
-			*pos++ = '%';
-			++pattern;
-			break;
-		    }
-		default:
-		    {
-			*pos++ = '%';
-			pattern = old_pattern + 1;
-			break;
-		    }
-		}
-	    }
-	}
-	/* TODO: How do we get rid of this? */
-	if(*pattern != '\0')
-	    KMP_FATAL( FileNameTooLong );
-    }
-
-    *pos = '\0';
+  *pos = '\0';
 }
-

runtime/src/kmp_version.cpp

@@ -18,197 +18,191 @@
 #include "kmp_version.h"
 
 // Replace with snapshot date YYYYMMDD for promotion build.
-#define KMP_VERSION_BUILD    20140926
+#define KMP_VERSION_BUILD 20140926
 
 // Helper macros to convert value of macro to string literal.
-#define _stringer( x ) #x
-#define stringer( x )  _stringer( x )
+#define _stringer(x) #x
+#define stringer(x) _stringer(x)
 
 // Detect compiler.
 #if KMP_COMPILER_ICC
-    #if   __INTEL_COMPILER == 1010
-        #define KMP_COMPILER "Intel C++ Compiler 10.1"
-    #elif __INTEL_COMPILER == 1100
-        #define KMP_COMPILER "Intel C++ Compiler 11.0"
-    #elif __INTEL_COMPILER == 1110
-        #define KMP_COMPILER "Intel C++ Compiler 11.1"
-    #elif __INTEL_COMPILER == 1200
-        #define KMP_COMPILER "Intel C++ Compiler 12.0"
-    #elif __INTEL_COMPILER == 1210
-        #define KMP_COMPILER "Intel C++ Compiler 12.1"
-    #elif __INTEL_COMPILER == 1300
-        #define KMP_COMPILER "Intel C++ Compiler 13.0"
-    #elif __INTEL_COMPILER == 1310
-        #define KMP_COMPILER "Intel C++ Compiler 13.1"
-    #elif __INTEL_COMPILER == 1400
-        #define KMP_COMPILER "Intel C++ Compiler 14.0"
-    #elif __INTEL_COMPILER == 1410
-        #define KMP_COMPILER "Intel C++ Compiler 14.1"
-    #elif __INTEL_COMPILER == 1500
-        #define KMP_COMPILER "Intel C++ Compiler 15.0"
-    #elif __INTEL_COMPILER == 1600
-        #define KMP_COMPILER "Intel C++ Compiler 16.0"
-    #elif __INTEL_COMPILER == 1700
-        #define KMP_COMPILER "Intel C++ Compiler 17.0"
-    #elif __INTEL_COMPILER == 9998
-        #define KMP_COMPILER "Intel C++ Compiler mainline"
-    #elif __INTEL_COMPILER == 9999
-        #define KMP_COMPILER "Intel C++ Compiler mainline"
-    #endif
+#if __INTEL_COMPILER == 1010
+#define KMP_COMPILER "Intel C++ Compiler 10.1"
+#elif __INTEL_COMPILER == 1100
+#define KMP_COMPILER "Intel C++ Compiler 11.0"
+#elif __INTEL_COMPILER == 1110
+#define KMP_COMPILER "Intel C++ Compiler 11.1"
+#elif __INTEL_COMPILER == 1200
+#define KMP_COMPILER "Intel C++ Compiler 12.0"
+#elif __INTEL_COMPILER == 1210
+#define KMP_COMPILER "Intel C++ Compiler 12.1"
+#elif __INTEL_COMPILER == 1300
+#define KMP_COMPILER "Intel C++ Compiler 13.0"
+#elif __INTEL_COMPILER == 1310
+#define KMP_COMPILER "Intel C++ Compiler 13.1"
+#elif __INTEL_COMPILER == 1400
+#define KMP_COMPILER "Intel C++ Compiler 14.0"
+#elif __INTEL_COMPILER == 1410
+#define KMP_COMPILER "Intel C++ Compiler 14.1"
+#elif __INTEL_COMPILER == 1500
+#define KMP_COMPILER "Intel C++ Compiler 15.0"
+#elif __INTEL_COMPILER == 1600
+#define KMP_COMPILER "Intel C++ Compiler 16.0"
+#elif __INTEL_COMPILER == 1700
+#define KMP_COMPILER "Intel C++ Compiler 17.0"
+#elif __INTEL_COMPILER == 9998
+#define KMP_COMPILER "Intel C++ Compiler mainline"
+#elif __INTEL_COMPILER == 9999
+#define KMP_COMPILER "Intel C++ Compiler mainline"
+#endif
 #elif KMP_COMPILER_CLANG
-    #define KMP_COMPILER "Clang " stringer( __clang_major__ ) "." stringer( __clang_minor__ )
+#define KMP_COMPILER                                                           \
+  "Clang " stringer(__clang_major__) "." stringer(__clang_minor__)
 #elif KMP_COMPILER_GCC
-    #define KMP_COMPILER "GCC " stringer( __GNUC__ ) "." stringer( __GNUC_MINOR__ )
+#define KMP_COMPILER "GCC " stringer(__GNUC__) "." stringer(__GNUC_MINOR__)
 #elif KMP_COMPILER_MSVC
-    #define KMP_COMPILER "MSVC " stringer( _MSC_FULL_VER )
+#define KMP_COMPILER "MSVC " stringer(_MSC_FULL_VER)
 #endif
 #ifndef KMP_COMPILER
-    #warning "Unknown compiler"
-    #define KMP_COMPILER "unknown compiler"
+#warning "Unknown compiler"
+#define KMP_COMPILER "unknown compiler"
 #endif
 
 // Detect librray type (perf, stub).
 #ifdef KMP_STUB
-    #define KMP_LIB_TYPE "stub"
+#define KMP_LIB_TYPE "stub"
 #else
-    #define KMP_LIB_TYPE "performance"
+#define KMP_LIB_TYPE "performance"
 #endif // KMP_LIB_TYPE
 
 // Detect link type (static, dynamic).
 #ifdef KMP_DYNAMIC_LIB
-    #define KMP_LINK_TYPE "dynamic"
+#define KMP_LINK_TYPE "dynamic"
 #else
-    #define KMP_LINK_TYPE "static"
+#define KMP_LINK_TYPE "static"
 #endif // KMP_LINK_TYPE
 
 // Finally, define strings.
-#define KMP_LIBRARY   KMP_LIB_TYPE " library (" KMP_LINK_TYPE ")"
+#define KMP_LIBRARY KMP_LIB_TYPE " library (" KMP_LINK_TYPE ")"
 #define KMP_COPYRIGHT ""
 
 int const __kmp_version_major = KMP_VERSION_MAJOR;
 int const __kmp_version_minor = KMP_VERSION_MINOR;
 int const __kmp_version_build = KMP_VERSION_BUILD;
 int const __kmp_openmp_version =
-    #if OMP_45_ENABLED
-        201511;
-    #elif OMP_40_ENABLED
-        201307;
-    #else
-        201107;
-    #endif
-
-/* Do NOT change the format of this string!  Intel(R) Thread Profiler checks for a
-   specific format some changes in the recognition routine there need to
-   be made before this is changed.
-*/
-char const __kmp_copyright[] =
-    KMP_VERSION_PREFIX KMP_LIBRARY
-    " ver. " stringer( KMP_VERSION_MAJOR ) "." stringer( KMP_VERSION_MINOR )
-    "." stringer( KMP_VERSION_BUILD ) " "
-    KMP_COPYRIGHT;
-
-char const __kmp_version_copyright[]      = KMP_VERSION_PREFIX KMP_COPYRIGHT;
-char const __kmp_version_lib_ver[]        = KMP_VERSION_PREFIX "version: " stringer( KMP_VERSION_MAJOR ) "." stringer( KMP_VERSION_MINOR ) "." stringer( KMP_VERSION_BUILD );
-char const __kmp_version_lib_type[]       = KMP_VERSION_PREFIX "library type: " KMP_LIB_TYPE;
-char const __kmp_version_link_type[]      = KMP_VERSION_PREFIX "link type: " KMP_LINK_TYPE;
-char const __kmp_version_build_time[]     = KMP_VERSION_PREFIX "build time: " "no_timestamp";
-#if KMP_MIC2
-    char const __kmp_version_target_env[] = KMP_VERSION_PREFIX "target environment: MIC2";
+#if OMP_50_ENABLED
+    201611;
+#elif OMP_45_ENABLED
+    201511;
+#elif OMP_40_ENABLED
+    201307;
+#else
+    201107;
 #endif
-char const __kmp_version_build_compiler[] = KMP_VERSION_PREFIX "build compiler: " KMP_COMPILER;
 
-//
+/* Do NOT change the format of this string!  Intel(R) Thread Profiler checks for
+   a specific format some changes in the recognition routine there need to be
+   made before this is changed. */
+char const __kmp_copyright[] = KMP_VERSION_PREFIX KMP_LIBRARY
+    " ver. " stringer(KMP_VERSION_MAJOR) "." stringer(
+        KMP_VERSION_MINOR) "." stringer(KMP_VERSION_BUILD) " " KMP_COPYRIGHT;
+
+char const __kmp_version_copyright[] = KMP_VERSION_PREFIX KMP_COPYRIGHT;
+char const __kmp_version_lib_ver[] =
+    KMP_VERSION_PREFIX "version: " stringer(KMP_VERSION_MAJOR) "." stringer(
+        KMP_VERSION_MINOR) "." stringer(KMP_VERSION_BUILD);
+char const __kmp_version_lib_type[] =
+    KMP_VERSION_PREFIX "library type: " KMP_LIB_TYPE;
+char const __kmp_version_link_type[] =
+    KMP_VERSION_PREFIX "link type: " KMP_LINK_TYPE;
+char const __kmp_version_build_time[] = KMP_VERSION_PREFIX "build time: "
+                                                           "no_timestamp";
+#if KMP_MIC2
+char const __kmp_version_target_env[] =
+    KMP_VERSION_PREFIX "target environment: MIC2";
+#endif
+char const __kmp_version_build_compiler[] =
+    KMP_VERSION_PREFIX "build compiler: " KMP_COMPILER;
+
 // Called at serial initialization time.
-//
 static int __kmp_version_1_printed = FALSE;
 
-void
-__kmp_print_version_1( void )
-{
-    if ( __kmp_version_1_printed ) {
-        return;
-    }; // if
-    __kmp_version_1_printed = TRUE;
+void __kmp_print_version_1(void) {
+  if (__kmp_version_1_printed) {
+    return;
+  }; // if
+  __kmp_version_1_printed = TRUE;
 
-    #ifndef KMP_STUB
-        kmp_str_buf_t buffer;
-        __kmp_str_buf_init( & buffer );
-        // Print version strings skipping initial magic.
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_lib_ver[ KMP_VERSION_MAGIC_LEN ] );
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_lib_type[ KMP_VERSION_MAGIC_LEN ] );
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_link_type[ KMP_VERSION_MAGIC_LEN ] );
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_build_time[ KMP_VERSION_MAGIC_LEN ] );
-      #if KMP_MIC
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_target_env[ KMP_VERSION_MAGIC_LEN ] );
-      #endif
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_build_compiler[ KMP_VERSION_MAGIC_LEN ] );
-        #if defined(KMP_GOMP_COMPAT)
-            __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_alt_comp[ KMP_VERSION_MAGIC_LEN ] );
-        #endif /* defined(KMP_GOMP_COMPAT) */
-        __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_omp_api[ KMP_VERSION_MAGIC_LEN ] );
-        __kmp_str_buf_print( & buffer, "%sdynamic error checking: %s\n", KMP_VERSION_PREF_STR, ( __kmp_env_consistency_check ? "yes" : "no" )  );
-        #ifdef KMP_DEBUG
-            for ( int i = bs_plain_barrier; i < bs_last_barrier; ++ i ) {
-                __kmp_str_buf_print(
-                    & buffer,
-                    "%s%s barrier branch bits: gather=%u, release=%u\n",
-                    KMP_VERSION_PREF_STR,
-                    __kmp_barrier_type_name[ i ],
-                    __kmp_barrier_gather_branch_bits[ i ],
-                    __kmp_barrier_release_branch_bits[ i ]
-                ); // __kmp_str_buf_print
-            }; // for i
-            for ( int i = bs_plain_barrier; i < bs_last_barrier; ++ i ) {
-                __kmp_str_buf_print(
-                    & buffer,
-                    "%s%s barrier pattern: gather=%s, release=%s\n",
-                    KMP_VERSION_PREF_STR,
-                    __kmp_barrier_type_name[ i ],
-                    __kmp_barrier_pattern_name[ __kmp_barrier_gather_pattern[ i ] ],
-                    __kmp_barrier_pattern_name[ __kmp_barrier_release_pattern[ i ] ]
-                ); // __kmp_str_buf_print
-            }; // for i
-            __kmp_str_buf_print( & buffer, "%s\n", & __kmp_version_lock[ KMP_VERSION_MAGIC_LEN ] );
-        #endif
-        __kmp_str_buf_print(
-            & buffer,
-            "%sthread affinity support: %s\n",
-            KMP_VERSION_PREF_STR,
-            #if KMP_AFFINITY_SUPPORTED
-                (
-                    KMP_AFFINITY_CAPABLE()
-                    ?
-                    (
-                        __kmp_affinity_type == affinity_none
-                        ?
-                        "not used"
-                        :
-                        "yes"
-                    )
-                    :
-                    "no"
-                )
-            #else
-                "no"
-            #endif
-        );
-        __kmp_printf( "%s", buffer.str );
-        __kmp_str_buf_free( & buffer );
-        K_DIAG( 1, ( "KMP_VERSION is true\n" ) );
-    #endif // KMP_STUB
+#ifndef KMP_STUB
+  kmp_str_buf_t buffer;
+  __kmp_str_buf_init(&buffer);
+  // Print version strings skipping initial magic.
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_lib_ver[KMP_VERSION_MAGIC_LEN]);
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_lib_type[KMP_VERSION_MAGIC_LEN]);
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_link_type[KMP_VERSION_MAGIC_LEN]);
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_build_time[KMP_VERSION_MAGIC_LEN]);
+#if KMP_MIC
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_target_env[KMP_VERSION_MAGIC_LEN]);
+#endif
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_build_compiler[KMP_VERSION_MAGIC_LEN]);
+#if defined(KMP_GOMP_COMPAT)
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_alt_comp[KMP_VERSION_MAGIC_LEN]);
+#endif /* defined(KMP_GOMP_COMPAT) */
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_omp_api[KMP_VERSION_MAGIC_LEN]);
+  __kmp_str_buf_print(&buffer, "%sdynamic error checking: %s\n",
+                      KMP_VERSION_PREF_STR,
+                      (__kmp_env_consistency_check ? "yes" : "no"));
+#ifdef KMP_DEBUG
+  for (int i = bs_plain_barrier; i < bs_last_barrier; ++i) {
+    __kmp_str_buf_print(
+        &buffer, "%s%s barrier branch bits: gather=%u, release=%u\n",
+        KMP_VERSION_PREF_STR, __kmp_barrier_type_name[i],
+        __kmp_barrier_gather_branch_bits[i],
+        __kmp_barrier_release_branch_bits[i]); // __kmp_str_buf_print
+  }; // for i
+  for (int i = bs_plain_barrier; i < bs_last_barrier; ++i) {
+    __kmp_str_buf_print(
+        &buffer, "%s%s barrier pattern: gather=%s, release=%s\n",
+        KMP_VERSION_PREF_STR, __kmp_barrier_type_name[i],
+        __kmp_barrier_pattern_name[__kmp_barrier_gather_pattern[i]],
+        __kmp_barrier_pattern_name
+            [__kmp_barrier_release_pattern[i]]); // __kmp_str_buf_print
+  }; // for i
+  __kmp_str_buf_print(&buffer, "%s\n",
+                      &__kmp_version_lock[KMP_VERSION_MAGIC_LEN]);
+#endif
+  __kmp_str_buf_print(
+      &buffer, "%sthread affinity support: %s\n", KMP_VERSION_PREF_STR,
+#if KMP_AFFINITY_SUPPORTED
+      (KMP_AFFINITY_CAPABLE()
+           ? (__kmp_affinity_type == affinity_none ? "not used" : "yes")
+           : "no")
+#else
+      "no"
+#endif
+          );
+  __kmp_printf("%s", buffer.str);
+  __kmp_str_buf_free(&buffer);
+  K_DIAG(1, ("KMP_VERSION is true\n"));
+#endif // KMP_STUB
 } // __kmp_print_version_1
 
-//
 // Called at parallel initialization time.
-//
 static int __kmp_version_2_printed = FALSE;
 
-void
-__kmp_print_version_2( void ) {
-    if ( __kmp_version_2_printed ) {
-        return;
-    }; // if
-    __kmp_version_2_printed = TRUE;
+void __kmp_print_version_2(void) {
+  if (__kmp_version_2_printed) {
+    return;
+  }; // if
+  __kmp_version_2_printed = TRUE;
 } // __kmp_print_version_2
 
 // end of file //

runtime/src/kmp_version.h

@@ -17,31 +17,32 @@
 #define KMP_VERSION_H
 
 #ifdef __cplusplus
-    extern "C" {
+extern "C" {
 #endif // __cplusplus
 
 #ifndef KMP_VERSION_MAJOR
-    #error KMP_VERSION_MAJOR macro is not defined.
+#error KMP_VERSION_MAJOR macro is not defined.
 #endif
-#define KMP_VERSION_MINOR       0
-/*
-    Using "magic" prefix in all the version strings is rather convenient to get static version info
-    from binaries by using standard utilities "strings" and "grep", e. g.:
+#define KMP_VERSION_MINOR 0
+/* Using "magic" prefix in all the version strings is rather convenient to get
+   static version info from binaries by using standard utilities "strings" and
+   "grep", e. g.:
         $ strings libomp.so | grep "@(#)"
-    gives clean list of all version strings in the library. Leading zero helps to keep version
-    string separate from printable characters which may occurs just before version string.
-*/
-#define KMP_VERSION_MAGIC_STR   "\x00@(#) "
-#define KMP_VERSION_MAGIC_LEN   6                // Length of KMP_VERSION_MAGIC_STR.
-#define KMP_VERSION_PREF_STR    "Intel(R) OMP "
-#define KMP_VERSION_PREFIX      KMP_VERSION_MAGIC_STR KMP_VERSION_PREF_STR
+   gives clean list of all version strings in the library. Leading zero helps
+   to keep version string separate from printable characters which may occurs
+   just before version string. */
+#define KMP_VERSION_MAGIC_STR "\x00@(#) "
+#define KMP_VERSION_MAGIC_LEN 6 // Length of KMP_VERSION_MAGIC_STR.
+#define KMP_VERSION_PREF_STR "Intel(R) OMP "
+#define KMP_VERSION_PREFIX KMP_VERSION_MAGIC_STR KMP_VERSION_PREF_STR
 
 /* declare all the version string constants for KMP_VERSION env. variable */
-extern int  const __kmp_version_major;
-extern int  const __kmp_version_minor;
-extern int  const __kmp_version_build;
-extern int  const __kmp_openmp_version;
-extern char const __kmp_copyright[];    // Old variable, kept for compatibility with ITC and ITP.
+extern int const __kmp_version_major;
+extern int const __kmp_version_minor;
+extern int const __kmp_version_build;
+extern int const __kmp_openmp_version;
+extern char const
+    __kmp_copyright[]; // Old variable, kept for compatibility with ITC and ITP.
 extern char const __kmp_version_copyright[];
 extern char const __kmp_version_lib_ver[];
 extern char const __kmp_version_lib_type[];
@@ -58,11 +59,11 @@ extern char const __kmp_version_ftnstdcall[];
 extern char const __kmp_version_ftncdecl[];
 extern char const __kmp_version_ftnextra[];
 
-void __kmp_print_version_1( void );
-void __kmp_print_version_2( void );
+void __kmp_print_version_1(void);
+void __kmp_print_version_2(void);
 
 #ifdef __cplusplus
-    } // extern "C"
+} // extern "C"
 #endif // __cplusplus
 
 #endif /* KMP_VERSION_H */