diff --git a/openmp/CMakeLists.txt b/openmp/CMakeLists.txt --- a/openmp/CMakeLists.txt +++ b/openmp/CMakeLists.txt @@ -81,6 +81,7 @@ ${ENABLE_LIBOMPTARGET}) option(OPENMP_ENABLE_LIBOMPTARGET_PROFILING "Enable time profiling for libomptarget." ${ENABLE_LIBOMPTARGET}) +option(OPENMP_ENABLE_LIBOMP_PROFILING "Enable time profiling for libomp." OFF) # Build host runtime library, after LIBOMPTARGET variables are set since they are needed # to enable time profiling support in the OpenMP runtime. diff --git a/openmp/docs/design/Runtimes.rst b/openmp/docs/design/Runtimes.rst --- a/openmp/docs/design/Runtimes.rst +++ b/openmp/docs/design/Runtimes.rst @@ -48,7 +48,10 @@ `Speedscope App`_. Building this feature depends on the `LLVM Support Library`_ for time trace output. Using this library is enabled by default when building using the CMake option ``OPENMP_ENABLE_LIBOMPTARGET_PROFILING``. The output will -be saved to the filename specified by the environment variable. +be saved to the filename specified by the environment variable. For multi-threaded +applications, profiling in ``libomp`` is also needed. Setting the CMake option +``OPENMP_ENABLE_LIBOMP_PROFILING=ON`` to enable the feature. Note that this will +turn ``libomp`` into a C++ library. .. _`Chrome Tracing`: https://www.chromium.org/developers/how-tos/trace-event-profiling-tool diff --git a/openmp/runtime/CMakeLists.txt b/openmp/runtime/CMakeLists.txt --- a/openmp/runtime/CMakeLists.txt +++ b/openmp/runtime/CMakeLists.txt @@ -34,7 +34,6 @@ # Should assertions be enabled? They are on by default. set(LIBOMP_ENABLE_ASSERTIONS TRUE CACHE BOOL "enable assertions?") - set(LIBOMPTARGET_PROFILING_SUPPORT FALSE) else() # Part of LLVM build # Determine the native architecture from LLVM. string(TOLOWER "${LLVM_TARGET_ARCH}" LIBOMP_NATIVE_ARCH) @@ -66,10 +65,11 @@ libomp_get_architecture(LIBOMP_ARCH) endif () set(LIBOMP_ENABLE_ASSERTIONS ${LLVM_ENABLE_ASSERTIONS}) - # Time profiling support - set(LIBOMPTARGET_PROFILING_SUPPORT ${OPENMP_ENABLE_LIBOMPTARGET_PROFILING}) endif() +# Time profiling support +set(LIBOMP_PROFILING_SUPPORT ${OPENMP_ENABLE_LIBOMP_PROFILING}) + # FUJITSU A64FX is a special processor because its cache line size is 256. # We need to pass this information into kmp_config.h. if(LIBOMP_ARCH STREQUAL "aarch64") diff --git a/openmp/runtime/src/CMakeLists.txt b/openmp/runtime/src/CMakeLists.txt --- a/openmp/runtime/src/CMakeLists.txt +++ b/openmp/runtime/src/CMakeLists.txt @@ -50,9 +50,8 @@ include_directories(${LIBOMP_HWLOC_INSTALL_DIR}/include) endif() -# Building with time profiling support for libomptarget requires -# LLVM directory includes. -if(LIBOMPTARGET_PROFILING_SUPPORT) +# Building with time profiling support requires LLVM directory includes. +if(LIBOMP_PROFILING_SUPPORT) include_directories( ${LLVM_MAIN_INCLUDE_DIR} ${LLVM_INCLUDE_DIR} @@ -144,7 +143,7 @@ libomp_get_libflags(LIBOMP_CONFIGURED_LIBFLAGS) # Build libomp library. Add LLVMSupport dependency if building in-tree with libomptarget profiling enabled. -if(OPENMP_STANDALONE_BUILD OR (NOT OPENMP_ENABLE_LIBOMPTARGET_PROFILING)) +if(OPENMP_STANDALONE_BUILD OR (NOT OPENMP_ENABLE_LIBOMP_PROFILING)) add_library(omp ${LIBOMP_LIBRARY_KIND} ${LIBOMP_SOURCE_FILES}) # Linking command will include libraries in LIBOMP_CONFIGURED_LIBFLAGS target_link_libraries(omp ${LIBOMP_CONFIGURED_LIBFLAGS} ${CMAKE_DL_LIBS}) @@ -153,6 +152,8 @@ LINK_LIBS ${LIBOMP_CONFIGURED_LIBFLAGS} ${CMAKE_DL_LIBS} LINK_COMPONENTS Support ) + # libomp must be a C++ library such that it can link libLLVMSupport + set(LIBOMP_LINKER_LANGUAGE CXX) endif() set_target_properties(omp PROPERTIES diff --git a/openmp/runtime/src/kmp_config.h.cmake b/openmp/runtime/src/kmp_config.h.cmake --- a/openmp/runtime/src/kmp_config.h.cmake +++ b/openmp/runtime/src/kmp_config.h.cmake @@ -44,8 +44,8 @@ #define OMPT_DEBUG LIBOMP_OMPT_DEBUG #cmakedefine01 LIBOMP_OMPT_SUPPORT #define OMPT_SUPPORT LIBOMP_OMPT_SUPPORT -#cmakedefine01 LIBOMPTARGET_PROFILING_SUPPORT -#define OMPTARGET_PROFILING_SUPPORT LIBOMPTARGET_PROFILING_SUPPORT +#cmakedefine01 LIBOMP_PROFILING_SUPPORT +#define OMP_PROFILING_SUPPORT LIBOMP_PROFILING_SUPPORT #cmakedefine01 LIBOMP_OMPT_OPTIONAL #define OMPT_OPTIONAL LIBOMP_OMPT_OPTIONAL #cmakedefine01 LIBOMP_USE_ADAPTIVE_LOCKS diff --git a/openmp/runtime/src/kmp_runtime.cpp b/openmp/runtime/src/kmp_runtime.cpp --- a/openmp/runtime/src/kmp_runtime.cpp +++ b/openmp/runtime/src/kmp_runtime.cpp @@ -32,7 +32,7 @@ #include "ompt-specific.h" #endif -#if OMPTARGET_PROFILING_SUPPORT +#if OMP_PROFILING_SUPPORT #include "llvm/Support/TimeProfiler.h" static char *ProfileTraceFile = nullptr; #endif @@ -5740,7 +5740,7 @@ /* ------------------------------------------------------------------------ */ void *__kmp_launch_thread(kmp_info_t *this_thr) { -#if OMPTARGET_PROFILING_SUPPORT +#if OMP_PROFILING_SUPPORT ProfileTraceFile = getenv("LIBOMPTARGET_PROFILE"); // TODO: add a configuration option for time granularity if (ProfileTraceFile) @@ -5848,7 +5848,7 @@ KA_TRACE(10, ("__kmp_launch_thread: T#%d done\n", gtid)); KMP_MB(); -#if OMPTARGET_PROFILING_SUPPORT +#if OMP_PROFILING_SUPPORT llvm::timeTraceProfilerFinishThread(); #endif return this_thr;