[clang] [llvm] [CMake][PGO] Build Sema.cpp to generate profdata for PGO builds (PR #77347)

[Petr Hosek via cfe-commits]

================
@@ -26,9 +30,23 @@ if(LLVM_BUILD_INSTRUMENTED)
     message(STATUS "To enable merging PGO data LLVM_PROFDATA has to point to llvm-profdata")
   else()
     add_custom_target(generate-profdata
-      COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge ${LLVM_PROFDATA} ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata ${CMAKE_CURRENT_BINARY_DIR}
+      COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge ${LLVM_PROFDATA} ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_BINARY_DIR}/profiles/
       COMMENT "Merging profdata"
       DEPENDS generate-profraw)
+    if (CLANG_PGO_TRAINING_DATA_SOURCE_DIR)
+      llvm_ExternalProject_Add(generate-profraw-external ${CLANG_PGO_TRAINING_DATA_SOURCE_DIR}
+              USE_TOOLCHAIN EXLUDE_FROM_ALL NO_INSTALL DEPENDS generate-profraw)
+      add_dependencies(generate-profdata generate-profraw-external)
+    else()
+      # Default to compiling a file from clang. This also builds all the
+      # dependencies needed to build this file, like TableGen.
+      set(generate_profraw_clang_sema tools/clang/lib/Sema/CMakeFiles/obj.clangSema.dir/Sema.cpp.o)
+      llvm_ExternalProject_Add(generate-profraw-clang ${CMAKE_CURRENT_SOURCE_DIR}/../../../llvm
+              USE_TOOLCHAIN EXLUDE_FROM_ALL NO_INSTALL DEPENDS generate-profraw
+              EXTRA_TARGETS generate_profraw_clang_sema
----------------
petrhosek wrote:

The idea I'd like explore is using libc++ (and perhaps also libc) test suite for training. It consists of self-contained test programs which should sufficiently exercise various aspects of C/C++ frontend.

https://github.com/llvm/llvm-project/pull/77347