[CMake] Replace clang binary if using clang-bolt target

[Amir]

Summary

Instead of creating an extra clang-bolt binary and clang++-bolt symlink,
replace the original clang binary with BOLT-optimized one.

This fixes the issue with installing optimized binary as install-clang
target now copies the new version.

[Amir]

Ping @phosek @MaskRay

[phosek]

clang/CMakeLists.txt

940

We should consider placing this and all other intermediate outputs in ${CMAKE_CURRENT_BINARY_DIR}.

947

This makes assumptions about the name of the binary which is chosen by CMake and can in theory change. Can you try to use generator expression instead?

[Amir]

Use generator expression, put clang-bolt temp binary to CMAKE_CURRENT_BINARY_DIR

[phosek]

LGTM

clang/CMakeLists.txt

if (CLANG_ENABLE_BOOTSTRAP)
   endforeach()
 endif()
 
 if (CLANG_BOLT_INSTRUMENT AND NOT LLVM_BUILD_INSTRUMENTED)
   set(CLANG_PATH ${LLVM_RUNTIME_OUTPUT_INTDIR}/clang)
   set(CLANGXX_PATH ${CLANG_PATH}++)
   set(CLANG_INSTRUMENTED ${CLANG_PATH}-bolt.inst)
   set(CLANGXX_INSTRUMENTED ${CLANGXX_PATH}-bolt.inst)
-  set(CLANG_OPTIMIZED ${CLANG_PATH}-bolt)
-  set(CLANGXX_OPTIMIZED ${CLANGXX_PATH}-bolt)
 
   # Instrument clang with BOLT
   add_custom_target(clang-instrumented
     DEPENDS ${CLANG_INSTRUMENTED}
   )
   add_custom_command(OUTPUT ${CLANG_INSTRUMENTED}
     DEPENDS clang llvm-bolt
     COMMAND llvm-bolt ${CLANG_PATH} -o ${CLANG_INSTRUMENTED}
COMMAND ${Python3_EXECUTABLE}
       ${CMAKE_CURRENT_SOURCE_DIR}/utils/perf-training/perf-helper.py merge-fdata
       $<TARGET_FILE:merge-fdata> ${CMAKE_CURRENT_BINARY_DIR}/prof.fdata
       ${CMAKE_CURRENT_BINARY_DIR}
     COMMENT "Preparing BOLT profile"
     VERBATIM
   )
 
   # Optimize original (pre-bolt) Clang using the collected profile
+  set(CLANG_OPTIMIZED ${CMAKE_CURRENT_BINARY_DIR}/clang.bolt)
   add_custom_target(clang-bolt
     DEPENDS ${CLANG_OPTIMIZED}
   )
   add_custom_command(OUTPUT ${CLANG_OPTIMIZED}
     DEPENDS clang-bolt-profile
     COMMAND llvm-bolt ${CLANG_PATH}
       -o ${CLANG_OPTIMIZED}
       -data ${CMAKE_CURRENT_BINARY_DIR}/prof.fdata
       -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions
       -split-all-cold -split-eh -dyno-stats -icf=1 -use-gnu-stack
+    COMMAND ${CMAKE_COMMAND} -E rename ${CLANG_OPTIMIZED} $<TARGET_FILE:clang>
     COMMENT "Optimizing Clang with BOLT"
     VERBATIM
   )
-
-  # Make a symlink from clang-bolt to clang++-bolt
-  add_custom_target(clang++-bolt
-    DEPENDS ${CLANGXX_OPTIMIZED}
-  )
-  add_custom_command(OUTPUT ${CLANGXX_OPTIMIZED}
-    DEPENDS clang-bolt
-    COMMAND ${CMAKE_COMMAND} -E create_symlink
-      ${CLANG_OPTIMIZED}
-      ${CLANGXX_OPTIMIZED}
-    COMMENT "Creating symlink from BOLT optimized clang to clang++"
-    VERBATIM
-  )
 endif()
 
 if (LLVM_ADD_NATIVE_VISUALIZERS_TO_SOLUTION)
   add_subdirectory(utils/ClangVisualizers)
 endif()
 add_subdirectory(utils/hmaptool)
 
 if(CLANG_BUILT_STANDALONE)

clang/cmake/caches/BOLT-PGO.cmake

 set(LLVM_ENABLE_PROJECTS "bolt;clang;lld" CACHE STRING "")
 
 set(CLANG_BOOTSTRAP_TARGETS
   stage2-clang-bolt
-  stage2-clang++-bolt
   CACHE STRING "")
 set(BOOTSTRAP_CLANG_BOOTSTRAP_TARGETS
   clang-bolt
-  clang++-bolt
   CACHE STRING "")
 
 set(PGO_BUILD_CONFIGURATION ${CMAKE_CURRENT_LIST_DIR}/BOLT.cmake CACHE STRING "")
 include(${CMAKE_CURRENT_LIST_DIR}/PGO.cmake)

llvm/docs/AdvancedBuilds.rst

 .. code-block:: console
 
   $ cmake <path to source>/llvm -C <path to source>/clang/cmake/caches/BOLT.cmake
 
 Then, build the BOLT-optimized binary by running the following ninja command:
 
 .. code-block:: console
 
-  $ ninja clang++-bolt
+  $ ninja clang-bolt
 
 If you're seeing errors in the build process, try building with a recent
 version of Clang/LLVM by setting the CMAKE_C_COMPILER and
 CMAKE_CXX_COMPILER flags to the appropriate values.
 
 It is also possible to use BOLT on top of PGO and (Thin)LTO for an even more
 significant runtime speedup. To configure a three stage PGO build with ThinLTO
 that optimizes the resulting binary with BOLT, use the following CMake
 configuration command:
 
 .. code-block:: console
 
   $ cmake -G Ninja <path to source>/llvm \
       -C <path to source>/clang/cmake/caches/BOLT-PGO.cmake \
       -DBOOTSTRAP_LLVM_ENABLE_LLD=ON \
       -DBOOTSTRAP_BOOTSTRAP_LLVM_ENABLE_LLD=ON \
       -DPGO_INSTRUMENT_LTO=Thin
 
-Then, to build the final optimized binary, build the stage2-clang++-bolt
-target:
+Then, to build the final optimized binary, build the stage2-clang-bolt target:
 
 .. code-block:: console
 
-  $ ninja stage2-clang++-bolt
+  $ ninja stage2-clang-bolt
 
 3-Stage Non-Determinism
 =======================
 
 In the ancient lore of compilers non-determinism is like the multi-headed hydra.
 Whenever its head pops up, terror and chaos ensue.
 
 Historically one of the tests to verify that a compiler was deterministic would