[Clang][CMake] Use perf-training for Clang-BOLT

[Amir]

Summary

Leverage perf-training flow for BOLT profile collection, enabling reproducible
BOLT optimization. Remove the use of bootstrapped build for profile collection.

Test Plan:

• Regular (single-stage) build

$ cmake ... -C .../clang/cmake/caches/BOLT.cmake
$ ninja clang-bolt
...
[21/24] Instrumenting clang binary with BOLT
[21/24] Generating BOLT profile for Clang
[23/24] Merging BOLT fdata
Profile from 2 files merged.
[24/24] Optimizing Clang with BOLT
... 
          1291202496 : executed instructions (-1.1%)
            27005133 : taken branches (-71.5%)
...

• Two stage build (ThinLTO+InstPGO)

$ cmake ... -C .../clang/cmake/caches/BOLT.cmake -C .../clang/cmake/caches/BOLT-PGO.cmake
$ ninja clang-bolt
$ ninja stage2-clang-bolt
...
[2756/2759] Instrumenting clang binary with BOLT
[2756/2759] Generating BOLT profile for Clang
[2758/2759] Merging BOLT fdata
[2759/2759] Optimizing Clang with BOLT
...
BOLT-INFO: 7092 out of 184104 functions in the binary (3.9%) have non-empty execution profile
           756531927 : executed instructions (-0.5%)
            15399400 : taken branches (-40.3%)
...

[Amir]

Fixes

[Amir]

Fixed BOLT-PGO build

[Amir]

Remove sysroot_flags

[Amir]

Rebase, reduce changes

[Amir]

Ping @phosek

[beanz]

LGTM.

Sorry for the delays reviewing!

[Amir]

In D143553#4339755, @beanz wrote:

LGTM.

Sorry for the delays reviewing!

Thanks!

clang/CMakeLists.txt

foreach(target ${CLANG_BOOTSTRAP_TARGETS})
     endif()
 
     ExternalProject_Add_StepTargets(${NEXT_CLANG_STAGE} ${target})
   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(BOLT_FDATA ${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/prof.fdata)
 
   # 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 ${CLANG_INSTRUMENTED}
       -instrument --instrumentation-file-append-pid
-      --instrumentation-file=${CMAKE_CURRENT_BINARY_DIR}/prof.fdata
+      --instrumentation-file=${BOLT_FDATA}
     COMMENT "Instrumenting clang binary with BOLT"
     VERBATIM
   )
 
-  # Make a symlink from clang-bolt.inst to clang++-bolt.inst
-  add_custom_target(clang++-instrumented
-    DEPENDS ${CLANGXX_INSTRUMENTED}
-  )
-  add_custom_command(OUTPUT ${CLANGXX_INSTRUMENTED}
-    DEPENDS clang-instrumented
-    COMMAND ${CMAKE_COMMAND} -E create_symlink
-      ${CLANG_INSTRUMENTED}
-      ${CLANGXX_INSTRUMENTED}
-    COMMENT "Creating symlink from BOLT instrumented clang to clang++"
-    VERBATIM
-  )
-
-  # Build specified targets with instrumented Clang to collect the profile
-  set(STAMP_DIR ${CMAKE_CURRENT_BINARY_DIR}/bolt-instrumented-clang-stamps/)
-  set(BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR}/bolt-instrumented-clang-bins/)
-  set(build_configuration "$<CONFIG>")
-  include(ExternalProject)
-  ExternalProject_Add(bolt-instrumentation-profile
-    DEPENDS clang++-instrumented
-    PREFIX bolt-instrumentation-profile
-    SOURCE_DIR ${CMAKE_SOURCE_DIR}
-    STAMP_DIR ${STAMP_DIR}
-    BINARY_DIR ${BINARY_DIR}
-    EXCLUDE_FROM_ALL 1
-    CMAKE_ARGS
-                ${CLANG_BOLT_INSTRUMENT_EXTRA_CMAKE_FLAGS}
-                # We shouldn't need to set this here, but INSTALL_DIR doesn't
-                # seem to work, so instead I'm passing this through
-                -DCMAKE_INSTALL_PREFIX=${CMAKE_INSTALL_PREFIX}
-                -DCMAKE_C_COMPILER=${CLANG_INSTRUMENTED}
-                -DCMAKE_CXX_COMPILER=${CLANGXX_INSTRUMENTED}
-                -DCMAKE_ASM_COMPILER=${CLANG_INSTRUMENTED}
-                -DCMAKE_ASM_COMPILER_ID=Clang
-                -DCMAKE_BUILD_TYPE=Release
-                -DLLVM_ENABLE_PROJECTS=${CLANG_BOLT_INSTRUMENT_PROJECTS}
-                -DLLVM_TARGETS_TO_BUILD=${LLVM_TARGETS_TO_BUILD}
-    BUILD_COMMAND ${CMAKE_COMMAND} --build ${BINARY_DIR}
-                                   --config ${build_configuration}
-                                   --target ${CLANG_BOLT_INSTRUMENT_TARGETS}
-    INSTALL_COMMAND ""
-    STEP_TARGETS configure build
-    USES_TERMINAL_CONFIGURE 1
-    USES_TERMINAL_BUILD 1
-    USES_TERMINAL_INSTALL 1
-  )
-
-  # Merge profiles into one using merge-fdata
-  add_custom_target(clang-bolt-profile
-    DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/prof.fdata
-  )
-  add_custom_command(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/prof.fdata
-    DEPENDS merge-fdata bolt-instrumentation-profile-build
-    WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}
-    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
+      -data ${BOLT_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
   )
 endif()
 

clang/cmake/caches/BOLT.cmake

 set(CMAKE_BUILD_TYPE Release CACHE STRING "")
 set(CLANG_BOLT_INSTRUMENT ON CACHE BOOL "")
-set(CLANG_BOLT_INSTRUMENT_PROJECTS "llvm" CACHE STRING "")
-set(CLANG_BOLT_INSTRUMENT_TARGETS "count" CACHE STRING "")
 set(CMAKE_EXE_LINKER_FLAGS "-Wl,--emit-relocs,-znow" CACHE STRING "")
-set(CLANG_BOLT_INSTRUMENT_EXTRA_CMAKE_FLAGS "" CACHE STRING "")
 
 set(LLVM_ENABLE_PROJECTS "bolt;clang" CACHE STRING "")
 set(LLVM_TARGETS_TO_BUILD Native CACHE STRING "")
 
 # setup toolchain
 set(LLVM_INSTALL_TOOLCHAIN_ONLY ON CACHE BOOL "")
 set(LLVM_DISTRIBUTION_COMPONENTS
   clang
   clang-resource-headers
   CACHE STRING "")
 
 # Disable function splitting enabled by default in GCC8+
 if("${CMAKE_CXX_COMPILER_ID}" MATCHES "GNU")
   set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fno-reorder-blocks-and-partition")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-reorder-blocks-and-partition")
 endif()

clang/utils/perf-training/CMakeLists.txt

if(NOT CLANG_ORDER_FILE)
     message(FATAL_ERROR "Output clang order file is not set")
   endif()
 
   add_custom_target(generate-order-file
     COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py gen-order-file --binary $<TARGET_FILE:clang> --output ${CLANG_ORDER_FILE} ${CMAKE_CURRENT_BINARY_DIR}
     COMMENT "Generating order file"
     DEPENDS generate-dtrace-logs)
 endif()
+
+if(CLANG_BOLT_INSTRUMENT AND NOT LLVM_BUILD_INSTRUMENTED)
+  configure_lit_site_cfg(
+    ${CMAKE_CURRENT_SOURCE_DIR}/bolt.lit.site.cfg.in
+    ${CMAKE_CURRENT_BINARY_DIR}/bolt-fdata/lit.site.cfg
+    )
+
+  add_lit_testsuite(generate-bolt-fdata "Generating BOLT profile for Clang"
+    ${CMAKE_CURRENT_BINARY_DIR}/bolt-fdata/
+    EXCLUDE_FROM_CHECK_ALL
+    DEPENDS clang-instrumented clear-bolt-fdata
+    )
+
+  add_custom_target(clear-bolt-fdata
+    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} fdata
+    COMMENT "Clearing old BOLT fdata")
+
+  # Merge profiles into one using merge-fdata
+  add_custom_target(clang-bolt-profile
+    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge-fdata $<TARGET_FILE:merge-fdata> ${CMAKE_CURRENT_BINARY_DIR}/prof.fdata ${CMAKE_CURRENT_BINARY_DIR}
+    COMMENT "Merging BOLT fdata"
+    DEPENDS merge-fdata generate-bolt-fdata)
+endif()

clang/utils/perf-training/bolt.lit.cfg

+# -*- Python -*-
+
+from lit import Test
+import lit.formats
+import lit.util
+import os
+import subprocess
+
+config.clang = os.path.realpath(lit.util.which('clang-bolt.inst', config.clang_tools_dir)).replace('\\', '/')
+
+config.name = 'Clang Perf Training'
+config.suffixes = ['.c', '.cc', '.cpp', '.m', '.mm', '.cu', '.ll', '.cl', '.s', '.S', '.modulemap', '.test']
+
+use_lit_shell = os.environ.get("LIT_USE_INTERNAL_SHELL")
+config.test_format = lit.formats.ShTest(use_lit_shell == "0")
+config.substitutions.append( ('%clang_cpp_skip_driver', ' %s --driver-mode=g++ ' % (config.clang)))
+config.substitutions.append( ('%clang_cpp', ' %s --driver-mode=g++ ' % (config.clang)))
+config.substitutions.append( ('%clang_skip_driver', ' %s ' % (config.clang)))
+config.substitutions.append( ('%clang', ' %s ' % (config.clang) ) )
+config.substitutions.append( ('%test_root', config.test_exec_root ) )

clang/utils/perf-training/bolt.lit.site.cfg.in

+@LIT_SITE_CFG_IN_HEADER@
+
+import sys
+
+config.clang_tools_dir = lit_config.substitute("@CURRENT_TOOLS_DIR@")
+config.perf_helper_dir = "@CMAKE_CURRENT_SOURCE_DIR@"
+config.test_exec_root = "@CMAKE_CURRENT_BINARY_DIR@"
+config.test_source_root = "@CLANG_PGO_TRAINING_DATA@"
+config.target_triple = "@LLVM_TARGET_TRIPLE@"
+config.python_exe = "@Python3_EXECUTABLE@"
+config.clang_obj_root = path(r"@CLANG_BINARY_DIR@")
+
+# Let the main config do the real work.
+lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/bolt.lit.cfg")