[CMake][PGO] Add option for using an external project to generate profile data (#78879)

The new CLANG_PGO_TRAINING_DATA_SOURCE_DIR allows users to specify a
CMake project to use for generating the profile data. For example, to
use the llvm-test-suite to generate profile data you would do:

$ cmake -G Ninja -B build -S llvm -C <path to
source>/clang/cmake/caches/PGO.cmake \
-DBOOTSTRAP_CLANG_PGO_TRAINING_DATA_SOURCE_DIR=<path to llvm-test-suite>
\
        -DBOOTSTRAP_CLANG_PGO_TRAINING_DEPS=runtimes

Note that the CLANG_PERF_TRAINING_DEPS has been renamed to
CLANG_PGO_TRAINING_DEPS.

---------

Co-authored-by: Petr Hosek <phosek@google.com>
(cherry picked from commit dd0356d741aefa25ece973d6cc4b55dcb73b84b4)

2 files changed, 21 insertions, 10 deletions

diff --git a/clang/utils/perf-training/CMakeLists.txt b/clang/utils/perf-training/CMakeLists.txt
index c6d5186..93744f4 100644
--- a/clang/utils/perf-training/CMakeLists.txt
+++ b/clang/utils/perf-training/CMakeLists.txt
@@ -1,6 +1,10 @@
+include(LLVMExternalProjectUtils)
+
 set(CLANG_PGO_TRAINING_DATA "${CMAKE_CURRENT_SOURCE_DIR}" CACHE PATH
   "The path to a lit testsuite containing samples for PGO and order file generation"
   )
+set(CLANG_PGO_TRAINING_DATA_SOURCE_DIR OFF CACHE STRING "Path to source directory containing cmake project with source files to use for generating pgo data")
+set(CLANG_PGO_TRAINING_DEPS "" CACHE STRING "Extra dependencies needed to build the PGO training data.")
 
 if(LLVM_BUILD_INSTRUMENTED)
   configure_lit_site_cfg(
@@ -11,11 +15,11 @@ if(LLVM_BUILD_INSTRUMENTED)
   add_lit_testsuite(generate-profraw "Generating clang PGO data"
     ${CMAKE_CURRENT_BINARY_DIR}/pgo-data/
     EXCLUDE_FROM_CHECK_ALL
-    DEPENDS clang clear-profraw ${CLANG_PERF_TRAINING_DEPS}
+    DEPENDS clang clear-profraw ${CLANG_PGO_TRAINING_DEPS}
     )
 
   add_custom_target(clear-profraw
-    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} profraw
+    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_BINARY_DIR}/profiles/ profraw
     COMMENT "Clearing old profraw data")
 
   if(NOT LLVM_PROFDATA)
@@ -26,9 +30,14 @@ 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)
+    endif()
   endif()
 endif()
 
diff --git a/clang/utils/perf-training/perf-helper.py b/clang/utils/perf-training/perf-helper.py
index 99d6a33..3e92cd3 100644
--- a/clang/utils/perf-training/perf-helper.py
+++ b/clang/utils/perf-training/perf-helper.py
@@ -30,26 +30,28 @@ def findFilesWithExtension(path, extension):
 
 
 def clean(args):
-    if len(args) != 2:
+    if len(args) < 2:
         print(
-            "Usage: %s clean <path> <extension>\n" % __file__
+            "Usage: %s clean <paths> <extension>\n" % __file__
             + "\tRemoves all files with extension from <path>."
         )
         return 1
-    for filename in findFilesWithExtension(args[0], args[1]):
-        os.remove(filename)
+    for path in args[1:-1]:
+        for filename in findFilesWithExtension(path, args[-1]):
+            os.remove(filename)
     return 0
 
 
 def merge(args):
-    if len(args) != 3:
+    if len(args) < 3:
         print(
-            "Usage: %s merge <llvm-profdata> <output> <path>\n" % __file__
+            "Usage: %s merge <llvm-profdata> <output> <paths>\n" % __file__
             + "\tMerges all profraw files from path into output."
         )
         return 1
     cmd = [args[0], "merge", "-o", args[1]]
-    cmd.extend(findFilesWithExtension(args[2], "profraw"))
+    for path in args[2:]:
+        cmd.extend(findFilesWithExtension(path, "profraw"))
     subprocess.check_call(cmd)
     return 0