[Clang][CMake] Add CSSPGO support to LLVM_BUILD_INSTRUMENTED

Build on Clang-BOLT infrastructure to collect sample profiles for CSSPGO.
Add clang/cmake/caches/CSSPGO.cmake to automate CSSPGO Clang build.

Differential Revision: https://reviews.llvm.org/D155419

Author: aaupov

clang/CMakeLists.txt

@@ -744,11 +744,21 @@ if (CLANG_ENABLE_BOOTSTRAP)
   if(BOOTSTRAP_LLVM_BUILD_INSTRUMENTED)
     add_dependencies(clang-bootstrap-deps llvm-profdata)
     set(PGO_OPT -DLLVM_PROFDATA=${LLVM_RUNTIME_OUTPUT_INTDIR}/llvm-profdata)
+    string(TOUPPER "${BOOTSTRAP_LLVM_BUILD_INSTRUMENTED}" BOOTSTRAP_LLVM_BUILD_INSTRUMENTED)
+    if (BOOTSTRAP_LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO")
+      add_dependencies(clang-bootstrap-deps llvm-profgen)
+      list(APPEND PGO_OPT -DLLVM_PROFGEN=${LLVM_RUNTIME_OUTPUT_INTDIR}/llvm-profgen)
+    endif()
   endif()
 
   if(LLVM_BUILD_INSTRUMENTED)
+    string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" LLVM_BUILD_INSTRUMENTED)
     add_dependencies(clang-bootstrap-deps generate-profdata)
-    set(PGO_OPT -DLLVM_PROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata)
+    if (LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO")
+      set(PGO_OPT -DLLVM_SPROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata)
+    else()
+      set(PGO_OPT -DLLVM_PROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata)
+    endif()
     # Use the current tools for LTO instead of the instrumented ones
     list(APPEND _BOOTSTRAP_DEFAULT_PASSTHROUGH
       CMAKE_CXX_COMPILER

clang/cmake/caches/CSSPGO.cmake

@@ -0,0 +1,3 @@
+set(CMAKE_BUILD_TYPE RelWithDebInfo CACHE STRING "")
+set(BOOTSTRAP_LLVM_BUILD_INSTRUMENTED "CSSPGO" CACHE STRING "")
+include(${CMAKE_CURRENT_LIST_DIR}/PGO.cmake)

clang/utils/perf-training/CMakeLists.txt

@@ -20,6 +20,7 @@ if(LLVM_BUILD_INSTRUMENTED)
 
   add_custom_target(clear-profraw
     COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_BINARY_DIR}/profiles/ profraw
+    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} perf.data
     COMMENT "Clearing old profraw data")
 
   if(NOT LLVM_PROFDATA)
@@ -29,6 +30,10 @@ if(LLVM_BUILD_INSTRUMENTED)
   if(NOT LLVM_PROFDATA)
     message(STATUS "To enable merging PGO data LLVM_PROFDATA has to point to llvm-profdata")
   else()
+    string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" LLVM_BUILD_INSTRUMENTED)
+    if (LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO")
+      set(PROFDATA_SAMPLE "--sample")
+    endif()
     add_custom_command(
       OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata
       # generate-profraw is a custom_target which are always considered stale.
@@ -39,7 +44,7 @@ if(LLVM_BUILD_INSTRUMENTED)
       # Therefor we call the generate-profraw target manually as part of this custom
       # command, which will only run if clang or ${CLANG_PGO_TRAINING_DEPS} are updated.
       COMMAND ${CMAKE_COMMAND} --build ${CMAKE_BINARY_DIR} --target generate-profraw
-      COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge ${LLVM_PROFDATA} ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_BINARY_DIR}/profiles/
+      COMMAND "${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/ ${PROFDATA_SAMPLE}
       COMMENT "Merging profdata"
       DEPENDS clang ${CLANG_PGO_TRAINING_DEPS}
     )
@@ -49,6 +54,25 @@ if(LLVM_BUILD_INSTRUMENTED)
               USE_TOOLCHAIN EXLUDE_FROM_ALL NO_INSTALL DEPENDS generate-profraw)
       add_dependencies(generate-profdata generate-profraw-external)
     endif()
+    if (LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO")
+      if(NOT LLVM_PROFGEN)
+        find_program(LLVM_PROFGEN llvm-profgen)
+      endif()
+
+      if(NOT LLVM_PROFGEN)
+        message(STATUS "To enable converting CSSPGO samples LLVM_PROFGEN has to point to llvm-profgen")
+      endif()
+
+      # Convert perf profiles into profraw
+      add_custom_target(convert-perf-profraw
+        COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py perf2prof ${LLVM_PROFGEN} $<TARGET_FILE:clang> ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_BINARY_DIR}/profiles/
+        COMMENT "Converting perf profiles into profraw"
+        DEPENDS generate-profraw)
+      if (CLANG_PGO_TRAINING_DATA_SOURCE_DIR)
+        add_dependencies(convert-perf-profraw generate-profraw-external)
+      endif()
+      add_dependencies(generate-profdata convert-perf-profraw)
+    endif()
   endif()
 endif()
 

clang/utils/perf-training/lit.cfg

@@ -28,6 +28,12 @@ config.name = 'Clang Perf Training'
 config.suffixes = ['.c', '.cc', '.cpp', '.m', '.mm', '.cu', '.ll', '.cl', '.s', '.S', '.modulemap', '.test']
 
 cc1_wrapper = '%s %s/perf-helper.py cc1' % (config.python_exe, config.perf_helper_dir)
+if config.llvm_build_instrumented.upper() == "CSSPGO":
+    perf_wrapper = "%s %s/perf-helper.py perf --lbr --call-graph --event=br_inst_retired.near_taken:uppp -- " % (
+        config.python_exe,
+        config.perf_helper_dir,
+    )
+    cc1_wrapper = perf_wrapper
 
 use_lit_shell = os.environ.get("LIT_USE_INTERNAL_SHELL")
 config.test_format = lit.formats.ShTest(use_lit_shell == "0")

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

@@ -8,6 +8,7 @@ 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.llvm_build_instrumented = "@LLVM_BUILD_INSTRUMENTED@"
 
 # Let the main config do the real work.
 lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/lit.cfg")

clang/utils/perf-training/perf-helper.py

@@ -43,14 +43,22 @@ def clean(args):
 
 
 def merge(args):
-    if len(args) < 3:
-        print(
-            "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]]
-    for path in args[2:]:
+    parser = argparse.ArgumentParser(
+        prog="perf-helper merge",
+        description="Merges all profraw files from path(s) into output",
+    )
+    parser.add_argument("profdata", help="Path to llvm-profdata tool")
+    parser.add_argument("output", help="Output filename")
+    parser.add_argument(
+        "paths", nargs="+", help="Folder(s) containing input profraw files"
+    )
+    parser.add_argument("--sample", action="store_true", help="Sample profile")
+    opts = parser.parse_args(args)
+
+    cmd = [opts.profdata, "merge", "-o", opts.output]
+    if opts.sample:
+        cmd += ["--sample"]
+    for path in opts.paths:
         cmd.extend(findFilesWithExtension(path, "profraw"))
     subprocess.check_call(cmd)
     return 0
@@ -71,11 +79,16 @@ def merge_fdata(args):
 
 def perf(args):
     parser = argparse.ArgumentParser(
-        prog="perf-helper perf", description="perf wrapper for BOLT profile collection"
+        prog="perf-helper perf",
+        description="perf wrapper for BOLT/CSSPGO profile collection",
     )
     parser.add_argument(
         "--lbr", action="store_true", help="Use perf with branch stacks"
     )
+    parser.add_argument("--call-graph", action="store_true", help="Collect call graph")
+    parser.add_argument(
+        "--event", help="PMU event name, defaults to cycles:u", default="cycles:u"
+    )
     parser.add_argument("cmd", nargs=argparse.REMAINDER, help="")
 
     opts = parser.parse_args(args)
@@ -84,12 +97,14 @@ def perf(args):
     perf_args = [
         "perf",
         "record",
-        "--event=cycles:u",
+        f"--event={opts.event}",
         "--freq=max",
         "--output=%d.perf.data" % os.getpid(),
     ]
     if opts.lbr:
         perf_args += ["--branch-filter=any,u"]
+    if opts.call_graph:
+        perf_args += ["-g", "--call-graph=fp"]
     perf_args.extend(cmd)
 
     start_time = time.time()
@@ -125,6 +140,26 @@ def perf2bolt(args):
     return 0
 
 
+def perf2prof(args):
+    parser = argparse.ArgumentParser(
+        prog="perf-helper perf2prof",
+        description="perf to CSSPGO prof conversion wrapper",
+    )
+    parser.add_argument("profgen", help="Path to llvm-profgen binary")
+    parser.add_argument("binary", help="Input binary")
+    parser.add_argument("paths", nargs="+", help="Path containing perf.data files")
+    opts = parser.parse_args(args)
+
+    profgen_args = [opts.profgen, f"--binary={opts.binary}"]
+    for path in opts.paths:
+        for filename in findFilesWithExtension(path, "perf.data"):
+            subprocess.check_call(
+                profgen_args
+                + [f"--perfdata={filename}", f"--output={filename}.profraw"]
+            )
+    return 0
+
+
 def dtrace(args):
     parser = argparse.ArgumentParser(
         prog="perf-helper dtrace",
@@ -567,6 +602,7 @@ def genOrderFile(args):
     "merge-fdata": merge_fdata,
     "perf": perf,
     "perf2bolt": perf2bolt,
+    "perf2prof": perf2prof,
 }
 
 

llvm/CMakeLists.txt

@@ -948,6 +948,9 @@ set(LLVM_ENABLE_PER_TARGET_RUNTIME_DIR ${LLVM_ENABLE_PER_TARGET_RUNTIME_DIR_defa
 set(LLVM_PROFDATA_FILE "" CACHE FILEPATH
   "Profiling data file to use when compiling in order to improve runtime performance.")
 
+set(LLVM_SPROFDATA_FILE "" CACHE FILEPATH
+  "Sampling profiling data file to use when compiling in order to improve runtime performance.")
+
 if(LLVM_INCLUDE_TESTS)
   # All LLVM Python files should be compatible down to this minimum version.
   set(LLVM_MINIMUM_PYTHON_VERSION 3.8)

llvm/cmake/modules/HandleLLVMOptions.cmake

@@ -1134,7 +1134,7 @@ endif()
 option(LLVM_ENABLE_IR_PGO "Build LLVM and tools with IR PGO instrumentation (deprecated)" Off)
 mark_as_advanced(LLVM_ENABLE_IR_PGO)
 
-set(LLVM_BUILD_INSTRUMENTED OFF CACHE STRING "Build LLVM and tools with PGO instrumentation. May be specified as IR or Frontend")
+set(LLVM_BUILD_INSTRUMENTED OFF CACHE STRING "Build LLVM and tools with PGO instrumentation. May be specified as IR, Frontend, CSIR, CSSPGO")
 set(LLVM_VP_COUNTERS_PER_SITE "1.5" CACHE STRING "Value profile counters to use per site for IR PGO with Clang")
 mark_as_advanced(LLVM_BUILD_INSTRUMENTED LLVM_VP_COUNTERS_PER_SITE)
 string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" uppercase_LLVM_BUILD_INSTRUMENTED)
@@ -1167,6 +1167,15 @@ if (LLVM_BUILD_INSTRUMENTED)
         CMAKE_EXE_LINKER_FLAGS
         CMAKE_SHARED_LINKER_FLAGS)
     endif()
+  elseif(uppercase_LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO")
+    append("-fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -fno-optimize-sibling-calls -fpseudo-probe-for-profiling"
+      CMAKE_CXX_FLAGS
+      CMAKE_C_FLAGS)
+    if(NOT LINKER_IS_LLD_LINK)
+      append("-fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -fno-optimize-sibling-calls -fpseudo-probe-for-profiling"
+        CMAKE_EXE_LINKER_FLAGS
+        CMAKE_SHARED_LINKER_FLAGS)
+    endif()
   else()
     append("-fprofile-instr-generate=\"${LLVM_PROFILE_FILE_PATTERN}\""
       CMAKE_CXX_FLAGS
@@ -1217,6 +1226,21 @@ if(LLVM_PROFDATA_FILE AND EXISTS ${LLVM_PROFDATA_FILE})
   endif()
 endif()
 
+if(LLVM_SPROFDATA_FILE AND EXISTS ${LLVM_SPROFDATA_FILE})
+  if ("${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang" )
+    append("-fpseudo-probe-for-profiling -fprofile-sample-use=\"${LLVM_SPROFDATA_FILE}\""
+      CMAKE_CXX_FLAGS
+      CMAKE_C_FLAGS)
+    if(NOT LINKER_IS_LLD_LINK)
+      append("-fpseudo-probe-for-profiling -fprofile-sample-use=\"${LLVM_SPROFDATA_FILE}\""
+        CMAKE_EXE_LINKER_FLAGS
+        CMAKE_SHARED_LINKER_FLAGS)
+    endif()
+  else()
+    message(FATAL_ERROR "LLVM_SPROFDATA_FILE can only be specified when compiling with clang")
+  endif()
+endif()
+
 option(LLVM_BUILD_INSTRUMENTED_COVERAGE "Build LLVM and tools with Code Coverage instrumentation" Off)
 option(LLVM_INDIVIDUAL_TEST_COVERAGE "Emit individual coverage file for each test case." OFF)
 mark_as_advanced(LLVM_BUILD_INSTRUMENTED_COVERAGE)