[clang] [CMake][PGO] Use check-clang target to generate profdata for PGO builds (PR #77347)

[Tom Stellard via cfe-commits]

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

>From 127e2ae83f33843cfb9c5cca314afa2fc9844239 Mon Sep 17 00:00:00 2001
From: Tom Stellard <tstellar at redhat.com>
Date: Sat, 6 Jan 2024 07:46:01 +0000
Subject: [PATCH 1/2] [CMake][PGO] Use check-clang target to generate profdata
 for PGO builds

When doing a multi-stage PGO build of clang, run the check-clang and
check-llvm targets using the instrumented clang and use that profile
data for building the final stage2 clang.  This is what is recommended
by our official documentation: https://llvm.org/docs/HowToBuildWithPGO.html#building-clang-with-pgo

I benchmarked this change by compiling the SemaChecking.cpp file from
clang.  Using check-clang/check-llvm to generate the profile data gives a 25% speedup
in the PGO+LTO stage2 clang when compared to the stage1 clang (no-LTO).

Prior to this change, I was only seeing ~5% speedup when comparing the
stage2 and stage1 builds.
---
 clang/utils/perf-training/CMakeLists.txt |  6 +++---
 clang/utils/perf-training/perf-helper.py | 16 +++++++++-------
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/clang/utils/perf-training/CMakeLists.txt b/clang/utils/perf-training/CMakeLists.txt
index c6d51863fb1b5c..95ff8115aa538b 100644
--- a/clang/utils/perf-training/CMakeLists.txt
+++ b/clang/utils/perf-training/CMakeLists.txt
@@ -15,7 +15,7 @@ if(LLVM_BUILD_INSTRUMENTED)
     )
 
   add_custom_target(clear-profraw
-    COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} profraw
+    COMMAND "${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 +26,9 @@ 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)
+      DEPENDS generate-profraw check-clang check-llvm)
   endif()
 endif()
 
diff --git a/clang/utils/perf-training/perf-helper.py b/clang/utils/perf-training/perf-helper.py
index 99d6a3333b6ef0..bd8f74c9c2e129 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 i in range(2, len(args)):
+      cmd.extend(findFilesWithExtension(args[i], "profraw"))
     subprocess.check_call(cmd)
     return 0
 

>From 4f7734584af3aa9a18bde17349ceccbef3658c53 Mon Sep 17 00:00:00 2001
From: Tom Stellard <tstellar at redhat.com>
Date: Mon, 8 Jan 2024 18:07:31 +0000
Subject: [PATCH 2/2] Fix python formatting

---
 clang/utils/perf-training/perf-helper.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/clang/utils/perf-training/perf-helper.py b/clang/utils/perf-training/perf-helper.py
index bd8f74c9c2e129..844aa274f049aa 100644
--- a/clang/utils/perf-training/perf-helper.py
+++ b/clang/utils/perf-training/perf-helper.py
@@ -37,8 +37,8 @@ def clean(args):
         )
         return 1
     for path in args[1:-1]:
-       for filename in findFilesWithExtension(path, args[-1]):
-           os.remove(filename)
+        for filename in findFilesWithExtension(path, args[-1]):
+            os.remove(filename)
     return 0
 
 
@@ -51,7 +51,7 @@ def merge(args):
         return 1
     cmd = [args[0], "merge", "-o", args[1]]
     for i in range(2, len(args)):
-      cmd.extend(findFilesWithExtension(args[i], "profraw"))
+        cmd.extend(findFilesWithExtension(args[i], "profraw"))
     subprocess.check_call(cmd)
     return 0