[llvm] [clang] [CMake][PGO] Add option for using an external project to generate profile data (PR #78879)
Tom Stellard via cfe-commits
cfe-commits at lists.llvm.org
Sat Jan 20 21:51:35 PST 2024
https://github.com/tstellar created https://github.com/llvm/llvm-project/pull/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_PERF_TRAINING_DEPS=runtimes
>From 0719f49ecc6dd69ae4698c3e84dbf175a1bf2ed3 Mon Sep 17 00:00:00 2001
From: Tom Stellard <tstellar at redhat.com>
Date: Sun, 21 Jan 2024 00:25:47 +0000
Subject: [PATCH 1/2] [CMake][PGO] Add libunwind to list of stage1 runtimes
This fixes the build since 8f90e6937a1fac80873bb2dab5f382c82ba1ba4e
which made libcxxabi use llvm's libunwind by default.
---
clang/cmake/caches/PGO.cmake | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/clang/cmake/caches/PGO.cmake b/clang/cmake/caches/PGO.cmake
index e1d0585e453f825..15bc755d110d19a 100644
--- a/clang/cmake/caches/PGO.cmake
+++ b/clang/cmake/caches/PGO.cmake
@@ -2,7 +2,7 @@ set(CMAKE_BUILD_TYPE RELEASE CACHE STRING "")
set(CLANG_ENABLE_BOOTSTRAP ON CACHE BOOL "")
set(LLVM_ENABLE_PROJECTS "clang;lld" CACHE STRING "")
-set(LLVM_ENABLE_RUNTIMES "compiler-rt;libcxx;libcxxabi" CACHE STRING "")
+set(LLVM_ENABLE_RUNTIMES "compiler-rt;libcxx;libcxxabi;libunwind" CACHE STRING "")
set(LLVM_TARGETS_TO_BUILD Native CACHE STRING "")
set(BOOTSTRAP_LLVM_BUILD_INSTRUMENTED ON CACHE BOOL "")
>From 5c602233ef4e54e850f6c8a17c25968bc706b898 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 2/2] [CMake][PGO] Add option for using an external project to
generate profile data.
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_PERF_TRAINING_DEPS=runtimes
---
clang/utils/perf-training/CMakeLists.txt | 13 +++++++++++--
clang/utils/perf-training/perf-helper.py | 16 +++++++++-------
llvm/docs/AdvancedBuilds.rst | 23 +++++++++++++++++++++++
3 files changed, 43 insertions(+), 9 deletions(-)
diff --git a/clang/utils/perf-training/CMakeLists.txt b/clang/utils/perf-training/CMakeLists.txt
index c6d51863fb1b5c2..f9d673b2e92e775 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 "${CMAKE_CURRENT_SOURCE_DIR}" CACHE PATH
"The path to a lit testsuite containing samples for PGO and order file generation"
)
+set(CLANG_PGO_TRAINING_DATA_SOURCE_DIR OFF CACHE STRING "Path to source directory containing cmake project with source files to use for generating pgo data")
+set(CLANG_PERF_TRAINING_DEPS "" CACHE STRING "Extra dependencies needed to build the PGO training data.")
if(LLVM_BUILD_INSTRUMENTED)
configure_lit_site_cfg(
@@ -15,7 +19,7 @@ if(LLVM_BUILD_INSTRUMENTED)
)
add_custom_target(clear-profraw
- COMMAND "${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} ${CMAKE_BINARY_DIR}/profiles/ profraw
COMMENT "Clearing old profraw data")
if(NOT LLVM_PROFDATA)
@@ -26,9 +30,14 @@ if(LLVM_BUILD_INSTRUMENTED)
message(STATUS "To enable merging PGO data LLVM_PROFDATA has to point to llvm-profdata")
else()
add_custom_target(generate-profdata
- COMMAND "${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 99d6a3333b6ef08..844aa274f049aaa 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
diff --git a/llvm/docs/AdvancedBuilds.rst b/llvm/docs/AdvancedBuilds.rst
index 960b19fa5317f3b..3ff630a1425691d 100644
--- a/llvm/docs/AdvancedBuilds.rst
+++ b/llvm/docs/AdvancedBuilds.rst
@@ -145,6 +145,29 @@ that also enables ThinTLO, use the following command:
-DPGO_INSTRUMENT_LTO=Thin \
<path to source>/llvm
+By default, clang will generate profile data by compiling a simple
+hello world program. You can also tell clang use an external
+project for generating profile data that may be a better fit for your
+use case. The project you specify must either be a lit test suite
+(use the CLANG_PGO_TRAINING_DATA option) or a CMake project (use the
+CLANG_PERF_TRAINING_DATA_SOURCE_DIR option).
+
+For example, If you wanted to use the
+`LLVM Test Suite <https://github.com/llvm/llvm-test-suite/>`_ to generate
+profile data you would use the following command:
+
+.. code-block:: console
+
+ $ cmake -G Ninja -C <path to source>/clang/cmake/caches/PGO.cmake \
+ -DBOOTSTRAP_CLANG_PGO_TRAINING_DATA_SOURCE_DIR=<path to llvm-test-suite> \
+ -DBOOTSTRAP_CLANG_PERF_TRAINING_DEPS=runtimes
+
+The BOOTSTRAP\_ prefixes tells CMake to pass the variables on to the instrumented
+stage two build. And the CLANG_PERF_TRAINING_DEPS option let's you specify
+additional build targets to build before building the external project. The
+LLVM Test Suite requires compiler-rt to build, so we need to add the
+`runtimes` target as a dependency.
+
After configuration, building the stage2-instrumented-generate-profdata target
will automatically build the stage1 compiler, build the instrumented compiler
with the stage1 compiler, and then run the instrumented compiler against the
More information about the cfe-commits
mailing list