mirror of
https://github.com/slsdetectorgroup/aare.git
synced 2026-10-29 03:11:29 +01:00
Erik Fröjdh
b40727ebdc
pybind11_add_module links pybind11::lto, which adds full -flto to the extension and ignores the target's INTERPROCEDURAL_OPTIMIZATION property. That link ran single-threaded for 19-22 s and was the longest step of the build. LTO cannot reach aare_core (a plain static library) and the hot loops are header templates compiled at -O3 inside the extension anyway. Pass NO_EXTRAS so the standard CMake property decides (off by default), and re-add the extras pybind11 would have applied: pybind11_strip for optimized builds and pybind11::windows_extras (/bigobj, /MP) on MSVC. set_property(TARGET _aare PROPERTY INTERPROCEDURAL_OPTIMIZATION ON) or -DCMAKE_INTERPROCEDURAL_OPTIMIZATION=ON brings LTO back as ThinLTO. Measured on a clean Release build with tests: 42 s -> 28 s, extension link 19 s -> 0.1 s, exports identical, all tests pass. The stripped binary grows from 4.7 MB to 5.6 MB. Pedestal, eta and the aare_core code paths (fits, calibration, decoding) run at the same speed; the ClusterFinder micro-benchmark is consistently 1-2 % slower without LTO.
114 lines
3.4 KiB
CMake
114 lines
3.4 KiB
CMake
# SPDX-License-Identifier: MPL-2.0
|
|
|
|
find_package(
|
|
Python 3.10
|
|
COMPONENTS Interpreter Development.Module
|
|
REQUIRED)
|
|
set(PYBIND11_FINDPYTHON ON) # Needed for RH8
|
|
|
|
# Download or find pybind11 depending on configuration
|
|
if(AARE_FETCH_PYBIND11)
|
|
FetchContent_Declare(
|
|
pybind11
|
|
GIT_REPOSITORY https://github.com/pybind/pybind11
|
|
GIT_TAG v3.0.3
|
|
GIT_SHALLOW TRUE)
|
|
FetchContent_MakeAvailable(pybind11)
|
|
else()
|
|
find_package(pybind11 3.0.3 REQUIRED)
|
|
endif()
|
|
|
|
# The compiled python extension: one translation unit per binding area so they
|
|
# compile in parallel; see src/module.cpp for the registration order.
|
|
#
|
|
# Without NO_EXTRAS pybind11 links pybind11::lto, which forces full LTO on the
|
|
# extension regardless of the target's INTERPROCEDURAL_OPTIMIZATION property.
|
|
# LTO cannot reach aare_core (a plain static library) and the templated hot
|
|
# paths are already compiled at -O3 inside the extension, so it only adds a long
|
|
# single-threaded link step. With NO_EXTRAS the standard target property decides
|
|
# (off by default); the other extras are re-added below.
|
|
pybind11_add_module(
|
|
_aare # name of the module
|
|
NO_EXTRAS
|
|
src/module.cpp
|
|
src/bind_io.cpp
|
|
src/bind_hist.cpp
|
|
src/bind_pedestal.cpp
|
|
src/bind_fit.cpp
|
|
src/bind_eta.cpp
|
|
src/bind_cluster_2x2.cpp
|
|
src/bind_cluster_3x3.cpp
|
|
src/bind_cluster_5x5.cpp
|
|
src/bind_cluster_7x7.cpp
|
|
src/bind_cluster_9x9.cpp)
|
|
|
|
set_target_properties(_aare PROPERTIES LIBRARY_OUTPUT_DIRECTORY
|
|
${CMAKE_BINARY_DIR})
|
|
target_link_libraries(_aare PRIVATE aare_core aare_compiler_flags)
|
|
|
|
# The pybind11_add_module extras that NO_EXTRAS skipped, LTO excepted
|
|
if(MSVC)
|
|
target_link_libraries(_aare PRIVATE pybind11::windows_extras) # /bigobj, /MP
|
|
elseif(CMAKE_BUILD_TYPE)
|
|
string(TOUPPER "${CMAKE_BUILD_TYPE}" _aare_build_type)
|
|
if(NOT _aare_build_type MATCHES "DEBUG|RELWITHDEBINFO|NONE")
|
|
pybind11_strip(_aare) # strip symbols from optimized builds
|
|
endif()
|
|
endif()
|
|
|
|
target_include_directories(
|
|
_aare SYSTEM
|
|
PRIVATE $<TARGET_PROPERTY:aare::Minuit2,INTERFACE_INCLUDE_DIRECTORIES>)
|
|
|
|
# List of python files to be copied to the build directory
|
|
set(PYTHON_FILES
|
|
aare/__init__.py
|
|
aare/_version.py
|
|
aare/CtbRawFile.py
|
|
aare/ClusterFinder.py
|
|
aare/ClusterVector.py
|
|
aare/Cluster.py
|
|
aare/FastPedestal.py
|
|
aare/Pedestal.py
|
|
aare/calibration.py
|
|
aare/factory.py
|
|
aare/experimental.py
|
|
aare/RawFile.py
|
|
aare/transform.py
|
|
aare/ScanParameters.py
|
|
aare/utils.py)
|
|
|
|
# Copy the python files to the build directory
|
|
foreach(FILE ${PYTHON_FILES})
|
|
configure_file(${FILE} ${CMAKE_BINARY_DIR}/${FILE})
|
|
endforeach(FILE ${PYTHON_FILES})
|
|
|
|
set_target_properties(_aare PROPERTIES LIBRARY_OUTPUT_DIRECTORY
|
|
${CMAKE_BINARY_DIR}/aare)
|
|
|
|
set(PYTHON_EXAMPLES examples/play.py examples/fits.py)
|
|
|
|
# Copy the python examples to the build directory
|
|
foreach(FILE ${PYTHON_EXAMPLES})
|
|
configure_file(${FILE} ${CMAKE_BINARY_DIR}/${FILE})
|
|
message(STATUS "Copying ${FILE} to ${CMAKE_BINARY_DIR}/${FILE}")
|
|
endforeach(FILE ${PYTHON_EXAMPLES})
|
|
|
|
configure_file(${CMAKE_CURRENT_SOURCE_DIR}/../VERSION
|
|
${CMAKE_BINARY_DIR}/aare/VERSION)
|
|
if(AARE_INSTALL_PYTHONEXT)
|
|
install(
|
|
TARGETS _aare
|
|
EXPORT "${TARGETS_EXPORT_NAME}"
|
|
LIBRARY DESTINATION aare COMPONENT python)
|
|
|
|
install(
|
|
FILES ${PYTHON_FILES}
|
|
DESTINATION aare
|
|
COMPONENT python)
|
|
install(
|
|
FILES ../VERSION
|
|
DESTINATION aare
|
|
COMPONENT python)
|
|
endif()
|