LightGBM/CMakeLists.txt

142 строки
4.0 KiB
CMake
Исходник Обычный вид История

2016-08-05 09:06:01 +03:00
cmake_minimum_required(VERSION 2.8)
if(APPLE)
SET(CMAKE_CXX_COMPILER "g++-6")
SET(CMAKE_C_COMPILER "gcc-6")
endif()
PROJECT(lightgbm)
2016-08-05 09:06:01 +03:00
OPTION(USE_MPI "MPI based parallel learning" OFF)
OPTION(USE_OPENMP "Enable OpenMP" ON)
Initial GPU acceleration support for LightGBM (#368) * add dummy gpu solver code * initial GPU code * fix crash bug * first working version * use asynchronous copy * use a better kernel for root * parallel read histogram * sparse features now works, but no acceleration, compute on CPU * compute sparse feature on CPU simultaneously * fix big bug; add gpu selection; add kernel selection * better debugging * clean up * add feature scatter * Add sparse_threshold control * fix a bug in feature scatter * clean up debug * temporarily add OpenCL kernels for k=64,256 * fix up CMakeList and definition USE_GPU * add OpenCL kernels as string literals * Add boost.compute as a submodule * add boost dependency into CMakeList * fix opencl pragma * use pinned memory for histogram * use pinned buffer for gradients and hessians * better debugging message * add double precision support on GPU * fix boost version in CMakeList * Add a README * reconstruct GPU initialization code for ResetTrainingData * move data to GPU in parallel * fix a bug during feature copy * update gpu kernels * update gpu code * initial port to LightGBM v2 * speedup GPU data loading process * Add 4-bit bin support to GPU * re-add sparse_threshold parameter * remove kMaxNumWorkgroups and allows an unlimited number of features * add feature mask support for skipping unused features * enable kernel cache * use GPU kernels withoug feature masks when all features are used * REAdme. * REAdme. * update README * fix typos (#349) * change compile to gcc on Apple as default * clean vscode related file * refine api of constructing from sampling data. * fix bug in the last commit. * more efficient algorithm to sample k from n. * fix bug in filter bin * change to boost from average output. * fix tests. * only stop training when all classes are finshed in multi-class. * limit the max tree output. change hessian in multi-class objective. * robust tree model loading. * fix test. * convert the probabilities to raw score in boost_from_average of classification. * fix the average label for binary classification. * Add boost_from_average to docs (#354) * don't use "ConvertToRawScore" for self-defined objective function. * boost_from_average seems doesn't work well in binary classification. remove it. * For a better jump link (#355) * Update Python-API.md * for a better jump in page A space is needed between `#` and the headers content according to Github's markdown format [guideline](https://guides.github.com/features/mastering-markdown/) After adding the spaces, we can jump to the exact position in page by click the link. * fixed something mentioned by @wxchan * Update Python-API.md * add FitByExistingTree. * adapt GPU tree learner for FitByExistingTree * avoid NaN output. * update boost.compute * fix typos (#361) * fix broken links (#359) * update README * disable GPU acceleration by default * fix image url * cleanup debug macro * remove old README * do not save sparse_threshold_ in FeatureGroup * add details for new GPU settings * ignore submodule when doing pep8 check * allocate workspace for at least one thread during builing Feature4 * move sparse_threshold to class Dataset * remove duplicated code in GPUTreeLearner::Split * Remove duplicated code in FindBestThresholds and BeforeFindBestSplit * do not rebuild ordered gradients and hessians for sparse features * support feature groups in GPUTreeLearner * Initial parallel learners with GPU support * add option device, cleanup code * clean up FindBestThresholds; add some omp parallel * constant hessian optimization for GPU * Fix GPUTreeLearner crash when there is zero feature * use np.testing.assert_almost_equal() to compare lists of floats in tests * travis for GPU
2017-04-09 16:53:14 +03:00
OPTION(USE_GPU "Enable GPU-acclerated training (EXPERIMENTAL)" OFF)
if(APPLE)
OPTION(APPLE_OUTPUT_DYLIB "Output dylib shared library" OFF)
endif()
2016-08-05 09:06:01 +03:00
if(USE_MPI)
2016-12-07 06:31:31 +03:00
find_package(MPI REQUIRED)
ADD_DEFINITIONS(-DUSE_MPI)
MESSAGE(${MPI_LIBRARIES})
MESSAGE(${MPI_CXX_LIBRARIES})
2016-08-05 09:06:01 +03:00
else()
2016-12-07 06:31:31 +03:00
ADD_DEFINITIONS(-DUSE_SOCKET)
2016-12-07 06:45:55 +03:00
endif(USE_MPI)
2016-08-05 09:06:01 +03:00
if(USE_OPENMP)
find_package(OpenMP REQUIRED)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
else()
# Ignore unknown #pragma warning
if( (CMAKE_CXX_COMPILER_ID MATCHES "[cC][lL][aA][nN][gG]")
OR (CMAKE_CXX_COMPILER_ID MATCHES "[gG][nN][uU]"))
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-unknown-pragmas")
endif()
endif(USE_OPENMP)
2016-12-07 06:31:31 +03:00
Initial GPU acceleration support for LightGBM (#368) * add dummy gpu solver code * initial GPU code * fix crash bug * first working version * use asynchronous copy * use a better kernel for root * parallel read histogram * sparse features now works, but no acceleration, compute on CPU * compute sparse feature on CPU simultaneously * fix big bug; add gpu selection; add kernel selection * better debugging * clean up * add feature scatter * Add sparse_threshold control * fix a bug in feature scatter * clean up debug * temporarily add OpenCL kernels for k=64,256 * fix up CMakeList and definition USE_GPU * add OpenCL kernels as string literals * Add boost.compute as a submodule * add boost dependency into CMakeList * fix opencl pragma * use pinned memory for histogram * use pinned buffer for gradients and hessians * better debugging message * add double precision support on GPU * fix boost version in CMakeList * Add a README * reconstruct GPU initialization code for ResetTrainingData * move data to GPU in parallel * fix a bug during feature copy * update gpu kernels * update gpu code * initial port to LightGBM v2 * speedup GPU data loading process * Add 4-bit bin support to GPU * re-add sparse_threshold parameter * remove kMaxNumWorkgroups and allows an unlimited number of features * add feature mask support for skipping unused features * enable kernel cache * use GPU kernels withoug feature masks when all features are used * REAdme. * REAdme. * update README * fix typos (#349) * change compile to gcc on Apple as default * clean vscode related file * refine api of constructing from sampling data. * fix bug in the last commit. * more efficient algorithm to sample k from n. * fix bug in filter bin * change to boost from average output. * fix tests. * only stop training when all classes are finshed in multi-class. * limit the max tree output. change hessian in multi-class objective. * robust tree model loading. * fix test. * convert the probabilities to raw score in boost_from_average of classification. * fix the average label for binary classification. * Add boost_from_average to docs (#354) * don't use "ConvertToRawScore" for self-defined objective function. * boost_from_average seems doesn't work well in binary classification. remove it. * For a better jump link (#355) * Update Python-API.md * for a better jump in page A space is needed between `#` and the headers content according to Github's markdown format [guideline](https://guides.github.com/features/mastering-markdown/) After adding the spaces, we can jump to the exact position in page by click the link. * fixed something mentioned by @wxchan * Update Python-API.md * add FitByExistingTree. * adapt GPU tree learner for FitByExistingTree * avoid NaN output. * update boost.compute * fix typos (#361) * fix broken links (#359) * update README * disable GPU acceleration by default * fix image url * cleanup debug macro * remove old README * do not save sparse_threshold_ in FeatureGroup * add details for new GPU settings * ignore submodule when doing pep8 check * allocate workspace for at least one thread during builing Feature4 * move sparse_threshold to class Dataset * remove duplicated code in GPUTreeLearner::Split * Remove duplicated code in FindBestThresholds and BeforeFindBestSplit * do not rebuild ordered gradients and hessians for sparse features * support feature groups in GPUTreeLearner * Initial parallel learners with GPU support * add option device, cleanup code * clean up FindBestThresholds; add some omp parallel * constant hessian optimization for GPU * Fix GPUTreeLearner crash when there is zero feature * use np.testing.assert_almost_equal() to compare lists of floats in tests * travis for GPU
2017-04-09 16:53:14 +03:00
if(USE_GPU)
SET(BOOST_COMPUTE_HEADER_DIR ${PROJECT_SOURCE_DIR}/compute/include)
include_directories (${BOOST_COMPUTE_HEADER_DIR})
Initial GPU acceleration support for LightGBM (#368) * add dummy gpu solver code * initial GPU code * fix crash bug * first working version * use asynchronous copy * use a better kernel for root * parallel read histogram * sparse features now works, but no acceleration, compute on CPU * compute sparse feature on CPU simultaneously * fix big bug; add gpu selection; add kernel selection * better debugging * clean up * add feature scatter * Add sparse_threshold control * fix a bug in feature scatter * clean up debug * temporarily add OpenCL kernels for k=64,256 * fix up CMakeList and definition USE_GPU * add OpenCL kernels as string literals * Add boost.compute as a submodule * add boost dependency into CMakeList * fix opencl pragma * use pinned memory for histogram * use pinned buffer for gradients and hessians * better debugging message * add double precision support on GPU * fix boost version in CMakeList * Add a README * reconstruct GPU initialization code for ResetTrainingData * move data to GPU in parallel * fix a bug during feature copy * update gpu kernels * update gpu code * initial port to LightGBM v2 * speedup GPU data loading process * Add 4-bit bin support to GPU * re-add sparse_threshold parameter * remove kMaxNumWorkgroups and allows an unlimited number of features * add feature mask support for skipping unused features * enable kernel cache * use GPU kernels withoug feature masks when all features are used * REAdme. * REAdme. * update README * fix typos (#349) * change compile to gcc on Apple as default * clean vscode related file * refine api of constructing from sampling data. * fix bug in the last commit. * more efficient algorithm to sample k from n. * fix bug in filter bin * change to boost from average output. * fix tests. * only stop training when all classes are finshed in multi-class. * limit the max tree output. change hessian in multi-class objective. * robust tree model loading. * fix test. * convert the probabilities to raw score in boost_from_average of classification. * fix the average label for binary classification. * Add boost_from_average to docs (#354) * don't use "ConvertToRawScore" for self-defined objective function. * boost_from_average seems doesn't work well in binary classification. remove it. * For a better jump link (#355) * Update Python-API.md * for a better jump in page A space is needed between `#` and the headers content according to Github's markdown format [guideline](https://guides.github.com/features/mastering-markdown/) After adding the spaces, we can jump to the exact position in page by click the link. * fixed something mentioned by @wxchan * Update Python-API.md * add FitByExistingTree. * adapt GPU tree learner for FitByExistingTree * avoid NaN output. * update boost.compute * fix typos (#361) * fix broken links (#359) * update README * disable GPU acceleration by default * fix image url * cleanup debug macro * remove old README * do not save sparse_threshold_ in FeatureGroup * add details for new GPU settings * ignore submodule when doing pep8 check * allocate workspace for at least one thread during builing Feature4 * move sparse_threshold to class Dataset * remove duplicated code in GPUTreeLearner::Split * Remove duplicated code in FindBestThresholds and BeforeFindBestSplit * do not rebuild ordered gradients and hessians for sparse features * support feature groups in GPUTreeLearner * Initial parallel learners with GPU support * add option device, cleanup code * clean up FindBestThresholds; add some omp parallel * constant hessian optimization for GPU * Fix GPUTreeLearner crash when there is zero feature * use np.testing.assert_almost_equal() to compare lists of floats in tests * travis for GPU
2017-04-09 16:53:14 +03:00
find_package(OpenCL REQUIRED)
include_directories(${OpenCL_INCLUDE_DIRS})
MESSAGE(STATUS "OpenCL include directory:" ${OpenCL_INCLUDE_DIRS})
find_package(Boost 1.56.0 COMPONENTS filesystem system REQUIRED)
include_directories(${Boost_INCLUDE_DIRS})
if (WIN32)
# disable autolinking in boost
ADD_DEFINITIONS(-DBOOST_ALL_NO_LIB)
endif()
Initial GPU acceleration support for LightGBM (#368) * add dummy gpu solver code * initial GPU code * fix crash bug * first working version * use asynchronous copy * use a better kernel for root * parallel read histogram * sparse features now works, but no acceleration, compute on CPU * compute sparse feature on CPU simultaneously * fix big bug; add gpu selection; add kernel selection * better debugging * clean up * add feature scatter * Add sparse_threshold control * fix a bug in feature scatter * clean up debug * temporarily add OpenCL kernels for k=64,256 * fix up CMakeList and definition USE_GPU * add OpenCL kernels as string literals * Add boost.compute as a submodule * add boost dependency into CMakeList * fix opencl pragma * use pinned memory for histogram * use pinned buffer for gradients and hessians * better debugging message * add double precision support on GPU * fix boost version in CMakeList * Add a README * reconstruct GPU initialization code for ResetTrainingData * move data to GPU in parallel * fix a bug during feature copy * update gpu kernels * update gpu code * initial port to LightGBM v2 * speedup GPU data loading process * Add 4-bit bin support to GPU * re-add sparse_threshold parameter * remove kMaxNumWorkgroups and allows an unlimited number of features * add feature mask support for skipping unused features * enable kernel cache * use GPU kernels withoug feature masks when all features are used * REAdme. * REAdme. * update README * fix typos (#349) * change compile to gcc on Apple as default * clean vscode related file * refine api of constructing from sampling data. * fix bug in the last commit. * more efficient algorithm to sample k from n. * fix bug in filter bin * change to boost from average output. * fix tests. * only stop training when all classes are finshed in multi-class. * limit the max tree output. change hessian in multi-class objective. * robust tree model loading. * fix test. * convert the probabilities to raw score in boost_from_average of classification. * fix the average label for binary classification. * Add boost_from_average to docs (#354) * don't use "ConvertToRawScore" for self-defined objective function. * boost_from_average seems doesn't work well in binary classification. remove it. * For a better jump link (#355) * Update Python-API.md * for a better jump in page A space is needed between `#` and the headers content according to Github's markdown format [guideline](https://guides.github.com/features/mastering-markdown/) After adding the spaces, we can jump to the exact position in page by click the link. * fixed something mentioned by @wxchan * Update Python-API.md * add FitByExistingTree. * adapt GPU tree learner for FitByExistingTree * avoid NaN output. * update boost.compute * fix typos (#361) * fix broken links (#359) * update README * disable GPU acceleration by default * fix image url * cleanup debug macro * remove old README * do not save sparse_threshold_ in FeatureGroup * add details for new GPU settings * ignore submodule when doing pep8 check * allocate workspace for at least one thread during builing Feature4 * move sparse_threshold to class Dataset * remove duplicated code in GPUTreeLearner::Split * Remove duplicated code in FindBestThresholds and BeforeFindBestSplit * do not rebuild ordered gradients and hessians for sparse features * support feature groups in GPUTreeLearner * Initial parallel learners with GPU support * add option device, cleanup code * clean up FindBestThresholds; add some omp parallel * constant hessian optimization for GPU * Fix GPUTreeLearner crash when there is zero feature * use np.testing.assert_almost_equal() to compare lists of floats in tests * travis for GPU
2017-04-09 16:53:14 +03:00
ADD_DEFINITIONS(-DUSE_GPU)
endif(USE_GPU)
2016-12-07 06:45:55 +03:00
if(UNIX OR MINGW OR CYGWIN)
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread -O3 -Wall -std=c++11 -Wno-ignored-attributes")
2016-12-07 06:31:31 +03:00
endif()
if(MSVC)
if(MSVC_VERSION LESS 1800)
message(STATUS "The compiler ${CMAKE_CXX_COMPILER} has no C++11 support. Please use a newer msvc.")
endif()
SET(variables
CMAKE_C_FLAGS_DEBUG
CMAKE_C_FLAGS_MINSIZEREL
CMAKE_C_FLAGS_RELEASE
CMAKE_C_FLAGS_RELWITHDEBINFO
CMAKE_CXX_FLAGS_DEBUG
CMAKE_CXX_FLAGS_MINSIZEREL
CMAKE_CXX_FLAGS_RELEASE
CMAKE_CXX_FLAGS_RELWITHDEBINFO
)
foreach(variable ${variables})
if(${variable} MATCHES "/MD")
string(REGEX REPLACE "/MD" "/MT" ${variable} "${${variable}}")
endif()
endforeach()
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /W4 /O2 /Ob2 /Oi /Ot /Oy /GL")
else()
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC")
2016-08-05 09:06:01 +03:00
endif()
SET(LightGBM_HEADER_DIR ${PROJECT_SOURCE_DIR}/include)
2016-12-07 06:31:31 +03:00
2016-08-05 09:06:01 +03:00
SET(EXECUTABLE_OUTPUT_PATH ${PROJECT_SOURCE_DIR})
2016-11-08 16:24:05 +03:00
SET(LIBRARY_OUTPUT_PATH ${PROJECT_SOURCE_DIR})
2016-08-05 09:06:01 +03:00
2016-12-07 06:31:31 +03:00
include_directories (${LightGBM_HEADER_DIR})
if(APPLE)
if (APPLE_OUTPUT_DYLIB)
SET(CMAKE_SHARED_LIBRARY_SUFFIX ".dylib")
else()
SET(CMAKE_SHARED_LIBRARY_SUFFIX ".so")
endif()
2016-12-07 06:31:31 +03:00
endif(APPLE)
if(USE_MPI)
include_directories(${MPI_CXX_INCLUDE_PATH})
2016-12-07 06:45:55 +03:00
endif(USE_MPI)
2016-12-07 06:31:31 +03:00
file(GLOB SOURCES
src/application/*.cpp
src/boosting/*.cpp
src/io/*.cpp
src/metric/*.cpp
src/objective/*.cpp
src/network/*.cpp
src/treelearner/*.cpp
)
add_executable(lightgbm src/main.cpp ${SOURCES})
add_library(_lightgbm SHARED src/c_api.cpp ${SOURCES})
2016-12-07 07:25:42 +03:00
if(MSVC)
set_target_properties(_lightgbm PROPERTIES OUTPUT_NAME "lib_lightgbm")
2016-12-07 07:25:42 +03:00
endif(MSVC)
2016-12-07 06:31:31 +03:00
if(USE_MPI)
TARGET_LINK_LIBRARIES(lightgbm ${MPI_CXX_LIBRARIES})
TARGET_LINK_LIBRARIES(_lightgbm ${MPI_CXX_LIBRARIES})
endif(USE_MPI)
Initial GPU acceleration support for LightGBM (#368) * add dummy gpu solver code * initial GPU code * fix crash bug * first working version * use asynchronous copy * use a better kernel for root * parallel read histogram * sparse features now works, but no acceleration, compute on CPU * compute sparse feature on CPU simultaneously * fix big bug; add gpu selection; add kernel selection * better debugging * clean up * add feature scatter * Add sparse_threshold control * fix a bug in feature scatter * clean up debug * temporarily add OpenCL kernels for k=64,256 * fix up CMakeList and definition USE_GPU * add OpenCL kernels as string literals * Add boost.compute as a submodule * add boost dependency into CMakeList * fix opencl pragma * use pinned memory for histogram * use pinned buffer for gradients and hessians * better debugging message * add double precision support on GPU * fix boost version in CMakeList * Add a README * reconstruct GPU initialization code for ResetTrainingData * move data to GPU in parallel * fix a bug during feature copy * update gpu kernels * update gpu code * initial port to LightGBM v2 * speedup GPU data loading process * Add 4-bit bin support to GPU * re-add sparse_threshold parameter * remove kMaxNumWorkgroups and allows an unlimited number of features * add feature mask support for skipping unused features * enable kernel cache * use GPU kernels withoug feature masks when all features are used * REAdme. * REAdme. * update README * fix typos (#349) * change compile to gcc on Apple as default * clean vscode related file * refine api of constructing from sampling data. * fix bug in the last commit. * more efficient algorithm to sample k from n. * fix bug in filter bin * change to boost from average output. * fix tests. * only stop training when all classes are finshed in multi-class. * limit the max tree output. change hessian in multi-class objective. * robust tree model loading. * fix test. * convert the probabilities to raw score in boost_from_average of classification. * fix the average label for binary classification. * Add boost_from_average to docs (#354) * don't use "ConvertToRawScore" for self-defined objective function. * boost_from_average seems doesn't work well in binary classification. remove it. * For a better jump link (#355) * Update Python-API.md * for a better jump in page A space is needed between `#` and the headers content according to Github's markdown format [guideline](https://guides.github.com/features/mastering-markdown/) After adding the spaces, we can jump to the exact position in page by click the link. * fixed something mentioned by @wxchan * Update Python-API.md * add FitByExistingTree. * adapt GPU tree learner for FitByExistingTree * avoid NaN output. * update boost.compute * fix typos (#361) * fix broken links (#359) * update README * disable GPU acceleration by default * fix image url * cleanup debug macro * remove old README * do not save sparse_threshold_ in FeatureGroup * add details for new GPU settings * ignore submodule when doing pep8 check * allocate workspace for at least one thread during builing Feature4 * move sparse_threshold to class Dataset * remove duplicated code in GPUTreeLearner::Split * Remove duplicated code in FindBestThresholds and BeforeFindBestSplit * do not rebuild ordered gradients and hessians for sparse features * support feature groups in GPUTreeLearner * Initial parallel learners with GPU support * add option device, cleanup code * clean up FindBestThresholds; add some omp parallel * constant hessian optimization for GPU * Fix GPUTreeLearner crash when there is zero feature * use np.testing.assert_almost_equal() to compare lists of floats in tests * travis for GPU
2017-04-09 16:53:14 +03:00
if(USE_GPU)
TARGET_LINK_LIBRARIES(lightgbm ${OpenCL_LIBRARY} ${Boost_LIBRARIES})
TARGET_LINK_LIBRARIES(_lightgbm ${OpenCL_LIBRARY} ${Boost_LIBRARIES})
endif(USE_GPU)
2016-12-07 06:45:55 +03:00
if(WIN32 AND (MINGW OR CYGWIN))
2016-12-07 06:31:31 +03:00
TARGET_LINK_LIBRARIES(lightgbm Ws2_32)
TARGET_LINK_LIBRARIES(_lightgbm Ws2_32)
TARGET_LINK_LIBRARIES(lightgbm IPHLPAPI)
TARGET_LINK_LIBRARIES(_lightgbm IPHLPAPI)
2016-12-07 06:45:55 +03:00
endif()
2016-08-05 09:06:01 +03:00
2016-12-07 06:31:31 +03:00
install(TARGETS lightgbm _lightgbm
RUNTIME DESTINATION ${CMAKE_INSTALL_PREFIX}/bin
2017-01-24 11:53:58 +03:00
LIBRARY DESTINATION ${CMAKE_INSTALL_PREFIX}/lib
ARCHIVE DESTINATION ${CMAKE_INSTALL_PREFIX}/lib)
install(DIRECTORY ${LightGBM_HEADER_DIR}/LightGBM DESTINATION ${CMAKE_INSTALL_PREFIX}/include)