Update the CMake file.

1. Support to generate the dynamic link library on GPU. 2. Support to compile the project on the MKL and OpenBLAS.

Update the CMake file.
1. Support to generate the dynamic link library on GPU. 2. Support to compile the project on the MKL and OpenBLAS.
b4785f07 · liyinqiao · 2cc0a82d · b4785f07
Commit b4785f07 authored Aug 29, 2020 by liyinqiao
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -6,39 +6,64 @@
 # cmake minimum version
 cmake_minimum_required(VERSION 2.8)
-# project's name
+# Project's name
 project(NiuTensor)
-# the prefix of the generated executable file
+# The name of the generated executable file
-set(NIUTRANS_EXE "NiuTensor")
+# The name of the dynamic link library
+set(NIUTENSOR_EXE "NiuTensor")
+set(NIUTENSOR_DLL "${NIUTENSOR_EXE}")
-# generated file path
+# Generated file path
 set(EXECUTABLE_OUTPUT_PATH ../bin)
+set(LIBRARY_OUTPUT_PATH ../lib)
-# 0 - Linux or macOS
+# Use CMAKE_MACOSX_RPATH for macOS 
-# 1 - Windows
+set(CMAKE_MACOSX_RPATH 1)
-set(ON_WINDOWS 0)
+# Open floder manage
+set_property(GLOBAL PROPERTY USE_FOLDERS ON)
+set(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS ON)
+option(USE_CUDA "Use CUDA" OFF)
+option(USE_MKL "Use MKL" OFF)
+option(USE_OPENBLAS "Use OpenBLAS" OFF)
+option(GEN_DLL "Generate Dynamic Link Library" OFF)
-# 0 - Not use
+# If set USE_CUDA ON, please modify CUDA_TOOLKIT_ROOT_DIR below.
-# 1 - Use, if set 1, please modify the CUDA_VERSION and CUDA_TOOLKIT_ROOT_DIR below
+# If set USE_MKL ON, please modify the INTEL_ROOT below.
-set(USE_CUDA 0)
+# If set USE_OPENBLAS ON, please modify the OPENBLAS_ROOT below.
 if (USE_CUDA)
-    set(CUDA_VERSION 9.2)
+    if(NOT EXISTS ${CUDA_TOOLKIT_ROOT_DIR})
-    set(CUDA_TOOLKIT_ROOT_DIR "/usr/local/cuda") 
+        if(WIN32)
+            set(CUDA_TOOLKIT_ROOT_DIR "C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v9.2")
+        else()
+            set(CUDA_TOOLKIT_ROOT_DIR "/usr/local/cuda-9.2")
+        endif()
+    endif()
+    message(STATUS "CUDA_TOOLKIT_ROOT_DIR: ${CUDA_TOOLKIT_ROOT_DIR}")
+endif()
+if(USE_MKL)
+    if(NOT DEFINED INTEL_ROOT)
+        if(WIN32)
+            set(INTEL_ROOT "C:/Program Files (x86)/IntelSWTools/compilers_and_libraries_2020.2.254/windows")
+        else()
+            set(INTEL_ROOT "/opt/intel/compilers_and_libraries_2020.2.254/linux")
+        endif()
+    endif()
+    message(STATUS "INTEL_ROOT: ${INTEL_ROOT}")
+endif()
+if(USE_OPENBLAS)
+    if(NOT DEFINED OPENBLAS_ROOT)
+        if(WIN32)
+            set(OPENBLAS_ROOT "C:/Program Files/OpenBLAS")
+        else()
+            set(OPENBLAS_ROOT "/opt/OpenBLAS")
+        endif()
+    endif()
+    message(STATUS "OPENBLAS_ROOT: ${OPENBLAS_ROOT}")
 endif()
-# 0 - Not use half precision in CUDA codes
+# Find all the .cpp .h .cu .chu files in source folder
-# 1 - Use, note the architecture of GPU must be newer than Pascal(including Pascal)
-set(USE_HALF_PRECISION 0)
-# use CMAKE_MACOSX_RPATH for macOS
-set(CMAKE_MACOSX_RPATH 1)
-# open floder manage
-set_property(GLOBAL PROPERTY USE_FOLDERS On)
-add_definitions(-std=c++11)
-# find all the .cpp .h .cu .chu files in source folder
 file(GLOB_RECURSE CPP_FILES source/*.cpp)
 file(GLOB_RECURSE H_FILES source/*.h)
 file(GLOB_RECURSE CU_FILES source/*.cu)
@@ -68,15 +93,14 @@ function(my_add_executable)
    endif()
 endfunction(my_add_executable)
+# Set libs and compiler options for CUDA
 if(USE_CUDA)
-    set(NIUTRANS_EXE "${NIUTRANS_EXE}.GPU")
    add_definitions(-DUSE_CUDA)
    if(USE_HALF_PRECISION)
        add_definitions(-DHALF_PRECISION)
    endif()
-    if(ON_WINDOWS)
+    find_package(CUDA REQUIRED)
-        find_package(CUDA ${CUDA_VERSION} REQUIRED)
+    if(WIN32)
-        add_compile_options(-Wno-dev)
        SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /wd4819")
        set(CMAKE_CUDA_FLAGS ${CMAKE_CUDA_FLAGS} "-maxrregcount=0 -m64 --disable-warnings -use_fast_math -DUSE_CUDA")
        if(USE_HALF_PRECISION)
@@ -86,7 +110,8 @@ if(USE_CUDA)
                -gencode=arch=compute_61,code=sm_61
                -gencode=arch=compute_62,code=sm_62
                -gencode=arch=compute_70,code=sm_70
-                -gencode=arch=compute_70,code=compute_70)
+                -gencode=arch=compute_70,code=compute_70
+            )
        else()
            set(CMAKE_CUDA_FLAGS ${CMAKE_CUDA_FLAGS} -arch=sm_30
                -gencode=arch=compute_30,code=sm_30
@@ -96,20 +121,19 @@ if(USE_CUDA)
                -gencode=arch=compute_61,code=sm_61
                -gencode=arch=compute_62,code=sm_62
                -gencode=arch=compute_70,code=sm_70
-                -gencode=arch=compute_70,code=compute_70)
+                -gencode=arch=compute_70,code=compute_70
+            )
        endif()
        set(CMAKE_POLICY_DEFAULT_CMP0028 NEW)
        link_directories("${CUDA_TOOLKIT_ROOT_DIR}/lib/x64")
        include_directories("${CUDA_TOOLKIT_ROOT_DIR}/include")
-        set(CUDA_LIB_PATH_ME "${CUDA_TOOLKIT_ROOT_DIR}/lib/x64/")
+        set(CUDA_LIB_DIR "${CUDA_TOOLKIT_ROOT_DIR}/lib/x64/")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}cublas.lib")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}cublas.lib")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}npps.lib")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}npps.lib")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}nppc.lib")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}nppc.lib")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}cudadevrt.lib")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}cudadevrt.lib")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}curand.lib")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}curand.lib")
-        my_add_executable(${NIUTRANS_EXE} ${CPP_FILES} ${H_FILES} ${CU_FILES} ${CUH_FILES})
+    else()
-    else()
-        find_package(CUDA ${CUDA_VERSION} REQUIRED)
        set(CMAKE_CXX_FLAGS "-fPIC -msse4.2 -w -march=native -Wno-enum-compare -Wno-sign-compare -Wno-format -Wno-dev -O3 -DNDEBUG -rdynamic")
        set(CUDA_NVCC_FLAGS "-Xcompiler -fPIC -maxrregcount=0 --disable-warnings -use_fast_math -DUSE_CUDA -Wno-deprecated-gpu-targets -std=c++11")
        if(USE_HALF_PRECISION)
@@ -119,7 +143,8 @@ if(USE_CUDA)
                -gencode=arch=compute_61,code=sm_61
                -gencode=arch=compute_62,code=sm_62
                -gencode=arch=compute_70,code=sm_70
-                -gencode=arch=compute_70,code=compute_70)
+                -gencode=arch=compute_70,code=compute_70
+            )
        else()
            set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} -arch=sm_30 
                -gencode=arch=compute_30,code=sm_30 
@@ -129,44 +154,152 @@ if(USE_CUDA)
                -gencode=arch=compute_61,code=sm_61 
                -gencode=arch=compute_62,code=sm_62 
                -gencode=arch=compute_70,code=sm_70 
-                -gencode=arch=compute_70,code=compute_70)
+                -gencode=arch=compute_70,code=compute_70 
+            )
        endif()
        link_directories(${CUDA_TOOLKIT_ROOT_DIR}/lib64)
        include_directories(${CUDA_TOOLKIT_ROOT_DIR}/include)
-        set(CUDA_LIB_PATH_ME "${CUDA_TOOLKIT_ROOT_DIR}/lib64/")
+        set(CUDA_LIB_DIR "${CUDA_TOOLKIT_ROOT_DIR}/lib64/")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libcublas_static.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libcublas_static.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libculibos.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libculibos.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libnpps_static.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libnpps_static.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libnppc_static.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libnppc_static.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libcudadevrt.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libcudadevrt.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "${CUDA_LIB_PATH_ME}libcurand_static.a")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "${CUDA_LIB_DIR}libcurand_static.a")
-        set(CUDA_LIBS_ME ${CUDA_LIBS_ME} "/usr/lib64/libdl.so.2")
+        set(CUDA_LIB_PATH ${CUDA_LIB_PATH} "/usr/lib64/libdl.so.2")
-        my_add_executable(${NIUTRANS_EXE} ${CPP_FILES} ${H_FILES} ${CU_FILES} ${CUH_FILES})
    endif()
-else()
-    set(NIUTRANS_EXE "${NIUTRANS_EXE}.CPU")
-    my_add_executable(${NIUTRANS_EXE} ${CPP_FILES} ${H_FILES})
 endif()
-set(CUDA_LIB ${CUDA_LIBS_ME})
+# Set libs and compiler options for MKL
+if(USE_MKL)
+    add_definitions(-DUSE_BLAS -DMKL)
+    set(COMPILER_DIR "${INTEL_ROOT}/compiler")
+    set(MKL_DIR "${INTEL_ROOT}/mkl")
+    set(CPU_ARCH intel64)
+    if(WIN32)
+        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DNDEBUG")
+        link_directories(${MKL_DIR}/lib/intel64/)
+        link_directories(${COMPILER_DIR}/lib/intel64)
+        include_directories(${MKL_DIR}/include)
+        set(COMPILER_LIB_DIR "${COMPILER_DIR}/lib/intel64/")
+        set(MKL_LIB_DIR "${MKL_DIR}/lib/intel64/")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}mkl_intel_lp64.lib")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}mkl_core.lib")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}mkl_intel_thread.lib")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${COMPILER_LIB_DIR}libiomp5md.lib")
+    else()
+        if(USE_CUDA)
+            set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-reorder")
+        else()
+            set(CMAKE_CXX_FLAGS "-std=c++11 -msse4.2 -w -march=native -Wno-enum-compare -Wno-sign-compare -Wno-reorder -Wno-format -O3 -flto -DNDEBUG -rdynamic -fkeep-inline-functions -fPIC")
+        endif(USE_CUDA)
+        link_directories(${MKL_DIR}/lib/intel64/)
+        link_directories(${COMPILER_DIR}/lib/intel64)
+        include_directories(${MKL_DIR}/include)
+        set(COMPILER_LIB_DIR "${COMPILER_DIR}/lib/intel64/")
+        set(MKL_LIB_DIR "${MKL_DIR}/lib/intel64/")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}libmkl_intel_lp64.a")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}libmkl_core.a")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${MKL_LIB_DIR}libmkl_intel_thread.a")
+        set(MKL_LIB_PATH ${MKL_LIB_PATH} "${COMPILER_LIB_DIR}libiomp5.a")
+    endif()
+endif()
-if(ON_WINDOWS)
+# Set libs and compiler options for OpenBLAS
-    add_definitions(-DWIN32) # for windows specially
+if(USE_OPENBLAS)
+    add_definitions(-DUSE_BLAS -DOPENBLAS)
+    set(OPENBLAS_INCLUDE_DIR "${OPENBLAS_ROOT}/include")
+    set(OPENBLAS_LIB_DIR "${OPENBLAS_ROOT}/lib")
+    if(WIN32)
+        link_directories(${OPENBLAS_LIB_DIR})
+        include_directories(${OPENBLAS_INCLUDE_DIR})
+        set(OPENBLAS_LIB_PATH ${OPENBLAS_LIB_PATH} "${OPENBLAS_LIB_DIR}/libopenblas.lib")
+    else()
+        link_directories(${OPENBLAS_LIB_DIR})
+        include_directories(${OPENBLAS_INCLUDE_DIR})
+        set(OPENBLAS_LIB_PATH ${OPENBLAS_LIB_PATH} "${OPENBLAS_LIB_DIR}/libopenblas.a")
+        set(OPENBLAS_LIB_PATH ${OPENBLAS_LIB_PATH} "${OPENBLAS_LIB_DIR}/libopenblas_haswellp-r0.3.10.a")
+    endif()
+endif()
+# Integrate all libs
+set(CUDA_LIB ${CUDA_LIB_PATH})
+set(MKL_LIB ${MKL_LIB_PATH})
+set(OPENBLAS_LIB ${OPENBLAS_LIB_PATH})
+# Add executable files to project
+# Generate dynamic link library about project
+if(USE_CUDA)
+    if(GEN_DLL)
+        cuda_add_library(${NIUTENSOR_DLL} SHARED ${CPP_FILES} ${H_FILES} ${CU_FILES} ${CUH_FILES})
+    else()
+        my_add_executable(${NIUTENSOR_EXE} ${CPP_FILES} ${H_FILES} ${CU_FILES} ${CUH_FILES})
+    endif()
+else()
+    if(GEN_DLL)
+        add_library(${NIUTENSOR_DLL} SHARED ${CPP_FILES} ${H_FILES})
+    else()
+        my_add_executable(${NIUTENSOR_EXE} ${CPP_FILES} ${H_FILES})
+    endif()
+endif()
+# Link external libs to executable files
+# Link external libs to dynamic link library
+if(WIN32)
+    add_definitions(-DWIN32)
+    set(MESS ${MESS} "On Windows")
    if(USE_CUDA)
-        message(STATUS "On Windows and use cuda")
+        set(MESS ${MESS} " Use CUDA")
-        target_link_libraries(${NIUTRANS_EXE} ${CUDA_LIB})
+        set(ALL_LIB ${ALL_LIB} ${CUDA_LIB})
+    endif()
+    if(USE_MKL)
+        set(MESS ${MESS} " Use MKL")
+        set(ALL_LIB ${ALL_LIB} ${MKL_LIB})
+    elseif(USE_OPENBLAS)
+        set(MESS ${MESS} " Use OpenBLAS")
+        set(ALL_LIB ${ALL_LIB} ${OPENBLAS_LIB})
+    else()
+    endif()
+    if(GEN_DLL)
+        message(STATUS "Generate Dynamic Link Library")
+        message(STATUS "Name of Dynamic Link Library: " ${NIUTENSOR_DLL})
+        target_link_libraries(${NIUTENSOR_DLL} ${ALL_LIB})
    else()
-        message(STATUS "On Windows and not use cuda")
+        message(STATUS "Generate Makefile For Executable File")
-        target_link_libraries(${NIUTRANS_EXE} ${CUDA_LIB})
+        message(STATUS "Name of Executable File :" ${NIUTENSOR_EXE})
+        target_link_libraries(${NIUTENSOR_EXE} ${ALL_LIB})
    endif()
+    message(STATUS "${MESS}")
 else()
+    add_definitions(-std=c++11)
+    set(MESS ${MESS} "On Linux or macOS")
    if(USE_CUDA)
-        message(STATUS "On Linux and use cuda")
+        set(MESS ${MESS} " Use CUDA")
-        target_link_libraries(${NIUTRANS_EXE} ${CUDA_LIB} -lpthread -lcudart -lnvidia-ml)
+        set(ALL_LIB ${ALL_LIB} ${CUDA_LIB})
+        set(FLAG ${FLAG} "-lpthread -lcudart -lnvidia-ml")
+    else()
+        set(FLAG ${FLAG} "-lpthread")
+    endif()
+    if(USE_MKL)
+        set(MESS ${MESS} " Use MKL")
+        set(ALL_LIB ${ALL_LIB} ${MKL_LIB})
+        set(FLAG ${FLAG} "-liomp5 -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -ldl")
+    elseif(USE_OPENBLAS)
+        set(MESS ${MESS} " Use OpenBLAS")
+        set(ALL_LIB ${ALL_LIB} ${OPENBLAS_LIB})
+        set(FLAG ${FLAG} "-lopenblas")
    else()
-        message(STATUS "On Linux and not use cuda")
-        target_link_libraries(${NIUTRANS_EXE} ${CUDA_LIB} -lpthread)
    endif()
-endif()
-message(STATUS "name of executable file:" ${NIUTRANS_EXE})
+    if(GEN_DLL)
\ No newline at end of file
+        message(STATUS "Generate Dynamic Link Library")
+        message(STATUS "Name of Dynamic Link Library: " ${NIUTENSOR_DLL})
+        target_link_libraries(${NIUTENSOR_DLL} ${ALL_LIB} ${FLAG})
+    else()
+        message(STATUS "Generate Makefile For Executable File")
+        message(STATUS "Name of Executable File: " ${NIUTENSOR_EXE})
+        target_link_libraries(${NIUTENSOR_EXE} ${ALL_LIB} ${FLAG})
+    endif()
+    message(STATUS "${MESS}")
+endif()
\ No newline at end of file