Skip to content

Commit

Permalink
Rework JNI CMake to leverage rapids_find_package (#10649)
Browse files Browse the repository at this point in the history 
The JNI CMakeLists.txt has been fragile, looking for specific .a or .so libraries and header file locations, and will break again when libcudf moves to a pre-installed nvcomp 2.3 package since it expects to find nvcomp in a very specific location today.  This refactors the JNI CMakeLists.txt to leverage `rapids_find_package` to reuse the work performed in the libcudf build and also has the nice side-effect of avoiding redundant pulls and builds of the Thrust and RMM repositories that is happening today.

Another side-effect is that the JNI will now automatically pull in the same RMM compile definitions that are used for libcudf, meaning the separate RMM logging flag for the JNI build is no longer necessary.  Similarly it's no longer necessary to explicitly specify to the JNI build which type of Arrow library to use (i.e,.: static or dynamic), it will automatically use whichever Arrow library was built by libcudf.

Authors:
  - Jason Lowe (https://github.com/jlowe)

Approvers:
  - Robert (Bobby) Evans (https://github.com/revans2)
  - Gera Shegalov (https://github.com/gerashegalov)

URL: #10649
  • Loading branch information
@jlowe
jlowe authored Apr 18, 2022
1 parent 94a5d41 commit 9409559
Show file tree
Hide file tree
Showing 5 changed files with 17 additions and 132 deletions.
2 changes: 0 additions & 2 deletions build.sh
View file
Original file line number Diff line number Diff line change
Expand Up @@ -148,10 +148,8 @@ function buildLibCudfJniInDocker {
-DCUDF_CPP_BUILD_DIR=$workspaceRepoDir/java/target/libcudf-cmake-build \
-DCUDA_STATIC_RUNTIME=ON \
-DPER_THREAD_DEFAULT_STREAM=ON \
-DRMM_LOGGING_LEVEL=OFF \
-DUSE_GDS=ON \
-DGPU_ARCHS=${CUDF_CMAKE_CUDA_ARCHITECTURES} \
-DCUDF_JNI_ARROW_STATIC=ON \
-DCUDF_JNI_LIBCUDF_STATIC=ON \
-Dtest=*,!CuFileTest"
}
Expand Down
10 changes: 0 additions & 10 deletions java/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -75,16 +75,6 @@ If you decide to build without Docker and the build script, examining the cmake
settings in the [Java CI build script](ci/build-in-docker.sh) can be helpful if you are
encountering difficulties during the build.

## Dynamically Linking Arrow

Since libcudf builds by default with a dynamically linked Arrow dependency, it may be
desirable to build the Java bindings without requiring a statically-linked Arrow to avoid
rebuilding an already built libcudf.so. To do so, specify the additional command-line flag
`-DCUDF_JNI_ARROW_STATIC=OFF` when building the Java bindings with Maven. However this will
result in a jar that requires the correct Arrow version to be available in the runtime
environment, and therefore is not recommended unless you are only performing local testing
within the libcudf build environment.

## Statically Linking the CUDA Runtime

If you use the default cmake options libcudart will be dynamically linked to libcudf and libcudfjni.
Expand Down
1 change: 0 additions & 1 deletion java/ci/build-in-docker.sh
View file
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,6 @@ BUILD_ARG="-Dmaven.repo.local=\"$WORKSPACE/.m2\"\
-DPER_THREAD_DEFAULT_STREAM=$ENABLE_PTDS\
-DCUDA_STATIC_RUNTIME=$ENABLE_CUDA_STATIC_RUNTIME\
-DCUDF_JNI_LIBCUDF_STATIC=ON\
-DRMM_LOGGING_LEVEL=$RMM_LOGGING_LEVEL\
-DUSE_GDS=$ENABLE_GDS -Dtest=*,!CuFileTest"

if [ "$SIGN_FILE" == true ]; then
Expand Down
4 changes: 0 additions & 4 deletions java/pom.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -165,10 +165,8 @@
<CMAKE_EXPORT_COMPILE_COMMANDS>OFF</CMAKE_EXPORT_COMPILE_COMMANDS>
<CUDA_STATIC_RUNTIME>OFF</CUDA_STATIC_RUNTIME>
<PER_THREAD_DEFAULT_STREAM>OFF</PER_THREAD_DEFAULT_STREAM>
<RMM_LOGGING_LEVEL>INFO</RMM_LOGGING_LEVEL>
<USE_GDS>OFF</USE_GDS>
<GPU_ARCHS>ALL</GPU_ARCHS>
<CUDF_JNI_ARROW_STATIC>ON</CUDF_JNI_ARROW_STATIC>
<CUDF_JNI_LIBCUDF_STATIC>OFF</CUDF_JNI_LIBCUDF_STATIC>
<native.build.path>${project.build.directory}/cmake-build</native.build.path>
<slf4j.version>1.7.30</slf4j.version>
Expand Down Expand Up @@ -386,13 +384,11 @@
<arg value="${basedir}/src/main/native"/>
<arg value="-DCUDA_STATIC_RUNTIME=${CUDA_STATIC_RUNTIME}" />
<arg value="-DPER_THREAD_DEFAULT_STREAM=${PER_THREAD_DEFAULT_STREAM}" />
<arg value="-DRMM_LOGGING_LEVEL=${RMM_LOGGING_LEVEL}" />
<arg value="-DUSE_GDS=${USE_GDS}" />
<arg value="-DCMAKE_CXX_FLAGS=${cxx.flags}"/>
<arg value="-DCMAKE_EXPORT_COMPILE_COMMANDS=${CMAKE_EXPORT_COMPILE_COMMANDS}"/>
<arg value="-DCUDF_CPP_BUILD_DIR=${CUDF_CPP_BUILD_DIR}"/>
<arg value="-DGPU_ARCHS=${GPU_ARCHS}"/>
<arg value="-DCUDF_JNI_ARROW_STATIC=${CUDF_JNI_ARROW_STATIC}"/>
<arg value="-DCUDF_JNI_LIBCUDF_STATIC=${CUDF_JNI_LIBCUDF_STATIC}"/>
<arg value="-DBUILD_SHARED_LIBS=ON"/>
</exec>
Expand Down
132 changes: 17 additions & 115 deletions java/src/main/native/CMakeLists.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@ option(BUILD_TESTS "Configure CMake to build tests" ON)
option(PER_THREAD_DEFAULT_STREAM "Build with per-thread default stream" OFF)
option(CUDA_STATIC_RUNTIME "Statically link the CUDA runtime" OFF)
option(USE_GDS "Build with GPUDirect Storage (GDS)/cuFile support" OFF)
option(CUDF_JNI_ARROW_STATIC "Statically link Arrow" ON)
option(CUDF_JNI_LIBCUDF_STATIC "Link with libcudf.a" OFF)

message(VERBOSE "CUDF_JNI: Build with NVTX support: ${USE_NVTX}")
Expand All @@ -50,7 +49,6 @@ message(VERBOSE "CUDF_JNI: Configure CMake to build tests: ${BUILD_TESTS}")
message(VERBOSE "CUDF_JNI: Build with per-thread default stream: ${PER_THREAD_DEFAULT_STREAM}")
message(VERBOSE "CUDF_JNI: Statically link the CUDA runtime: ${CUDA_STATIC_RUNTIME}")
message(VERBOSE "CUDF_JNI: Build with GPUDirect Storage support: ${USE_GDS}")
message(VERBOSE "CUDF_JNI: Build with static Arrow library: ${CUDF_JNI_ARROW_STATIC}")
message(VERBOSE "CUDF_JNI: Link with libcudf statically: ${CUDF_JNI_LIBCUDF_STATIC}")

set(CUDF_SOURCE_DIR "${PROJECT_SOURCE_DIR}/../../../../cpp")
Expand Down Expand Up @@ -93,67 +91,16 @@ endif()
rapids_cmake_build_type("Release")

# ##################################################################################################
# * Thrust/CUB
# ------------------------------------------------------------------------------------
include(${CUDF_SOURCE_DIR}/cmake/thirdparty/get_thrust.cmake)
# * nvcomp------------------------------------------------------------------------------------------

# ##################################################################################################
# * CUDF ------------------------------------------------------------------------------------------

set(CUDF_INCLUDE "${PROJECT_SOURCE_DIR}/../../../../cpp/include"
"${PROJECT_SOURCE_DIR}/../../../../cpp/src/"
)

set(CUDF_LIB_HINTS HINTS "$ENV{CUDF_ROOT}" "$ENV{CUDF_ROOT}/lib" "$ENV{CONDA_PREFIX}/lib"
"${CUDF_CPP_BUILD_DIR}"
)

find_library(CUDF_LIB "cudf" REQUIRED HINTS ${CUDF_LIB_HINTS})

# ##################################################################################################
# * ZLIB ------------------------------------------------------------------------------------------

# find zlib
rapids_find_package(ZLIB REQUIRED)
set(nvcomp_DIR "${CUDF_CPP_BUILD_DIR}/_deps/nvcomp-build")
rapids_find_package(nvcomp REQUIRED)

# ##################################################################################################
# * RMM -------------------------------------------------------------------------------------------
# * CUDF ------------------------------------------------------------------------------------------

include(${CUDF_SOURCE_DIR}/cmake/thirdparty/get_rmm.cmake)

# ##################################################################################################
# * ARROW -----------------------------------------------------------------------------------------

find_path(ARROW_INCLUDE "arrow" HINTS "$ENV{ARROW_ROOT}/include"
"${CUDF_CPP_BUILD_DIR}/_deps/arrow-src/cpp/src"
)

message(STATUS "ARROW: ARROW_INCLUDE set to ${ARROW_INCLUDE}")

if(CUDF_JNI_ARROW_STATIC)
# Find static version of Arrow lib
set(CUDF_JNI_ARROW_LIBNAME "libarrow.a")
else()
set(CUDF_JNI_ARROW_LIBNAME "arrow")
endif()

find_library(
ARROW_LIBRARY ${CUDF_JNI_ARROW_LIBNAME} REQUIRED
HINTS "$ENV{ARROW_ROOT}/lib" "${CUDF_CPP_BUILD_DIR}/_deps/arrow-build/release"
"${CUDF_CPP_BUILD_DIR}/_deps/arrow-build/debug"
)

if(NOT ARROW_LIBRARY)
if(CUDF_JNI_ARROW_STATIC)
message(
FATAL_ERROR "Arrow static library not found. Was libcudf built with CUDF_USE_ARROW_STATIC=ON?"
)
else()
message(FATAL_ERROR "Arrow dynamic library not found.")
endif()
else()
message(STATUS "ARROW: ARROW_LIBRARY set to ${ARROW_LIBRARY}")
endif()
set(cudf_ROOT "${CUDF_CPP_BUILD_DIR}")
rapids_find_package(cudf REQUIRED)

# ##################################################################################################
# * find JNI -------------------------------------------------------------------------------------
Expand All @@ -164,27 +111,6 @@ else()
message(FATAL_ERROR "JDK with JNI not found, please check your settings.")
endif()

# ##################################################################################################
# * nvcomp ----------------------------------------------------------------------------------------

find_path(NVCOMP_INCLUDE "nvcomp" HINTS "${CUDF_CPP_BUILD_DIR}/_deps/nvcomp-src/include"
"$ENV{CONDA_PREFIX}/include"
)

message(STATUS "NVCOMP: NVCOMP_INCLUDE set to ${NVCOMP_INCLUDE}")

set(CUDF_JNI_NVCOMP_LIBNAME "libnvcomp.a")
find_library(
NVCOMP_LIBRARY ${CUDF_JNI_NVCOMP_LIBNAME} REQUIRED HINTS "${CUDF_CPP_BUILD_DIR}/lib"
"$ENV{CONDA_PREFIX}/lib"
)

if(NOT NVCOMP_LIBRARY)
message(FATAL_ERROR "nvcomp static library not found.")
else()
message(STATUS "NVCOMP: NVCOMP_LIBRARY set to ${NVCOMP_LIBRARY}")
endif()

# ##################################################################################################
# * GDS/cufile ------------------------------------------------------------------------------------

Expand Down Expand Up @@ -238,17 +164,8 @@ endif()
# * include paths ---------------------------------------------------------------------------------

target_include_directories(
cudfjni
PUBLIC cudf::Thrust
"${LIBCUDACXX_INCLUDE}"
"${CUDAToolkit_INCLUDE_DIRS}"
"${NVCOMP_INCLUDE}"
"${CMAKE_BINARY_DIR}/include"
"${CMAKE_SOURCE_DIR}/include"
"${CMAKE_SOURCE_DIR}/src"
"${JNI_INCLUDE_DIRS}"
"${CUDF_INCLUDE}"
"${ARROW_INCLUDE}"
cudfjni PUBLIC "${CMAKE_BINARY_DIR}/include" "${CMAKE_SOURCE_DIR}/include"
"${CMAKE_SOURCE_DIR}/src" "${JNI_INCLUDE_DIRS}"
)

# ##################################################################################################
Expand Down Expand Up @@ -291,39 +208,24 @@ if(USE_GDS)
POSITION_INDEPENDENT_CODE ON
INTERFACE_POSITION_INDEPENDENT_CODE ON
)
target_include_directories(
cufilejni
PUBLIC "${LIBCUDACXX_INCLUDE}" "${CUDF_INCLUDE}"
PRIVATE "${cuFile_INCLUDE_DIRS}"
)
target_link_libraries(cufilejni PRIVATE cudfjni rmm::rmm "${cuFile_LIBRARIES}")
target_include_directories(cufilejni PRIVATE "${cuFile_INCLUDE_DIRS}")
target_link_libraries(cufilejni PRIVATE cudfjni "${cuFile_LIBRARIES}")
endif()

# ##################################################################################################
# * rmm logging level -----------------------------------------------------------------------------

set(RMM_LOGGING_LEVEL
"INFO"
CACHE STRING "Choose the logging level."
)
# Set the possible values of build type for cmake-gui
set_property(
CACHE RMM_LOGGING_LEVEL PROPERTY STRINGS "TRACE" "DEBUG" "INFO" "WARN" "ERROR" "CRITICAL" "OFF"
)
message(STATUS "RMM_LOGGING_LEVEL = '${RMM_LOGGING_LEVEL}'.")

target_compile_definitions(cudfjni PUBLIC SPDLOG_ACTIVE_LEVEL=SPDLOG_LEVEL_${RMM_LOGGING_LEVEL})

# ##################################################################################################
# * link libraries --------------------------------------------------------------------------------

set(CUDF_LINK ${CUDF_LIB})
set(CUDF_LINK PUBLIC cudf::cudf)
if(CUDF_JNI_LIBCUDF_STATIC)
set(CUDF_LINK -Wl,--whole-archive ${CUDF_LIB} -Wl,--no-whole-archive ZLIB::ZLIB)
# Whole-link libcudf.a into the shared library but not its dependencies
set(CUDF_LINK PRIVATE -Wl,--whole-archive cudf::cudf -Wl,--no-whole-archive PUBLIC cudf::cudf)
endif()

# When nvcomp is installed we need to use nvcomp::nvcomp but from the cudf build directory it will
# just be nvcomp.
target_link_libraries(
cudfjni PRIVATE ${CUDF_LINK} ${NVCOMP_LIBRARY} ${ARROW_LIBRARY} rmm::rmm CUDA::cuda_driver
cudfjni ${CUDF_LINK} PRIVATE $<TARGET_NAME_IF_EXISTS:nvcomp>
$<TARGET_NAME_IF_EXISTS:nvcomp::nvcomp>
)

# ##################################################################################################
Expand Down

0 comments on commit 9409559

Please sign in to comment.