Automate Java cudf jar build with statically linked dependencies

build.sh

@@ -17,12 +17,13 @@ ARGS=$*
 # script, and that this script resides in the repo dir!
 REPODIR=$(cd $(dirname $0); pwd)
 
-VALIDARGS="clean libcudf cudf dask_cudf benchmarks tests libcudf_kafka cudf_kafka custreamz -v -g -n -l --allgpuarch --disable_nvtx --show_depr_warn --ptds -h --build_metrics --incl_cache_stats"
-HELP="$0 [clean] [libcudf] [cudf] [dask_cudf] [benchmarks] [tests] [libcudf_kafka] [cudf_kafka] [custreamz] [-v] [-g] [-n] [-h] [--cmake-args=\\\"<args>\\\"]
+VALIDARGS="clean libcudf cudf cudfjar dask_cudf benchmarks tests libcudf_kafka cudf_kafka custreamz -v -g -n -l --allgpuarch --disable_nvtx --show_depr_warn --ptds -h --build_metrics --incl_cache_stats"
+HELP="$0 [clean] [libcudf] [cudf] [cudfjar] [dask_cudf] [benchmarks] [tests] [libcudf_kafka] [cudf_kafka] [custreamz] [-v] [-g] [-n] [-h] [--cmake-args=\\\"<args>\\\"]
    clean                         - remove all existing build artifacts and configuration (start
                                    over)
    libcudf                       - build the cudf C++ code only
    cudf                          - build the cudf Python package
+   cudfjar                       - build cudf JAR with static libcudf using devtoolset toolchain
    dask_cudf                     - build the dask_cudf Python package
    benchmarks                    - build benchmarks
    tests                         - build tests
@@ -50,7 +51,9 @@ CUDF_KAFKA_BUILD_DIR=${REPODIR}/python/cudf_kafka/build
 CUDF_BUILD_DIR=${REPODIR}/python/cudf/build
 DASK_CUDF_BUILD_DIR=${REPODIR}/python/dask_cudf/build
 CUSTREAMZ_BUILD_DIR=${REPODIR}/python/custreamz/build
-BUILD_DIRS="${LIB_BUILD_DIR} ${CUDF_BUILD_DIR} ${DASK_CUDF_BUILD_DIR} ${KAFKA_LIB_BUILD_DIR} ${CUDF_KAFKA_BUILD_DIR} ${CUSTREAMZ_BUILD_DIR}"
+CUDF_JAR_JAVA_BUILD_DIR="$REPODIR/java/target"
+
+BUILD_DIRS="${LIB_BUILD_DIR} ${CUDF_BUILD_DIR} ${DASK_CUDF_BUILD_DIR} ${KAFKA_LIB_BUILD_DIR} ${CUDF_KAFKA_BUILD_DIR} ${CUSTREAMZ_BUILD_DIR} ${CUDF_JAR_JAVA_BUILD_DIR}"
 
 # Set defaults for vars modified by flags to this script
 VERBOSE_FLAG=""
@@ -101,6 +104,58 @@ function buildAll {
     ((${NUMARGS} == 0 )) || !(echo " ${ARGS} " | grep -q " [^-]\+ ")
 }
 
+function buildLibCudfJniInDocker {
+    local cudaVersion="11.5.0"
+    local imageName="cudf-build:${cudaVersion}-devel-centos7"
+    local CMAKE_GENERATOR="${CMAKE_GENERATOR:-Ninja}"
+    local workspaceDir="/rapids"
+    local localMavenRepo=${LOCAL_MAVEN_REPO:-"$HOME/.m2/repository"}
+    local workspaceRepoDir="$workspaceDir/cudf"
+    local workspaceMavenRepoDir="$workspaceDir/.m2/repository"
+    mkdir -p "$CUDF_JAR_JAVA_BUILD_DIR/libcudf-cmake-build"
+    nvidia-docker build \
+        -f java/ci/Dockerfile.centos7 \
+        --build-arg CUDA_VERSION=${cudaVersion} \
+        -t $imageName .
+    nvidia-docker run -it -u $(id -u):$(id -g) --rm \
+        -v "/etc/group:/etc/group:ro" \
+        -v "/etc/passwd:/etc/passwd:ro" \
+        -v "/etc/shadow:/etc/shadow:ro" \
+        -v "/etc/sudoers.d:/etc/sudoers.d:ro" \
+        -v "$REPODIR:$workspaceRepoDir:rw" \
+        -v "$localMavenRepo:$workspaceMavenRepoDir:rw" \
+        --workdir "$workspaceRepoDir/java/target/libcudf-cmake-build" \
+        ${imageName} \
+        scl enable devtoolset-9 \
+            "cmake $workspaceRepoDir/cpp \
+                -G${CMAKE_GENERATOR} \
+                -DCMAKE_BUILD_TYPE=${BUILD_TYPE} \
+                -DCUDA_STATIC_RUNTIME=ON \
+                -DCMAKE_CUDA_ARCHITECTURES=${CUDF_CMAKE_CUDA_ARCHITECTURES} \
+                -DCMAKE_INSTALL_PREFIX==/usr/local/rapids \
+                -DUSE_NVTX=ON -DCUDF_USE_ARROW_STATIC=ON \
+                -DCUDF_ENABLE_ARROW_S3=OFF \
+                -DBUILD_TESTS=OFF \
+                -DPER_THREAD_DEFAULT_STREAM=ON \
+                -DRMM_LOGGING_LEVEL=OFF \
+                -DBUILD_SHARED_LIBS=OFF && \
+             cmake --build . --parallel ${PARALLEL_LEVEL} && \
+             cd $workspaceRepoDir/java && \
+             mvn ${MVN_PHASES:-"package"} \
+                -Dmaven.repo.local=$workspaceMavenRepoDir \
+                -DskipTests=${SKIP_TESTS:-false} \
+                -Dparallel.level=${PARALLEL_LEVEL} \
+                -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"
+}
+
 if hasArg -h || hasArg --h || hasArg --help; then
     echo "${HELP}"
     exit 0
@@ -178,15 +233,21 @@ fi
 ################################################################################
 # Configure, build, and install libcudf
 
-if buildAll || hasArg libcudf; then
+if buildAll || hasArg libcudf || hasArg cudfjar; then
     if (( ${BUILD_ALL_GPU_ARCH} == 0 )); then
-        CUDF_CMAKE_CUDA_ARCHITECTURES="-DCMAKE_CUDA_ARCHITECTURES=NATIVE"
-        echo "Building for the architecture of the GPU in the system..."
+        CUDF_CMAKE_CUDA_ARCHITECTURES="${CUDF_CMAKE_CUDA_ARCHITECTURES:-NATIVE}"
+        if [[ "$CUDF_CMAKE_CUDA_ARCHITECTURES" == "NATIVE" ]]; then
+            echo "Building for the architecture of the GPU in the system..."
+        else
+            echo "Building for the GPU architecture(s) $CUDF_CMAKE_CUDA_ARCHITECTURES ..."
+        fi
     else
-        CUDF_CMAKE_CUDA_ARCHITECTURES="-DCMAKE_CUDA_ARCHITECTURES=ALL"
+        CUDF_CMAKE_CUDA_ARCHITECTURES="ALL"
         echo "Building for *ALL* supported GPU architectures..."
     fi
+fi
 
+if buildAll || hasArg libcudf; then
     # get the current count before the compile starts
     if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" && -x "$(command -v sccache)" ]]; then
         # zero the sccache statistics
@@ -195,7 +256,7 @@ if buildAll || hasArg libcudf; then
 
     cmake -S $REPODIR/cpp -B ${LIB_BUILD_DIR} \
           -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX} \
-          ${CUDF_CMAKE_CUDA_ARCHITECTURES} \
+          -DCMAKE_CUDA_ARCHITECTURES=${CUDF_CMAKE_CUDA_ARCHITECTURES} \
           -DUSE_NVTX=${BUILD_NVTX} \
           -DBUILD_TESTS=${BUILD_TESTS} \
           -DBUILD_BENCHMARKS=${BUILD_BENCHMARKS} \
@@ -262,6 +323,10 @@ if buildAll || hasArg dask_cudf; then
     fi
 fi
 
+if hasArg cudfjar; then
+    buildLibCudfJniInDocker
+fi
+
 # Build libcudf_kafka library
 if hasArg libcudf_kafka; then
     cmake -S $REPODIR/cpp/libcudf_kafka -B ${KAFKA_LIB_BUILD_DIR} \

java/ci/Dockerfile.centos7

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2020-2021, NVIDIA CORPORATION. All rights reserved.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -33,16 +33,8 @@ RUN yum install -y git zlib-devel maven tar wget patch ninja-build
 ## pre-create the CMAKE_INSTALL_PREFIX folder, set writable by any user for Jenkins
 RUN mkdir /usr/local/rapids && mkdir /rapids && chmod 777 /usr/local/rapids && chmod 777 /rapids
 
-ARG CMAKE_VERSION=3.20.5
+ARG CMAKE_VERSION=3.22.3
 RUN cd /usr/local/ && wget --quiet https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz && \
    tar zxf cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz && \
    rm cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz
 ENV PATH /usr/local/cmake-${CMAKE_VERSION}-linux-x86_64/bin:$PATH
-
-# get GDS user-space lib
-ARG GDS_VERSION=1.0.0
-RUN cd /tmp/ && wget https://developer.download.nvidia.com/gds/redist/rel-${GDS_VERSION}/gds-redistrib-${GDS_VERSION}.tgz && \
-    tar zxf gds-redistrib-${GDS_VERSION}.tgz && \
-    cp -R ./gds-redistrib-${GDS_VERSION}/targets/x86_64-linux/lib/* /usr/local/cuda/targets/x86_64-linux/lib && \
-    cp -R ./gds-redistrib-${GDS_VERSION}/targets/x86_64-linux/include/* /usr/local/cuda/targets/x86_64-linux/include && \
-    rm -rf gds-redistrib-*

java/pom.xml

@@ -173,6 +173,8 @@
         <native.build.path>${project.build.directory}/cmake-build</native.build.path>
         <slf4j.version>1.7.30</slf4j.version>
         <arrow.version>0.15.1</arrow.version>
+        <parallel.level>4</parallel.level>
+        <CUDF_CPP_BUILD_DIR/>
     </properties>
 
     <profiles>
@@ -395,8 +397,11 @@
                                 </exec>
                                 <exec dir="${native.build.path}"
                                       failonerror="true"
-                                      executable="make">
-                                    <arg value="-j"/>
+                                      executable="cmake">
+                                    <arg value="--build"/>
+                                    <arg value="."/>
+                                    <arg value="--parallel"/>
+                                    <arg value="${parallel.level}"/>
                                 </exec>
                                 <mkdir dir="${project.build.directory}/extra-resources"/>
                                 <exec executable="bash" output="${project.build.directory}/extra-resources/cudf-java-version-info.properties">

java/src/main/native/CMakeLists.txt

@@ -52,10 +52,12 @@ message(VERBOSE "CUDF_JNI: Build with static Arrow library: ${CUDF_JNI_ARROW_STA
 message(VERBOSE "CUDF_JNI: Link with libcudf statically: ${CUDF_JNI_LIBCUDF_STATIC}")
 
 set(CUDF_SOURCE_DIR "${PROJECT_SOURCE_DIR}/../../../../cpp")
-if(DEFINED ENV{CUDF_CPP_BUILD_DIR})
-  set(CUDF_CPP_BUILD_DIR "$ENV{CUDF_CPP_BUILD_DIR}")
-else()
-  set(CUDF_CPP_BUILD_DIR "${CUDF_SOURCE_DIR}/build")
+if(NOT DEFINED CUDF_CPP_BUILD_DIR OR CUDF_CPP_BUILD_DIR STREQUAL "")
+  if(DEFINED ENV{CUDF_CPP_BUILD_DIR})
+    set(CUDF_CPP_BUILD_DIR "$ENV{CUDF_CPP_BUILD_DIR}")
+  else()
+    set(CUDF_CPP_BUILD_DIR "${CUDF_SOURCE_DIR}/build")
+  endif()
 endif()
 
 set(CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/Modules/"