[jvm-packages] Fix up build for xgboost4j-gpu, xgboost4j-spark-gpu (#6216)

* [CI] Clean up build for JVM packages

* Use correct path for saving native lib

* Fix groupId of maven-surefire-plugin

* Fix stashing of xgboost4j_jar_gpu

* [CI] Don't run xgboost4j-tester with GPU, since it doesn't use gpu_hist

Jenkinsfile

@@ -84,7 +84,6 @@ pipeline {
             'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', multi_gpu: true, test_rmm: true) },
             'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2', test_rmm: true) },
             'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-jvm-jdk8-cuda10.0': { CrossTestJVMwithJDKGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.0') },
             'test-jvm-jdk8': { CrossTestJVMwithJDK(jdk_version: '8', spark_version: '3.0.0') },
             'test-jvm-jdk11': { CrossTestJVMwithJDK(jdk_version: '11') },
             'test-jvm-jdk12': { CrossTestJVMwithJDK(jdk_version: '12') },
@@ -243,7 +242,7 @@ def BuildJVMPackagesWithCUDA(args) {
     ${docker_extra_params} ${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/build_jvm_packages.sh ${args.spark_version} -Duse.cuda=ON $arch_flag
     """
     echo "Stashing XGBoost4J JAR with CUDA ${args.cuda_version} ..."
-    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j/target/*.jar,jvm-packages/xgboost4j-spark/target/*.jar,jvm-packages/xgboost4j-example/target/*.jar"
+    stash name: 'xgboost4j_jar_gpu', includes: "jvm-packages/xgboost4j-gpu/target/*.jar,jvm-packages/xgboost4j-spark-gpu/target/*.jar"
     deleteDir()
   }
 }
@@ -362,24 +361,6 @@ def TestCppGPU(args) {
   }
 }
 
-def CrossTestJVMwithJDKGPU(args) {
-  def nodeReq = 'linux && mgpu'
-  node(nodeReq) {
-    unstash name: "xgboost4j_jar_gpu"
-    unstash name: 'srcs'
-    if (args.spark_version != null) {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, Spark ${args.spark_version}, CUDA ${args.host_cuda_version}"
-    } else {
-      echo "Test XGBoost4J on a machine with JDK ${args.jdk_version}, CUDA ${args.host_cuda_version}"
-    }
-    def container_type = "gpu_jvm"
-    def docker_binary = "nvidia-docker"
-    def docker_args = "--build-arg CUDA_VERSION_ARG=${args.host_cuda_version}"
-    sh "${dockerRun} ${container_type} ${docker_binary} ${docker_args} tests/ci_build/test_jvm_gpu_cross.sh"
-    deleteDir()
-  }
-}
-
 def CrossTestJVMwithJDK(args) {
   node('linux && cpu') {
     unstash name: 'xgboost4j_jar'
@@ -423,10 +404,7 @@ def DeployJVMPackages(args) {
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Deploying to xgboost-maven-repo S3 repo...'
       sh """
-      ${dockerRun} jvm docker tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 0
+      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
-      """
-      sh """
-      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION_ARG=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 1
       """
     }
     deleteDir()

jvm-packages/create_jni.py

@@ -120,30 +120,33 @@ if __name__ == "__main__":
             run(sys.executable + " mapfeat.py")
             run(sys.executable + " mknfold.py machine.txt 1")
 
+    xgboost4j = 'xgboost4j-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j'
+    xgboost4j_spark = 'xgboost4j-spark-gpu' if cli_args.use_cuda == 'ON' else 'xgboost4j-spark'
+
     print("copying native library")
     library_name = {
         "win32": "xgboost4j.dll",
         "darwin": "libxgboost4j.dylib",
         "linux": "libxgboost4j.so"
     }[sys.platform]
-    maybe_makedirs("xgboost4j/src/main/resources/lib")
+    maybe_makedirs("{}/src/main/resources/lib".format(xgboost4j))
-    cp("../lib/" + library_name, "xgboost4j/src/main/resources/lib")
+    cp("../lib/" + library_name, "{}/src/main/resources/lib".format(xgboost4j))
 
     print("copying pure-Python tracker")
     cp("../dmlc-core/tracker/dmlc_tracker/tracker.py",
-       "xgboost4j/src/main/resources")
+       "{}/src/main/resources".format(xgboost4j))
 
     print("copying train/test files")
-    maybe_makedirs("xgboost4j-spark/src/test/resources")
+    maybe_makedirs("{}/src/test/resources".format(xgboost4j_spark))
     with cd("../demo/regression"):
         run("{} mapfeat.py".format(sys.executable))
         run("{} mknfold.py machine.txt 1".format(sys.executable))
 
     for file in glob.glob("../demo/regression/machine.txt.t*"):
-        cp(file, "xgboost4j-spark/src/test/resources")
+        cp(file, "{}/src/test/resources".format(xgboost4j_spark))
     for file in glob.glob("../demo/data/agaricus.*"):
-        cp(file, "xgboost4j-spark/src/test/resources")
+        cp(file, "{}/src/test/resources".format(xgboost4j_spark))
 
-    maybe_makedirs("xgboost4j/src/test/resources")
+    maybe_makedirs("{}/src/test/resources".format(xgboost4j))
     for file in glob.glob("../demo/data/agaricus.*"):
-        cp(file, "xgboost4j/src/test/resources")
+        cp(file, "{}/src/test/resources".format(xgboost4j))

jvm-packages/pom.xml

@@ -50,12 +50,6 @@
         </repository>
     </repositories>
     <modules>
-        <module>xgboost4j</module>
-        <module>xgboost4j-example</module>
-        <module>xgboost4j-spark</module>
-	      <module>xgboost4j-flink</module>
-	      <module>xgboost4j-gpu</module>
-	      <module>xgboost4j-spark-gpu</module>
     </modules>
 
     <profiles>
@@ -65,6 +59,12 @@
             <activation>
                 <activeByDefault>true</activeByDefault>
             </activation>
+            <modules>
+                <module>xgboost4j</module>
+                <module>xgboost4j-example</module>
+                <module>xgboost4j-spark</module>
+                <module>xgboost4j-flink</module>
+            </modules>
             <build>
                 <plugins>
                     <plugin>
@@ -87,6 +87,10 @@
                     <value>ON</value>
                 </property>
             </activation>
+            <modules>
+                <module>xgboost4j-gpu</module>
+                <module>xgboost4j-spark-gpu</module>
+            </modules>
             <build>
                 <plugins>
                     <plugin>
@@ -103,6 +107,10 @@
             <properties>
                 <use.cuda>ON</use.cuda>
             </properties>
+            <modules>
+                <module>xgboost4j-gpu</module>
+                <module>xgboost4j-spark-gpu</module>
+            </modules>
             <build>
                 <plugins>
                     <plugin>
@@ -118,6 +126,14 @@
 
         <profile>
             <id>release</id>
+            <modules>
+                <module>xgboost4j</module>
+                <module>xgboost4j-example</module>
+                <module>xgboost4j-spark</module>
+                <module>xgboost4j-flink</module>
+                <module>xgboost4j-gpu</module>
+                <module>xgboost4j-spark-gpu</module>
+            </modules>
             <build>
                 <plugins>
                     <plugin>
@@ -187,6 +203,13 @@
                             <autoReleaseAfterClose>false</autoReleaseAfterClose>
                         </configuration>
                     </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-surefire-plugin</artifactId>
+                        <configuration>
+                            <skipTests>true</skipTests>
+                        </configuration>
+                    </plugin>
                 </plugins>
             </build>
         </profile>
@@ -229,6 +252,14 @@
             <properties>
                 <github.global.server>github</github.global.server>
             </properties>
+            <modules>
+                <module>xgboost4j</module>
+                <module>xgboost4j-example</module>
+                <module>xgboost4j-spark</module>
+                <module>xgboost4j-flink</module>
+                <module>xgboost4j-gpu</module>
+                <module>xgboost4j-spark-gpu</module>
+            </modules>
             <build>
                 <plugins>
                     <plugin>
@@ -265,6 +296,13 @@
                             <altDeploymentRepository>internal.repo::default::file://${project.build.directory}/mvn-repo</altDeploymentRepository>
                         </configuration>
                     </plugin>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-surefire-plugin</artifactId>
+                        <configuration>
+                            <skipTests>true</skipTests>
+                        </configuration>
+                    </plugin>
                 </plugins>
             </build>
         </profile>
@@ -290,6 +328,25 @@
                     <url>https://s3.amazonaws.com/xgboost-maven-repo/release</url>
                 </repository>
             </repositories>
+            <modules>
+                <module>xgboost4j</module>
+                <module>xgboost4j-example</module>
+                <module>xgboost4j-spark</module>
+                <module>xgboost4j-flink</module>
+                <module>xgboost4j-gpu</module>
+                <module>xgboost4j-spark-gpu</module>
+            </modules>
+            <build>
+                <plugins>
+                    <plugin>
+                        <groupId>org.apache.maven.plugins</groupId>
+                        <artifactId>maven-surefire-plugin</artifactId>
+                        <configuration>
+                            <skipTests>true</skipTests>
+                        </configuration>
+                    </plugin>
+                </plugins>
+            </build>
         </profile>
     </profiles>
     <distributionManagement>

jvm-packages/xgboost4j-gpu/src

@@ -0,0 +1 @@
+../xgboost4j/src/

jvm-packages/xgboost4j-spark-gpu/src

@@ -0,0 +1 @@
+../xgboost4j-spark/src/

jvm-packages/xgboost4j/pom.xml

@@ -86,8 +86,6 @@
                             <argument>create_jni.py</argument>
                             <argument>--log-capi-invocation</argument>
                             <argument>${log.capi.invocation}</argument>
-                            <argument>--use-cuda</argument>
-                            <argument>${use.cuda}</argument>
                           </arguments>
                           <workingDirectory>${user.dir}</workingDirectory>
                       </configuration>

tests/ci_build/build_jvm_packages.sh

@@ -10,7 +10,7 @@ gpu_arch=$3
 gpu_options=""
 if [ "x$use_cuda" == "x-Duse.cuda=ON" ]; then
   # Since building jvm for CPU will do unit tests, choose gpu-with-gpu-tests profile to build
-  gpu_options=" -Pgpu-with-gpu-tests "
+  gpu_options="$use_cuda -Pgpu-with-gpu-tests "
 fi
 
 # Initialize local Maven repository

tests/ci_build/deploy_jvm_packages.sh

@@ -3,13 +3,12 @@
 set -e
 set -x
 
-if [ $# -ne 2 ]; then
+if [ $# -ne 1 ]; then
-  echo "Usage: $0 [spark version] [build_gpu? 0 or 1]"
+  echo "Usage: $0 [spark version]"
   exit 1
 fi
 
 spark_version=$1
-build_gpu=$2
 
 # Initialize local Maven repository
 ./tests/ci_build/initialize_maven.sh
@@ -20,15 +19,7 @@ rm -rf ../build/
 
 # Re-build package without Mock Rabit
 # Deploy to S3 bucket xgboost-maven-repo
-if [[ "$build_gpu" == "0" ]]
+mvn --no-transfer-progress package deploy -Duse.cuda=ON -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
-then
-  # Build CPU artifact
-  mvn --no-transfer-progress package deploy -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
-else
-  # Build GPU artifact
-  sed -i -e 's/<artifactId>xgboost\(.*\)_\(.*\)<\/artifactId>/<artifactId>xgboost\1-gpu_\2<\/artifactId>/' $(find . -name pom.xml)
-  mvn --no-transfer-progress package deploy -Duse.cuda=ON -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
-fi
 
 set +x
 set +e

tests/ci_build/test_jvm_gpu_cross.sh

@@ -1,40 +0,0 @@
-#!/bin/bash
-
-set -e
-set -x
-
-
-nvidia-smi
-
-ls /usr/local/
-
-# Initialize local Maven repository
-./tests/ci_build/initialize_maven.sh
-
-# Get version number of XGBoost4J and other auxiliary information
-cd jvm-packages
-xgboost4j_version=$(mvn help:evaluate -Dexpression=project.version -q -DforceStdout)
-scala_binary_version=$(mvn help:evaluate -Dexpression=scala.binary.version -q -DforceStdout)
-
-python3 xgboost4j-tester/get_iris.py
-xgb_jars="./xgboost4j/target/xgboost4j_${scala_binary_version}-${xgboost4j_version}.jar,./xgboost4j-spark/target/xgboost4j-spark_${scala_binary_version}-${xgboost4j_version}.jar"
-example_jar="./xgboost4j-example/target/xgboost4j-example_${scala_binary_version}-${xgboost4j_version}.jar"
-
-echo "Run SparkTraining locally ... "
-spark-submit \
-  --master 'local[1]' \
-  --class ml.dmlc.xgboost4j.scala.example.spark.SparkTraining \
-  --jars $xgb_jars \
-    $example_jar \
-      ${PWD}/iris.csv gpu \
-
-echo "Run SparkMLlibPipeline locally ... "
-spark-submit \
-  --master 'local[1]' \
-  --class ml.dmlc.xgboost4j.scala.example.spark.SparkMLlibPipeline \
-  --jars $xgb_jars \
-    $example_jar \
-      ${PWD}/iris.csv ${PWD}/native_model ${PWD}/pipeline_model gpu \
-
-set +x
-set +e