[CI] Add CI pipeline to build libxgboost4j.so targeting Linux ARM64 (#10487)

dev/prepare_jvm_release.py

@@ -134,6 +134,7 @@ def main():
         print("====Creating directories to hold native binaries====")
         for os_ident, arch in [
             ("linux", "x86_64"),
+            ("linux", "aarch64"),
             ("windows", "x86_64"),
             ("macos", "x86_64"),
             ("macos", "aarch64"),
@@ -156,6 +157,14 @@ def main():
             url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/xgboost4j_{commit_hash}.dll",
             filename="xgboost4j/src/main/resources/lib/windows/x86_64/xgboost4j.dll",
         )
+        retrieve(
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_linux_x86_64_{commit_hash}.so",
+            filename="xgboost4j/src/main/resources/lib/linux/x86_64/libxgboost4j.so",
+        )
+        retrieve(
+            url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_linux_arm64_{commit_hash}.so",
+            filename="xgboost4j/src/main/resources/lib/linux/aarch64/libxgboost4j.so",
+        )
         retrieve(
             url=f"{nightly_bucket_prefix}/{git_branch}/libxgboost4j/libxgboost4j_{commit_hash}.dylib",
             filename="xgboost4j/src/main/resources/lib/macos/x86_64/libxgboost4j.dylib",
@@ -166,22 +175,6 @@ def main():
         )
 
         with tempfile.TemporaryDirectory() as tempdir:
-            # libxgboost4j.so for Linux x86_64, CPU only
-            zip_path = os.path.join(tempdir, "xgboost4j_2.12.jar")
-            extract_dir = os.path.join(tempdir, "xgboost4j")
-            retrieve(
-                url=f"{maven_repo_prefix}/xgboost4j_2.12/{version}/"
-                f"xgboost4j_2.12-{version}.jar",
-                filename=zip_path,
-            )
-            os.mkdir(extract_dir)
-            with zipfile.ZipFile(zip_path, "r") as t:
-                t.extractall(extract_dir)
-            cp(
-                os.path.join(extract_dir, "lib", "linux", "x86_64", "libxgboost4j.so"),
-                "xgboost4j/src/main/resources/lib/linux/x86_64/libxgboost4j.so",
-            )
-
             # libxgboost4j.so for Linux x86_64, GPU support
             zip_path = os.path.join(tempdir, "xgboost4j-gpu_2.12.jar")
             extract_dir = os.path.join(tempdir, "xgboost4j-gpu")

tests/buildkite/build-jvm-linux-arm64-manylinux2014.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source tests/buildkite/conftest.sh
+
+command_wrapper="tests/ci_build/ci_build.sh jvm_manylinux2014_aarch64"
+
+# Build XGBoost4J binary
+echo "--- Build libxgboost4j.so (targeting glibc 2.17)"
+set -x
+mkdir build
+$command_wrapper bash -c \
+  "cd build && cmake .. -DJVM_BINDINGS=ON -DUSE_OPENMP=ON && make -j$(nproc)"
+ldd lib/libxgboost4j.so
+objdump -T lib/libxgboost4j.so | grep GLIBC_ | sed 's/.*GLIBC_\([.0-9]*\).*/\1/g' | sort -Vu
+
+echo "--- Upload libxgboost4j.so"
+pushd lib
+libname=libxgboost4j_linux_arm64_${BUILDKITE_COMMIT}.so
+mv -v libxgboost4j.so ${libname}
+buildkite-agent artifact upload ${libname}
+#if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+#then
+  aws s3 cp ${libname} \
+    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
+    --acl public-read --no-progress
+#fi
+popd

tests/buildkite/build-jvm-linux-x86_64-manylinux2014.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source tests/buildkite/conftest.sh
+
+command_wrapper="tests/ci_build/ci_build.sh jvm_manylinux2014_x86_64"
+
+# Build XGBoost4J binary
+echo "--- Build libxgboost4j.so (targeting glibc 2.17)"
+set -x
+mkdir build
+$command_wrapper bash -c \
+  "cd build && cmake .. -GNinja -DJVM_BINDINGS=ON -DUSE_OPENMP=ON && ninja -v"
+ldd lib/libxgboost4j.so
+objdump -T lib/libxgboost4j.so | grep GLIBC_ | sed 's/.*GLIBC_\([.0-9]*\).*/\1/g' | sort -Vu
+
+echo "--- Upload libxgboost4j.so"
+pushd lib
+libname=libxgboost4j_linux_x86_64_${BUILDKITE_COMMIT}.so
+mv -v libxgboost4j.so ${libname}
+buildkite-agent artifact upload ${libname}
+#if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+#then
+  aws s3 cp ${libname} \
+    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
+    --acl public-read --no-progress
+#fi
+popd

tests/buildkite/build-jvm-macos-m1.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source tests/buildkite/conftest.sh
+
+# Display system info
+echo "--- Display system information"
+set -x
+system_profiler SPSoftwareDataType
+sysctl -n machdep.cpu.brand_string
+uname -m
+set +x
+
+# Build XGBoost4J binary
+echo "--- Build libxgboost4j.dylib"
+set -x
+mkdir build
+pushd build
+export JAVA_HOME=$(/usr/libexec/java_home)
+cmake .. -GNinja -DJVM_BINDINGS=ON -DUSE_OPENMP=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=10.15
+ninja -v
+popd
+rm -rf build
+otool -L lib/libxgboost.dylib
+set +x
+
+echo "--- Upload libxgboost4j.dylib"
+set -x
+pushd lib
+libname=libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
+mv -v libxgboost4j.dylib ${libname}
+buildkite-agent artifact upload ${libname}
+#if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+#then
+  aws s3 cp ${libname} \
+    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
+    --acl public-read --no-progress
+#fi
+popd
+set +x

tests/buildkite/pipeline-mac-m1.yml

@@ -1,6 +1,11 @@
 steps:
   - block: ":rocket: Run this test job"
     if: build.pull_request.id != null || build.branch =~ /^dependabot\//
+  - label: ":macos: Build libxgboost4j.dylib for MacOS M1"
+    command: "tests/buildkite/build-jvm-macos-m1.sh"
+    key: mac-m1-jvm
+    agents:
+      queue: mac-mini-m1
   - label: ":macos: Build and Test XGBoost for MacOS M1 with Clang 11"
     command: "tests/buildkite/test-macos-m1-clang11.sh"
     key: mac-m1-appleclang11

tests/buildkite/pipeline.yml

@@ -56,6 +56,16 @@ steps:
     key: build-jvm-packages
     agents:
       queue: linux-amd64-cpu
+  - label: ":console: Build libxgboost4j.so for Linux ARM64 (targeting glibc 2.17)"
+    command: "tests/buildkite/build-jvm-linux-arm64-manylinux2014.sh"
+    key: build-jvm-linux-arm64-manylinux2014
+    agents:
+      queue: linux-arm64-cpu
+  - label: ":console: Build libxgboost4j.so for Linux x86_64 (targeting glibc 2.17)"
+    command: "tests/buildkite/build-jvm-linux-x86_64-manylinux2014.sh"
+    key: build-jvm-linux-x86_64-manylinux2014
+    agents:
+      queue: linux-amd64-cpu
   - label: ":console: Build JVM package doc"
     command: "tests/buildkite/build-jvm-doc.sh"
     key: build-jvm-doc

tests/buildkite/test-macos-m1-clang11.sh

@@ -12,33 +12,6 @@ sysctl -n machdep.cpu.brand_string
 uname -m
 set +x
 
-# Build XGBoost4J binary
-echo "--- Build libxgboost4j.dylib"
-set -x
-mkdir build
-pushd build
-export JAVA_HOME=$(/usr/libexec/java_home)
-cmake .. -GNinja -DJVM_BINDINGS=ON -DUSE_OPENMP=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=10.15
-ninja -v
-popd
-rm -rf build
-otool -L lib/libxgboost.dylib
-set +x
-
-echo "--- Upload Python wheel"
-set -x
-pushd lib
-mv -v libxgboost4j.dylib libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
-buildkite-agent artifact upload libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
-if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
-then
-  aws s3 cp libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib \
-    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
-    --acl public-read --no-progress
-fi
-popd
-set +x
-
 # Ensure that XGBoost can be built with Clang 11
 echo "--- Build and Test XGBoost with MacOS M1, Clang 11"
 set -x
@@ -49,3 +22,4 @@ cmake .. -GNinja -DCMAKE_C_COMPILER=${LLVM11_PATH}/bin/clang \
   -DCMAKE_CXX_COMPILER=${LLVM11_PATH}/bin/clang++ -DGOOGLE_TEST=ON \
   -DUSE_DMLC_GTEST=ON
 ninja -v
+./testxgboost

tests/ci_build/Dockerfile.jvm_manylinux2014_aarch64

@@ -0,0 +1,17 @@
+FROM quay.io/pypa/manylinux2014_aarch64
+
+RUN yum update -y && yum install -y java-1.8.0-openjdk-devel
+
+# Install lightweight sudo (not bound to TTY)
+ENV GOSU_VERSION 1.10
+RUN set -ex; \
+    curl -o /usr/local/bin/gosu -L "https://github.com/tianon/gosu/releases/download/$GOSU_VERSION/gosu-arm64" && \
+    chmod +x /usr/local/bin/gosu && \
+    gosu nobody true
+
+# Default entry-point to use if running locally
+# It will preserve attributes of created files
+COPY entrypoint.sh /scripts/
+
+WORKDIR /workspace
+ENTRYPOINT ["/scripts/entrypoint.sh"]

tests/ci_build/Dockerfile.jvm_manylinux2014_x86_64

@@ -0,0 +1,17 @@
+FROM quay.io/pypa/manylinux2014_x86_64
+
+RUN yum update -y && yum install -y java-1.8.0-openjdk-devel ninja-build
+
+# Install lightweight sudo (not bound to TTY)
+ENV GOSU_VERSION 1.10
+RUN set -ex; \
+    curl -o /usr/local/bin/gosu -L "https://github.com/tianon/gosu/releases/download/$GOSU_VERSION/gosu-amd64" && \
+    chmod +x /usr/local/bin/gosu && \
+    gosu nobody true
+
+# Default entry-point to use if running locally
+# It will preserve attributes of created files
+COPY entrypoint.sh /scripts/
+
+WORKDIR /workspace
+ENTRYPOINT ["/scripts/entrypoint.sh"]