Update cudf Java bindings to 21.06.1

docs/configs.md

@@ -10,7 +10,7 @@ The following is the list of options that `rapids-plugin-4-spark` supports.
 On startup use: `--conf [conf key]=[conf value]`. For example:
 
 ```
-${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-21.06.0.jar,cudf-21.06.0-cuda11.jar' \
+${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-21.06.0.jar,cudf-21.06.1-cuda11.jar' \
 --conf spark.plugins=com.nvidia.spark.SQLPlugin \
 --conf spark.rapids.sql.incompatibleOps.enabled=true
 ```

docs/demo/Databricks/generate-init-script-cuda11.ipynb

@@ -1 +1 @@
-{"cells":[{"cell_type":"code","source":["dbutils.fs.mkdirs(\"dbfs:/databricks/init_scripts/\")\n \ndbutils.fs.put(\"/databricks/init_scripts/init.sh\",\"\"\"\n#!/bin/bash\nsudo wget -O /databricks/jars/rapids-4-spark_2.12-21.06.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/21.06.0/rapids-4-spark_2.12-21.06.0.jar\nsudo wget -O /databricks/jars/cudf-21.06.0-cuda11.jar https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.0/cudf-21.06.0-cuda11.jar\n\nsudo wget -O /etc/apt/preferences.d/cuda-repository-pin-600 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin\nsudo wget -O ~/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb https://developer.download.nvidia.com/compute/cuda/11.0.3/local_installers/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb\nsudo dpkg -i ~/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb\nsudo apt-key add /var/cuda-repo-ubuntu1804-11-0-local/7fa2af80.pub\nsudo apt-get update\nsudo apt -y install cuda-toolkit-11-0\"\"\", True)"],"metadata":{},"outputs":[],"execution_count":1},{"cell_type":"code","source":["%sh\ncd ../../dbfs/databricks/init_scripts\npwd\nls -ltr\ncat init.sh"],"metadata":{},"outputs":[],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"generate-init-script","notebookId":2645746662301564},"nbformat":4,"nbformat_minor":0}
+{"cells":[{"cell_type":"code","source":["dbutils.fs.mkdirs(\"dbfs:/databricks/init_scripts/\")\n \ndbutils.fs.put(\"/databricks/init_scripts/init.sh\",\"\"\"\n#!/bin/bash\nsudo wget -O /databricks/jars/rapids-4-spark_2.12-21.06.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/21.06.0/rapids-4-spark_2.12-21.06.0.jar\nsudo wget -O /databricks/jars/cudf-21.06.1-cuda11.jar https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.1/cudf-21.06.1-cuda11.jar\n\nsudo wget -O /etc/apt/preferences.d/cuda-repository-pin-600 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin\nsudo wget -O ~/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb https://developer.download.nvidia.com/compute/cuda/11.0.3/local_installers/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb\nsudo dpkg -i ~/cuda-repo-ubuntu1804-11-0-local_11.0.3-450.51.06-1_amd64.deb\nsudo apt-key add /var/cuda-repo-ubuntu1804-11-0-local/7fa2af80.pub\nsudo apt-get update\nsudo apt -y install cuda-toolkit-11-0\"\"\", True)"],"metadata":{},"outputs":[],"execution_count":1},{"cell_type":"code","source":["%sh\ncd ../../dbfs/databricks/init_scripts\npwd\nls -ltr\ncat init.sh"],"metadata":{},"outputs":[],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"generate-init-script","notebookId":2645746662301564},"nbformat":4,"nbformat_minor":0}

docs/demo/Databricks/generate-init-script.ipynb

@@ -1 +1 @@
-{"cells":[{"cell_type":"code","source":["dbutils.fs.mkdirs(\"dbfs:/databricks/init_scripts/\")\n \ndbutils.fs.put(\"/databricks/init_scripts/init.sh\",\"\"\"\n#!/bin/bash\nsudo wget -O /databricks/jars/rapids-4-spark_2.12-21.06.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/21.06.0/rapids-4-spark_2.12-21.06.0.jar\nsudo wget -O /databricks/jars/cudf-21.06-cuda11.jar https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.0/cudf-21.06.0-cuda11.jar\"\"\", True)"],"metadata":{},"outputs":[],"execution_count":1},{"cell_type":"code","source":["%sh\ncd ../../dbfs/databricks/init_scripts\npwd\nls -ltr\ncat init.sh"],"metadata":{},"outputs":[],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"generate-init-script","notebookId":2645746662301564},"nbformat":4,"nbformat_minor":0}
+{"cells":[{"cell_type":"code","source":["dbutils.fs.mkdirs(\"dbfs:/databricks/init_scripts/\")\n \ndbutils.fs.put(\"/databricks/init_scripts/init.sh\",\"\"\"\n#!/bin/bash\nsudo wget -O /databricks/jars/rapids-4-spark_2.12-21.06.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/21.06.0/rapids-4-spark_2.12-21.06.0.jar\nsudo wget -O /databricks/jars/cudf-21.06.1-cuda11.jar https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.1/cudf-21.06.1-cuda11.jar\"\"\", True)"],"metadata":{},"outputs":[],"execution_count":1},{"cell_type":"code","source":["%sh\ncd ../../dbfs/databricks/init_scripts\npwd\nls -ltr\ncat init.sh"],"metadata":{},"outputs":[],"execution_count":2},{"cell_type":"code","source":[""],"metadata":{},"outputs":[],"execution_count":3}],"metadata":{"name":"generate-init-script","notebookId":2645746662301564},"nbformat":4,"nbformat_minor":0}

docs/download.md

@@ -44,7 +44,7 @@ Software Requirements:
 ### Download v21.06.0
 * Download the [RAPIDS
   Accelerator for Apache Spark 21.06.0 jar](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/21.06.0/rapids-4-spark_2.12-21.06.0.jar)
-* Download the [RAPIDS cuDF 21.06.0 jar](https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.0/cudf-21.06.0-cuda11.jar) 
+* Download the [RAPIDS cuDF 21.06.1 jar](https://repo1.maven.org/maven2/ai/rapids/cudf/21.06.1/cudf-21.06.1-cuda11.jar)
 
 This package is built against CUDA 11.2 and has [CUDA forward
 compatibility](https://docs.nvidia.com/deploy/cuda-compatibility/index.html) enabled.  It is tested

docs/get-started/Dockerfile.cuda

@@ -50,7 +50,7 @@ COPY spark-3.0.2-bin-hadoop3.2/examples /opt/spark/examples
 COPY spark-3.0.2-bin-hadoop3.2/kubernetes/tests /opt/spark/tests
 COPY spark-3.0.2-bin-hadoop3.2/data /opt/spark/data
 
-COPY cudf-21.06.0-cuda11.jar /opt/sparkRapidsPlugin
+COPY cudf-21.06.1-cuda11.jar /opt/sparkRapidsPlugin
 COPY rapids-4-spark_2.12-21.06.0.jar /opt/sparkRapidsPlugin
 COPY getGpusResources.sh /opt/sparkRapidsPlugin
 

docs/get-started/getting-started-on-prem.md

@@ -55,7 +55,7 @@ CUDA and will not run on other versions. The jars use a maven classifier to keep
 - CUDA 11.0/11.1/11.2 => classifier cuda11
 
 For example, here is a sample version of the jars and cudf with CUDA 11.0 support:
-- cudf-21.06.0-cuda11.jar
+- cudf-21.06.1-cuda11.jar
 - rapids-4-spark_2.12-21.06.0.jar
 jar that your version of the accelerator depends on.
 
@@ -64,7 +64,7 @@ For simplicity export the location to these jars. This example assumes the sampl
 been placed in the `/opt/sparkRapidsPlugin` directory:
 ```shell 
 export SPARK_RAPIDS_DIR=/opt/sparkRapidsPlugin
-export SPARK_CUDF_JAR=${SPARK_RAPIDS_DIR}/cudf-21.06.0-cuda11.jar
+export SPARK_CUDF_JAR=${SPARK_RAPIDS_DIR}/cudf-21.06.1-cuda11.jar
 export SPARK_RAPIDS_PLUGIN_JAR=${SPARK_RAPIDS_DIR}/rapids-4-spark_2.12-21.06.0.jar
 ```
 

integration_tests/README.md

@@ -158,7 +158,7 @@ If you just want to verify the SQL replacement is working you will need to add t
 example assumes CUDA 11.0 is being used.
 
 ```
-$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-21.06.0.jar,rapids-4-spark-udf-examples_2.12-21.06.0.jar,cudf-21.06.0-cuda11.jar" ./runtests.py
+$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-21.06.0.jar,rapids-4-spark-udf-examples_2.12-21.06.0.jar,cudf-21.06.1-cuda11.jar" ./runtests.py
 ```
 
 You don't have to enable the plugin for this to work, the test framework will do that for you.
@@ -249,7 +249,7 @@ To run cudf_udf tests, need following configuration changes:
 As an example, here is the `spark-submit` command with the cudf_udf parameter on CUDA 11.0:
 
 ```
-$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-21.06.0.jar,rapids-4-spark-udf-examples_2.12-21.06.0.jar,cudf-21.06.0-cuda11.jar,rapids-4-spark-tests_2.12-21.06.0.jar" --conf spark.rapids.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.concurrentPythonWorkers=2 --py-files "rapids-4-spark_2.12-21.06.0.jar" --conf spark.executorEnv.PYTHONPATH="rapids-4-spark_2.12-21.06.0.jar" ./runtests.py --cudf_udf
+$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-21.06.0.jar,rapids-4-spark-udf-examples_2.12-21.06.0.jar,cudf-21.06.1-cuda11.jar,rapids-4-spark-tests_2.12-21.06.0.jar" --conf spark.rapids.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.concurrentPythonWorkers=2 --py-files "rapids-4-spark_2.12-21.06.0.jar" --conf spark.executorEnv.PYTHONPATH="rapids-4-spark_2.12-21.06.0.jar" ./runtests.py --cudf_udf
 ```
 
 ## Writing tests

jenkins/Dockerfile-blossom.integration.centos

@@ -19,7 +19,7 @@
 # Arguments:
 #    CUDA_VER=11.0, 11.1 or 11.2.x
 #    CENTOS_VER=7 or 8
-#    CUDF_VER=21.06
+#    CUDF_VER=<cudf-py version>
 #    URM_URL=<maven repo url>
 ###
 

jenkins/Dockerfile-blossom.integration.ubuntu

@@ -21,7 +21,7 @@
 # Arguments:
 #    CUDA_VER=11.0, 11.1 or 11.2.x
 #    UBUNTU_VER=18.04 or 20.04
-#    CUDF_VER=21.06
+#    CUDF_VER=<cudf-py version>
 ###
 
 ARG CUDA_VER=11.0

jenkins/databricks/init_cudf_udf.sh

@@ -18,7 +18,7 @@
 # The initscript to set up environment for the cudf_udf tests on Databricks
 # Will be automatically pushed into the dbfs:/databricks/init_scripts once it is updated.
 
-CUDF_VER=${CUDF_VER:-21.06}
+CUDF_VER=${CUDF_VER:-21.06.01}
 
 # Use mamba to install cudf-udf packages to speed up conda resolve time
 base=$(conda info --base)

jenkins/printJarVersion.sh

@@ -24,7 +24,7 @@ function print_ver(){
     SERVER_ID=$5
 
     # Collect snapshot dependency info only in Jenkins build
-    # In dev build, print 'SNAPSHOT' tag without time stamp, e.g.: cudf-21.06.0-SNAPSHOT.jar
+    # In dev build, print 'SNAPSHOT' tag without time stamp, e.g.: cudf-<version>-SNAPSHOT.jar
     if [[ "$VERSION" == *"-SNAPSHOT" && -n "$JENKINS_URL" ]]; then
         PREFIX=${VERSION%-SNAPSHOT}
         # List the latest SNAPSHOT jar file in the maven repo

jenkins/version-def.sh

@@ -26,7 +26,7 @@ for VAR in $OVERWRITE_PARAMS;do
 done
 IFS=$PRE_IFS
 
-CUDF_VER=${CUDF_VER:-"21.06.0"}
+CUDF_VER=${CUDF_VER:-"21.06.1"}
 CUDA_CLASSIFIER=${CUDA_CLASSIFIER:-"cuda11"}
 PROJECT_VER=${PROJECT_VER:-"21.06.0-SNAPSHOT"}
 PROJECT_TEST_VER=${PROJECT_TEST_VER:-"21.06.0-SNAPSHOT"}

pom.xml

@@ -228,7 +228,7 @@
         <spark.version>${spark301.version}</spark.version>
         <spark.test.version>${spark301.version}</spark.test.version>
         <cuda.version>cuda11</cuda.version>
-        <cudf.version>21.06.0</cudf.version>
+        <cudf.version>21.06.1</cudf.version>
         <scala.binary.version>2.12</scala.binary.version>
         <scala.version>2.12.8</scala.version>
         <orc.version>1.5.8</orc.version>

sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala

@@ -1241,7 +1241,7 @@ object RapidsConf {
         |On startup use: `--conf [conf key]=[conf value]`. For example:
         |
         |```
-        |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-21.06.0.jar,cudf-21.06.0-cuda11.jar' \
+        |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-21.06.0.jar,cudf-21.06.1-cuda11.jar' \
         |--conf spark.plugins=com.nvidia.spark.SQLPlugin \
         |--conf spark.rapids.sql.incompatibleOps.enabled=true
         |```

udf-examples/src/main/cpp/CMakeLists.txt

@@ -90,7 +90,7 @@ set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -w --expt-extended-lambda --expt-relax
 set(CUDA_USE_STATIC_CUDA_RUNTIME OFF)
 
 CPMAddPackage(NAME  cudf
-        VERSION         "21.06.00"
+        VERSION         "21.06.01"
         GIT_REPOSITORY  https://github.com/rapidsai/cudf.git
         GIT_TAG         branch-21.06
         GIT_SHALLOW     TRUE