Move to cudf 0.18-SNAPSHOT

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:
 
 ```
-${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.17-SNAPSHOT-cuda10-1.jar' \
+${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.18-SNAPSHOT-cuda10-1.jar' \
 --conf spark.plugins=com.nvidia.spark.SQLPlugin \
 --conf spark.rapids.sql.incompatibleOps.enabled=true
 ```

docs/get-started/Dockerfile.cuda

@@ -53,7 +53,7 @@ COPY spark-3.0.1-bin-hadoop3.2/examples /opt/spark/examples
 COPY spark-3.0.1-bin-hadoop3.2/kubernetes/tests /opt/spark/tests
 COPY spark-3.0.1-bin-hadoop3.2/data /opt/spark/data
 
-COPY cudf-0.17-SNAPSHOT-cuda10-1.jar /opt/sparkRapidsPlugin
+COPY cudf-0.18-SNAPSHOT-cuda10-1.jar /opt/sparkRapidsPlugin
 COPY rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar /opt/sparkRapidsPlugin
 COPY getGpusResources.sh /opt/sparkRapidsPlugin
 

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

@@ -55,15 +55,15 @@ CUDA and will not run on other versions. The jars use a maven classifier to keep
 - CUDA 11.0 => classifier cuda11
 
 For example, here is a sample version of the jars and cudf with CUDA 10.1 support:
-- cudf-0.17-SNAPSHOT-cuda10-1.jar
+- cudf-0.18-SNAPSHOT-cuda10-1.jar
 - rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar
 
 
 For simplicity export the location to these jars. This example assumes the sample jars above have
 been placed in the `/opt/sparkRapidsPlugin` directory:
 ```shell 
 export SPARK_RAPIDS_DIR=/opt/sparkRapidsPlugin
-export SPARK_CUDF_JAR=${SPARK_RAPIDS_DIR}/cudf-0.17-SNAPSHOT-cuda10-1.jar
+export SPARK_CUDF_JAR=${SPARK_RAPIDS_DIR}/cudf-0.18-SNAPSHOT-cuda10-1.jar
 export SPARK_RAPIDS_PLUGIN_JAR=${SPARK_RAPIDS_DIR}/rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar
 ```
 

integration_tests/README.md

@@ -128,7 +128,7 @@ Most clusters probably will not have the RAPIDS plugin installed in the cluster
 If you just want to verify the SQL replacement is working you will need to add the `rapids-4-spark` and `cudf` jars to your `spark-submit` command.
 
 ```
-$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.17-SNAPSHOT.jar" ./runtests.py
+$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.18-SNAPSHOT.jar" ./runtests.py
 ```
 
 You don't have to enable the plugin for this to work, the test framework will do that for you.
@@ -180,7 +180,7 @@ The TPCxBB, TPCH, TPCDS, and Mortgage tests in this framework can be enabled by
 As an example, here is the `spark-submit` command with the TPCxBB parameters:
 
 ```
-$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.17-SNAPSHOT.jar,rapids-4-spark-tests_2.12-0.4.0-SNAPSHOT.jar" ./runtests.py --tpcxbb_format="csv" --tpcxbb_path="/path/to/tpcxbb/csv"
+$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.18-SNAPSHOT.jar,rapids-4-spark-tests_2.12-0.4.0-SNAPSHOT.jar" ./runtests.py --tpcxbb_format="csv" --tpcxbb_path="/path/to/tpcxbb/csv"
 ```
 
 Be aware that running these tests with read data requires at least an entire GPU, and preferable several GPUs/executors
@@ -209,7 +209,7 @@ To run cudf_udf tests, need following configuration changes:
 As an example, here is the `spark-submit` command with the cudf_udf parameter:
 
 ```
-$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.17-SNAPSHOT.jar,rapids-4-spark-tests_2.12-0.4.0-SNAPSHOT.jar" --conf spark.rapids.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.memory.gpu.allocFraction=0.3 --conf spark.rapids.python.concurrentPythonWorkers=2 --py-files "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar" --conf spark.executorEnv.PYTHONPATH="rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar" ./runtests.py --cudf_udf
+$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.18-SNAPSHOT.jar,rapids-4-spark-tests_2.12-0.4.0-SNAPSHOT.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_2.12-0.4.0-SNAPSHOT.jar" --conf spark.executorEnv.PYTHONPATH="rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar" ./runtests.py --cudf_udf
 ```
 
 ## Writing tests

jenkins/Dockerfile-blossom.integration.centos7

@@ -18,7 +18,7 @@
 #
 # Arguments:
 #    CUDA_VER=10.1 or 10.2
-#    CUDF_VER=0.16 or 0.17-SNAPSHOT
+#    CUDF_VER=0.16, 0.17-SNAPSHOT, or 0.18-SNAPSHOT
 #    URM_URL=<maven repo url>
 ###
 ARG CUDA_VER=10.1

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-0.17-SNAPSHOT.jar
+    # In dev build, print 'SNAPSHOT' tag without time stamp, e.g.: cudf-0.18-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=${CUDF_VER:-"0.17-SNAPSHOT"}
+CUDF_VER=${CUDF_VER:-"0.18-SNAPSHOT"}
 CUDA_CLASSIFIER=${CUDA_CLASSIFIER:-"cuda10-1"}
 PROJECT_VER=${PROJECT_VER:-"0.4.0-SNAPSHOT"}
 SPARK_VER=${SPARK_VER:-"3.0.0"}

pom.xml

@@ -143,7 +143,7 @@
         <maven.compiler.target>1.8</maven.compiler.target>
         <spark.version>3.0.0</spark.version>
         <cuda.version>cuda10-1</cuda.version>
-        <cudf.version>0.17-SNAPSHOT</cudf.version>
+        <cudf.version>0.18-SNAPSHOT</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

@@ -824,7 +824,7 @@ object RapidsConf {
         |On startup use: `--conf [conf key]=[conf value]`. For example:
         |
         |```
-        |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.17-SNAPSHOT-cuda10-1.jar' \
+        |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.4.0-SNAPSHOT.jar,cudf-0.18-SNAPSHOT-cuda10-1.jar' \
         |--conf spark.plugins=com.nvidia.spark.SQLPlugin \
         |--conf spark.rapids.sql.incompatibleOps.enabled=true
         |```