From ea5f6a3986dc3c1eb54b655d88ffc82c00f20f7c Mon Sep 17 00:00:00 2001 From: Jason Lowe Date: Thu, 10 Sep 2020 14:24:40 -0500 Subject: [PATCH] Update cudf dependency to 0.16-SNAPSHOT Signed-off-by: Jason Lowe --- docs/configs.md | 2 +- docs/get-started/getting-started-on-prem.md | 4 ++-- integration_tests/README.md | 4 ++-- jenkins/Jenkinsfile.databricksnightly | 2 +- jenkins/databricks/run-tests.py | 2 +- jenkins/version-def.sh | 2 +- pom.xml | 2 +- .../src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala | 2 +- 8 files changed, 10 insertions(+), 10 deletions(-) diff --git a/docs/configs.md b/docs/configs.md index c8c5ec517b08..1dc4255904cd 100644 --- a/docs/configs.md +++ b/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: ``` -${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.15-cuda10-1.jar' \ +${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.16-SNAPSHOT-cuda10-1.jar' \ --conf spark.plugins=com.nvidia.spark.SQLPlugin \ --conf spark.rapids.sql.incompatibleOps.enabled=true ``` diff --git a/docs/get-started/getting-started-on-prem.md b/docs/get-started/getting-started-on-prem.md index bc5f165362b7..db33f905fb54 100644 --- a/docs/get-started/getting-started-on-prem.md +++ b/docs/get-started/getting-started-on-prem.md @@ -54,14 +54,14 @@ CUDA and will not run on other versions. The jars use a maven classifier to keep - CUDA 11.0 => classifier cuda11-0 For example, here is a sample version of the jars and cudf with CUDA 10.1 support: -- cudf-0.15-cuda10-1.jar +- cudf-0.16-SNAPSHOT-cuda10-1.jar - rapids-4-spark_2.12-0.1.0.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=${SPARK_RAPIDS_DIR}/cudf-0.15-cuda10-1.jar +export SPARK_CUDF_JAR=${SPARK_RAPIDS_DIR}/cudf-0.16-SNAPSHOT-cuda10-1.jar export SPARK_RAPIDS_PLUGIN_JAR=${SPARK_RAPIDS_DIR}/rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar ``` diff --git a/integration_tests/README.md b/integration_tests/README.md index 0e9bbda14f51..660635fbd644 100644 --- a/integration_tests/README.md +++ b/integration_tests/README.md @@ -39,7 +39,7 @@ Most clusters probably will not have the RAPIDS plugin installed in the cluster If just want to verify the SQL replacement is working you will need to add the `rapids-4-spark` and `cudf` jars to your `spark-submit` command. ``` -$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.15.jar" ./runtests.py +$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.16-SNAPSHOT.jar" ./runtests.py ``` You don't have to enable the plugin for this to work, the test framework will do that for you. @@ -70,7 +70,7 @@ The TPCxBB, TPCH, and Mortgage tests in this framework can be enabled by providi As an example, here is the `spark-submit` command with the TPCxBB parameters: ``` -$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.15.jar,rapids-4-spark-tests_2.12-0.2.0-SNAPSHOT.jar" ./runtests.py --tpcxbb_format="csv" --tpcxbb_path="/path/to/tpcxbb/csv" +$SPARK_HOME/bin/spark-submit --jars "rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.16-SNAPSHOT.jar,rapids-4-spark-tests_2.12-0.2.0-SNAPSHOT.jar" ./runtests.py --tpcxbb_format="csv" --tpcxbb_path="/path/to/tpcxbb/csv" ``` ## Writing tests diff --git a/jenkins/Jenkinsfile.databricksnightly b/jenkins/Jenkinsfile.databricksnightly index 82d903c49e1f..a5810a38bfa4 100644 --- a/jenkins/Jenkinsfile.databricksnightly +++ b/jenkins/Jenkinsfile.databricksnightly @@ -46,7 +46,7 @@ pipeline { string(name: 'DATABRICKS_VERSION', defaultValue: '0.3.0-SNAPSHOT', description: 'Version to set') string(name: 'CUDF_VERSION', - defaultValue: '0.15', description: 'Cudf version to use') + defaultValue: '0.16-SNAPSHOT', description: 'Cudf version to use') string(name: 'CUDA_VERSION', defaultValue: 'cuda10-1', description: 'cuda version to use') string(name: 'CLUSTER_ID', diff --git a/jenkins/databricks/run-tests.py b/jenkins/databricks/run-tests.py index 24ae2b226244..8b4bd4ba7537 100644 --- a/jenkins/databricks/run-tests.py +++ b/jenkins/databricks/run-tests.py @@ -49,7 +49,7 @@ def main(): db_version = '0.1-databricks-SNAPSHOT' scala_version = '2.12' spark_version = '3.0.0' - cudf_version = '0.15' + cudf_version = '0.16-SNAPSHOT' cuda_version = 'cuda10-1' ci_cudf_jar = 'cudf-0.14-cuda10-1.jar' base_spark_pom_version = '3.0.0' diff --git a/jenkins/version-def.sh b/jenkins/version-def.sh index d2160d0d3173..ea83ecd22d02 100755 --- a/jenkins/version-def.sh +++ b/jenkins/version-def.sh @@ -26,7 +26,7 @@ for VAR in $OVERWRITE_PARAMS;do done IFS=$PRE_IFS -CUDF_VER=${CUDF_VER:-"0.15"} +CUDF_VER=${CUDF_VER:-"0.16-SNAPSHOT"} CUDA_CLASSIFIER=${CUDA_CLASSIFIER:-"cuda10-1"} PROJECT_VER=${PROJECT_VER:-"0.3.0-SNAPSHOT"} SPARK_VER=${SPARK_VER:-"3.0.0"} diff --git a/pom.xml b/pom.xml index 3dc20a8f27a4..72c92b295141 100644 --- a/pom.xml +++ b/pom.xml @@ -149,7 +149,7 @@ 1.8 3.0.0 cuda10-1 - 0.15 + 0.16-SNAPSHOT 2.12 2.12.8 1.5.8 diff --git a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala index f8de4941962d..ae6a04e04e51 100644 --- a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala +++ b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala @@ -689,7 +689,7 @@ object RapidsConf { |On startup use: `--conf [conf key]=[conf value]`. For example: | |``` - |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.15-cuda10-1.jar' \ + |${SPARK_HOME}/bin/spark --jars 'rapids-4-spark_2.12-0.2.0-SNAPSHOT.jar,cudf-0.16-SNAPSHOT-cuda10-1.jar' \ |--conf spark.plugins=com.nvidia.spark.SQLPlugin \ |--conf spark.rapids.sql.incompatibleOps.enabled=true |```