[RELEASE] cudf v22.04

.github/ops-bot.yaml

@@ -0,0 +1,8 @@
+# This file controls which features from the `ops-bot` repository below are enabled.
+# - https://github.com/rapidsai/ops-bot
+
+auto_merger: true
+branch_checker: true
+label_checker: true
+release_drafter: true
+external_contributors: false

.pre-commit-config.yaml

@@ -32,6 +32,8 @@ repos:
         hooks:
               - id: black
                 files: python/.*
+                additional_dependencies:
+                  - click==8.0.4
       - repo: https://github.com/PyCQA/flake8
         rev: 3.8.3
         hooks:
@@ -88,6 +90,13 @@ repos:
                 # of dependencies, so we'll have to update this manually.
                 additional_dependencies:
                   - cmake-format==0.6.11
+              - id: copyright-check
+                name: copyright-check
+                # This hook's use of Git tools appears to conflict with
+                # existing CI invocations so we don't invoke it during CI runs.
+                stages: [commit]
+                entry: python ./ci/checks/copyright.py --git-modified-only
+                language: python
 
 default_language_version:
       python: python3

build.sh

@@ -18,7 +18,7 @@ ARGS=$*
 REPODIR=$(cd $(dirname $0); pwd)
 
 VALIDARGS="clean libcudf cudf dask_cudf benchmarks tests libcudf_kafka cudf_kafka custreamz -v -g -n -l --allgpuarch --disable_nvtx --show_depr_warn --ptds -h --build_metrics --incl_cache_stats"
-HELP="$0 [clean] [libcudf] [cudf] [dask_cudf] [benchmarks] [tests] [libcudf_kafka] [cudf_kafka] [custreamz] [-v] [-g] [-n] [-h] [-l] [--cmake-args=\\\"<args>\\\"]
+HELP="$0 [clean] [libcudf] [cudf] [dask_cudf] [benchmarks] [tests] [libcudf_kafka] [cudf_kafka] [custreamz] [-v] [-g] [-n] [-h] [--cmake-args=\\\"<args>\\\"]
    clean                         - remove all existing build artifacts and configuration (start
                                    over)
    libcudf                       - build the cudf C++ code only
@@ -32,7 +32,6 @@ HELP="$0 [clean] [libcudf] [cudf] [dask_cudf] [benchmarks] [tests] [libcudf_kafk
    -v                            - verbose build mode
    -g                            - build for debug
    -n                            - no install step
-   -l                            - build legacy tests
    --allgpuarch                  - build for all supported GPU architectures
    --disable_nvtx                - disable inserting NVTX profiling ranges
    --show_depr_warn              - show cmake deprecation warnings
@@ -169,6 +168,10 @@ if hasArg clean; then
         rmdir ${bd} || true
     fi
     done
+
+    # Cleaning up python artifacts
+    find ${REPODIR}/python/ | grep -E "(__pycache__|\.pyc|\.pyo|\.so$)"  | xargs rm -rf
+
 fi
 
 
@@ -185,12 +188,9 @@ if buildAll || hasArg libcudf; then
     fi
 
     # get the current count before the compile starts
-    FILES_IN_CCACHE=""
-    if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" && -x "$(command -v ccache)" ]]; then
-        FILES_IN_CCACHE=$(ccache -s | grep "files in cache")
-        echo "$FILES_IN_CCACHE"
-        # zero the ccache statistics
-        ccache -z
+    if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" && -x "$(command -v sccache)" ]]; then
+        # zero the sccache statistics
+        sccache --zero-stats
     fi
 
     cmake -S $REPODIR/cpp -B ${LIB_BUILD_DIR} \
@@ -216,11 +216,12 @@ if buildAll || hasArg libcudf; then
         echo "Formatting build metrics"
         python ${REPODIR}/cpp/scripts/sort_ninja_log.py ${LIB_BUILD_DIR}/.ninja_log --fmt xml > ${LIB_BUILD_DIR}/ninja_log.xml
         MSG="<p>"
-        # get some ccache stats after the compile
-        if [[ "$BUILD_REPORT_INCL_CACHE_STATS"=="ON" && -x "$(command -v ccache)" ]]; then
-           MSG="${MSG}<br/>$FILES_IN_CCACHE"
-           HIT_RATE=$(ccache -s | grep "cache hit rate")
-           MSG="${MSG}<br/>${HIT_RATE}"
+        # get some sccache stats after the compile
+        if [[ "$BUILD_REPORT_INCL_CACHE_STATS" == "ON" && -x "$(command -v sccache)" ]]; then
+           COMPILE_REQUESTS=$(sccache -s | grep "Compile requests \+ [0-9]\+$" | awk '{ print $NF }')
+           CACHE_HITS=$(sccache -s | grep "Cache hits \+ [0-9]\+$" | awk '{ print $NF }')
+           HIT_RATE=$(echo - | awk "{printf \"%.2f\n\", $CACHE_HITS / $COMPILE_REQUESTS * 100}")
+           MSG="${MSG}<br/>cache hit rate ${HIT_RATE} %"
         fi
         MSG="${MSG}<br/>parallel setting: $PARALLEL_LEVEL"
         MSG="${MSG}<br/>parallel build time: $compile_total seconds"
@@ -230,6 +231,7 @@ if buildAll || hasArg libcudf; then
         fi
         echo "$MSG"
         python ${REPODIR}/cpp/scripts/sort_ninja_log.py ${LIB_BUILD_DIR}/.ninja_log --fmt html --msg "$MSG" > ${LIB_BUILD_DIR}/ninja_log.html
+        cp ${LIB_BUILD_DIR}/.ninja_log ${LIB_BUILD_DIR}/ninja.log
     fi
 
     if [[ ${INSTALL_TARGET} != "" ]]; then

ci/benchmark/build.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
 #########################################
 # cuDF GPU build and test script for CI #
 #########################################
@@ -36,8 +36,8 @@ export GBENCH_BENCHMARKS_DIR="$WORKSPACE/cpp/build/gbenchmarks/"
 # like `/tmp` is.
 export LIBCUDF_KERNEL_CACHE_PATH="$HOME/.jitify-cache"
 
-# Dask & Distributed git tag
-export DASK_DISTRIBUTED_GIT_TAG='2022.01.0'
+# Dask & Distributed option to install main(nightly) or `conda-forge` packages.
+export INSTALL_DASK_MAIN=0
 
 function remove_libcudf_kernel_cache_dir {
     EXITCODE=$?
@@ -77,11 +77,16 @@ conda install "rmm=$MINOR_VERSION.*" "cudatoolkit=$CUDA_REL" \
 # conda remove -f rapids-build-env rapids-notebook-env
 # conda install "your-pkg=1.0.0"
 
-# Install the master version of dask, distributed, and streamz
-logger "pip install git+https://github.com/dask/distributed.git@$DASK_DISTRIBUTED_GIT_TAG --upgrade --no-deps"
-pip install "git+https://github.com/dask/distributed.git@$DASK_DISTRIBUTED_GIT_TAG" --upgrade --no-deps
-logger "pip install git+https://github.com/dask/dask.git@$DASK_DISTRIBUTED_GIT_TAG --upgrade --no-deps"
-pip install "git+https://github.com/dask/dask.git@$DASK_DISTRIBUTED_GIT_TAG" --upgrade --no-deps
+# Install the conda-forge or nightly version of dask and distributed
+if [[ "${INSTALL_DASK_MAIN}" == 1 ]]; then
+    gpuci_logger "gpuci_mamba_retry update dask"
+    gpuci_mamba_retry update dask
+else
+    gpuci_logger "gpuci_mamba_retry install conda-forge::dask==2022.03.0 conda-forge::distributed==2022.03.0 conda-forge::dask-core==2022.03.0 --force-reinstall"
+    gpuci_mamba_retry install conda-forge::dask==2022.03.0 conda-forge::distributed==2022.03.0 conda-forge::dask-core==2022.03.0 --force-reinstall
+fi
+
+# Install the master version of streamz
 logger "pip install git+https://github.com/python-streamz/streamz.git@master --upgrade --no-deps"
 pip install "git+https://github.com/python-streamz/streamz.git@master" --upgrade --no-deps
 
@@ -98,11 +103,7 @@ conda list --show-channel-urls
 ################################################################################
 
 logger "Build libcudf..."
-if [[ "${BUILD_MODE}" == "pull-request" ]]; then
-    "$WORKSPACE/build.sh" clean libcudf cudf dask_cudf benchmarks tests --ptds
-else
-    "$WORKSPACE/build.sh" clean libcudf cudf dask_cudf benchmarks tests -l --ptds
-fi
+"$WORKSPACE/build.sh" clean libcudf cudf dask_cudf benchmarks tests --ptds
 
 ################################################################################
 # BENCHMARK - Run and parse libcudf and cuDF benchmarks