Merge remote-tracking branch 'upstream/branch-25.02' into cudf/_libs/…

…transpose

.github/workflows/pr.yaml

@@ -10,6 +10,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  # Please keep pr-builder as the top job here
   pr-builder:
     needs:
       - changed-files
@@ -37,13 +38,23 @@ jobs:
       - unit-tests-cudf-pandas
       - pandas-tests
       - pandas-tests-diff
+      - telemetry-setup
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     if: always()
     with:
       needs: ${{ toJSON(needs) }}
+  telemetry-setup:
+    continue-on-error: true
+    runs-on: ubuntu-latest
+    env:
+      OTEL_SERVICE_NAME: 'pr-cudf'
+    steps:
+      - name: Telemetry setup
+        uses: rapidsai/shared-actions/telemetry-dispatch-stash-base-env-vars@main
   changed-files:
     secrets: inherit
+    needs: telemetry-setup
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
       files_yaml: |
@@ -91,9 +102,11 @@ jobs:
           - '!notebooks/**'
   checks:
     secrets: inherit
+    needs: telemetry-setup
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
       enable_check_generated_files: false
+      ignored_pr_jobs: "telemetry-summarize"
   conda-cpp-build:
     needs: checks
     secrets: inherit
@@ -259,6 +272,7 @@ jobs:
       script: ci/test_wheel_dask_cudf.sh
   devcontainer:
     secrets: inherit
+    needs: telemetry-setup
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
       arch: '["amd64"]'
@@ -298,3 +312,18 @@ jobs:
         node_type: cpu4
         build_type: pull-request
         run_script: "ci/cudf_pandas_scripts/pandas-tests/diff.sh"
+
+  telemetry-summarize:
+    runs-on: ubuntu-latest
+    needs: pr-builder
+    if: always()
+    continue-on-error: true
+    steps:
+      - name: Load stashed telemetry env vars
+        uses: rapidsai/shared-actions/telemetry-dispatch-load-base-env-vars@main
+        with:
+            load_service_name: true
+      - name: Telemetry summarize
+        uses: rapidsai/shared-actions/telemetry-dispatch-write-summary@main
+        with:
+          cert_concat: "${{ secrets.OTEL_EXPORTER_OTLP_CA_CERTIFICATE }};${{ secrets.OTEL_EXPORTER_OTLP_CLIENT_CERTIFICATE }};${{ secrets.OTEL_EXPORTER_OTLP_CLIENT_KEY }}"

.github/workflows/test.yaml

@@ -121,8 +121,6 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
-      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
-      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
       build_type: nightly
       branch: ${{ inputs.branch }}
       date: ${{ inputs.date }}
@@ -153,8 +151,6 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
-      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
-      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
       build_type: nightly
       branch: ${{ inputs.branch }}
       date: ${{ inputs.date }}
@@ -164,8 +160,6 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
-      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
-      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
       build_type: nightly
       branch: ${{ inputs.branch }}
       date: ${{ inputs.date }}

ci/run_cudf_polars_polars_tests.sh

@@ -12,8 +12,29 @@ DESELECTED_TESTS=(
     "tests/unit/streaming/test_streaming_sort.py::test_streaming_sort[True]" # relies on polars built in debug mode
     "tests/unit/test_cpu_check.py::test_check_cpu_flags_skipped_no_flags" # Mock library error
     "tests/docs/test_user_guide.py" # No dot binary in CI image
+    "tests/unit/test_polars_import.py::test_fork_safety" # test started to hang in polars-1.14
+    "tests/unit/operations/test_join.py::test_join_4_columns_with_validity" # fails in some systems, see https://github.com/pola-rs/polars/issues/19870
+    "tests/unit/io/test_csv.py::test_read_web_file" # fails in rockylinux8 due to SSL CA issues
 )
 
+if [[ $(arch) == "aarch64" ]]; then
+    # The binary used for TPC-H generation is compiled for x86_64, not aarch64.
+    DESELECTED_TESTS+=("tests/benchmark/test_pdsh.py::test_pdsh")
+    # The connectorx package is not available on arm
+    DESELECTED_TESTS+=("tests/unit/io/database/test_read.py::test_read_database")
+    # The necessary timezone information cannot be found in our CI image.
+    DESELECTED_TESTS+=("tests/unit/io/test_parquet.py::test_parametric_small_page_mask_filtering")
+    DESELECTED_TESTS+=("tests/unit/testing/test_assert_series_equal.py::test_assert_series_equal_parametric")
+    DESELECTED_TESTS+=("tests/unit/operations/test_join.py::test_join_4_columns_with_validity")
+else
+    # Ensure that we don't run dbgen when it uses newer symbols than supported by the glibc version in the CI image.
+    glibc_minor_version=$(ldd --version | head -1 | grep -o "[0-9]\.[0-9]\+" | tail -1 | cut -d '.' -f2)
+    latest_glibc_symbol_found=$(nm py-polars/tests/benchmark/data/pdsh/dbgen/dbgen | grep GLIBC | grep -o "[0-9]\.[0-9]\+" | sort --version-sort | tail -1 | cut -d "." -f 2)
+    if [[ ${glibc_minor_version} -lt ${latest_glibc_symbol_found} ]]; then
+        DESELECTED_TESTS+=("tests/benchmark/test_pdsh.py::test_pdsh")
+    fi
+fi
+
 DESELECTED_TESTS=$(printf -- " --deselect %s" "${DESELECTED_TESTS[@]}")
 python -m pytest \
        --import-mode=importlib \

conda/environments/all_cuda-118_arch-x86_64.yaml

@@ -66,7 +66,7 @@ dependencies:
 - pandas
 - pandas>=2.0,<2.2.4dev0
 - pandoc
-- polars>=1.11,<1.14
+- polars>=1.11,<1.15
 - pre-commit
 - ptxcompiler
 - pyarrow>=14.0.0,<19.0.0a0

conda/environments/all_cuda-125_arch-x86_64.yaml

@@ -64,7 +64,7 @@ dependencies:
 - pandas
 - pandas>=2.0,<2.2.4dev0
 - pandoc
-- polars>=1.11,<1.14
+- polars>=1.11,<1.15
 - pre-commit
 - pyarrow>=14.0.0,<19.0.0a0
 - pydata-sphinx-theme!=0.14.2

conda/recipes/cudf-polars/meta.yaml

@@ -43,7 +43,7 @@ requirements:
   run:
     - python
     - pylibcudf ={{ version }}
-    - polars >=1.11,<1.14
+    - polars >=1.11,<1.15
     - {{ pin_compatible('cuda-version', max_pin='x', min_pin='x') }}
 
 test:

cpp/CMakeLists.txt

@@ -464,6 +464,7 @@ add_library(
   src/io/avro/avro_gpu.cu
   src/io/avro/reader_impl.cu
   src/io/comp/brotli_dict.cpp
+  src/io/comp/comp.cpp
   src/io/comp/cpu_unbz2.cpp
   src/io/comp/debrotli.cu
   src/io/comp/gpuinflate.cu

cpp/benchmarks/CMakeLists.txt

@@ -286,6 +286,12 @@ ConfigureNVBench(
 ConfigureBench(HASHING_BENCH hashing/partition.cpp)
 ConfigureNVBench(HASHING_NVBENCH hashing/hash.cpp)
 
+# ##################################################################################################
+# * interop benchmark ------------------------------------------------------------------------------
+ConfigureNVBench(INTEROP_NVBENCH interop/interop.cpp)
+target_link_libraries(INTEROP_NVBENCH PRIVATE nanoarrow)
+target_include_directories(INTEROP_NVBENCH PRIVATE ${CMAKE_SOURCE_DIR}/tests/interop)
+
 # ##################################################################################################
 # * merge benchmark -------------------------------------------------------------------------------
 ConfigureBench(MERGE_BENCH merge/merge.cpp)
@@ -354,10 +360,7 @@ ConfigureNVBench(
 
 # ##################################################################################################
 # * strings benchmark -------------------------------------------------------------------
-ConfigureBench(
-  STRINGS_BENCH string/factory.cu string/repeat_strings.cpp string/replace.cpp string/translate.cpp
-  string/url_decode.cu
-)
+ConfigureBench(STRINGS_BENCH string/factory.cu string/repeat_strings.cpp)
 
 ConfigureNVBench(
   STRINGS_NVBENCH
@@ -381,11 +384,14 @@ ConfigureNVBench(
   string/lengths.cpp
   string/like.cpp
   string/make_strings_column.cu
+  string/replace.cpp
   string/replace_re.cpp
   string/reverse.cpp
   string/slice.cpp
   string/split.cpp
   string/split_re.cpp
+  string/translate.cpp
+  string/url_decode.cu
 )
 
 # ##################################################################################################