Merge branch 'branch-25.02' into wence/chore/pre-commit-upgrade

.github/workflows/pr.yaml

@@ -61,6 +61,7 @@ jobs:
       files_yaml: |
         test_cpp:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
@@ -71,6 +72,7 @@ jobs:
           - '!python/**'
         test_cudf_pandas:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!docs/**'
@@ -79,6 +81,7 @@ jobs:
           - '!notebooks/**'
         test_java:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
@@ -88,12 +91,14 @@ jobs:
           - '!python/**'
         test_notebooks:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
           - '!java/**'
         test_python:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'

cpp/benchmarks/CMakeLists.txt

@@ -360,8 +360,6 @@ ConfigureNVBench(
 
 # ##################################################################################################
 # * strings benchmark -------------------------------------------------------------------
-ConfigureBench(STRINGS_BENCH string/factory.cu)
-
 ConfigureNVBench(
   STRINGS_NVBENCH
   string/case.cpp
@@ -377,6 +375,7 @@ ConfigureNVBench(
   string/copy_range.cpp
   string/count.cpp
   string/extract.cpp
+  string/factory.cpp
   string/filter.cpp
   string/find.cpp
   string/find_multiple.cpp

cpp/benchmarks/string/factory.cpp

@@ -0,0 +1,60 @@
+/*
+ * Copyright (c) 2021-2024, NVIDIA CORPORATION.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <benchmarks/common/generate_input.hpp>
+
+#include <cudf/column/column_factories.hpp>
+#include <cudf/strings/detail/utilities.hpp>
+#include <cudf/strings/string_view.cuh>
+#include <cudf/strings/strings_column_view.hpp>
+#include <cudf/utilities/default_stream.hpp>
+
+#include <rmm/device_uvector.hpp>
+
+#include <nvbench/nvbench.cuh>
+
+#include <limits>
+
+static void bench_factory(nvbench::state& state)
+{
+  auto const num_rows  = static_cast<cudf::size_type>(state.get_int64("num_rows"));
+  auto const min_width = static_cast<cudf::size_type>(state.get_int64("min_width"));
+  auto const max_width = static_cast<cudf::size_type>(state.get_int64("max_width"));
+
+  data_profile const profile = data_profile_builder().distribution(
+    cudf::type_id::STRING, distribution_id::NORMAL, min_width, max_width);
+  auto const column = create_random_column(cudf::type_id::STRING, row_count{num_rows}, profile);
+  auto const sv     = cudf::strings_column_view(column->view());
+
+  auto stream    = cudf::get_default_stream();
+  auto mr        = cudf::get_current_device_resource_ref();
+  auto d_strings = cudf::strings::detail::create_string_vector_from_column(sv, stream, mr);
+
+  state.set_cuda_stream(nvbench::make_cuda_stream_view(stream.value()));
+  auto chars_size = sv.chars_size(stream);
+  state.add_global_memory_reads<nvbench::int8_t>(chars_size);
+  state.add_global_memory_writes<nvbench::int8_t>(chars_size);
+
+  state.exec(nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
+    cudf::make_strings_column(d_strings, cudf::string_view{nullptr, 0});
+  });
+}
+
+NVBENCH_BENCH(bench_factory)
+  .set_name("factory")
+  .add_int64_axis("min_width", {0})
+  .add_int64_axis("max_width", {32, 64, 128, 256})
+  .add_int64_axis("num_rows", {32768, 262144, 2097152});

cpp/src/replace/nans.cu

@@ -244,7 +244,7 @@ std::unique_ptr<column> normalize_nans_and_zeros(column_view const& input,
 void normalize_nans_and_zeros(mutable_column_view& in_out, rmm::cuda_stream_view stream)
 {
   CUDF_FUNC_RANGE();
-  detail::normalize_nans_and_zeros(in_out, cudf::get_default_stream());
+  detail::normalize_nans_and_zeros(in_out, stream);
 }
 
 }  // namespace cudf

cpp/tests/streams/replace_test.cpp

@@ -107,6 +107,6 @@ TEST_F(ReplaceTest, NormalizeNansAndZerosMutable)
   auto nan          = std::numeric_limits<double>::quiet_NaN();
   auto input_column = cudf::test::make_type_param_vector<double>({-0.0, 0.0, -nan, nan, nan});
   cudf::test::fixed_width_column_wrapper<double> input(input_column.begin(), input_column.end());
-  cudf::normalize_nans_and_zeros(static_cast<cudf::mutable_column_view>(input),
-                                 cudf::test::get_default_stream());
+  cudf::mutable_column_view mutable_view = cudf::column(input, cudf::test::get_default_stream());
+  cudf::normalize_nans_and_zeros(mutable_view, cudf::test::get_default_stream());
 }

python/custreamz/custreamz/tests/test_dataframes.py

@@ -216,7 +216,13 @@ def test_set_index():
     assert_eq(b[0], df.set_index(df.y + 1))
 
 
-def test_binary_stream_operators(stream):
+def test_binary_stream_operators(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     df = cudf.DataFrame({"x": [1, 2, 3], "y": [4, 5, 6]})
 
     expected = df.x + df.y
@@ -242,7 +248,13 @@ def test_index(stream):
     assert_eq(L[1], df.index + 5)
 
 
-def test_pair_arithmetic(stream):
+def test_pair_arithmetic(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     df = cudf.DataFrame({"x": list(range(10)), "y": [1] * 10})
 
     a = DataFrame(example=df.iloc[:0], stream=stream)
@@ -255,7 +267,13 @@ def test_pair_arithmetic(stream):
     assert_eq(cudf.concat(L), (df.x + df.y) * 2)
 
 
-def test_getitem(stream):
+def test_getitem(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     df = cudf.DataFrame({"x": list(range(10)), "y": [1] * 10})
 
     a = DataFrame(example=df.iloc[:0], stream=stream)
@@ -332,7 +350,13 @@ def test_repr_html(stream):
         assert "1" in html
 
 
-def test_setitem(stream):
+def test_setitem(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     df = cudf.DataFrame({"x": list(range(10)), "y": [1] * 10})
 
     sdf = DataFrame(example=df.iloc[:0], stream=stream)
@@ -356,7 +380,13 @@ def test_setitem(stream):
     assert_eq(L[-1], df.mean())
 
 
-def test_setitem_overwrites(stream):
+def test_setitem_overwrites(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     df = cudf.DataFrame({"x": list(range(10))})
     sdf = DataFrame(example=df.iloc[:0], stream=stream)
     stream = sdf.stream
@@ -413,8 +443,14 @@ def test_setitem_overwrites(stream):
     ],
 )
 def test_rolling_count_aggregations(
-    op, window, m, pre_get, post_get, kwargs, stream
+    request, op, window, m, pre_get, post_get, kwargs, stream
 ):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream) and len(kwargs) == 0,
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     index = pd.DatetimeIndex(
         pd.date_range("2000-01-01", "2000-01-03", freq="1h")
     )
@@ -808,7 +844,13 @@ def test_reductions_with_start_state(stream):
     assert output2[0] == 360
 
 
-def test_rolling_aggs_with_start_state(stream):
+def test_rolling_aggs_with_start_state(request, stream):
+    request.applymarker(
+        pytest.mark.xfail(
+            isinstance(stream, DaskStream),
+            reason="https://github.com/dask/distributed/issues/8953",
+        )
+    )
     example = cudf.DataFrame({"name": [], "amount": []}, dtype="float64")
     sdf = DataFrame(stream, example=example)
     output0 = (