Merge branch 'branch-22.12' of https://github.com/rapidsai/cudf into …

…BaseIndex_simplify
rapidsai · Oct 6, 2022 · 82f5dfc · 82f5dfc
2 parents 26216f8 + 4525474
commit 82f5dfc
Show file tree

Hide file tree

Showing 39 changed files with 1,402 additions and 1,281 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,7 @@
+# cuDF 22.12.00 (Date TBD)
+
+Please see https://github.com/rapidsai/cudf/releases/tag/v22.12.00a for the latest changes to this development branch.
+
 # cuDF 22.10.00 (Date TBD)
 
 Please see https://github.com/rapidsai/cudf/releases/tag/v22.10.00a for the latest changes to this development branch.

diff --git a/ci/benchmark/build.sh b/ci/benchmark/build.sh
@@ -37,7 +37,7 @@ export GBENCH_BENCHMARKS_DIR="$WORKSPACE/cpp/build/gbenchmarks/"
 export LIBCUDF_KERNEL_CACHE_PATH="$HOME/.jitify-cache"
 
 # Dask & Distributed option to install main(nightly) or `conda-forge` packages.
-export INSTALL_DASK_MAIN=0
+export INSTALL_DASK_MAIN=1
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
 export DASK_STABLE_VERSION="2022.9.2"

diff --git a/ci/checks/style.sh b/ci/checks/style.sh
@@ -14,7 +14,7 @@ LANG=C.UTF-8
 . /opt/conda/etc/profile.d/conda.sh
 conda activate rapids
 
-FORMAT_FILE_URL=https://raw.githubusercontent.com/rapidsai/rapids-cmake/branch-22.10/cmake-format-rapids-cmake.json
+FORMAT_FILE_URL=https://raw.githubusercontent.com/rapidsai/rapids-cmake/branch-22.12/cmake-format-rapids-cmake.json
 export RAPIDS_CMAKE_FORMAT_FILE=/tmp/rapids_cmake_ci/cmake-formats-rapids-cmake.json
 mkdir -p $(dirname ${RAPIDS_CMAKE_FORMAT_FILE})
 wget -O ${RAPIDS_CMAKE_FORMAT_FILE} ${FORMAT_FILE_URL}

diff --git a/ci/cpu/build.sh b/ci/cpu/build.sh
@@ -28,7 +28,7 @@ export CONDA_BLD_DIR="$WORKSPACE/.conda-bld"
 
 # Whether to keep `dask/label/dev` channel in the env. If INSTALL_DASK_MAIN=0,
 # `dask/label/dev` channel is removed.
-export INSTALL_DASK_MAIN=0
+export INSTALL_DASK_MAIN=1
 
 # Switch to project root; also root of repo checkout
 cd "$WORKSPACE"

diff --git a/ci/gpu/build.sh b/ci/gpu/build.sh
@@ -32,13 +32,13 @@ export MINOR_VERSION=`echo $GIT_DESCRIBE_TAG | grep -o -E '([0-9]+\.[0-9]+)'`
 unset GIT_DESCRIBE_TAG
 
 # Dask & Distributed option to install main(nightly) or `conda-forge` packages.
-export INSTALL_DASK_MAIN=0
+export INSTALL_DASK_MAIN=1
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
 export DASK_STABLE_VERSION="2022.9.2"
 
 # ucx-py version
-export UCX_PY_VERSION='0.28.*'
+export UCX_PY_VERSION='0.29.*'
 
 ################################################################################
 # TRAP - Setup trap for removing jitify cache

diff --git a/ci/gpu/java.sh b/ci/gpu/java.sh
@@ -31,7 +31,7 @@ export GIT_DESCRIBE_TAG=`git describe --tags`
 export MINOR_VERSION=`echo $GIT_DESCRIBE_TAG | grep -o -E '([0-9]+\.[0-9]+)'`
 
 # ucx-py version
-export UCX_PY_VERSION='0.28.*'
+export UCX_PY_VERSION='0.29.*'
 
 ################################################################################
 # TRAP - Setup trap for removing jitify cache

diff --git a/conda/environments/cudf_dev_cuda11.5.yml b/conda/environments/cudf_dev_cuda11.5.yml
@@ -13,7 +13,7 @@ dependencies:
   - clang=11.1.0
   - clang-tools=11.1.0
   - cupy>=9.5.0,<12.0.0a0
-  - rmm=22.10.*
+  - rmm=22.12.*
   - cmake>=3.23.1
   - cmake_setuptools>=0.1.3
   - scikit-build>=0.13.1
@@ -49,8 +49,8 @@ dependencies:
   - pydocstyle=6.1.1
   - typing_extensions
   - pre-commit
-  - dask==2022.9.2
-  - distributed==2022.9.2
+  - dask>=2022.9.2
+  - distributed>=2022.9.2
   - streamz
   - arrow-cpp=9
   - dlpack>=0.5,<0.6.0a0
@@ -62,14 +62,15 @@ dependencies:
   - sphinx-autobuild
   - myst-nb
   - scipy
-  - dask-cuda=22.10.*
+  - dask-cuda=22.12.*
   - mimesis<4.1
   - packaging
   - protobuf>=3.20.1,<3.21.0a0
   - nvtx>=0.2.1
   - cachetools
   - transformers<=4.10.3
   - pydata-sphinx-theme
+  - pyorc
   - librdkafka=1.7.0
   - python-confluent-kafka=1.7.0
   - moto>=3.1.6
@@ -79,9 +80,6 @@ dependencies:
   - s3fs>=2022.3.0
   - werkzeug<2.2.0 # Temporary transient dependency pinning to avoid URL-LIB3 + moto timeouts
   - pytorch<1.12.0
-  - pip:
-      - git+https://github.com/python-streamz/streamz.git@master
-      - pyorc
   - cubinlinker  # [linux64]
   - gcc_linux-64=9.* # [linux64]
   - sysroot_linux-64==2.17 # [linux64]
@@ -90,3 +88,5 @@ dependencies:
   # - gcc_linux-aarch64=9.* # [aarch64]
   # - sysroot_linux-aarch64==2.17 # [aarch64]
   # - nvcc_linux-aarch64=11.5 # [aarch64]
+  - pip:
+      - git+https://github.com/python-streamz/streamz.git@master
diff --git a/conda/recipes/custreamz/meta.yaml b/conda/recipes/custreamz/meta.yaml
@@ -29,8 +29,8 @@ requirements:
     - python
     - streamz
     - cudf ={{ version }}
-    - dask==2022.9.2
-    - distributed==2022.9.2
+    - dask>=2022.9.2
+    - distributed>=2022.9.2
     - python-confluent-kafka >=1.7.0,<1.8.0a0
     - cudf_kafka ={{ version }}
 

diff --git a/conda/recipes/dask-cudf/meta.yaml b/conda/recipes/dask-cudf/meta.yaml
@@ -24,14 +24,14 @@ requirements:
   host:
     - python
     - cudf ={{ version }}
-    - dask==2022.9.2
-    - distributed==2022.9.2
+    - dask>=2022.9.2
+    - distributed>=2022.9.2
     - cudatoolkit ={{ cuda_version }}
   run:
     - python
     - cudf ={{ version }}
-    - dask==2022.9.2
-    - distributed==2022.9.2
+    - dask>=2022.9.2
+    - distributed>=2022.9.2
     - {{ pin_compatible('cudatoolkit', max_pin='x', min_pin='x') }}
 
 test:                                   # [linux64]

diff --git a/cpp/CMakeLists.txt b/cpp/CMakeLists.txt
@@ -25,7 +25,7 @@ rapids_cuda_init_architectures(CUDF)
 
 project(
   CUDF
-  VERSION 22.10.00
+  VERSION 22.12.00
   LANGUAGES C CXX CUDA
 )
 if(CMAKE_CUDA_COMPILER_ID STREQUAL "NVIDIA" AND CMAKE_CUDA_COMPILER_VERSION VERSION_LESS 11.5)

diff --git a/cpp/benchmarks/io/csv/csv_writer.cpp b/cpp/benchmarks/io/csv/csv_writer.cpp
@@ -26,8 +26,6 @@
 constexpr size_t data_size         = 256 << 20;
 constexpr cudf::size_type num_cols = 64;
 
-namespace cudf_io = cudf::io;
-
 class CsvWrite : public cudf::benchmark {
 };
 
@@ -44,9 +42,9 @@ void BM_csv_write_varying_inout(benchmark::State& state)
   auto mem_stats_logger = cudf::memory_stats_logger();
   for (auto _ : state) {
     cuda_event_timer raii(state, true);  // flush_l2_cache = true, stream = 0
-    cudf_io::csv_writer_options options =
-      cudf_io::csv_writer_options::builder(source_sink.make_sink_info(), view).include_header(true);
-    cudf_io::write_csv(options);
+    cudf::io::csv_writer_options options =
+      cudf::io::csv_writer_options::builder(source_sink.make_sink_info(), view);
+    cudf::io::write_csv(options);
   }
 
   state.SetBytesProcessed(data_size * state.iterations());
@@ -74,12 +72,11 @@ void BM_csv_write_varying_options(benchmark::State& state)
   auto mem_stats_logger = cudf::memory_stats_logger();
   for (auto _ : state) {
     cuda_event_timer raii(state, true);  // flush_l2_cache = true, stream = 0
-    cudf_io::csv_writer_options options =
-      cudf_io::csv_writer_options::builder(source_sink.make_sink_info(), view)
-        .include_header(true)
+    cudf::io::csv_writer_options options =
+      cudf::io::csv_writer_options::builder(source_sink.make_sink_info(), view)
         .na_rep(na_per)
         .rows_per_chunk(rows_per_chunk);
-    cudf_io::write_csv(options);
+    cudf::io::write_csv(options);
   }
 
   state.SetBytesProcessed(data_size * state.iterations());

diff --git a/cpp/benchmarks/io/cuio_common.cpp b/cpp/benchmarks/io/cuio_common.cpp
@@ -23,8 +23,6 @@
 
 #include <unistd.h>
 
-namespace cudf_io = cudf::io;
-
 temp_directory const cuio_source_sink_pair::tmpdir{"cudf_gbench"};
 
 std::string random_file_in_dir(std::string const& dir_path)
@@ -43,21 +41,21 @@ cuio_source_sink_pair::cuio_source_sink_pair(io_type type)
 {
 }
 
-cudf_io::source_info cuio_source_sink_pair::make_source_info()
+cudf::io::source_info cuio_source_sink_pair::make_source_info()
 {
   switch (type) {
-    case io_type::FILEPATH: return cudf_io::source_info(file_name);
-    case io_type::HOST_BUFFER: return cudf_io::source_info(buffer.data(), buffer.size());
+    case io_type::FILEPATH: return cudf::io::source_info(file_name);
+    case io_type::HOST_BUFFER: return cudf::io::source_info(buffer.data(), buffer.size());
     default: CUDF_FAIL("invalid input type");
   }
 }
 
-cudf_io::sink_info cuio_source_sink_pair::make_sink_info()
+cudf::io::sink_info cuio_source_sink_pair::make_sink_info()
 {
   switch (type) {
-    case io_type::VOID: return cudf_io::sink_info(&void_sink);
-    case io_type::FILEPATH: return cudf_io::sink_info(file_name);
-    case io_type::HOST_BUFFER: return cudf_io::sink_info(&buffer);
+    case io_type::VOID: return cudf::io::sink_info(&void_sink);
+    case io_type::FILEPATH: return cudf::io::sink_info(file_name);
+    case io_type::HOST_BUFFER: return cudf::io::sink_info(&buffer);
     default: CUDF_FAIL("invalid output type");
   }
 }

diff --git a/cpp/doxygen/Doxyfile b/cpp/doxygen/Doxyfile
@@ -38,7 +38,7 @@ PROJECT_NAME           = "libcudf"
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
 
-PROJECT_NUMBER         = 22.10.00
+PROJECT_NUMBER         = 22.12.00
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a
@@ -2162,7 +2162,7 @@ SKIP_FUNCTION_MACROS   = YES
 # the path). If a tag file is not located in the directory in which doxygen is
 # run, you must also specify the path to the tagfile here.
 
-TAGFILES               = rmm.tag=https://docs.rapids.ai/api/librmm/22.10
+TAGFILES               = rmm.tag=https://docs.rapids.ai/api/librmm/22.12
 
 # When a file name is specified after GENERATE_TAGFILE, doxygen will create a
 # tag file that is based on the input files it reads. See section "Linking to

diff --git a/cpp/examples/basic/CMakeLists.txt b/cpp/examples/basic/CMakeLists.txt
@@ -16,7 +16,7 @@ file(
 )
 include(${CMAKE_BINARY_DIR}/cmake/get_cpm.cmake)
 
-set(CUDF_TAG branch-22.10)
+set(CUDF_TAG branch-22.12)
 CPMFindPackage(
   NAME cudf GIT_REPOSITORY https://github.com/rapidsai/cudf
   GIT_TAG ${CUDF_TAG}

diff --git a/cpp/include/cudf/detail/nvtx/nvtx3.hpp b/cpp/include/cudf/detail/nvtx/nvtx3.hpp
@@ -1907,7 +1907,7 @@ inline void mark(event_attributes const& attr) noexcept
 #define NVTX3_FUNC_RANGE_IN(D)                                                 \
   static ::nvtx3::registered_message<D> const nvtx3_func_name__{__func__};     \
   static ::nvtx3::event_attributes const nvtx3_func_attr__{nvtx3_func_name__}; \
-  ::nvtx3::domain_thread_range<D> const nvtx3_range__{nvtx3_func_attr__};
+  [[maybe_unused]] ::nvtx3::domain_thread_range<D> const nvtx3_range__{nvtx3_func_attr__};
 
 /**
  * @brief Convenience macro for generating a range in the global domain from the

diff --git a/cpp/include/cudf_test/tdigest_utilities.cuh b/cpp/include/cudf_test/tdigest_utilities.cuh
@@ -118,7 +118,7 @@ void tdigest_minmax_compare(cudf::tdigest::tdigest_column_view const& tdv,
   // verify min/max
   thrust::host_vector<device_span<T const>> h_spans;
   h_spans.push_back({input_values.begin<T>(), static_cast<size_t>(input_values.size())});
-  thrust::device_vector<device_span<T const>> spans(h_spans);
+  auto spans = cudf::detail::make_device_uvector_async(h_spans, cudf::default_stream_value);
 
   auto expected_min = cudf::make_fixed_width_column(
     data_type{type_id::FLOAT64}, spans.size(), mask_state::UNALLOCATED);

diff --git a/cpp/libcudf_kafka/CMakeLists.txt b/cpp/libcudf_kafka/CMakeLists.txt
@@ -22,7 +22,7 @@ include(rapids-find)
 
 project(
   CUDA_KAFKA
-  VERSION 22.10.00
+  VERSION 22.12.00
   LANGUAGES CXX
 )
 

diff --git a/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh b/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh
@@ -25,7 +25,6 @@
 #include <cudf/detail/iterator.cuh>
 #include <cudf/detail/utilities/element_argminmax.cuh>
 #include <cudf/detail/valid_if.cuh>
-#include <cudf/table/row_operators.cuh>
 #include <cudf/types.hpp>
 #include <cudf/utilities/span.hpp>