Merge branch 'branch-24.02' into refactor-inline

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

@@ -31,7 +31,7 @@ dependencies:
 - dlpack>=0.5,<0.6.0a0
 - doxygen=1.9.1
 - fastavro>=0.22.9
-- fmt>=9.1.0,<10
+- fmt>=10.1.1,<11
 - fsspec>=0.6.0
 - gcc_linux-64=11.*
 - gmock>=1.13.0
@@ -88,7 +88,7 @@ dependencies:
 - s3fs>=2022.3.0
 - scikit-build>=0.13.1
 - scipy
-- spdlog>=1.11.0,<1.12
+- spdlog>=1.12.0,<1.13
 - sphinx
 - sphinx-autobuild
 - sphinx-copybutton

conda/environments/all_cuda-120_arch-x86_64.yaml

@@ -32,7 +32,7 @@ dependencies:
 - dlpack>=0.5,<0.6.0a0
 - doxygen=1.9.1
 - fastavro>=0.22.9
-- fmt>=9.1.0,<10
+- fmt>=10.1.1,<11
 - fsspec>=0.6.0
 - gcc_linux-64=11.*
 - gmock>=1.13.0
@@ -85,7 +85,7 @@ dependencies:
 - s3fs>=2022.3.0
 - scikit-build>=0.13.1
 - scipy
-- spdlog>=1.11.0,<1.12
+- spdlog>=1.12.0,<1.13
 - sphinx
 - sphinx-autobuild
 - sphinx-copybutton

conda/recipes/libcudf/conda_build_config.yaml

@@ -32,10 +32,10 @@ librdkafka_version:
   - ">=1.9.0,<1.10.0a0"
 
 fmt_version:
-  - ">=9.1.0,<10"
+  - ">=10.1.1,<11"
 
 spdlog_version:
-  - ">=1.11.0,<1.12"
+  - ">=1.12.0,<1.13"
 
 nvcomp_version:
   - "=3.0.4"

cpp/src/io/utilities/datasource.cpp

@@ -194,7 +194,9 @@ class memory_mapped_source : public file_source {
     if (result == cudaSuccess) {
       _is_map_registered = true;
     } else {
-      CUDF_LOG_WARN("cudaHostRegister failed with {} ({})", result, cudaGetErrorString(result));
+      CUDF_LOG_WARN("cudaHostRegister failed with {} ({})",
+                    static_cast<int>(result),
+                    cudaGetErrorString(result));
     }
   }
 
@@ -207,7 +209,9 @@ class memory_mapped_source : public file_source {
 
     auto const result = cudaHostUnregister(_map_addr);
     if (result != cudaSuccess) {
-      CUDF_LOG_WARN("cudaHostUnregister failed with {} ({})", result, cudaGetErrorString(result));
+      CUDF_LOG_WARN("cudaHostUnregister failed with {} ({})",
+                    static_cast<int>(result),
+                    cudaGetErrorString(result));
     }
   }
 

dependencies.yaml

@@ -237,7 +237,7 @@ dependencies:
     common:
       - output_types: conda
         packages:
-          - fmt>=9.1.0,<10
+          - fmt>=10.1.1,<11
           - &gbench benchmark==1.8.0
           - &gtest gtest>=1.13.0
           - &gmock gmock>=1.13.0
@@ -246,7 +246,7 @@ dependencies:
           - librdkafka>=1.9.0,<1.10.0a0
           # Align nvcomp version with rapids-cmake
           - nvcomp==3.0.4
-          - spdlog>=1.11.0,<1.12
+          - spdlog>=1.12.0,<1.13
   build_wheels:
     common:
       - output_types: [requirements, pyproject]

python/cudf/cudf/core/column/column.py

@@ -919,13 +919,21 @@ def _obtain_isin_result(self, rhs: ColumnBase) -> ColumnBase:
         Helper function for `isin` which merges `self` & `rhs`
         to determine what values of `rhs` exist in `self`.
         """
-        ldf = cudf.DataFrame({"x": self, "orig_order": arange(len(self))})
-        rdf = cudf.DataFrame(
-            {"x": rhs, "bool": full(len(rhs), True, dtype="bool")}
-        )
-        res = ldf.merge(rdf, on="x", how="left").sort_values(by="orig_order")
-        res = res.drop_duplicates(subset="orig_order", ignore_index=True)
-        return res._data["bool"].fillna(False)
+        # We've already matched dtypes by now
+        # self.isin(other) asks "which values of self are in other"
+        # contains(haystack, needles) asks "which needles are in haystack"
+        # hence this argument ordering.
+        result = libcudf.search.contains(rhs, self)
+        if self.null_count > 0:
+            # If one of the needles is null, then the result contains
+            # nulls, these nulls should be replaced by whether or not the
+            # haystack contains a null.
+            # TODO: this is unnecessary if we resolve
+            # https://github.com/rapidsai/cudf/issues/14515 by
+            # providing a mode in which cudf::contains does not mask
+            # the result.
+            result = result.fillna(rhs.null_count > 0, dtype=bool)
+        return result
 
     def as_mask(self) -> Buffer:
         """Convert booleans to bitmask

python/cudf/cudf/core/multiindex.py

@@ -747,7 +747,7 @@ def isin(self, values, level=None):
                 )
             self_df = self.to_frame(index=False).reset_index()
             values_df = values_idx.to_frame(index=False)
-            idx = self_df.merge(values_df)._data["index"]
+            idx = self_df.merge(values_df, how="leftsemi")._data["index"]
             res = cudf.core.column.full(size=len(self), fill_value=False)
             res[idx] = True
             result = res.values