Merge pull request #13471 from rapidsai/branch-23.06

Forward-merge branch-23.06 to branch-23.08
rapidsai · May 30, 2023 · 5e12c25 · 5e12c25
2 parents 4384c3b + 5541e64
commit 5e12c25
Show file tree

Hide file tree

Showing 4 changed files with 37 additions and 5 deletions.
diff --git a/cpp/src/filling/repeat.cu b/cpp/src/filling/repeat.cu
@@ -137,13 +137,13 @@ std::unique_ptr<table> repeat(table_view const& input_table,
                               rmm::cuda_stream_view stream,
                               rmm::mr::device_memory_resource* mr)
 {
+  if ((input_table.num_rows() == 0) || (count == 0)) { return cudf::empty_like(input_table); }
+
   CUDF_EXPECTS(count >= 0, "count value should be non-negative");
   CUDF_EXPECTS(input_table.num_rows() <= std::numeric_limits<size_type>::max() / count,
                "The resulting table exceeds the column size limit",
                std::overflow_error);
 
-  if ((input_table.num_rows() == 0) || (count == 0)) { return cudf::empty_like(input_table); }
-
   auto output_size = input_table.num_rows() * count;
   auto map_begin   = cudf::detail::make_counting_transform_iterator(
     0, [count] __device__(auto i) { return i / count; });

diff --git a/cpp/src/io/orc/stripe_enc.cu b/cpp/src/io/orc/stripe_enc.cu
@@ -1108,11 +1108,10 @@ __global__ void __launch_bounds__(compact_streams_block_size)
       for (uint32_t i = t; i < len; i += blockDim.x) {
         dst_ptr[i] = src_ptr[i];
       }
-
       __syncthreads();
-      if (t == 0) { streams[ss.column_id][group].data_ptrs[cid] = dst_ptr; }
-      dst_ptr += len;
     }
+    if (t == 0) { streams[ss.column_id][group].data_ptrs[cid] = dst_ptr; }
+    dst_ptr += len;
   }
 }
 

diff --git a/cpp/tests/filling/repeat_tests.cpp b/cpp/tests/filling/repeat_tests.cpp
@@ -174,6 +174,21 @@ TYPED_TEST(RepeatTypedTestFixture, ZeroSizeInput)
   CUDF_TEST_EXPECT_COLUMNS_EQUAL(p_ret->view().column(0), expected);
 }
 
+TYPED_TEST(RepeatTypedTestFixture, ZeroCount)
+{
+  using T = TypeParam;
+  cudf::test::fixed_width_column_wrapper<T, int32_t> input(thrust::make_counting_iterator(0),
+                                                           thrust::make_counting_iterator(10));
+
+  auto expected = cudf::make_empty_column(cudf::type_to_id<T>());
+
+  cudf::table_view input_table{{input}};
+  auto p_ret = cudf::repeat(input_table, 0);
+
+  EXPECT_EQ(p_ret->num_columns(), 1);
+  CUDF_TEST_EXPECT_COLUMNS_EQUAL(p_ret->view().column(0), expected->view());
+}
+
 class RepeatStringTestFixture : public cudf::test::BaseFixture,
                                 cudf::test::UniformRandomGenerator<cudf::size_type> {
  public:

diff --git a/cpp/tests/io/orc_test.cpp b/cpp/tests/io/orc_test.cpp
@@ -1788,4 +1788,22 @@ TEST_F(OrcChunkedWriterTest, CompStatsEmptyTable)
   expect_compression_stats_empty(stats);
 }
 
+TEST_F(OrcWriterTest, EmptyRowGroup)
+{
+  std::vector<int> ints(10000 + 5, -1);
+  auto mask = cudf::detail::make_counting_transform_iterator(0, [](auto i) { return i >= 10000; });
+  int32_col col{ints.begin(), ints.end(), mask};
+  table_view expected({col});
+
+  auto filepath = temp_env->get_temp_filepath("OrcEmptyRowGroup.orc");
+  cudf::io::orc_writer_options out_opts =
+    cudf::io::orc_writer_options::builder(cudf::io::sink_info{filepath}, expected);
+  cudf::io::write_orc(out_opts);
+
+  cudf::io::orc_reader_options in_opts =
+    cudf::io::orc_reader_options::builder(cudf::io::source_info{filepath});
+  auto result = cudf::io::read_orc(in_opts);
+  CUDF_TEST_EXPECT_TABLES_EQUAL(expected, result.tbl->view());
+}
+
 CUDF_TEST_PROGRAM_MAIN()