pitrou commented on code in PR #44073:
URL: https://github.com/apache/arrow/pull/44073#discussion_r1755124006
##########
cpp/src/parquet/arrow/reader_writer_benchmark.cc:
##########
@@ -369,6 +394,45 @@ BENCHMARK_TEMPLATE2(BM_ReadColumn, true, BooleanType)
->Args({kAlternatingOrNa, 1})
->Args({5, 10});
+//
+// Benchmark reading a PLAIN-encoded primitive column
+//
+
+template <bool nullable, typename ParquetType>
+static void BM_ReadColumnPlain(::benchmark::State& state) {
+ using c_type = typename ArrowType<ParquetType>::c_type;
+
+ const std::vector<c_type> values(BENCHMARK_SIZE, static_cast<c_type>(42));
+ std::shared_ptr<::arrow::Table> table =
+ TableFromVector<ParquetType>(values, /*nullable=*/nullable,
state.range(0));
+
+ auto properties = WriterProperties::Builder().disable_dictionary()->build();
+ BenchmarkReadTable(state, *table, properties, table->num_rows(),
+ sizeof(c_type) * table->num_rows());
+}
+
+BENCHMARK_TEMPLATE2(BM_ReadColumnPlain, false, Int32Type)
Review Comment:
Yes, and because the other benchmarks are dict-encoded.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]