mapleFU commented on code in PR #34323:
URL: https://github.com/apache/arrow/pull/34323#discussion_r1118306858
##########
cpp/src/parquet/encoding_benchmark.cc:
##########
@@ -569,6 +569,126 @@
BENCHMARK(BM_DeltaBitPackingDecode_Int64_Narrow)->Range(MIN_RANGE, MAX_RANGE);
BENCHMARK(BM_DeltaBitPackingDecode_Int32_Wide)->Range(MIN_RANGE, MAX_RANGE);
BENCHMARK(BM_DeltaBitPackingDecode_Int64_Wide)->Range(MIN_RANGE, MAX_RANGE);
+void EncodingByteArrayBenchmark(benchmark::State& state, Encoding::type
encoding) {
+ ::arrow::random::RandomArrayGenerator rag(0);
+ // Using arrow generator to generate random data.
+ int32_t max_length = state.range(0);
+ auto array =
+ rag.String(/* size */ 1024, /* min_length */ 0, /* max_length */
max_length,
+ /* null_probability */ 0);
+ const auto array_actual =
+ ::arrow::internal::checked_pointer_cast<::arrow::StringArray>(array);
+ auto encoder = MakeTypedEncoder<ByteArrayType>(encoding);
+ std::vector<ByteArray> values;
+ for (int i = 0; i < array_actual->length(); ++i) {
+ values.emplace_back(array_actual->GetView(i));
+ }
+
+ for (auto _ : state) {
+ encoder->Put(values.data(), static_cast<int>(values.size()));
+ encoder->FlushValues();
+ }
+ state.SetItemsProcessed(state.iterations() * array_actual->length());
+ state.counters["byte_array_bytes"] =
+ state.iterations() * array_actual->total_values_length();
+}
+
+static void BM_DeltaBitLengthEncodingByteArray(benchmark::State& state) {
+ EncodingByteArrayBenchmark(state, Encoding::DELTA_LENGTH_BYTE_ARRAY);
+}
+
+static void BM_PlainEncodingByteArray(benchmark::State& state) {
+ EncodingByteArrayBenchmark(state, Encoding::PLAIN);
Review Comment:
Sure, but dictionary encoder is listed later. Let me take a look
--
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]
