mapleFU commented on code in PR #34323:
URL: https://github.com/apache/arrow/pull/34323#discussion_r1118619281
##########
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);
+}
+
+void DecodingByteArrayBenchmark(benchmark::State& state, Encoding::type
encoding) {
+ ::arrow::random::RandomArrayGenerator rag(0);
+ int32_t max_length = state.range(0);
+ // Using arrow to write, because we just benchmark decoding here.
+ 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);
+ encoder->Put(*array);
+ std::shared_ptr<Buffer> buf = encoder->FlushValues();
+
+ std::vector<ByteArray> values;
+ values.resize(array->length());
+ for (auto _ : state) {
+ auto decoder = MakeTypedDecoder<ByteArrayType>(encoding);
+ decoder->SetData(static_cast<int>(array->length()), buf->data(),
+ static_cast<int>(buf->size()));
+ decoder->Decode(values.data(), static_cast<int>(values.size()));
+ ::benchmark::DoNotOptimize(values);
+ }
+ state.SetItemsProcessed(state.iterations() * array->length());
+ state.counters["byte_array_bytes"] =
+ state.iterations() * array_actual->total_values_length();
+}
+
+static void BM_PlainDecodingByteArray(benchmark::State& state) {
+ DecodingByteArrayBenchmark(state, Encoding::PLAIN);
+}
+
+static void BM_DeltaBitLengthDecodingByteArray(benchmark::State& state) {
+ DecodingByteArrayBenchmark(state, Encoding::DELTA_LENGTH_BYTE_ARRAY);
+}
+
+BENCHMARK(BM_PlainEncodingByteArray)->Range(8, 1024);
+BENCHMARK(BM_DeltaBitLengthEncodingByteArray)->Range(8, 1024);
+BENCHMARK(BM_PlainDecodingByteArray)->Range(8, 1024);
+BENCHMARK(BM_DeltaBitLengthDecodingByteArray)->Range(8, 1024);
+
+static void BM_DecodingByteArraySpaced(benchmark::State& state, Encoding::type
encoding) {
+ const int num_values = 1024;
+ const double null_percent = 0.02;
+
+ auto rand = ::arrow::random::RandomArrayGenerator(0);
+ int32_t max_length = state.range(0);
+ const auto array = rand.String(num_values, /* min_length */ 0,
+ /* max_length */ max_length, null_percent);
+ const auto valid_bits = array->null_bitmap_data();
+ const int null_count = static_cast<int>(array->null_count());
+ const auto array_actual =
+ ::arrow::internal::checked_pointer_cast<::arrow::StringArray>(array);
+
+ std::vector<ByteArray> byte_arrays;
+ byte_arrays.reserve(array_actual->length());
+ for (int i = 0; i < array_actual->length(); ++i) {
+ byte_arrays.emplace_back(array_actual->GetView(i));
+ }
+
+ auto encoder = MakeTypedEncoder<ByteArrayType>(encoding);
+ encoder->PutSpaced(byte_arrays.data(), num_values, valid_bits, 0);
+ std::shared_ptr<Buffer> buf = encoder->FlushValues();
+
+ auto decoder = MakeTypedDecoder<ByteArrayType>(encoding);
+ std::vector<uint8_t> decode_values(num_values * sizeof(ByteArray));
+ auto decode_buf = reinterpret_cast<ByteArray*>(decode_values.data());
+ for (auto _ : state) {
+ decoder->SetData(num_values - null_count, buf->data(),
static_cast<int>(buf->size()));
+ decoder->DecodeSpaced(decode_buf, num_values, null_count, valid_bits, 0);
+ ::benchmark::DoNotOptimize(decode_buf);
+ }
+ state.counters["null_percent"] = null_percent * 100;
Review Comment:
`"null_percent"` is already widely used. So keep them equal
--
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]