[GitHub] [arrow] mapleFU commented on a diff in pull request #34323: GH-34322: [C++][Parquet] Encoding Microbench for ByteArray

["mapleFU (via GitHub)" <gi...@apache.org>]

mapleFU commented on code in PR #34323:
URL: https://github.com/apache/arrow/pull/34323#discussion_r1128335912


##########
cpp/src/parquet/encoding_benchmark.cc:
##########
@@ -569,6 +569,130 @@ 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);
 
+static void ByteArrayCustomArguments(benchmark::internal::Benchmark* b) {
+  b->ArgsProduct({{8, 64, 1024}, {512, 2048}})
+      ->ArgNames({"max-string-length", "batch-size"});
+}
+
+void EncodingByteArrayBenchmark(benchmark::State& state, Encoding::type encoding) {
+  ::arrow::random::RandomArrayGenerator rag(0);
+  // Using arrow generator to generate random data.
+  int32_t max_length = static_cast<int32_t>(state.range(0));
+  int32_t array_size = static_cast<int32_t>(state.range(1));
+  auto array =
+      rag.String(/* size */ array_size, /* 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.SetBytesProcessed(state.iterations() * array_actual->total_values_length());
+}
+
+static void BM_DeltaLengthEncodingByteArray(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 = static_cast<int32_t>(state.range(0));
+  int32_t array_size = static_cast<int32_t>(state.range(1));
+  // Using arrow to write, because we just benchmark decoding here.
+  auto array =
+      rag.String(/* size */ array_size, /* 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());

Review Comment:
   `array` is an `::arrow::Array`, and `array_actual` is underlying typed array, there length are equal, so I think it's not neccessary to change it



-- 
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: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org