zanmato1984 commented on code in PR #44053:
URL: https://github.com/apache/arrow/pull/44053#discussion_r1763379627
##########
cpp/src/arrow/acero/aggregate_benchmark.cc:
##########
@@ -866,5 +887,61 @@
BENCHMARK(TDigestKernelDoubleMedian)->Apply(QuantileKernelArgs);
BENCHMARK(TDigestKernelDoubleDeciles)->Apply(QuantileKernelArgs);
BENCHMARK(TDigestKernelDoubleCentiles)->Apply(QuantileKernelArgs);
+//
+// Segmented Aggregate
+//
+
+static void BenchmarkSegmentedAggregate(
+ benchmark::State& state, int64_t num_rows, std::vector<Aggregate>
aggregates,
+ const std::vector<std::shared_ptr<Array>>& arguments,
+ const std::vector<std::shared_ptr<Array>>& keys, int64_t num_segment_keys,
+ int64_t num_segments) {
+ ASSERT_GT(num_segments, 0);
+
+ auto rng = random::RandomArrayGenerator(42);
+ auto segment_key = rng.Int64(num_rows, /*min=*/0, /*max=*/num_segments - 1);
+ int64_t* values = segment_key->data()->GetMutableValues<int64_t>(1);
+ std::sort(values, values + num_rows);
+ // num_segment_keys copies of the segment key.
+ ArrayVector segment_keys(num_segment_keys, segment_key);
+
+ BenchmarkAggregate(state, std::move(aggregates), arguments, keys,
segment_keys);
+}
+
+template <typename... Args>
+static void CountScalarSegmentedByInts(benchmark::State& state, Args&&...) {
+ constexpr int64_t num_rows = 32 * 1024;
+
+ // A trivial column to count from.
+ auto arg = ConstantArrayGenerator::Zeroes(num_rows, int32());
+
+ BenchmarkSegmentedAggregate(state, num_rows, {{"count", ""}}, {arg}, {},
state.range(0),
+ state.range(1));
+}
+BENCHMARK(CountScalarSegmentedByInts)
+ ->ArgNames({"SegmentKeys", "Segments"})
+ ->ArgsProduct({{0, 1, 2}, benchmark::CreateRange(1, 256, 8)});
+
+template <typename... Args>
+static void CountGroupByIntsSegmentedByInts(benchmark::State& state,
Args&&...) {
+ constexpr int64_t num_rows = 32 * 1024;
+
+ // A trivial column to count from.
+ auto arg = ConstantArrayGenerator::Zeroes(num_rows, int32());
+
+ auto rng = random::RandomArrayGenerator(42);
+ int64_t num_keys = state.range(0);
+ ArrayVector keys(num_keys);
+ for (auto& key : keys) {
+ key = rng.Int64(num_rows, /*min=*/0, /*max=*/64);
Review Comment:
Generally the cardinalities of a segment key and a group by key are
relatively independent, so I chose not to use the one of segment key for group
by as well. If we want to make the group by cardinality variable, we can use
another independent parameter.
But my concerns is that the performance of segment keys and group by keys
are also independent, that is why this benchmark uses a fixed group by key
cardinality. What do you think?
--
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]
