pitrou commented on code in PR #44053:
URL: https://github.com/apache/arrow/pull/44053#discussion_r1763223991
##########
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);
Review Comment:
This is not much better than before, is it? I would expect something like:
```suggestion
ArrayVector segment_keys(num_segment_keys);
for (auto& segment_key : segment_keys) {
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);
}
```
##########
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);
+ }
+
+ BenchmarkSegmentedAggregate(state, num_rows, {{"hash_count", ""}}, {arg},
+ std::move(keys), state.range(1), state.range(2));
+}
+BENCHMARK(CountGroupByIntsSegmentedByInts)
+ ->ArgNames({"Keys", "SegmentKeys", "Segments"})
+ ->ArgsProduct({{1, 2}, {0, 1, 2}, benchmark::CreateRange(1, 256, 8)});
Review Comment:
I've tried to use 1+ segment keys and 0 non-segment keys to get an idea of
the purely-segmented performance, but I get:
```
Invalid: The provided function (hash_count) is a hash aggregate function.
Since there are no keys to group by, a scalar aggregate function was expected
(normally these do not start with hash_)
```
It's a bit of a bummer, isn't 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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
