pitrou commented on code in PR #44053:
URL: https://github.com/apache/arrow/pull/44053#discussion_r1763231118
##########
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&&...) {
Review Comment:
So "CountScalar" is actually the case where Keys=0 but there are segment
keys?
This is quite misleading.
--
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]
