Rich-T-kid commented on code in PR #11925:
URL: https://github.com/apache/arrow-rs/pull/11925#discussion_r4390490360
##########
arrow/benches/merge_kernels.rs:
##########
@@ -225,6 +225,36 @@ fn bench_merge_input_on_all_masks(
}
}
+/// An Int8-keyed dictionary of `len` random keys into `distinct` string
values.
+/// Each call builds its own values array, so two calls share values but not
+/// the dictionary itself
+fn generate_int8_dictionary(seed: u64, len: usize, distinct: usize) ->
ArrayRef {
+ let mut rng = StdRng::seed_from_u64(seed);
+ let values = StringArray::from_iter_values((0..distinct).map(|i|
format!("value_{i}")));
+ let keys = Int8Array::from_iter_values((0..len).map(|_|
rng.random_range(0..distinct) as i8));
+ Arc::new(DictionaryArray::<Int8Type>::try_new(keys,
Arc::new(values)).unwrap())
+}
+
+fn bench_merge_dictionaries(c: &mut Criterion) {
+ const ARRAY_LEN: usize = 8192;
+
+ let mut group =
c.benchmark_group(format!("merge_{ARRAY_LEN}_from_int8_dictionaries"));
+ let masks = mask_cases(ARRAY_LEN);
+
+ // 2 x 50 values fit in Int8 keys when the dictionaries are concatenated,
+ // 2 x 100 values do not, so merging them has to merge the dictionaries
+ for (description, distinct) in [
+ ("array_vs_array_concatenated_values_fit", 50),
Review Comment:
okay thanks for checking
--
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]
