Dandandan commented on code in PR #21586:
URL: https://github.com/apache/datafusion/pull/21586#discussion_r3106980280
##########
datafusion/physical-plan/src/aggregates/group_values/multi_group_by/bytes_view.rs:
##########
@@ -179,6 +181,133 @@ impl<B: ByteViewType> ByteViewGroupValueBuilder<B> {
}
}
+ fn vectorized_append_non_null_views(
+ &mut self,
+ array: &GenericByteViewArray<B>,
+ rows: &[usize],
+ ) {
+ let source_views = array.views();
+ self.views.reserve(rows.len());
+
+ if array.data_buffers().is_empty() {
+ self.views.extend(rows.iter().map(|&row| source_views[row]));
+ return;
+ }
+
+ let start_idx = self.views.len();
+ let mut pending = Vec::with_capacity(rows.len().saturating_add(1) / 2);
+ for (idx, &row) in rows.iter().enumerate() {
+ let view = source_views[row];
+ self.views.push(view);
+ if (view as u32) > 12 {
+ pending.push(PendingByteViewCopy {
+ dest_index: start_idx + idx,
+ source: ByteView::from(view),
+ });
+ }
+ }
+
+ self.batch_copy_long_views(array.data_buffers(), &pending);
+ }
+
+ fn vectorized_append_views_with_nulls(
+ &mut self,
+ array: &GenericByteViewArray<B>,
+ rows: &[usize],
+ ) {
+ let source_views = array.views();
+ let mut pending = Vec::with_capacity(rows.len().saturating_add(1) / 2);
+ self.views.reserve(rows.len());
+
+ for &row in rows {
Review Comment:
We should use `extend` more in this code path which reduces capacity checks
/ improves code gen.
It also reduces reallocations
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
