alamb commented on code in PR #21456:
URL: https://github.com/apache/datafusion/pull/21456#discussion_r3067858261
##########
datafusion/functions-aggregate-common/src/aggregate/count_distinct/native.rs:
##########
@@ -165,3 +165,354 @@ impl<T: ArrowPrimitiveType + Debug> Accumulator for
FloatDistinctCountAccumulato
size_of_val(self) + self.values.size()
}
}
+
+/// Optimized COUNT DISTINCT accumulator for u8 using a bool array.
+/// Uses 256 bytes to track all possible u8 values.
+#[derive(Debug)]
+pub struct BoolArray256DistinctCountAccumulator {
+ seen: [bool; 256],
+}
+
+impl BoolArray256DistinctCountAccumulator {
+ pub fn new() -> Self {
+ Self { seen: [false; 256] }
+ }
+
+ #[inline]
+ fn count(&self) -> i64 {
+ self.seen.iter().filter(|&&b| b).count() as i64
+ }
+}
+
+impl Default for BoolArray256DistinctCountAccumulator {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
+impl Accumulator for BoolArray256DistinctCountAccumulator {
+ #[inline(never)]
+ fn update_batch(&mut self, values: &[ArrayRef]) ->
datafusion_common::Result<()> {
+ if values.is_empty() {
+ return Ok(());
+ }
+
+ let arr =
as_primitive_array::<arrow::datatypes::UInt8Type>(&values[0])?;
+ for value in arr.iter().flatten() {
Review Comment:
I wonder if this need to be checking for null values?
--
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]
