mbutrovich commented on code in PR #11818:
URL: https://github.com/apache/arrow-rs/pull/11818#discussion_r4443580226
##########
arrow-buffer/src/util/bit_chunk_iterator.rs:
##########
@@ -168,10 +170,46 @@ impl<'a> UnalignedBitChunk<'a> {
/// Counts the number of ones
pub fn count_ones(&self) -> usize {
- self.iter().map(|x| x.count_ones() as usize).sum()
+ let edges = self.prefix.into_iter().chain(self.suffix);
+ edges.map(|x| x.count_ones() as usize).sum::<usize>() +
count_ones_words(self.chunks)
}
}
+#[cfg(not(target_arch = "aarch64"))]
+fn count_ones_words(words: &[u64]) -> usize {
+ words.iter().map(|x| x.count_ones() as usize).sum()
+}
+
+/// Summing four byte popcounts in `u8` lanes before widening lets LLVM emit
one
+/// widening per 64 bytes. A `u64::count_ones` sum widens every 16 bytes. On
x86
+/// the `u64` sum measured faster (#11776), so this is only used on aarch64.
+#[cfg(target_arch = "aarch64")]
+fn count_ones_words(words: &[u64]) -> usize {
+ let (chunks, tail) = words.as_chunks::<8>();
Review Comment:
> chunks is somewhat overloaded here
I renamed the 64-byte groups to `blocks` and the constant to
`BLOCKS_PER_FLUSH`, and added a comment that a block is 8 words.
--
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]
