You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by "Dandandan (via GitHub)" <gi...@apache.org> on 2025/06/17 20:29:43 UTC
[PR] Speedup interleave string views [arrow-rs]
Dandandan opened a new pull request, #7695:
URL: https://github.com/apache/arrow-rs/pull/7695
# Which issue does this PR close?
We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax.
Closes #(https://github.com/apache/arrow-rs/issues/7688)
# Rationale for this change
interleave_views is *really* slow - taking up ~25% of the samples in `SortPreservingMergeExec`
Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes.
# What changes are included in this PR?
There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR.
# Are there any user-facing changes?
If there are user-facing changes then we may require documentation to be updated before approving the PR.
If there are any breaking changes to public APIs, please call them out.
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (4-7x faster) [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan merged PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (x4-6) [arrow-rs]
Posted by "mbutrovich (via GitHub)" <gi...@apache.org>.
mbutrovich commented on PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#issuecomment-2981839527
Was the change to parquet-testing submodule intended?
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (x4-6) [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#issuecomment-2981842129
> Was the change to parquet-testing submodule intended?
Thanks - fixed
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (x4-6) [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on code in PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#discussion_r2153152210
##########
arrow-select/src/interleave.rs:
##########
@@ -238,32 +237,45 @@ fn interleave_views<T: ByteViewType>(
indices: &[(usize, usize)],
) -> Result<ArrayRef, ArrowError> {
let interleaved = Interleave::<'_, GenericByteViewArray<T>>::new(values, indices);
- let mut views_builder = BufferBuilder::new(indices.len());
let mut buffers = Vec::new();
// (input array_index, input buffer_index) -> output buffer_index
- let mut buffer_lookup: HashMap<(usize, u32), u32> = HashMap::new();
- for (array_idx, value_idx) in indices {
- let array = interleaved.arrays[*array_idx];
- let raw_view = array.views().get(*value_idx).unwrap();
- let view_len = *raw_view as u32;
- if view_len <= 12 {
- views_builder.append(*raw_view);
- continue;
- }
- // value is big enough to be in a variadic buffer
- let view = ByteView::from(*raw_view);
- let new_buffer_idx: &mut u32 = buffer_lookup
- .entry((*array_idx, view.buffer_index))
- .or_insert_with(|| {
- buffers.push(array.data_buffers()[view.buffer_index as usize].clone());
- (buffers.len() - 1) as u32
- });
- views_builder.append(view.with_buffer_index(*new_buffer_idx).into());
- }
+ // A mapping from (input array_index, input buffer_index) -> output buffer_index
+ // The outer vec corresponds to the input array index.
+ // The inner vec corresponds to the buffer index within that input array.
+ // The value is the index of the buffer in the output array.
+ let mut buffer_remap: Vec<Vec<Option<u32>>> = interleaved
Review Comment:
We can perhaps store this in two vecs - (offsets / values) - let me check
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (x4-6) [arrow-rs]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on code in PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#discussion_r2153143959
##########
arrow-select/src/interleave.rs:
##########
@@ -238,32 +237,45 @@ fn interleave_views<T: ByteViewType>(
indices: &[(usize, usize)],
) -> Result<ArrayRef, ArrowError> {
let interleaved = Interleave::<'_, GenericByteViewArray<T>>::new(values, indices);
- let mut views_builder = BufferBuilder::new(indices.len());
let mut buffers = Vec::new();
// (input array_index, input buffer_index) -> output buffer_index
- let mut buffer_lookup: HashMap<(usize, u32), u32> = HashMap::new();
- for (array_idx, value_idx) in indices {
- let array = interleaved.arrays[*array_idx];
- let raw_view = array.views().get(*value_idx).unwrap();
- let view_len = *raw_view as u32;
- if view_len <= 12 {
- views_builder.append(*raw_view);
- continue;
- }
- // value is big enough to be in a variadic buffer
- let view = ByteView::from(*raw_view);
- let new_buffer_idx: &mut u32 = buffer_lookup
- .entry((*array_idx, view.buffer_index))
- .or_insert_with(|| {
- buffers.push(array.data_buffers()[view.buffer_index as usize].clone());
- (buffers.len() - 1) as u32
- });
- views_builder.append(view.with_buffer_index(*new_buffer_idx).into());
- }
+ // A mapping from (input array_index, input buffer_index) -> output buffer_index
+ // The outer vec corresponds to the input array index.
+ // The inner vec corresponds to the buffer index within that input array.
+ // The value is the index of the buffer in the output array.
Review Comment:
```suggestion
// The value is
// * Some(index of the buffer in the `buffers` array)
// * None: the input buffer has not yet been used
```
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Speedup `interleave_views` (4-7x faster) [arrow-rs]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #7695:
URL: https://github.com/apache/arrow-rs/pull/7695#issuecomment-2983586913
🥳
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org