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 2026/01/27 21:26:42 UTC
[PR] Optimize `UnalignedBitChunk` [arrow-rs]
Dandandan opened a new pull request, #9284:
URL: https://github.com/apache/arrow-rs/pull/9284
# 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 #NNN.
# Rationale for this change
<!--
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 these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example, are they covered by existing tests)?
-->
# 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] Optimize boolean operations [arrow-rs]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3819522617
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3819576603
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.01 210.3±9.16ns ? ?/sec 1.00 207.5±0.62ns ? ?/sec
and_sliced_1 4.23 1102.3±29.61ns ? ?/sec 1.00 260.5±1.03ns ? ?/sec
and_sliced_24 1.06 245.4±0.75ns ? ?/sec 1.00 232.3±10.65ns ? ?/sec
not 1.00 145.9±1.69ns ? ?/sec 1.03 150.4±0.53ns ? ?/sec
not_slice_24 1.02 192.4±1.27ns ? ?/sec 1.00 188.0±1.46ns ? ?/sec
not_sliced_1 3.49 627.8±33.64ns ? ?/sec 1.00 179.9±0.64ns ? ?/sec
or 1.00 197.6±2.80ns ? ?/sec 1.00 197.5±1.73ns ? ?/sec
or_sliced_1 3.92 1101.5±31.17ns ? ?/sec 1.00 280.9±12.34ns ? ?/sec
or_sliced_24 1.07 248.4±4.06ns ? ?/sec 1.00 232.1±8.23ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812696574
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (060afb8ccada7f5fa888e3b8da110bd7c803839d) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..060afb8ccada7f5fa888e3b8da110bd7c803839d)
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811003371
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811836041
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 209.5±2.43ns ? ?/sec 1.12 235.3±2.74ns ? ?/sec
and_sliced_1 4.27 1102.0±16.28ns ? ?/sec 1.00 258.3±0.80ns ? ?/sec
and_sliced_24 1.07 247.6±1.57ns ? ?/sec 1.00 230.9±0.91ns ? ?/sec
not 1.00 146.4±0.89ns ? ?/sec 1.04 151.7±1.66ns ? ?/sec
not_slice_24 1.03 194.6±2.11ns ? ?/sec 1.00 188.3±1.39ns ? ?/sec
not_sliced_1 2.58 622.6±15.57ns ? ?/sec 1.00 241.1±2.83ns ? ?/sec
or 1.00 199.3±2.13ns ? ?/sec 1.17 232.8±0.92ns ? ?/sec
or_sliced_1 3.93 1097.9±2.51ns ? ?/sec 1.00 279.3±2.24ns ? ?/sec
or_sliced_24 1.06 248.7±2.98ns ? ?/sec 1.00 234.2±1.28ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808121778
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter context decimal128 (kept 1/2) 1.08 45.0±6.00µs ? ?/sec 1.00 41.7±1.63µs ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024) 1.00 50.6±1.10µs ? ?/sec 1.02 51.8±0.92µs ? ?/sec
filter context decimal128 low selectivity (kept 1/1024) 1.02 232.1±2.99ns ? ?/sec 1.00 226.4±2.00ns ? ?/sec
filter context f32 (kept 1/2) 1.00 77.5±0.62µs ? ?/sec 1.13 87.9±0.61µs ? ?/sec
filter context f32 high selectivity (kept 1023/1024) 1.02 10.1±0.41µs ? ?/sec 1.00 9.9±0.56µs ? ?/sec
filter context f32 low selectivity (kept 1/1024) 1.02 427.5±4.68ns ? ?/sec 1.00 420.7±1.93ns ? ?/sec
filter context fsb with value length 20 (kept 1/2) 1.00 60.6±0.23µs ? ?/sec 1.16 70.5±0.24µs ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024) 1.00 60.6±0.41µs ? ?/sec 1.17 70.6±0.48µs ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024) 1.00 60.6±0.26µs ? ?/sec 1.17 70.6±0.25µs ? ?/sec
filter context fsb with value length 5 (kept 1/2) 1.00 60.6±0.54µs ? ?/sec 1.16 70.5±0.22µs ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024) 1.00 60.6±0.48µs ? ?/sec 1.17 70.6±0.87µs ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024) 1.00 60.6±0.49µs ? ?/sec 1.17 70.7±0.43µs ? ?/sec
filter context fsb with value length 50 (kept 1/2) 1.00 60.6±0.32µs ? ?/sec 1.17 70.7±0.52µs ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024) 1.00 60.6±0.33µs ? ?/sec 1.17 70.7±0.57µs ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024) 1.00 60.7±0.74µs ? ?/sec 1.17 70.7±0.88µs ? ?/sec
filter context i32 (kept 1/2) 1.01 16.7±0.10µs ? ?/sec 1.00 16.5±0.14µs ? ?/sec
filter context i32 high selectivity (kept 1023/1024) 1.09 6.8±0.41µs ? ?/sec 1.00 6.2±0.34µs ? ?/sec
filter context i32 low selectivity (kept 1/1024) 1.00 219.3±1.72ns ? ?/sec 1.01 221.9±1.43ns ? ?/sec
filter context i32 w NULLs (kept 1/2) 1.00 77.7±0.87µs ? ?/sec 1.13 87.7±1.03µs ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024) 1.01 10.3±0.41µs ? ?/sec 1.00 10.2±0.48µs ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024) 1.01 423.6±10.73ns ? ?/sec 1.00 418.9±4.40ns ? ?/sec
filter context mixed string view (kept 1/2) 1.00 104.1±4.37µs ? ?/sec 1.11 115.2±5.03µs ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024) 1.00 55.2±1.16µs ? ?/sec 1.01 55.4±1.38µs ? ?/sec
filter context mixed string view low selectivity (kept 1/1024) 1.00 605.9±4.53ns ? ?/sec 1.02 616.7±9.10ns ? ?/sec
filter context short string view (kept 1/2) 1.00 106.7±6.58µs ? ?/sec 1.14 122.0±6.87µs ? ?/sec
filter context short string view high selectivity (kept 1023/1024) 1.00 53.8±1.46µs ? ?/sec 1.03 55.3±1.01µs ? ?/sec
filter context short string view low selectivity (kept 1/1024) 1.01 475.7±18.16ns ? ?/sec 1.00 472.6±2.53ns ? ?/sec
filter context string (kept 1/2) 1.00 578.8±7.31µs ? ?/sec 1.04 603.4±15.56µs ? ?/sec
filter context string dictionary (kept 1/2) 1.00 16.9±0.31µs ? ?/sec 1.04 17.5±0.71µs ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024) 1.03 7.2±0.51µs ? ?/sec 1.00 7.0±0.48µs ? ?/sec
filter context string dictionary low selectivity (kept 1/1024) 1.00 637.7±4.22ns ? ?/sec 1.00 637.0±3.36ns ? ?/sec
filter context string dictionary w NULLs (kept 1/2) 1.00 78.5±1.31µs ? ?/sec 1.13 88.5±0.71µs ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024) 1.00 10.5±0.40µs ? ?/sec 1.03 10.8±0.58µs ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024) 1.01 865.4±5.85ns ? ?/sec 1.00 856.5±53.29ns ? ?/sec
filter context string high selectivity (kept 1023/1024) 1.00 634.1±22.32µs ? ?/sec 1.02 646.8±20.49µs ? ?/sec
filter context string low selectivity (kept 1/1024) 1.00 909.3±3.51ns ? ?/sec 1.08 985.7±12.71ns ? ?/sec
filter context u8 (kept 1/2) 1.00 15.0±0.10µs ? ?/sec 1.00 15.0±0.15µs ? ?/sec
filter context u8 high selectivity (kept 1023/1024) 1.09 1997.8±17.80ns ? ?/sec 1.00 1836.2±11.64ns ? ?/sec
filter context u8 low selectivity (kept 1/1024) 1.01 215.2±4.55ns ? ?/sec 1.00 213.9±0.83ns ? ?/sec
filter context u8 w NULLs (kept 1/2) 1.00 76.0±0.63µs ? ?/sec 1.13 85.9±0.39µs ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024) 1.01 5.1±0.04µs ? ?/sec 1.00 5.0±0.06µs ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024) 1.00 418.1±4.15ns ? ?/sec 1.00 417.6±6.57ns ? ?/sec
filter decimal128 (kept 1/2) 1.11 51.1±5.46µs ? ?/sec 1.00 45.8±4.29µs ? ?/sec
filter decimal128 high selectivity (kept 1023/1024) 1.04 55.2±0.82µs ? ?/sec 1.00 53.3±1.33µs ? ?/sec
filter decimal128 low selectivity (kept 1/1024) 1.91 3.2±0.03µs ? ?/sec 1.00 1658.8±9.53ns ? ?/sec
filter f32 (kept 1/2) 1.12 141.2±1.65µs ? ?/sec 1.00 126.2±0.75µs ? ?/sec
filter fsb with value length 20 (kept 1/2) 1.09 137.4±2.22µs ? ?/sec 1.00 126.4±0.89µs ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024) 1.00 71.2±1.94µs ? ?/sec 1.01 72.0±1.75µs ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024) 1.80 3.5±0.22µs ? ?/sec 1.00 1944.9±29.22ns ? ?/sec
filter fsb with value length 5 (kept 1/2) 1.08 142.1±0.76µs ? ?/sec 1.00 132.1±1.80µs ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024) 1.12 11.7±0.61µs ? ?/sec 1.00 10.5±0.56µs ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024) 1.89 3.4±0.03µs ? ?/sec 1.00 1809.3±13.79ns ? ?/sec
filter fsb with value length 50 (kept 1/2) 1.13 170.2±17.54µs ? ?/sec 1.00 150.5±10.19µs ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024) 1.00 208.9±9.23µs ? ?/sec 1.00 209.3±6.50µs ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024) 1.81 3.4±0.04µs ? ?/sec 1.00 1906.0±17.68ns ? ?/sec
filter i32 (kept 1/2) 1.24 53.8±1.00µs ? ?/sec 1.00 43.5±0.36µs ? ?/sec
filter i32 high selectivity (kept 1023/1024) 1.03 9.1±0.55µs ? ?/sec 1.00 8.7±0.51µs ? ?/sec
filter i32 low selectivity (kept 1/1024) 1.98 3.0±0.02µs ? ?/sec 1.00 1499.1±11.19ns ? ?/sec
filter optimize (kept 1/2) 1.01 35.9±0.21µs ? ?/sec 1.00 35.6±0.24µs ? ?/sec
filter optimize high selectivity (kept 1023/1024) 1.19 2.7±0.02µs ? ?/sec 1.00 2.3±0.02µs ? ?/sec
filter optimize low selectivity (kept 1/1024) 1.33 1793.3±24.31ns ? ?/sec 1.00 1349.2±14.95ns ? ?/sec
filter run array (kept 1/2) 1.00 381.6±5.29µs ? ?/sec 1.21 460.2±4.38µs ? ?/sec
filter run array high selectivity (kept 1023/1024) 1.00 395.8±3.91µs ? ?/sec 1.25 496.0±1.61µs ? ?/sec
filter run array low selectivity (kept 1/1024) 1.00 284.4±4.80µs ? ?/sec 1.34 380.3±3.07µs ? ?/sec
filter single record batch 1.19 38.5±0.50µs ? ?/sec 1.00 32.2±0.24µs ? ?/sec
filter u8 (kept 1/2) 1.12 36.1±0.31µs ? ?/sec 1.00 32.2±0.12µs ? ?/sec
filter u8 high selectivity (kept 1023/1024) 1.08 3.8±0.03µs ? ?/sec 1.00 3.5±0.02µs ? ?/sec
filter u8 low selectivity (kept 1/1024) 1.97 3.0±0.03µs ? ?/sec 1.00 1501.2±11.78ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812854225
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 209.2±1.88ns ? ?/sec 1.13 237.2±1.43ns ? ?/sec
and_sliced_1 4.21 1099.4±14.92ns ? ?/sec 1.00 261.3±3.45ns ? ?/sec
and_sliced_24 1.08 249.1±6.95ns ? ?/sec 1.00 229.9±1.46ns ? ?/sec
not 1.00 146.7±2.22ns ? ?/sec 1.06 154.8±2.42ns ? ?/sec
not_slice_24 1.09 194.5±1.03ns ? ?/sec 1.00 178.0±0.80ns ? ?/sec
not_sliced_1 2.57 619.5±2.63ns ? ?/sec 1.00 241.5±2.66ns ? ?/sec
or 1.00 198.5±0.77ns ? ?/sec 1.17 231.6±4.39ns ? ?/sec
or_sliced_1 4.22 1099.3±5.54ns ? ?/sec 1.00 260.5±1.23ns ? ?/sec
or_sliced_24 1.09 248.4±1.25ns ? ?/sec 1.00 228.8±4.34ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on code in PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#discussion_r2737777188
##########
arrow-buffer/src/buffer/mutable.rs:
##########
@@ -872,15 +872,16 @@ impl MutableBuffer {
let mut buffer = MutableBuffer::new(len);
- let mut dst = buffer.data.as_ptr();
- for item in iterator {
+ let mut dst = buffer.data.as_ptr() as *mut T;
+ iterator.for_each(|item| {
Review Comment:
`for_each` uses `fold` so can use a more efficient implementation if it is available.
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3807622749
🤖 Hi @Dandandan, thanks for the request (https://github.com/apache/arrow-rs/pull/9284#issuecomment-3807622376).
[`scrape_comments.py`](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/scrape_comments.py) only supports whitelisted benchmarks.
- Standard: (none)
- Criterion: array_iter, arrow_reader, arrow_reader_clickbench, arrow_reader_row_filter, arrow_statistics, arrow_writer, bitwise_kernel, boolean_kernels, buffer_bit_ops, cast_kernels, coalesce_kernels, comparison_kernels, concatenate_kernel, csv_writer, encoding, filter_kernels, interleave_kernels, json-reader, metadata, row_format, take_kernels, union_array, variant_builder, variant_kernels, variant_validation, view_types, zip_kernels
Please choose one or more of these with `run benchmark <name>` or `run benchmark <name1> <name2>...`
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808121900
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (b4b71aa2ed596a56f0abb9e77552011a875e617a) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..b4b71aa2ed596a56f0abb9e77552011a875e617a)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811038433
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.01 209.3±2.51ns ? ?/sec 1.00 207.1±2.82ns ? ?/sec
and_sliced_1 4.27 1098.8±18.60ns ? ?/sec 1.00 257.0±1.94ns ? ?/sec
and_sliced_24 1.00 248.0±5.92ns ? ?/sec 1.22 302.3±3.33ns ? ?/sec
not 1.02 146.6±4.34ns ? ?/sec 1.00 143.0±0.66ns ? ?/sec
not_slice_24 1.00 194.2±1.16ns ? ?/sec 1.25 242.8±1.06ns ? ?/sec
not_sliced_1 2.61 623.9±18.17ns ? ?/sec 1.00 238.8±6.95ns ? ?/sec
or 1.01 198.7±1.11ns ? ?/sec 1.00 196.4±1.07ns ? ?/sec
or_sliced_1 4.27 1096.8±1.58ns ? ?/sec 1.00 256.7±1.07ns ? ?/sec
or_sliced_24 1.00 248.6±2.68ns ? ?/sec 1.21 300.9±3.22ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811446014
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.01 209.2±2.21ns ? ?/sec 1.00 206.9±0.95ns ? ?/sec
and_sliced_1 3.93 1098.8±4.39ns ? ?/sec 1.00 279.3±3.38ns ? ?/sec
and_sliced_24 1.00 247.7±1.19ns ? ?/sec 1.06 261.8±2.56ns ? ?/sec
not 1.00 146.7±1.26ns ? ?/sec 1.03 150.6±1.33ns ? ?/sec
not_slice_24 1.04 195.1±2.49ns ? ?/sec 1.00 187.6±0.70ns ? ?/sec
not_sliced_1 2.57 620.0±3.57ns ? ?/sec 1.00 241.1±6.37ns ? ?/sec
or 1.00 199.3±5.45ns ? ?/sec 1.00 198.3±6.43ns ? ?/sec
or_sliced_1 4.22 1099.0±7.10ns ? ?/sec 1.00 260.5±5.20ns ? ?/sec
or_sliced_24 1.07 249.0±3.83ns ? ?/sec 1.00 232.4±8.44ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812854496
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (060afb8ccada7f5fa888e3b8da110bd7c803839d) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..060afb8ccada7f5fa888e3b8da110bd7c803839d)
BENCH_NAME=arrow_reader_clickbench
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader_clickbench
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808028798
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (b4b71aa2ed596a56f0abb9e77552011a875e617a) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..b4b71aa2ed596a56f0abb9e77552011a875e617a)
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810444902
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 210.6±5.55ns ? ?/sec 1.32 278.7±2.24ns ? ?/sec
and_sliced_1 1.95 1101.7±18.85ns ? ?/sec 1.00 564.1±3.51ns ? ?/sec
and_sliced_24 1.00 248.6±2.07ns ? ?/sec 1.17 289.8±3.47ns ? ?/sec
not 1.00 148.4±2.89ns ? ?/sec 1.26 187.1±3.70ns ? ?/sec
not_slice_24 1.00 197.9±9.43ns ? ?/sec 1.18 232.6±3.45ns ? ?/sec
not_sliced_1 1.30 621.0±7.59ns ? ?/sec 1.00 478.4±5.67ns ? ?/sec
or 1.00 200.4±11.38ns ? ?/sec 1.28 256.4±4.39ns ? ?/sec
or_sliced_1 1.97 1099.8±9.53ns ? ?/sec 1.00 558.9±1.48ns ? ?/sec
or_sliced_24 1.00 249.3±2.19ns ? ?/sec 1.16 290.0±1.67ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on code in PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#discussion_r2737754463
##########
arrow-buffer/src/buffer/boolean.rs:
##########
@@ -336,28 +329,60 @@ impl BooleanBuffer {
}
}
}
+
+ if left_offset_in_bits == right_offset_in_bits {
+ // is aligned to byte boundary
+ if left_offset_in_bits & 0x7 == 0 {
+ let left = &left[left_offset_in_bits / 8..];
+ let right = &right[right_offset_in_bits / 8..];
+
+ let left_chunks = BitChunks::new(left, 0, len_in_bits);
+ let right_chunks = BitChunks::new(right, 0, len_in_bits);
+ let mut result = Vec::with_capacity(bit_util::ceil(len_in_bits, 64));
+
+ let l_iter = left
+ .chunks_exact(8)
+ .map(|c| u64::from_le_bytes(c.try_into().unwrap()));
+ let r_iter = right
+ .chunks_exact(8)
+ .map(|c| u64::from_le_bytes(c.try_into().unwrap()));
+
+ result.extend(l_iter.zip(r_iter).map(|(l, r)| op(l, r)));
+
+ if left_chunks.remainder_len() > 0 {
+ result.push(op(
+ left_chunks.remainder_bits(),
+ right_chunks.remainder_bits(),
+ ));
+ }
+ return BooleanBuffer::new(Buffer::from(result), 0, len_in_bits);
+ }
+
+ // both buffers have the same offset, we can use UnalignedBitChunk for both
+ let left_chunks = UnalignedBitChunk::new(left, left_offset_in_bits, len_in_bits);
Review Comment:
I think we actually don't have to use this part (use the byte aligned one above and set the correct offset).
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3809469313
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (15ad389623350e47f0c30ea2980d550a12624ff3) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..15ad389623350e47f0c30ea2980d550a12624ff3)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812316290
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, mandatory, no NULLs 1.00 1180.3±11.63µs ? ?/sec 1.01 1194.1±23.49µs ? ?/sec
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, optional, half NULLs 1.00 1249.6±9.93µs ? ?/sec 1.03 1288.4±11.98µs ? ?/sec
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, optional, no NULLs 1.00 1188.9±15.84µs ? ?/sec 1.00 1191.6±16.35µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, mandatory, no NULLs 1.00 481.3±4.12µs ? ?/sec 1.29 623.1±8.25µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, optional, half NULLs 1.00 658.5±3.93µs ? ?/sec 1.15 757.9±4.17µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, optional, no NULLs 1.00 486.4±6.39µs ? ?/sec 1.26 614.9±5.04µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, mandatory, no NULLs 1.03 557.5±4.56µs ? ?/sec 1.00 543.7±3.71µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, optional, half NULLs 1.00 727.4±8.72µs ? ?/sec 1.03 749.6±7.81µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, optional, no NULLs 1.02 572.3±8.45µs ? ?/sec 1.00 562.4±25.21µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, mandatory, no NULLs 1.00 154.1±3.06µs ? ?/sec 1.04 159.7±2.24µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, optional, half NULLs 1.18 225.4±1.87µs ? ?/sec 1.00 191.3±1.53µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, optional, no NULLs 1.08 163.5±2.46µs ? ?/sec 1.00 150.9±1.92µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, mandatory, no NULLs 1.09 224.2±3.55µs ? ?/sec 1.00 204.8±5.19µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, mandatory, no NULLs, short string 1.00 195.8±10.48µs ? ?/sec 1.19 232.0±1.34µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, optional, half NULLs 1.13 258.7±2.61µs ? ?/sec 1.00 228.0±6.63µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, optional, no NULLs 1.09 232.6±3.37µs ? ?/sec 1.00 213.7±5.13µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.01 1091.8±11.29µs ? ?/sec 1.00 1085.9±12.99µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.03 982.2±17.60µs ? ?/sec 1.00 955.9±14.56µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.01 1097.8±6.39µs ? ?/sec 1.00 1090.4±10.33µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, mandatory, no NULLs 1.18 467.7±8.08µs ? ?/sec 1.00 397.6±3.18µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, optional, half NULLs 1.14 672.6±22.86µs ? ?/sec 1.00 590.8±8.40µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, optional, no NULLs 1.15 467.1±4.47µs ? ?/sec 1.00 405.8±6.69µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, mandatory, no NULLs 1.21 195.0±1.05µs ? ?/sec 1.00 161.5±3.32µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, optional, half NULLs 1.14 340.5±6.02µs ? ?/sec 1.00 298.9±3.37µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, optional, no NULLs 1.21 200.7±3.88µs ? ?/sec 1.00 166.2±3.76µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, mandatory, no NULLs 1.54 118.1±2.87µs ? ?/sec 1.00 76.4±0.94µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, optional, half NULLs 1.18 301.3±6.66µs ? ?/sec 1.00 254.8±2.38µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, optional, no NULLs 1.51 123.0±1.11µs ? ?/sec 1.00 81.2±0.99µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, mandatory, no NULLs 1.00 690.0±4.04µs ? ?/sec 1.07 738.0±4.56µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, optional, half NULLs 1.00 587.9±12.97µs ? ?/sec 1.00 588.9±6.59µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, optional, no NULLs 1.00 698.6±7.79µs ? ?/sec 1.08 752.0±59.02µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, mandatory, no NULLs 1.02 63.8±1.64µs ? ?/sec 1.00 62.7±1.55µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, optional, half NULLs 1.07 273.0±2.60µs ? ?/sec 1.00 255.9±3.61µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, optional, no NULLs 1.02 71.3±2.25µs ? ?/sec 1.00 70.2±2.52µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, mandatory, no NULLs 1.00 86.2±0.88µs ? ?/sec 1.09 94.3±1.36µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, optional, half NULLs 1.01 231.7±4.74µs ? ?/sec 1.00 229.0±1.12µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, optional, no NULLs 1.00 91.0±0.38µs ? ?/sec 1.09 99.5±3.03µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, mandatory, no NULLs 1.00 9.1±0.20µs ? ?/sec 1.03 9.4±0.19µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, optional, half NULLs 1.03 191.7±0.79µs ? ?/sec 1.00 186.9±4.44µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, optional, no NULLs 1.00 14.2±0.24µs ? ?/sec 1.01 14.4±0.30µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, mandatory, no NULLs 1.00 170.7±3.78µs ? ?/sec 1.08 184.3±2.85µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, optional, half NULLs 1.06 372.3±2.41µs ? ?/sec 1.00 349.9±2.97µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, optional, no NULLs 1.00 175.7±0.79µs ? ?/sec 1.08 189.2±1.71µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, mandatory, no NULLs 1.00 14.5±0.56µs ? ?/sec 1.00 14.5±0.32µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, optional, half NULLs 1.12 298.5±7.32µs ? ?/sec 1.00 266.4±2.38µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, optional, no NULLs 1.02 20.3±0.51µs ? ?/sec 1.00 20.0±0.49µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, mandatory, no NULLs 1.00 342.2±2.13µs ? ?/sec 1.07 366.7±5.13µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, optional, half NULLs 1.02 400.8±2.33µs ? ?/sec 1.00 393.0±3.18µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, optional, no NULLs 1.00 349.4±4.10µs ? ?/sec 1.07 373.6±7.69µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, mandatory, no NULLs 1.00 26.8±0.38µs ? ?/sec 1.06 28.5±1.10µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, optional, half NULLs 1.10 246.5±3.77µs ? ?/sec 1.00 224.0±1.13µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, optional, no NULLs 1.00 33.8±0.78µs ? ?/sec 1.06 35.8±1.16µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, mandatory, no NULLs 1.00 108.9±2.21µs ? ?/sec 1.00 108.4±1.31µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, optional, half NULLs 1.00 129.7±0.61µs ? ?/sec 1.06 137.8±0.68µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, optional, no NULLs 1.00 111.9±0.57µs ? ?/sec 1.00 111.9±2.79µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, mandatory, no NULLs 1.00 159.2±1.49µs ? ?/sec 1.00 158.5±3.33µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, optional, half NULLs 1.00 222.7±2.10µs ? ?/sec 1.07 237.4±2.07µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, optional, no NULLs 1.01 164.5±2.55µs ? ?/sec 1.00 163.0±1.82µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.00 75.4±0.54µs ? ?/sec 1.00 75.7±1.18µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.00 179.4±3.63µs ? ?/sec 1.09 194.8±3.29µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.01 80.8±0.65µs ? ?/sec 1.00 80.4±0.40µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, mandatory, no NULLs 1.01 145.4±1.28µs ? ?/sec 1.00 143.5±5.76µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, optional, half NULLs 1.00 217.7±3.14µs ? ?/sec 1.06 230.9±1.59µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, optional, no NULLs 1.01 150.0±0.89µs ? ?/sec 1.00 148.2±2.12µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, mandatory, no NULLs 1.02 73.5±1.29µs ? ?/sec 1.00 71.7±0.46µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, optional, half NULLs 1.00 179.5±1.57µs ? ?/sec 1.07 192.7±1.70µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, optional, no NULLs 1.01 78.4±1.33µs ? ?/sec 1.00 77.6±1.76µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, mandatory, no NULLs 1.02 109.2±1.12µs ? ?/sec 1.00 106.8±2.42µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, optional, half NULLs 1.01 118.5±1.34µs ? ?/sec 1.00 116.8±1.44µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, optional, no NULLs 1.01 110.3±0.35µs ? ?/sec 1.00 109.2±0.80µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, mandatory, no NULLs 1.01 161.5±0.93µs ? ?/sec 1.00 160.1±1.45µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, optional, half NULLs 1.02 208.4±1.22µs ? ?/sec 1.00 205.1±1.09µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, optional, no NULLs 1.02 167.3±3.33µs ? ?/sec 1.00 164.7±0.58µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.01 201.9±1.48µs ? ?/sec 1.00 199.3±1.03µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.01 226.2±1.28µs ? ?/sec 1.00 223.6±8.08µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.02 207.7±0.73µs ? ?/sec 1.00 204.5±1.29µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, mandatory, no NULLs 1.01 143.0±1.00µs ? ?/sec 1.00 141.0±2.26µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, optional, half NULLs 1.03 196.4±10.31µs ? ?/sec 1.00 190.9±2.51µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, optional, no NULLs 1.01 148.7±0.83µs ? ?/sec 1.00 147.0±3.07µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, mandatory, no NULLs 1.01 100.6±1.20µs ? ?/sec 1.00 100.1±0.94µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, optional, half NULLs 1.02 172.4±1.13µs ? ?/sec 1.00 168.8±5.50µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, optional, no NULLs 1.04 113.5±1.30µs ? ?/sec 1.00 108.8±2.59µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, mandatory, no NULLs 1.00 76.8±1.31µs ? ?/sec 1.00 76.8±0.38µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, optional, half NULLs 1.00 102.9±0.68µs ? ?/sec 1.09 111.9±1.20µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, optional, no NULLs 1.00 79.2±0.52µs ? ?/sec 1.01 79.9±1.73µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, mandatory, no NULLs 1.00 106.1±0.45µs ? ?/sec 1.00 106.2±1.75µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, optional, half NULLs 1.00 176.8±15.56µs ? ?/sec 1.08 191.7±3.23µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, optional, no NULLs 1.02 112.6±10.32µs ? ?/sec 1.00 110.2±0.69µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, mandatory, no NULLs 1.00 40.8±0.40µs ? ?/sec 1.05 42.8±0.13µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, optional, half NULLs 1.00 141.8±1.62µs ? ?/sec 1.11 157.9±0.96µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, optional, no NULLs 1.00 45.4±0.34µs ? ?/sec 1.03 46.7±0.27µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, mandatory, no NULLs 1.01 111.7±0.92µs ? ?/sec 1.00 110.3±1.19µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, optional, half NULLs 1.00 180.1±1.38µs ? ?/sec 1.09 196.6±4.10µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, optional, no NULLs 1.01 115.8±0.48µs ? ?/sec 1.00 114.9±2.66µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, mandatory, no NULLs 1.00 36.7±0.12µs ? ?/sec 1.00 36.8±0.21µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, optional, half NULLs 1.00 138.8±1.95µs ? ?/sec 1.12 155.5±1.14µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, optional, no NULLs 1.02 42.1±0.18µs ? ?/sec 1.00 41.2±0.21µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, mandatory, no NULLs 1.00 82.2±0.45µs ? ?/sec 1.01 83.0±2.24µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, optional, half NULLs 1.00 101.1±0.97µs ? ?/sec 1.10 111.0±1.82µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, optional, no NULLs 1.00 85.4±4.48µs ? ?/sec 1.00 85.1±0.53µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, mandatory, no NULLs 1.01 107.0±1.72µs ? ?/sec 1.00 105.9±2.46µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, optional, half NULLs 1.00 165.4±1.02µs ? ?/sec 1.11 183.4±1.12µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, optional, no NULLs 1.01 111.1±0.97µs ? ?/sec 1.00 110.4±0.84µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, mandatory, no NULLs 1.00 23.0±0.24µs ? ?/sec 1.01 23.2±0.24µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, optional, half NULLs 1.00 121.8±1.07µs ? ?/sec 1.14 138.6±1.78µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, optional, no NULLs 1.00 27.7±0.62µs ? ?/sec 1.00 27.7±0.38µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, mandatory, no NULLs 1.02 93.1±1.71µs ? ?/sec 1.00 91.0±0.74µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, optional, half NULLs 1.00 160.8±1.37µs ? ?/sec 1.10 177.4±3.73µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, optional, no NULLs 1.01 96.5±1.55µs ? ?/sec 1.00 96.0±1.59µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, mandatory, no NULLs 1.01 15.5±0.67µs ? ?/sec 1.00 15.3±0.25µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, optional, half NULLs 1.00 120.0±1.11µs ? ?/sec 1.13 135.9±0.74µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, optional, no NULLs 1.01 21.2±0.40µs ? ?/sec 1.00 21.1±0.45µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, mandatory, no NULLs 1.00 79.8±0.60µs ? ?/sec 1.00 79.8±2.90µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, optional, half NULLs 1.00 89.4±0.65µs ? ?/sec 1.00 89.5±0.94µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, optional, no NULLs 1.00 82.0±0.87µs ? ?/sec 1.00 82.0±1.69µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, mandatory, no NULLs 1.01 108.0±1.70µs ? ?/sec 1.00 106.5±0.96µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, optional, half NULLs 1.00 141.9±1.23µs ? ?/sec 1.00 141.4±1.02µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, optional, no NULLs 1.01 110.1±1.22µs ? ?/sec 1.00 108.6±2.68µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, mandatory, no NULLs 1.00 146.2±0.84µs ? ?/sec 1.00 146.3±0.57µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, optional, half NULLs 1.01 168.2±4.88µs ? ?/sec 1.00 166.7±1.16µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, optional, no NULLs 1.00 151.4±1.35µs ? ?/sec 1.00 150.9±1.42µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, mandatory, no NULLs 1.01 88.4±1.23µs ? ?/sec 1.00 87.6±0.69µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, optional, half NULLs 1.01 135.6±1.26µs ? ?/sec 1.00 134.4±0.59µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, optional, no NULLs 1.01 93.2±0.69µs ? ?/sec 1.00 92.6±2.06µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, mandatory, no NULLs 1.00 39.4±0.76µs ? ?/sec 1.05 41.6±1.47µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, optional, half NULLs 1.02 112.3±3.75µs ? ?/sec 1.00 110.1±1.08µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, optional, no NULLs 1.00 43.1±0.86µs ? ?/sec 1.10 47.4±0.85µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, mandatory, no NULLs 1.00 80.6±1.51µs ? ?/sec 1.02 81.8±0.52µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, optional, half NULLs 1.00 102.9±0.63µs ? ?/sec 1.10 112.8±0.89µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, optional, no NULLs 1.00 82.9±0.37µs ? ?/sec 1.03 85.3±1.52µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, mandatory, no NULLs 1.00 108.1±2.27µs ? ?/sec 1.00 108.6±1.80µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, optional, half NULLs 1.00 173.3±15.71µs ? ?/sec 1.09 189.3±1.59µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, optional, no NULLs 1.00 112.2±0.46µs ? ?/sec 1.01 113.0±0.54µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, mandatory, no NULLs 1.02 34.7±0.32µs ? ?/sec 1.00 34.1±0.12µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, optional, half NULLs 1.00 133.6±1.66µs ? ?/sec 1.12 149.9±1.89µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, optional, no NULLs 1.05 39.1±0.15µs ? ?/sec 1.00 37.3±0.21µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, mandatory, no NULLs 1.02 104.0±0.42µs ? ?/sec 1.00 102.4±1.50µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, optional, half NULLs 1.00 175.3±12.52µs ? ?/sec 1.08 189.1±7.11µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, optional, no NULLs 1.02 108.5±0.98µs ? ?/sec 1.00 106.6±0.74µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, mandatory, no NULLs 1.00 28.9±0.21µs ? ?/sec 1.00 29.0±0.18µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, optional, half NULLs 1.00 131.9±2.40µs ? ?/sec 1.13 148.3±2.36µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, optional, no NULLs 1.03 34.1±0.53µs ? ?/sec 1.00 33.3±0.19µs ? ?/sec
arrow_array_reader/ListArray/plain encoded optional strings half NULLs 1.00 6.2±0.09ms ? ?/sec 1.02 6.3±0.05ms ? ?/sec
arrow_array_reader/ListArray/plain encoded optional strings no NULLs 1.00 12.3±0.17ms ? ?/sec 1.03 12.7±0.34ms ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, mandatory, no NULLs 1.00 491.7±5.07µs ? ?/sec 1.27 622.7±7.51µs ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, optional, half NULLs 1.00 659.4±11.23µs ? ?/sec 1.15 761.1±14.06µs ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, optional, no NULLs 1.00 487.9±5.70µs ? ?/sec 1.28 624.8±5.70µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, mandatory, no NULLs 1.01 659.7±12.91µs ? ?/sec 1.00 655.4±6.38µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, optional, half NULLs 1.00 775.2±4.43µs ? ?/sec 1.03 800.8±8.44µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, optional, no NULLs 1.01 671.5±7.74µs ? ?/sec 1.00 666.8±16.58µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, mandatory, no NULLs 1.02 335.6±15.45µs ? ?/sec 1.00 330.2±20.28µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, optional, half NULLs 1.08 417.3±3.69µs ? ?/sec 1.00 385.8±4.08µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, optional, no NULLs 1.02 337.5±4.74µs ? ?/sec 1.00 331.4±3.02µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, mandatory, no NULLs 1.00 140.4±4.08µs ? ?/sec 1.08 151.7±2.37µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, optional, half NULLs 1.11 201.5±2.21µs ? ?/sec 1.00 182.1±4.74µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, optional, no NULLs 1.03 143.8±2.40µs ? ?/sec 1.00 140.2±1.84µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, mandatory, no NULLs 1.03 368.3±8.24µs ? ?/sec 1.00 357.2±4.16µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, optional, half NULLs 1.09 326.4±2.58µs ? ?/sec 1.00 300.4±3.67µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, optional, no NULLs 1.03 376.7±4.85µs ? ?/sec 1.00 366.5±4.60µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, mandatory, no NULLs 1.00 92.1±0.31µs ? ?/sec 1.00 92.5±1.71µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, optional, half NULLs 1.00 111.5±1.73µs ? ?/sec 1.08 120.4±0.94µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, optional, no NULLs 1.00 95.3±2.06µs ? ?/sec 1.00 95.1±1.17µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, mandatory, no NULLs 1.00 126.2±1.13µs ? ?/sec 1.00 125.7±0.98µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, optional, half NULLs 1.00 185.4±1.07µs ? ?/sec 1.10 204.2±9.90µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, optional, no NULLs 1.00 130.7±1.62µs ? ?/sec 1.00 130.7±1.56µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, mandatory, no NULLs 1.00 40.9±0.22µs ? ?/sec 1.05 42.9±0.23µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, optional, half NULLs 1.00 141.2±1.09µs ? ?/sec 1.12 157.9±1.01µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, optional, no NULLs 1.00 45.4±0.52µs ? ?/sec 1.03 47.0±0.58µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, mandatory, no NULLs 1.02 111.9±1.71µs ? ?/sec 1.00 110.2±0.48µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, optional, half NULLs 1.00 180.2±3.41µs ? ?/sec 1.09 197.1±2.97µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, optional, no NULLs 1.01 116.2±1.35µs ? ?/sec 1.00 115.0±3.00µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, mandatory, no NULLs 1.00 36.9±0.14µs ? ?/sec 1.00 36.8±0.22µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, optional, half NULLs 1.00 138.7±3.07µs ? ?/sec 1.12 155.2±0.95µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, optional, no NULLs 1.02 42.2±0.55µs ? ?/sec 1.00 41.2±1.02µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, mandatory, no NULLs 1.00 82.4±0.56µs ? ?/sec 1.00 82.1±1.11µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, optional, half NULLs 1.00 101.5±1.71µs ? ?/sec 1.09 110.1±2.03µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, optional, no NULLs 1.01 85.1±0.70µs ? ?/sec 1.00 84.5±0.79µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, mandatory, no NULLs 1.01 106.9±1.40µs ? ?/sec 1.00 105.6±0.64µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, optional, half NULLs 1.00 167.3±2.81µs ? ?/sec 1.09 183.1±3.67µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, optional, no NULLs 1.02 111.6±3.30µs ? ?/sec 1.00 109.9±0.67µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, mandatory, no NULLs 1.00 22.3±0.37µs ? ?/sec 1.00 22.4±0.41µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, optional, half NULLs 1.00 122.2±1.73µs ? ?/sec 1.14 138.8±0.77µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, optional, no NULLs 1.00 26.8±0.48µs ? ?/sec 1.00 26.8±0.34µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, mandatory, no NULLs 1.02 93.3±3.05µs ? ?/sec 1.00 91.3±0.86µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, optional, half NULLs 1.00 161.2±0.93µs ? ?/sec 1.10 177.4±1.20µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, optional, no NULLs 1.02 97.6±1.44µs ? ?/sec 1.00 95.9±1.57µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, mandatory, no NULLs 1.00 17.9±0.37µs ? ?/sec 1.04 18.7±0.68µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, optional, half NULLs 1.00 121.1±3.36µs ? ?/sec 1.13 136.7±4.31µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, optional, no NULLs 1.02 23.5±0.66µs ? ?/sec 1.00 23.1±0.76µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, mandatory, no NULLs 1.01 80.5±2.30µs ? ?/sec 1.00 80.0±1.83µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, optional, half NULLs 1.00 90.3±0.84µs ? ?/sec 1.00 90.3±2.40µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, optional, no NULLs 1.01 82.6±0.80µs ? ?/sec 1.00 82.2±0.40µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, mandatory, no NULLs 1.00 107.0±2.26µs ? ?/sec 1.00 106.6±0.68µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, optional, half NULLs 1.00 144.4±2.30µs ? ?/sec 1.05 151.8±2.13µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, optional, no NULLs 1.00 110.3±2.58µs ? ?/sec 1.00 110.0±0.81µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, mandatory, no NULLs 1.01 147.1±0.62µs ? ?/sec 1.00 146.1±0.50µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, optional, half NULLs 1.01 167.5±1.01µs ? ?/sec 1.00 166.0±1.56µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, optional, no NULLs 1.01 151.9±0.91µs ? ?/sec 1.00 150.8±0.73µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, mandatory, no NULLs 1.02 89.2±1.02µs ? ?/sec 1.00 87.5±0.49µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, optional, half NULLs 1.02 137.9±3.47µs ? ?/sec 1.00 134.7±1.71µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, optional, no NULLs 1.01 93.8±0.85µs ? ?/sec 1.00 92.6±0.50µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, mandatory, no NULLs 1.00 39.3±0.47µs ? ?/sec 1.09 42.8±1.48µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, optional, half NULLs 1.01 112.1±1.82µs ? ?/sec 1.00 110.7±0.96µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, optional, no NULLs 1.00 46.6±0.61µs ? ?/sec 1.06 49.4±3.33µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, mandatory, no NULLs 1.00 87.9±0.62µs ? ?/sec 1.00 87.6±0.63µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, optional, half NULLs 1.00 106.9±2.79µs ? ?/sec 1.08 115.4±1.45µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, optional, no NULLs 1.00 90.3±1.14µs ? ?/sec 1.00 90.1±0.93µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, mandatory, no NULLs 1.00 118.1±2.63µs ? ?/sec 1.01 118.8±3.90µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, optional, half NULLs 1.00 177.0±3.57µs ? ?/sec 1.10 194.2±3.59µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, optional, no NULLs 1.00 121.7±0.39µs ? ?/sec 1.01 122.8±1.82µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, mandatory, no NULLs 1.00 34.7±0.22µs ? ?/sec 1.00 34.6±0.18µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, optional, half NULLs 1.00 133.0±0.76µs ? ?/sec 1.13 150.1±1.59µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, optional, no NULLs 1.01 38.9±0.33µs ? ?/sec 1.00 38.7±0.29µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, mandatory, no NULLs 1.02 104.2±2.51µs ? ?/sec 1.00 102.0±0.31µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, optional, half NULLs 1.00 173.2±2.97µs ? ?/sec 1.09 188.2±0.74µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, optional, no NULLs 1.02 108.5±1.81µs ? ?/sec 1.00 106.4±0.72µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, mandatory, no NULLs 1.00 29.0±0.17µs ? ?/sec 1.00 28.9±0.28µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, optional, half NULLs 1.00 131.1±0.93µs ? ?/sec 1.13 147.6±4.59µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, optional, no NULLs 1.00 33.4±0.21µs ? ?/sec 1.00 33.4±0.18µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, mandatory struct, optional data, half NULLs 1.00 121.2±1.70µs ? ?/sec 1.12 136.2±2.56µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, mandatory struct, optional data, no NULLs 1.01 22.8±0.70µs ? ?/sec 1.00 22.6±0.56µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, optional struct, optional data, half NULLs 1.00 242.9±4.69µs ? ?/sec 1.07 260.4±3.51µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, optional struct, optional data, no NULLs 1.02 120.0±2.52µs ? ?/sec 1.00 118.1±1.65µs ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893798248
run benchmark coalesce_kernels
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811417681
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (d8a6aacabdef17fb899c24358ff89180548c84ea) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..d8a6aacabdef17fb899c24358ff89180548c84ea)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808873718
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter context decimal128 (kept 1/2) 1.11 49.4±8.65µs ? ?/sec 1.00 44.5±4.73µs ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024) 1.00 50.4±1.05µs ? ?/sec 1.00 50.5±1.09µs ? ?/sec
filter context decimal128 low selectivity (kept 1/1024) 1.00 230.5±2.32ns ? ?/sec 1.01 232.6±2.95ns ? ?/sec
filter context f32 (kept 1/2) 1.13 87.8±1.02µs ? ?/sec 1.00 77.9±0.45µs ? ?/sec
filter context f32 high selectivity (kept 1023/1024) 1.00 10.4±0.48µs ? ?/sec 1.04 10.8±0.58µs ? ?/sec
filter context f32 low selectivity (kept 1/1024) 1.01 441.6±6.87ns ? ?/sec 1.00 437.0±2.24ns ? ?/sec
filter context fsb with value length 20 (kept 1/2) 1.17 70.7±0.70µs ? ?/sec 1.00 60.6±0.49µs ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024) 1.17 70.8±0.46µs ? ?/sec 1.00 60.7±0.46µs ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024) 1.17 70.8±1.36µs ? ?/sec 1.00 60.7±0.60µs ? ?/sec
filter context fsb with value length 5 (kept 1/2) 1.16 70.7±0.42µs ? ?/sec 1.00 60.7±0.26µs ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024) 1.17 70.8±1.24µs ? ?/sec 1.00 60.6±0.26µs ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024) 1.17 70.6±0.23µs ? ?/sec 1.00 60.6±0.30µs ? ?/sec
filter context fsb with value length 50 (kept 1/2) 1.16 70.7±0.80µs ? ?/sec 1.00 60.8±0.51µs ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024) 1.16 70.7±0.63µs ? ?/sec 1.00 60.7±1.05µs ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024) 1.16 70.6±0.47µs ? ?/sec 1.00 60.6±0.35µs ? ?/sec
filter context i32 (kept 1/2) 1.00 16.4±0.10µs ? ?/sec 1.00 16.4±0.13µs ? ?/sec
filter context i32 high selectivity (kept 1023/1024) 1.01 6.8±0.42µs ? ?/sec 1.00 6.7±0.53µs ? ?/sec
filter context i32 low selectivity (kept 1/1024) 1.00 221.7±3.27ns ? ?/sec 1.00 221.6±2.90ns ? ?/sec
filter context i32 w NULLs (kept 1/2) 1.13 87.7±0.48µs ? ?/sec 1.00 77.4±0.26µs ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024) 1.04 10.9±0.43µs ? ?/sec 1.00 10.4±0.56µs ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024) 1.00 439.1±4.38ns ? ?/sec 1.00 437.1±3.30ns ? ?/sec
filter context mixed string view (kept 1/2) 1.05 112.6±2.79µs ? ?/sec 1.00 107.0±5.97µs ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024) 1.01 54.9±1.44µs ? ?/sec 1.00 54.5±0.95µs ? ?/sec
filter context mixed string view low selectivity (kept 1/1024) 1.04 650.8±23.08ns ? ?/sec 1.00 626.6±27.40ns ? ?/sec
filter context short string view (kept 1/2) 1.06 113.4±2.71µs ? ?/sec 1.00 107.3±6.52µs ? ?/sec
filter context short string view high selectivity (kept 1023/1024) 1.05 56.4±1.58µs ? ?/sec 1.00 53.6±1.10µs ? ?/sec
filter context short string view low selectivity (kept 1/1024) 1.03 503.2±7.50ns ? ?/sec 1.00 487.5±7.58ns ? ?/sec
filter context string (kept 1/2) 1.02 583.6±18.28µs ? ?/sec 1.00 574.7±12.77µs ? ?/sec
filter context string dictionary (kept 1/2) 1.00 17.1±0.07µs ? ?/sec 1.01 17.3±0.06µs ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024) 1.00 7.1±0.59µs ? ?/sec 1.02 7.2±0.37µs ? ?/sec
filter context string dictionary low selectivity (kept 1/1024) 1.00 641.0±14.66ns ? ?/sec 1.02 652.6±20.05ns ? ?/sec
filter context string dictionary w NULLs (kept 1/2) 1.12 88.4±0.67µs ? ?/sec 1.00 78.6±1.20µs ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024) 1.03 11.0±0.61µs ? ?/sec 1.00 10.8±0.46µs ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024) 1.00 868.4±11.96ns ? ?/sec 1.01 876.3±11.34ns ? ?/sec
filter context string high selectivity (kept 1023/1024) 1.01 639.8±14.48µs ? ?/sec 1.00 631.4±21.80µs ? ?/sec
filter context string low selectivity (kept 1/1024) 1.00 879.1±14.34ns ? ?/sec 1.09 957.8±9.40ns ? ?/sec
filter context u8 (kept 1/2) 1.00 15.0±0.28µs ? ?/sec 1.01 15.1±0.81µs ? ?/sec
filter context u8 high selectivity (kept 1023/1024) 1.09 2.0±0.01µs ? ?/sec 1.00 1830.5±20.10ns ? ?/sec
filter context u8 low selectivity (kept 1/1024) 1.00 214.9±9.12ns ? ?/sec 1.00 214.6±2.01ns ? ?/sec
filter context u8 w NULLs (kept 1/2) 1.15 87.2±5.56µs ? ?/sec 1.00 75.9±0.37µs ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024) 1.01 5.4±0.03µs ? ?/sec 1.00 5.3±0.04µs ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024) 1.00 433.9±2.96ns ? ?/sec 1.01 436.8±16.96ns ? ?/sec
filter decimal128 (kept 1/2) 1.00 49.4±4.87µs ? ?/sec 1.15 56.9±5.85µs ? ?/sec
filter decimal128 high selectivity (kept 1023/1024) 1.02 54.8±1.06µs ? ?/sec 1.00 53.8±1.22µs ? ?/sec
filter decimal128 low selectivity (kept 1/1024) 1.87 3.2±0.03µs ? ?/sec 1.00 1708.1±16.85ns ? ?/sec
filter f32 (kept 1/2) 1.02 157.3±0.53µs ? ?/sec 1.00 154.2±4.84µs ? ?/sec
filter fsb with value length 20 (kept 1/2) 1.08 136.4±1.69µs ? ?/sec 1.00 126.5±1.50µs ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024) 1.01 73.0±2.12µs ? ?/sec 1.00 72.0±2.15µs ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024) 1.55 2.6±0.02µs ? ?/sec 1.00 1713.3±36.83ns ? ?/sec
filter fsb with value length 5 (kept 1/2) 1.16 141.4±1.73µs ? ?/sec 1.00 121.5±2.48µs ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024) 1.08 11.4±0.68µs ? ?/sec 1.00 10.5±0.48µs ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024) 1.53 2.6±0.03µs ? ?/sec 1.00 1679.0±12.86ns ? ?/sec
filter fsb with value length 50 (kept 1/2) 1.11 167.6±12.64µs ? ?/sec 1.00 150.7±14.26µs ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024) 1.00 210.0±6.22µs ? ?/sec 1.03 215.4±8.76µs ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024) 1.51 2.7±0.08µs ? ?/sec 1.00 1785.0±57.36ns ? ?/sec
filter i32 (kept 1/2) 1.14 36.5±0.29µs ? ?/sec 1.00 32.0±1.25µs ? ?/sec
filter i32 high selectivity (kept 1023/1024) 1.11 9.5±0.51µs ? ?/sec 1.00 8.5±0.51µs ? ?/sec
filter i32 low selectivity (kept 1/1024) 1.37 2.4±0.01µs ? ?/sec 1.00 1742.3±17.01ns ? ?/sec
filter optimize (kept 1/2) 1.02 35.8±0.75µs ? ?/sec 1.00 35.2±0.23µs ? ?/sec
filter optimize high selectivity (kept 1023/1024) 1.32 3.0±0.04µs ? ?/sec 1.00 2.3±0.03µs ? ?/sec
filter optimize low selectivity (kept 1/1024) 1.51 2.5±0.01µs ? ?/sec 1.00 1667.8±10.36ns ? ?/sec
filter run array (kept 1/2) 1.01 464.2±1.82µs ? ?/sec 1.00 459.8±3.98µs ? ?/sec
filter run array high selectivity (kept 1023/1024) 1.00 497.1±6.75µs ? ?/sec 1.00 496.4±7.66µs ? ?/sec
filter run array low selectivity (kept 1/1024) 1.00 382.6±4.88µs ? ?/sec 1.00 381.9±3.74µs ? ?/sec
filter single record batch 1.00 38.5±1.11µs ? ?/sec 1.12 43.3±0.24µs ? ?/sec
filter u8 (kept 1/2) 1.11 36.1±0.32µs ? ?/sec 1.00 32.5±0.45µs ? ?/sec
filter u8 high selectivity (kept 1023/1024) 1.14 4.0±0.07µs ? ?/sec 1.00 3.5±0.09µs ? ?/sec
filter u8 low selectivity (kept 1/1024) 1.98 3.0±0.01µs ? ?/sec 1.00 1505.6±5.97ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812832145
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter context decimal128 (kept 1/2) 1.00 42.9±1.20µs ? ?/sec 1.04 44.6±3.83µs ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024) 1.00 49.5±1.01µs ? ?/sec 1.05 51.9±1.60µs ? ?/sec
filter context decimal128 low selectivity (kept 1/1024) 1.01 239.9±5.20ns ? ?/sec 1.00 237.5±6.21ns ? ?/sec
filter context f32 (kept 1/2) 1.00 87.5±0.52µs ? ?/sec 1.00 87.8±1.36µs ? ?/sec
filter context f32 high selectivity (kept 1023/1024) 1.02 10.5±0.52µs ? ?/sec 1.00 10.3±0.48µs ? ?/sec
filter context f32 low selectivity (kept 1/1024) 1.00 432.8±7.96ns ? ?/sec 1.03 447.7±3.75ns ? ?/sec
filter context fsb with value length 20 (kept 1/2) 1.00 70.7±1.06µs ? ?/sec 1.00 71.0±1.66µs ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024) 1.00 70.8±0.82µs ? ?/sec 1.00 70.8±0.91µs ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024) 1.00 70.7±0.44µs ? ?/sec 1.00 70.7±0.35µs ? ?/sec
filter context fsb with value length 5 (kept 1/2) 1.00 70.8±1.27µs ? ?/sec 1.00 71.1±1.10µs ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024) 1.00 70.7±0.32µs ? ?/sec 1.00 70.9±0.65µs ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024) 1.00 70.7±0.51µs ? ?/sec 1.01 71.3±3.79µs ? ?/sec
filter context fsb with value length 50 (kept 1/2) 1.00 70.6±0.30µs ? ?/sec 1.01 71.0±1.45µs ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024) 1.00 70.7±0.32µs ? ?/sec 1.01 71.1±2.48µs ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024) 1.00 70.7±0.79µs ? ?/sec 1.00 70.7±1.18µs ? ?/sec
filter context i32 (kept 1/2) 1.00 16.5±0.15µs ? ?/sec 1.00 16.5±0.66µs ? ?/sec
filter context i32 high selectivity (kept 1023/1024) 1.00 6.7±0.37µs ? ?/sec 1.00 6.7±0.35µs ? ?/sec
filter context i32 low selectivity (kept 1/1024) 1.00 228.7±4.14ns ? ?/sec 1.00 229.1±2.95ns ? ?/sec
filter context i32 w NULLs (kept 1/2) 1.00 88.5±3.49µs ? ?/sec 1.00 88.6±4.38µs ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024) 1.00 10.3±0.39µs ? ?/sec 1.00 10.4±0.51µs ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024) 1.00 431.2±9.95ns ? ?/sec 1.04 449.1±5.12ns ? ?/sec
filter context mixed string view (kept 1/2) 1.00 116.8±5.98µs ? ?/sec 1.07 125.0±5.35µs ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024) 1.00 55.1±1.34µs ? ?/sec 1.03 56.5±2.33µs ? ?/sec
filter context mixed string view low selectivity (kept 1/1024) 1.00 625.0±10.74ns ? ?/sec 1.02 640.1±7.62ns ? ?/sec
filter context short string view (kept 1/2) 1.00 113.5±4.30µs ? ?/sec 1.08 122.5±6.16µs ? ?/sec
filter context short string view high selectivity (kept 1023/1024) 1.00 53.8±1.02µs ? ?/sec 1.02 55.0±1.02µs ? ?/sec
filter context short string view low selectivity (kept 1/1024) 1.00 476.8±8.22ns ? ?/sec 1.04 498.2±4.77ns ? ?/sec
filter context string (kept 1/2) 1.00 613.7±17.44µs ? ?/sec 1.04 636.9±18.63µs ? ?/sec
filter context string dictionary (kept 1/2) 1.01 17.2±0.38µs ? ?/sec 1.00 17.0±0.12µs ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024) 1.09 7.3±0.42µs ? ?/sec 1.00 6.7±0.24µs ? ?/sec
filter context string dictionary low selectivity (kept 1/1024) 1.00 641.4±8.49ns ? ?/sec 1.03 660.4±10.10ns ? ?/sec
filter context string dictionary w NULLs (kept 1/2) 1.01 88.9±2.42µs ? ?/sec 1.00 88.1±0.39µs ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024) 1.00 10.4±0.38µs ? ?/sec 1.01 10.5±0.27µs ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024) 1.00 865.4±26.97ns ? ?/sec 1.03 889.5±11.77ns ? ?/sec
filter context string high selectivity (kept 1023/1024) 1.00 764.8±22.09µs ? ?/sec 1.25 955.4±100.71µs ? ?/sec
filter context string low selectivity (kept 1/1024) 1.00 933.1±10.93ns ? ?/sec 1.07 998.5±28.23ns ? ?/sec
filter context u8 (kept 1/2) 1.00 15.0±0.12µs ? ?/sec 1.00 15.0±0.07µs ? ?/sec
filter context u8 high selectivity (kept 1023/1024) 1.09 2.0±0.02µs ? ?/sec 1.00 1846.3±9.41ns ? ?/sec
filter context u8 low selectivity (kept 1/1024) 1.00 219.9±4.38ns ? ?/sec 1.01 222.7±2.77ns ? ?/sec
filter context u8 w NULLs (kept 1/2) 1.00 86.0±0.62µs ? ?/sec 1.01 86.4±2.53µs ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024) 1.00 5.1±0.07µs ? ?/sec 1.01 5.1±0.05µs ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024) 1.00 427.1±9.17ns ? ?/sec 1.04 442.7±4.46ns ? ?/sec
filter decimal128 (kept 1/2) 1.05 47.2±1.90µs ? ?/sec 1.00 45.1±3.55µs ? ?/sec
filter decimal128 high selectivity (kept 1023/1024) 1.00 52.7±1.18µs ? ?/sec 1.03 54.1±1.46µs ? ?/sec
filter decimal128 low selectivity (kept 1/1024) 1.62 3.2±0.01µs ? ?/sec 1.00 1965.9±36.41ns ? ?/sec
filter f32 (kept 1/2) 1.17 155.0±0.86µs ? ?/sec 1.00 132.6±1.53µs ? ?/sec
filter fsb with value length 20 (kept 1/2) 1.06 137.7±3.45µs ? ?/sec 1.00 129.6±0.87µs ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024) 1.00 70.7±2.49µs ? ?/sec 1.00 70.8±2.13µs ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024) 1.78 3.4±0.03µs ? ?/sec 1.00 1935.6±21.66ns ? ?/sec
filter fsb with value length 5 (kept 1/2) 1.04 142.5±1.45µs ? ?/sec 1.00 136.4±1.61µs ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024) 1.00 11.3±0.60µs ? ?/sec 1.04 11.8±0.54µs ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024) 1.90 3.5±0.38µs ? ?/sec 1.00 1832.9±14.44ns ? ?/sec
filter fsb with value length 50 (kept 1/2) 1.11 171.4±15.65µs ? ?/sec 1.00 154.5±13.21µs ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024) 1.03 218.6±8.51µs ? ?/sec 1.00 211.7±9.23µs ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024) 1.80 3.4±0.12µs ? ?/sec 1.00 1913.1±10.36ns ? ?/sec
filter i32 (kept 1/2) 1.67 54.2±1.58µs ? ?/sec 1.00 32.5±0.40µs ? ?/sec
filter i32 high selectivity (kept 1023/1024) 1.00 8.9±0.44µs ? ?/sec 1.02 9.1±0.44µs ? ?/sec
filter i32 low selectivity (kept 1/1024) 1.69 3.0±0.01µs ? ?/sec 1.00 1753.7±10.40ns ? ?/sec
filter optimize (kept 1/2) 1.00 36.3±1.38µs ? ?/sec 1.01 36.6±0.38µs ? ?/sec
filter optimize high selectivity (kept 1023/1024) 1.08 2.8±0.02µs ? ?/sec 1.00 2.6±0.03µs ? ?/sec
filter optimize low selectivity (kept 1/1024) 1.22 1797.4±17.72ns ? ?/sec 1.00 1474.2±113.98ns ? ?/sec
filter run array (kept 1/2) 1.03 380.7±3.79µs ? ?/sec 1.00 370.9±4.62µs ? ?/sec
filter run array high selectivity (kept 1023/1024) 1.00 401.3±7.90µs ? ?/sec 1.02 408.6±4.60µs ? ?/sec
filter run array low selectivity (kept 1/1024) 1.00 285.6±2.25µs ? ?/sec 1.03 294.3±6.44µs ? ?/sec
filter single record batch 1.22 52.7±0.40µs ? ?/sec 1.00 43.2±0.16µs ? ?/sec
filter u8 (kept 1/2) 1.23 53.5±0.18µs ? ?/sec 1.00 43.4±0.32µs ? ?/sec
filter u8 high selectivity (kept 1023/1024) 1.00 3.8±0.02µs ? ?/sec 1.00 3.8±0.02µs ? ?/sec
filter u8 low selectivity (kept 1/1024) 1.68 3.3±0.07µs ? ?/sec 1.00 1957.9±10.67ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812832339
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (060afb8ccada7f5fa888e3b8da110bd7c803839d) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..060afb8ccada7f5fa888e3b8da110bd7c803839d)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812601658
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_reader_clickbench/async/Q1 1.01 2.3±0.01ms ? ?/sec 1.00 2.3±0.04ms ? ?/sec
arrow_reader_clickbench/async/Q10 1.02 12.6±0.31ms ? ?/sec 1.00 12.3±0.31ms ? ?/sec
arrow_reader_clickbench/async/Q11 1.02 14.5±0.26ms ? ?/sec 1.00 14.2±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q12 1.03 23.8±0.32ms ? ?/sec 1.00 23.2±0.24ms ? ?/sec
arrow_reader_clickbench/async/Q13 1.01 29.2±0.46ms ? ?/sec 1.00 28.9±0.53ms ? ?/sec
arrow_reader_clickbench/async/Q14 1.03 26.5±0.82ms ? ?/sec 1.00 25.8±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q19 1.01 6.0±0.13ms ? ?/sec 1.00 5.9±0.13ms ? ?/sec
arrow_reader_clickbench/async/Q20 1.08 132.2±1.07ms ? ?/sec 1.00 122.2±0.97ms ? ?/sec
arrow_reader_clickbench/async/Q21 1.07 166.5±1.33ms ? ?/sec 1.00 155.2±1.92ms ? ?/sec
arrow_reader_clickbench/async/Q22 1.00 248.2±25.40ms ? ?/sec 1.13 281.0±33.44ms ? ?/sec
arrow_reader_clickbench/async/Q23 1.00 409.0±3.34ms ? ?/sec 1.00 409.0±5.62ms ? ?/sec
arrow_reader_clickbench/async/Q24 1.01 32.2±0.31ms ? ?/sec 1.00 31.9±0.32ms ? ?/sec
arrow_reader_clickbench/async/Q27 1.01 99.9±0.84ms ? ?/sec 1.00 98.8±0.60ms ? ?/sec
arrow_reader_clickbench/async/Q28 1.01 97.6±1.38ms ? ?/sec 1.00 96.8±1.12ms ? ?/sec
arrow_reader_clickbench/async/Q30 1.02 28.9±0.34ms ? ?/sec 1.00 28.4±0.34ms ? ?/sec
arrow_reader_clickbench/async/Q36 1.01 108.5±1.11ms ? ?/sec 1.00 107.7±0.95ms ? ?/sec
arrow_reader_clickbench/async/Q37 1.01 84.6±0.67ms ? ?/sec 1.00 83.6±0.49ms ? ?/sec
arrow_reader_clickbench/async/Q38 1.01 33.9±0.29ms ? ?/sec 1.00 33.7±0.51ms ? ?/sec
arrow_reader_clickbench/async/Q39 1.01 46.8±0.56ms ? ?/sec 1.00 46.5±0.55ms ? ?/sec
arrow_reader_clickbench/async/Q40 1.00 29.3±0.83ms ? ?/sec 1.01 29.5±0.39ms ? ?/sec
arrow_reader_clickbench/async/Q41 1.00 23.8±0.36ms ? ?/sec 1.00 23.8±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q42 1.00 11.2±0.17ms ? ?/sec 1.00 11.2±0.25ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q1 1.00 2.3±0.05ms ? ?/sec 1.00 2.3±0.06ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q10 1.01 11.8±0.25ms ? ?/sec 1.00 11.7±0.43ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q11 1.00 13.3±0.34ms ? ?/sec 1.01 13.5±0.30ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q12 1.02 22.7±0.20ms ? ?/sec 1.00 22.2±0.27ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q13 1.00 27.6±0.40ms ? ?/sec 1.00 27.5±0.26ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q14 1.02 25.2±0.28ms ? ?/sec 1.00 24.8±0.21ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q19 1.01 5.4±0.14ms ? ?/sec 1.00 5.4±0.09ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q20 1.01 110.3±1.21ms ? ?/sec 1.00 109.4±1.27ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q21 1.01 125.8±1.87ms ? ?/sec 1.00 124.6±0.93ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q22 1.01 231.8±1.69ms ? ?/sec 1.00 229.4±1.91ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q23 1.07 375.5±8.91ms ? ?/sec 1.00 352.2±1.52ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q24 1.00 30.5±0.45ms ? ?/sec 1.00 30.6±0.31ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q27 1.01 95.4±0.49ms ? ?/sec 1.00 94.1±0.58ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q28 1.01 93.0±0.74ms ? ?/sec 1.00 92.1±0.81ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q30 1.01 27.2±0.33ms ? ?/sec 1.00 27.0±0.24ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q36 1.01 104.0±1.20ms ? ?/sec 1.00 102.8±1.20ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q37 1.01 81.4±0.60ms ? ?/sec 1.00 80.4±0.90ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q38 1.01 30.7±0.42ms ? ?/sec 1.00 30.4±0.39ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q39 1.01 41.9±0.38ms ? ?/sec 1.00 41.5±0.42ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q40 1.00 27.1±0.42ms ? ?/sec 1.01 27.4±0.43ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q41 1.00 21.6±0.30ms ? ?/sec 1.01 21.9±0.28ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q42 1.01 10.6±0.27ms ? ?/sec 1.00 10.5±0.12ms ? ?/sec
arrow_reader_clickbench/sync/Q1 1.01 2.1±0.04ms ? ?/sec 1.00 2.0±0.01ms ? ?/sec
arrow_reader_clickbench/sync/Q10 1.00 8.0±0.09ms ? ?/sec 1.00 8.0±0.12ms ? ?/sec
arrow_reader_clickbench/sync/Q11 1.01 9.7±0.29ms ? ?/sec 1.00 9.6±0.16ms ? ?/sec
arrow_reader_clickbench/sync/Q12 1.00 29.7±0.51ms ? ?/sec 1.21 35.8±0.58ms ? ?/sec
arrow_reader_clickbench/sync/Q13 1.01 44.9±1.27ms ? ?/sec 1.00 44.4±0.62ms ? ?/sec
arrow_reader_clickbench/sync/Q14 1.01 31.8±0.27ms ? ?/sec 1.00 31.5±0.66ms ? ?/sec
arrow_reader_clickbench/sync/Q19 1.00 4.3±0.04ms ? ?/sec 1.03 4.4±0.09ms ? ?/sec
arrow_reader_clickbench/sync/Q20 1.01 177.9±1.47ms ? ?/sec 1.00 175.7±1.08ms ? ?/sec
arrow_reader_clickbench/sync/Q21 1.00 236.1±2.33ms ? ?/sec 1.00 234.9±2.08ms ? ?/sec
arrow_reader_clickbench/sync/Q22 1.02 486.5±3.97ms ? ?/sec 1.00 474.7±2.88ms ? ?/sec
arrow_reader_clickbench/sync/Q23 1.00 442.5±20.96ms ? ?/sec 1.01 445.0±15.54ms ? ?/sec
arrow_reader_clickbench/sync/Q24 1.00 40.6±0.53ms ? ?/sec 1.03 41.9±0.38ms ? ?/sec
arrow_reader_clickbench/sync/Q27 1.03 155.9±1.36ms ? ?/sec 1.00 152.0±0.95ms ? ?/sec
arrow_reader_clickbench/sync/Q28 1.02 150.3±1.24ms ? ?/sec 1.00 146.9±1.40ms ? ?/sec
arrow_reader_clickbench/sync/Q30 1.00 29.3±0.46ms ? ?/sec 1.01 29.5±0.43ms ? ?/sec
arrow_reader_clickbench/sync/Q36 1.01 156.1±1.01ms ? ?/sec 1.00 155.1±1.36ms ? ?/sec
arrow_reader_clickbench/sync/Q37 1.01 88.3±0.89ms ? ?/sec 1.00 87.3±1.11ms ? ?/sec
arrow_reader_clickbench/sync/Q38 1.01 30.0±0.29ms ? ?/sec 1.00 29.7±0.21ms ? ?/sec
arrow_reader_clickbench/sync/Q39 1.03 35.5±0.59ms ? ?/sec 1.00 34.6±0.46ms ? ?/sec
arrow_reader_clickbench/sync/Q40 1.04 28.3±0.68ms ? ?/sec 1.00 27.2±0.43ms ? ?/sec
arrow_reader_clickbench/sync/Q41 1.05 31.0±0.54ms ? ?/sec 1.00 29.6±0.70ms ? ?/sec
arrow_reader_clickbench/sync/Q42 1.03 12.8±0.11ms ? ?/sec 1.00 12.5±0.10ms ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "github-actions[bot] (via GitHub)" <gi...@apache.org>.
github-actions[bot] commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-4785348485
Thank you for your contribution. Unfortunately, this pull request is stale because it has been open 60 days with no activity. Please remove the stale label or comment or this will be closed in 7 days.
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3807622376
run benchmarks filter_kernels boolean_kernels arrow_reader arrow_reader_clickbench
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810416757
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (72a963254dd1c8583fc0f3604c15fa1404a8e823) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..72a963254dd1c8583fc0f3604c15fa1404a8e823)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811416956
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811836381
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (0d425e4f9ea4bcf43f1efc3298a9359d977b5208) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..0d425e4f9ea4bcf43f1efc3298a9359d977b5208)
BENCH_NAME=arrow_reader
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812775615
FYI @alamb this is starting to look good perf wise
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3809468501
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3819523846
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (1d307cb7351b3843d854a747316a69b40235c01e) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..1d307cb7351b3843d854a747316a69b40235c01e)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808807803
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (af1cdf235bbf4e94e4b8eae21d18bd9fab1c21ae) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..af1cdf235bbf4e94e4b8eae21d18bd9fab1c21ae)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812695961
run benchmark filter_kernels boolean_kernels arrow_reader_clickbench
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on code in PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#discussion_r2737758375
##########
arrow-buffer/src/buffer/boolean.rs:
##########
@@ -191,67 +192,48 @@ impl BooleanBuffer {
where
F: FnMut(u64) -> u64,
{
- // try fast path for aligned input
if offset_in_bits & 0x7 == 0 {
// align to byte boundary
let aligned = &src.as_ref()[offset_in_bits / 8..];
- if let Some(result) =
- Self::try_from_aligned_bitwise_unary_op(aligned, len_in_bits, &mut op)
- {
- return result;
- }
+ return Self::from_aligned_bitwise_unary_op(aligned, len_in_bits, &mut op);
}
- let chunks = BitChunks::new(src.as_ref(), offset_in_bits, len_in_bits);
- let mut result = MutableBuffer::with_capacity(chunks.num_u64s() * 8);
- for chunk in chunks.iter() {
- // SAFETY: reserved enough capacity above, (exactly num_u64s()
- // items) and we assume `BitChunks` correctly reports upper bound
- unsafe {
- result.push_unchecked(op(chunk));
- }
- }
- if chunks.remainder_len() > 0 {
- debug_assert!(result.capacity() >= result.len() + 8); // should not reallocate
- // SAFETY: reserved enough capacity above, (exactly num_u64s()
- // items) and we assume `BitChunks` correctly reports upper bound
- unsafe {
- result.push_unchecked(op(chunks.remainder_bits()));
- }
- // Just pushed one u64, which may have trailing zeros
- result.truncate(chunks.num_bytes());
- }
+ let src = src.as_ref();
+ let chunks = UnalignedBitChunk::new(src, offset_in_bits, len_in_bits);
Review Comment:
Probably not needed now that we have a fast byte aligned version.
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3813058694
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (060afb8ccada7f5fa888e3b8da110bd7c803839d) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..060afb8ccada7f5fa888e3b8da110bd7c803839d)
BENCH_NAME=coalesce_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench coalesce_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3809500598
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.02 209.4±6.44ns ? ?/sec 1.00 206.0±1.39ns ? ?/sec
and_sliced_1 1.00 1098.9±6.72ns ? ?/sec 1.24 1366.2±7.13ns ? ?/sec
and_sliced_24 1.00 247.3±1.06ns ? ?/sec 1.28 316.9±3.89ns ? ?/sec
not 1.00 146.4±2.53ns ? ?/sec 1.29 189.5±4.04ns ? ?/sec
not_slice_24 1.00 193.5±1.46ns ? ?/sec 1.27 246.6±1.92ns ? ?/sec
not_sliced_1 2.49 621.2±6.22ns ? ?/sec 1.00 249.2±32.36ns ? ?/sec
or 1.00 197.2±1.36ns ? ?/sec 1.00 196.8±1.72ns ? ?/sec
or_sliced_1 1.00 1102.3±30.29ns ? ?/sec 1.18 1304.2±13.07ns ? ?/sec
or_sliced_24 1.00 248.8±3.12ns ? ?/sec 1.54 383.0±3.72ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811687567
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (00d36c063e75415d73dd0c46a6ec260fc9816747) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..00d36c063e75415d73dd0c46a6ec260fc9816747)
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812316650
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (060afb8ccada7f5fa888e3b8da110bd7c803839d) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..060afb8ccada7f5fa888e3b8da110bd7c803839d)
BENCH_NAME=arrow_reader_clickbench
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader_clickbench
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808136408
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 208.4±2.17ns ? ?/sec 1.00 208.1±3.03ns ? ?/sec
and_sliced_1 1.00 1097.7±9.34ns ? ?/sec 1.19 1305.8±16.47ns ? ?/sec
and_sliced_24 1.00 246.5±0.46ns ? ?/sec 1.30 319.7±1.06ns ? ?/sec
not 1.00 145.9±2.30ns ? ?/sec 1.34 195.2±1.31ns ? ?/sec
not_slice_24 1.00 194.5±1.26ns ? ?/sec 1.28 249.8±1.61ns ? ?/sec
not_sliced_1 2.48 620.6±10.46ns ? ?/sec 1.00 250.1±4.67ns ? ?/sec
or 1.00 197.4±1.76ns ? ?/sec 1.18 232.5±2.72ns ? ?/sec
or_sliced_1 1.00 1099.7±10.23ns ? ?/sec 1.25 1377.8±28.46ns ? ?/sec
or_sliced_24 1.00 248.3±1.25ns ? ?/sec 1.30 321.8±2.49ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808469507
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_reader_clickbench/async/Q1 1.02 2.4±0.05ms ? ?/sec 1.00 2.3±0.04ms ? ?/sec
arrow_reader_clickbench/async/Q10 1.14 12.4±0.16ms ? ?/sec 1.00 10.9±0.22ms ? ?/sec
arrow_reader_clickbench/async/Q11 1.15 14.5±0.40ms ? ?/sec 1.00 12.6±0.32ms ? ?/sec
arrow_reader_clickbench/async/Q12 1.06 23.6±0.50ms ? ?/sec 1.00 22.3±0.25ms ? ?/sec
arrow_reader_clickbench/async/Q13 1.07 29.6±0.30ms ? ?/sec 1.00 27.7±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q14 1.04 26.1±0.16ms ? ?/sec 1.00 25.0±0.35ms ? ?/sec
arrow_reader_clickbench/async/Q19 1.10 6.0±0.09ms ? ?/sec 1.00 5.4±0.25ms ? ?/sec
arrow_reader_clickbench/async/Q20 1.02 125.4±1.81ms ? ?/sec 1.00 122.8±1.31ms ? ?/sec
arrow_reader_clickbench/async/Q21 1.03 159.3±2.26ms ? ?/sec 1.00 155.1±2.41ms ? ?/sec
arrow_reader_clickbench/async/Q22 1.00 257.9±5.39ms ? ?/sec 1.13 291.0±28.48ms ? ?/sec
arrow_reader_clickbench/async/Q23 1.03 426.9±5.97ms ? ?/sec 1.00 414.1±5.11ms ? ?/sec
arrow_reader_clickbench/async/Q24 1.03 33.0±0.65ms ? ?/sec 1.00 32.0±0.48ms ? ?/sec
arrow_reader_clickbench/async/Q27 1.01 101.6±0.57ms ? ?/sec 1.00 100.8±0.78ms ? ?/sec
arrow_reader_clickbench/async/Q28 1.01 99.3±0.46ms ? ?/sec 1.00 98.4±0.55ms ? ?/sec
arrow_reader_clickbench/async/Q30 1.01 29.2±0.21ms ? ?/sec 1.00 29.0±0.27ms ? ?/sec
arrow_reader_clickbench/async/Q36 1.01 110.3±1.08ms ? ?/sec 1.00 109.7±0.65ms ? ?/sec
arrow_reader_clickbench/async/Q37 1.01 85.9±0.88ms ? ?/sec 1.00 85.4±1.14ms ? ?/sec
arrow_reader_clickbench/async/Q38 1.01 34.7±0.30ms ? ?/sec 1.00 34.4±0.41ms ? ?/sec
arrow_reader_clickbench/async/Q39 1.00 48.2±0.57ms ? ?/sec 1.01 48.5±0.89ms ? ?/sec
arrow_reader_clickbench/async/Q40 1.00 30.0±0.21ms ? ?/sec 1.01 30.4±0.82ms ? ?/sec
arrow_reader_clickbench/async/Q41 1.01 24.3±0.24ms ? ?/sec 1.00 24.2±0.16ms ? ?/sec
arrow_reader_clickbench/async/Q42 1.00 11.6±0.18ms ? ?/sec 1.00 11.5±0.11ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q1 1.01 2.3±0.06ms ? ?/sec 1.00 2.3±0.03ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q10 1.00 12.0±0.23ms ? ?/sec 1.02 12.3±0.38ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q11 1.00 13.8±0.22ms ? ?/sec 1.00 13.9±0.25ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q12 1.00 21.8±0.25ms ? ?/sec 1.07 23.2±0.24ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q13 1.00 26.8±0.50ms ? ?/sec 1.06 28.3±0.26ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q14 1.00 24.4±0.33ms ? ?/sec 1.05 25.6±0.28ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q19 1.00 5.1±0.05ms ? ?/sec 1.05 5.4±0.10ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q20 1.00 110.4±0.97ms ? ?/sec 1.02 112.4±1.21ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q21 1.00 125.8±1.29ms ? ?/sec 1.02 128.2±0.82ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q22 1.00 231.2±2.57ms ? ?/sec 1.02 235.7±1.99ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q23 1.00 368.8±2.14ms ? ?/sec 1.02 374.9±1.95ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q24 1.00 29.5±0.38ms ? ?/sec 1.07 31.6±0.36ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q27 1.00 95.1±0.59ms ? ?/sec 1.01 96.0±0.59ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q28 1.00 92.7±0.57ms ? ?/sec 1.02 94.4±0.81ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q30 1.00 26.2±0.34ms ? ?/sec 1.06 27.7±0.32ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q36 1.00 103.5±1.13ms ? ?/sec 1.01 104.3±1.21ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q37 1.00 80.9±0.69ms ? ?/sec 1.00 81.3±1.17ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q38 1.00 29.7±0.30ms ? ?/sec 1.02 30.3±0.92ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q39 1.00 40.7±0.48ms ? ?/sec 1.02 41.6±0.32ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q40 1.00 25.5±0.42ms ? ?/sec 1.07 27.2±0.41ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q41 1.00 20.6±0.35ms ? ?/sec 1.07 21.9±0.24ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q42 1.00 10.2±0.23ms ? ?/sec 1.02 10.4±0.12ms ? ?/sec
arrow_reader_clickbench/sync/Q1 1.01 2.1±0.01ms ? ?/sec 1.00 2.0±0.02ms ? ?/sec
arrow_reader_clickbench/sync/Q10 1.03 8.0±0.14ms ? ?/sec 1.00 7.8±0.13ms ? ?/sec
arrow_reader_clickbench/sync/Q11 1.06 9.9±0.29ms ? ?/sec 1.00 9.3±0.07ms ? ?/sec
arrow_reader_clickbench/sync/Q12 1.00 29.7±0.37ms ? ?/sec 1.17 34.7±1.06ms ? ?/sec
arrow_reader_clickbench/sync/Q13 1.05 45.2±1.10ms ? ?/sec 1.00 43.0±0.49ms ? ?/sec
arrow_reader_clickbench/sync/Q14 1.04 32.2±0.57ms ? ?/sec 1.00 31.0±0.58ms ? ?/sec
arrow_reader_clickbench/sync/Q19 1.08 4.5±0.15ms ? ?/sec 1.00 4.2±0.06ms ? ?/sec
arrow_reader_clickbench/sync/Q20 1.03 181.7±1.47ms ? ?/sec 1.00 177.0±1.59ms ? ?/sec
arrow_reader_clickbench/sync/Q21 1.02 240.8±2.20ms ? ?/sec 1.00 235.7±1.32ms ? ?/sec
arrow_reader_clickbench/sync/Q22 1.04 492.0±4.86ms ? ?/sec 1.00 475.3±2.90ms ? ?/sec
arrow_reader_clickbench/sync/Q23 1.01 451.4±21.84ms ? ?/sec 1.00 445.6±14.99ms ? ?/sec
arrow_reader_clickbench/sync/Q24 1.07 43.2±1.15ms ? ?/sec 1.00 40.4±0.43ms ? ?/sec
arrow_reader_clickbench/sync/Q27 1.04 159.4±1.52ms ? ?/sec 1.00 153.2±1.02ms ? ?/sec
arrow_reader_clickbench/sync/Q28 1.03 152.9±1.98ms ? ?/sec 1.00 147.9±1.77ms ? ?/sec
arrow_reader_clickbench/sync/Q30 1.06 29.5±0.39ms ? ?/sec 1.00 27.9±0.37ms ? ?/sec
arrow_reader_clickbench/sync/Q36 1.06 162.6±1.88ms ? ?/sec 1.00 153.2±2.01ms ? ?/sec
arrow_reader_clickbench/sync/Q37 1.04 90.1±1.24ms ? ?/sec 1.00 86.5±1.34ms ? ?/sec
arrow_reader_clickbench/sync/Q38 1.03 30.1±0.15ms ? ?/sec 1.00 29.2±0.38ms ? ?/sec
arrow_reader_clickbench/sync/Q39 1.08 36.2±0.33ms ? ?/sec 1.00 33.5±0.80ms ? ?/sec
arrow_reader_clickbench/sync/Q40 1.08 28.1±0.22ms ? ?/sec 1.00 26.1±0.39ms ? ?/sec
arrow_reader_clickbench/sync/Q41 1.08 30.8±0.74ms ? ?/sec 1.00 28.6±0.39ms ? ?/sec
arrow_reader_clickbench/sync/Q42 1.05 13.0±0.27ms ? ?/sec 1.00 12.4±0.19ms ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893143063
run benchmark arrow_reader_clickbench
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811808740
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter context decimal128 (kept 1/2) 1.00 45.2±5.62µs ? ?/sec 1.07 48.6±7.24µs ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024) 1.00 50.3±1.16µs ? ?/sec 1.03 51.6±1.67µs ? ?/sec
filter context decimal128 low selectivity (kept 1/1024) 1.02 232.2±2.27ns ? ?/sec 1.00 227.5±2.16ns ? ?/sec
filter context f32 (kept 1/2) 1.00 88.0±0.93µs ? ?/sec 1.00 88.2±0.50µs ? ?/sec
filter context f32 high selectivity (kept 1023/1024) 1.00 10.4±0.51µs ? ?/sec 1.01 10.5±0.45µs ? ?/sec
filter context f32 low selectivity (kept 1/1024) 1.00 428.7±3.76ns ? ?/sec 1.04 443.8±6.21ns ? ?/sec
filter context fsb with value length 20 (kept 1/2) 1.00 70.8±1.04µs ? ?/sec 1.00 71.0±1.69µs ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024) 1.00 70.8±0.68µs ? ?/sec 1.00 70.8±0.45µs ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024) 1.00 70.7±0.70µs ? ?/sec 1.00 71.0±1.48µs ? ?/sec
filter context fsb with value length 5 (kept 1/2) 1.00 70.7±0.29µs ? ?/sec 1.00 70.8±1.24µs ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024) 1.00 71.0±2.16µs ? ?/sec 1.00 70.8±1.02µs ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024) 1.00 70.7±0.35µs ? ?/sec 1.00 70.7±0.52µs ? ?/sec
filter context fsb with value length 50 (kept 1/2) 1.00 70.6±0.21µs ? ?/sec 1.00 70.8±0.73µs ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024) 1.00 70.7±0.39µs ? ?/sec 1.00 70.7±0.38µs ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024) 1.00 70.9±1.45µs ? ?/sec 1.00 70.7±0.37µs ? ?/sec
filter context i32 (kept 1/2) 1.01 16.5±0.09µs ? ?/sec 1.00 16.4±0.10µs ? ?/sec
filter context i32 high selectivity (kept 1023/1024) 1.00 6.3±0.37µs ? ?/sec 1.02 6.4±0.26µs ? ?/sec
filter context i32 low selectivity (kept 1/1024) 1.01 223.8±5.99ns ? ?/sec 1.00 221.3±2.68ns ? ?/sec
filter context i32 w NULLs (kept 1/2) 1.00 87.9±0.97µs ? ?/sec 1.00 87.6±1.11µs ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024) 1.03 10.6±0.52µs ? ?/sec 1.00 10.3±0.32µs ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024) 1.00 426.3±10.15ns ? ?/sec 1.04 444.7±4.24ns ? ?/sec
filter context mixed string view (kept 1/2) 1.06 121.9±6.83µs ? ?/sec 1.00 114.6±5.06µs ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024) 1.00 54.3±1.82µs ? ?/sec 1.00 54.5±1.02µs ? ?/sec
filter context mixed string view low selectivity (kept 1/1024) 1.00 629.6±18.13ns ? ?/sec 1.02 640.3±8.29ns ? ?/sec
filter context short string view (kept 1/2) 1.00 114.3±3.04µs ? ?/sec 1.01 115.3±6.22µs ? ?/sec
filter context short string view high selectivity (kept 1023/1024) 1.00 53.7±1.35µs ? ?/sec 1.00 53.7±1.38µs ? ?/sec
filter context short string view low selectivity (kept 1/1024) 1.00 481.8±7.92ns ? ?/sec 1.04 500.8±20.49ns ? ?/sec
filter context string (kept 1/2) 1.00 589.5±14.27µs ? ?/sec 1.03 607.6±20.92µs ? ?/sec
filter context string dictionary (kept 1/2) 1.00 17.3±0.09µs ? ?/sec 1.02 17.6±0.16µs ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024) 1.00 7.0±0.38µs ? ?/sec 1.01 7.1±0.38µs ? ?/sec
filter context string dictionary low selectivity (kept 1/1024) 1.00 641.0±8.40ns ? ?/sec 1.00 642.6±9.49ns ? ?/sec
filter context string dictionary w NULLs (kept 1/2) 1.00 88.4±0.67µs ? ?/sec 1.00 88.7±1.12µs ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024) 1.00 10.8±0.47µs ? ?/sec 1.00 10.8±0.42µs ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024) 1.00 865.5±16.35ns ? ?/sec 1.02 880.2±18.21ns ? ?/sec
filter context string high selectivity (kept 1023/1024) 1.00 628.6±13.12µs ? ?/sec 1.22 769.8±30.41µs ? ?/sec
filter context string low selectivity (kept 1/1024) 1.00 986.3±18.17ns ? ?/sec 1.00 988.6±7.58ns ? ?/sec
filter context u8 (kept 1/2) 1.00 15.0±0.10µs ? ?/sec 1.00 15.0±0.21µs ? ?/sec
filter context u8 high selectivity (kept 1023/1024) 1.09 2.0±0.02µs ? ?/sec 1.00 1838.9±11.06ns ? ?/sec
filter context u8 low selectivity (kept 1/1024) 1.01 215.8±4.71ns ? ?/sec 1.00 214.2±4.20ns ? ?/sec
filter context u8 w NULLs (kept 1/2) 1.00 85.9±0.35µs ? ?/sec 1.00 85.9±0.40µs ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024) 1.00 5.1±0.02µs ? ?/sec 1.05 5.3±0.34µs ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024) 1.00 422.6±6.69ns ? ?/sec 1.04 439.5±3.95ns ? ?/sec
filter decimal128 (kept 1/2) 1.06 49.1±4.61µs ? ?/sec 1.00 46.3±4.13µs ? ?/sec
filter decimal128 high selectivity (kept 1023/1024) 1.00 53.7±1.31µs ? ?/sec 1.00 53.7±1.21µs ? ?/sec
filter decimal128 low selectivity (kept 1/1024) 1.64 3.2±0.03µs ? ?/sec 1.00 1930.5±12.51ns ? ?/sec
filter f32 (kept 1/2) 1.18 155.3±2.01µs ? ?/sec 1.00 132.1±0.73µs ? ?/sec
filter fsb with value length 20 (kept 1/2) 1.06 137.0±0.76µs ? ?/sec 1.00 129.8±2.34µs ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024) 1.02 72.0±1.59µs ? ?/sec 1.00 70.2±1.52µs ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024) 1.80 3.5±0.03µs ? ?/sec 1.00 1928.0±12.91ns ? ?/sec
filter fsb with value length 5 (kept 1/2) 1.04 142.2±1.24µs ? ?/sec 1.00 136.3±1.94µs ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024) 1.03 11.6±0.50µs ? ?/sec 1.00 11.2±0.49µs ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024) 1.85 3.4±0.02µs ? ?/sec 1.00 1833.9±42.42ns ? ?/sec
filter fsb with value length 50 (kept 1/2) 1.09 165.2±13.42µs ? ?/sec 1.00 151.0±12.52µs ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024) 1.00 218.9±4.77µs ? ?/sec 1.01 220.4±9.74µs ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024) 1.68 3.4±0.02µs ? ?/sec 1.00 2.0±0.03µs ? ?/sec
filter i32 (kept 1/2) 1.64 54.2±0.90µs ? ?/sec 1.00 33.1±0.14µs ? ?/sec
filter i32 high selectivity (kept 1023/1024) 1.01 9.0±0.55µs ? ?/sec 1.00 8.9±0.38µs ? ?/sec
filter i32 low selectivity (kept 1/1024) 1.74 3.0±0.02µs ? ?/sec 1.00 1699.0±26.09ns ? ?/sec
filter optimize (kept 1/2) 1.00 36.0±0.37µs ? ?/sec 1.01 36.5±0.22µs ? ?/sec
filter optimize high selectivity (kept 1023/1024) 1.06 2.7±0.01µs ? ?/sec 1.00 2.6±0.03µs ? ?/sec
filter optimize low selectivity (kept 1/1024) 1.23 1802.2±54.38ns ? ?/sec 1.00 1460.3±12.84ns ? ?/sec
filter run array (kept 1/2) 1.03 380.2±6.73µs ? ?/sec 1.00 370.2±5.94µs ? ?/sec
filter run array high selectivity (kept 1023/1024) 1.00 397.3±3.49µs ? ?/sec 1.03 409.1±7.72µs ? ?/sec
filter run array low selectivity (kept 1/1024) 1.00 283.8±4.16µs ? ?/sec 1.04 294.0±3.47µs ? ?/sec
filter single record batch 1.22 52.8±0.66µs ? ?/sec 1.00 43.2±0.22µs ? ?/sec
filter u8 (kept 1/2) 1.23 53.6±0.62µs ? ?/sec 1.00 43.4±0.63µs ? ?/sec
filter u8 high selectivity (kept 1023/1024) 1.01 3.8±0.08µs ? ?/sec 1.00 3.8±0.04µs ? ?/sec
filter u8 low selectivity (kept 1/1024) 1.67 3.3±0.04µs ? ?/sec 1.00 1974.5±11.18ns ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3813180417
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.001 1.01 263.4±1.78ms ? ?/sec 1.00 261.9±2.41ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.01 1.02 8.3±0.12ms ? ?/sec 1.00 8.1±0.13ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.1 1.00 3.9±0.11ms ? ?/sec 1.02 4.0±0.09ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.8 1.00 3.4±0.05ms ? ?/sec 1.01 3.5±0.03ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.001 1.02 248.3±2.63ms ? ?/sec 1.00 244.1±2.45ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.01 1.03 9.0±0.10ms ? ?/sec 1.00 8.8±0.10ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.1 1.02 4.4±0.10ms ? ?/sec 1.00 4.3±0.10ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.8 1.01 4.6±0.04ms ? ?/sec 1.00 4.5±0.04ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.001 1.06 56.6±1.19ms ? ?/sec 1.00 53.5±0.76ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.01 1.00 11.1±0.11ms ? ?/sec 1.00 11.1±0.19ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.1 1.01 9.3±0.36ms ? ?/sec 1.00 9.1±0.14ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.8 1.25 11.4±0.25ms ? ?/sec 1.00 9.1±0.31ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.001 1.05 65.3±0.49ms ? ?/sec 1.00 62.1±0.69ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.01 1.01 12.3±0.13ms ? ?/sec 1.00 12.1±0.23ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.1 1.03 9.9±0.27ms ? ?/sec 1.00 9.6±0.23ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.8 1.00 10.6±0.20ms ? ?/sec 1.00 10.6±0.14ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.001 1.07 44.1±0.65ms ? ?/sec 1.00 41.2±0.57ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.01 1.05 5.5±0.08ms ? ?/sec 1.00 5.2±0.09ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.1 1.02 4.3±0.17ms ? ?/sec 1.00 4.3±0.16ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.8 1.00 3.0±0.06ms ? ?/sec 1.02 3.1±0.10ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.001 1.05 54.2±0.31ms ? ?/sec 1.00 51.5±2.00ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.01 1.01 7.5±0.07ms ? ?/sec 1.00 7.4±0.08ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.1 1.00 5.2±0.13ms ? ?/sec 1.00 5.2±0.15ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.8 1.00 3.7±0.03ms ? ?/sec 1.00 3.7±0.02ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.001 1.07 39.6±0.50ms ? ?/sec 1.00 37.0±0.48ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.01 1.03 4.3±0.05ms ? ?/sec 1.00 4.2±0.10ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.1 1.01 2.0±0.07ms ? ?/sec 1.00 2.0±0.05ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.8 1.00 1317.6±27.12µs ? ?/sec 1.02 1342.0±19.16µs ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.001 1.06 48.7±0.20ms ? ?/sec 1.00 46.1±0.65ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.01 1.02 6.5±0.11ms ? ?/sec 1.00 6.3±0.11ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.1 1.00 3.3±0.11ms ? ?/sec 1.04 3.4±0.18ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.8 1.01 3.7±0.05ms ? ?/sec 1.00 3.7±0.02ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.001 1.10 88.7±1.28ms ? ?/sec 1.00 80.3±1.28ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.01 1.09 8.4±0.12ms ? ?/sec 1.00 7.7±0.06ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.1 1.04 3.2±0.24ms ? ?/sec 1.00 3.1±0.15ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.8 1.00 2.8±0.04ms ? ?/sec 1.04 2.9±0.02ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.001 1.07 116.5±1.72ms ? ?/sec 1.00 108.9±1.39ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.01 1.04 13.9±0.09ms ? ?/sec 1.00 13.3±0.16ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.1 1.00 6.3±0.22ms ? ?/sec 1.06 6.7±0.40ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.8 1.00 8.8±0.06ms ? ?/sec 1.00 8.8±0.04ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.001 1.11 63.4±0.62ms ? ?/sec 1.00 57.0±1.35ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.01 1.08 7.6±0.12ms ? ?/sec 1.00 7.0±0.05ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.1 1.07 3.8±0.19ms ? ?/sec 1.00 3.6±0.15ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.8 1.00 1282.4±11.51µs ? ?/sec 1.02 1312.9±12.98µs ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.001 1.19 89.6±1.99ms ? ?/sec 1.00 75.2±0.46ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.01 1.14 11.3±0.30ms ? ?/sec 1.00 9.9±0.26ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.1 1.09 5.2±0.30ms ? ?/sec 1.00 4.8±0.30ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.8 1.01 3.8±0.02ms ? ?/sec 1.00 3.7±0.11ms ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808136547
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (b4b71aa2ed596a56f0abb9e77552011a875e617a) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..b4b71aa2ed596a56f0abb9e77552011a875e617a)
BENCH_NAME=arrow_reader
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808367712
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (b4b71aa2ed596a56f0abb9e77552011a875e617a) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..b4b71aa2ed596a56f0abb9e77552011a875e617a)
BENCH_NAME=arrow_reader_clickbench
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader_clickbench
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3816203563
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3812999591
run benchmark coalesce_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3897966028
Those are some impressive benchmark results
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893399515
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (d20ef3573d7205f053b9cbb79c1b63c8c7dcd570) to d6168e526aae79d6fbafe8c11062b5f834021052 [diff](https://github.com/apache/arrow-rs/compare/d6168e526aae79d6fbafe8c11062b5f834021052..d20ef3573d7205f053b9cbb79c1b63c8c7dcd570)
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "github-actions[bot] (via GitHub)" <gi...@apache.org>.
github-actions[bot] closed pull request #9284: Optimize boolean operations
URL: https://github.com/apache/arrow-rs/pull/9284
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3894243207
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (d20ef3573d7205f053b9cbb79c1b63c8c7dcd570) to d6168e526aae79d6fbafe8c11062b5f834021052 [diff](https://github.com/apache/arrow-rs/compare/d6168e526aae79d6fbafe8c11062b5f834021052..d20ef3573d7205f053b9cbb79c1b63c8c7dcd570)
BENCH_NAME=coalesce_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench coalesce_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893104116
run benchmark filter_kernels
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810008796
run benchmark boolean_kernels
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811017381
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (6d953141f033a03845fb74107d8d3ef190efcb82) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..6d953141f033a03845fb74107d8d3ef190efcb82)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811809026
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (0d425e4f9ea4bcf43f1efc3298a9359d977b5208) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..0d425e4f9ea4bcf43f1efc3298a9359d977b5208)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3813058409
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_reader_clickbench/async/Q1 1.04 2.4±0.03ms ? ?/sec 1.00 2.3±0.04ms ? ?/sec
arrow_reader_clickbench/async/Q10 1.17 14.2±0.26ms ? ?/sec 1.00 12.2±0.34ms ? ?/sec
arrow_reader_clickbench/async/Q11 1.15 16.0±0.31ms ? ?/sec 1.00 13.9±0.29ms ? ?/sec
arrow_reader_clickbench/async/Q12 1.43 32.9±0.35ms ? ?/sec 1.00 23.0±0.35ms ? ?/sec
arrow_reader_clickbench/async/Q13 1.42 40.5±0.66ms ? ?/sec 1.00 28.5±0.31ms ? ?/sec
arrow_reader_clickbench/async/Q14 1.40 36.2±0.48ms ? ?/sec 1.00 25.8±0.43ms ? ?/sec
arrow_reader_clickbench/async/Q19 1.26 7.3±0.14ms ? ?/sec 1.00 5.8±0.13ms ? ?/sec
arrow_reader_clickbench/async/Q20 1.45 176.6±1.89ms ? ?/sec 1.00 121.8±1.47ms ? ?/sec
arrow_reader_clickbench/async/Q21 1.28 197.5±3.34ms ? ?/sec 1.00 154.2±2.08ms ? ?/sec
arrow_reader_clickbench/async/Q22 1.44 341.2±36.98ms ? ?/sec 1.00 236.9±2.37ms ? ?/sec
arrow_reader_clickbench/async/Q23 1.05 429.2±4.35ms ? ?/sec 1.00 407.3±2.78ms ? ?/sec
arrow_reader_clickbench/async/Q24 1.13 35.8±1.20ms ? ?/sec 1.00 31.7±0.57ms ? ?/sec
arrow_reader_clickbench/async/Q27 1.05 103.7±0.82ms ? ?/sec 1.00 99.0±0.86ms ? ?/sec
arrow_reader_clickbench/async/Q28 1.04 100.6±1.10ms ? ?/sec 1.00 96.7±0.71ms ? ?/sec
arrow_reader_clickbench/async/Q30 1.07 30.2±0.60ms ? ?/sec 1.00 28.4±0.52ms ? ?/sec
arrow_reader_clickbench/async/Q36 1.05 113.1±0.96ms ? ?/sec 1.00 107.7±1.00ms ? ?/sec
arrow_reader_clickbench/async/Q37 1.04 88.0±1.27ms ? ?/sec 1.00 84.3±0.87ms ? ?/sec
arrow_reader_clickbench/async/Q38 1.06 35.3±0.28ms ? ?/sec 1.00 33.3±0.40ms ? ?/sec
arrow_reader_clickbench/async/Q39 1.08 50.3±0.64ms ? ?/sec 1.00 46.4±0.45ms ? ?/sec
arrow_reader_clickbench/async/Q40 1.10 31.5±0.71ms ? ?/sec 1.00 28.6±0.48ms ? ?/sec
arrow_reader_clickbench/async/Q41 1.13 26.1±0.51ms ? ?/sec 1.00 23.1±0.29ms ? ?/sec
arrow_reader_clickbench/async/Q42 1.08 12.0±0.16ms ? ?/sec 1.00 11.1±0.27ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q1 1.04 2.3±0.04ms ? ?/sec 1.00 2.3±0.05ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q10 1.16 13.4±0.30ms ? ?/sec 1.00 11.6±0.29ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q11 1.16 15.3±0.39ms ? ?/sec 1.00 13.2±0.27ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q12 1.08 24.2±0.38ms ? ?/sec 1.00 22.4±0.46ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q13 1.05 29.5±0.33ms ? ?/sec 1.00 28.0±0.46ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q14 1.06 26.9±0.27ms ? ?/sec 1.00 25.3±0.21ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q19 1.15 6.5±0.22ms ? ?/sec 1.00 5.6±0.14ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q20 1.04 114.2±1.22ms ? ?/sec 1.00 110.3±1.15ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q21 1.04 131.0±1.51ms ? ?/sec 1.00 125.6±0.73ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q22 1.05 242.8±2.71ms ? ?/sec 1.00 231.8±1.78ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q23 1.04 373.6±10.75ms ? ?/sec 1.00 359.7±6.89ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q24 1.06 32.9±0.47ms ? ?/sec 1.00 31.0±0.57ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q27 1.04 98.9±1.17ms ? ?/sec 1.00 94.9±1.01ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q28 1.05 97.5±1.27ms ? ?/sec 1.00 92.9±0.63ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q30 1.05 29.0±0.84ms ? ?/sec 1.00 27.6±0.61ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q36 1.04 107.6±1.50ms ? ?/sec 1.00 103.0±1.10ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q37 1.05 84.7±1.10ms ? ?/sec 1.00 80.4±0.68ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q38 1.07 32.4±0.37ms ? ?/sec 1.00 30.2±0.35ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q39 1.07 44.8±0.76ms ? ?/sec 1.00 41.7±0.39ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q40 1.06 28.5±0.51ms ? ?/sec 1.00 27.0±0.34ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q41 1.03 22.3±0.36ms ? ?/sec 1.00 21.6±0.25ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q42 1.03 10.8±0.22ms ? ?/sec 1.00 10.5±0.14ms ? ?/sec
arrow_reader_clickbench/sync/Q1 1.01 2.1±0.01ms ? ?/sec 1.00 2.0±0.01ms ? ?/sec
arrow_reader_clickbench/sync/Q10 1.03 8.4±0.14ms ? ?/sec 1.00 8.2±0.19ms ? ?/sec
arrow_reader_clickbench/sync/Q11 1.03 10.0±0.27ms ? ?/sec 1.00 9.6±0.15ms ? ?/sec
arrow_reader_clickbench/sync/Q12 1.00 29.8±0.38ms ? ?/sec 1.22 36.2±1.06ms ? ?/sec
arrow_reader_clickbench/sync/Q13 1.01 45.3±1.61ms ? ?/sec 1.00 44.8±0.52ms ? ?/sec
arrow_reader_clickbench/sync/Q14 1.28 40.8±1.18ms ? ?/sec 1.00 31.7±0.33ms ? ?/sec
arrow_reader_clickbench/sync/Q19 1.03 4.6±0.13ms ? ?/sec 1.00 4.5±0.07ms ? ?/sec
arrow_reader_clickbench/sync/Q20 1.07 187.6±3.02ms ? ?/sec 1.00 176.1±1.63ms ? ?/sec
arrow_reader_clickbench/sync/Q21 1.05 247.2±4.30ms ? ?/sec 1.00 234.7±1.72ms ? ?/sec
arrow_reader_clickbench/sync/Q22 1.09 515.9±4.75ms ? ?/sec 1.00 473.8±3.78ms ? ?/sec
arrow_reader_clickbench/sync/Q23 1.05 467.2±20.23ms ? ?/sec 1.00 446.2±15.69ms ? ?/sec
arrow_reader_clickbench/sync/Q24 1.07 44.9±0.79ms ? ?/sec 1.00 41.9±0.77ms ? ?/sec
arrow_reader_clickbench/sync/Q27 1.11 168.6±3.06ms ? ?/sec 1.00 152.0±1.14ms ? ?/sec
arrow_reader_clickbench/sync/Q28 1.07 157.7±2.21ms ? ?/sec 1.00 147.1±1.98ms ? ?/sec
arrow_reader_clickbench/sync/Q30 1.08 31.3±0.37ms ? ?/sec 1.00 28.9±0.35ms ? ?/sec
arrow_reader_clickbench/sync/Q36 1.09 166.7±1.99ms ? ?/sec 1.00 152.8±1.02ms ? ?/sec
arrow_reader_clickbench/sync/Q37 1.07 92.5±0.90ms ? ?/sec 1.00 86.2±0.62ms ? ?/sec
arrow_reader_clickbench/sync/Q38 1.05 30.9±0.27ms ? ?/sec 1.00 29.4±0.20ms ? ?/sec
arrow_reader_clickbench/sync/Q39 1.15 39.2±0.77ms ? ?/sec 1.00 34.1±0.44ms ? ?/sec
arrow_reader_clickbench/sync/Q40 1.16 31.4±0.55ms ? ?/sec 1.00 27.2±0.47ms ? ?/sec
arrow_reader_clickbench/sync/Q41 1.14 33.8±0.62ms ? ?/sec 1.00 29.6±0.67ms ? ?/sec
arrow_reader_clickbench/sync/Q42 1.06 13.2±0.13ms ? ?/sec 1.00 12.5±0.15ms ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3816380462
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3819523896
(sorry runner had been restarted for some reason)
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808807561
run benchmark boolean_kernels filter_kernels
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810540656
run benchmark boolean_kernels
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893821590
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_reader_clickbench/async/Q1 1.01 2.3±0.02ms ? ?/sec 1.00 2.3±0.04ms ? ?/sec
arrow_reader_clickbench/async/Q10 1.00 11.4±0.33ms ? ?/sec 1.00 11.4±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q11 1.00 12.8±0.27ms ? ?/sec 1.02 13.1±0.47ms ? ?/sec
arrow_reader_clickbench/async/Q12 1.00 22.8±0.26ms ? ?/sec 1.01 23.0±0.29ms ? ?/sec
arrow_reader_clickbench/async/Q13 1.00 28.5±0.34ms ? ?/sec 1.00 28.4±0.49ms ? ?/sec
arrow_reader_clickbench/async/Q14 1.00 25.2±0.22ms ? ?/sec 1.02 25.6±0.64ms ? ?/sec
arrow_reader_clickbench/async/Q19 1.01 5.6±0.11ms ? ?/sec 1.00 5.5±0.13ms ? ?/sec
arrow_reader_clickbench/async/Q20 1.09 125.2±10.94ms ? ?/sec 1.00 114.7±0.65ms ? ?/sec
arrow_reader_clickbench/async/Q21 1.26 164.4±1.55ms ? ?/sec 1.00 130.7±0.77ms ? ?/sec
arrow_reader_clickbench/async/Q22 1.14 284.7±40.96ms ? ?/sec 1.00 250.8±4.23ms ? ?/sec
arrow_reader_clickbench/async/Q23 1.00 406.3±3.25ms ? ?/sec 1.02 413.6±5.17ms ? ?/sec
arrow_reader_clickbench/async/Q24 1.00 31.0±0.31ms ? ?/sec 1.03 32.0±0.54ms ? ?/sec
arrow_reader_clickbench/async/Q27 1.00 98.4±0.81ms ? ?/sec 1.01 99.8±0.51ms ? ?/sec
arrow_reader_clickbench/async/Q28 1.00 96.5±0.53ms ? ?/sec 1.01 97.4±0.57ms ? ?/sec
arrow_reader_clickbench/async/Q30 1.01 28.0±0.38ms ? ?/sec 1.00 27.7±0.30ms ? ?/sec
arrow_reader_clickbench/async/Q36 1.00 116.4±0.82ms ? ?/sec 1.01 118.0±0.64ms ? ?/sec
arrow_reader_clickbench/async/Q37 1.00 91.7±0.71ms ? ?/sec 1.02 93.5±0.71ms ? ?/sec
arrow_reader_clickbench/async/Q38 1.00 35.0±0.45ms ? ?/sec 1.02 35.7±0.69ms ? ?/sec
arrow_reader_clickbench/async/Q39 1.00 45.3±0.37ms ? ?/sec 1.03 46.5±0.54ms ? ?/sec
arrow_reader_clickbench/async/Q40 1.01 40.4±0.44ms ? ?/sec 1.00 40.0±0.58ms ? ?/sec
arrow_reader_clickbench/async/Q41 1.01 29.5±0.33ms ? ?/sec 1.00 29.3±0.36ms ? ?/sec
arrow_reader_clickbench/async/Q42 1.02 11.1±0.11ms ? ?/sec 1.00 10.8±0.11ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q1 1.02 2.3±0.01ms ? ?/sec 1.00 2.2±0.02ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q10 1.00 10.9±0.30ms ? ?/sec 1.00 11.0±0.35ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q11 1.00 12.4±0.29ms ? ?/sec 1.00 12.3±0.36ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q12 1.00 22.2±0.22ms ? ?/sec 1.01 22.4±0.34ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q13 1.00 27.3±0.37ms ? ?/sec 1.00 27.4±0.47ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q14 1.00 24.7±0.27ms ? ?/sec 1.01 24.9±0.38ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q19 1.00 5.1±0.15ms ? ?/sec 1.00 5.1±0.10ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q20 1.00 108.5±0.51ms ? ?/sec 1.02 111.1±0.57ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q21 1.00 123.9±0.79ms ? ?/sec 1.02 126.5±0.91ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q22 1.00 228.2±1.55ms ? ?/sec 1.02 232.8±1.97ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q23 1.00 350.9±1.85ms ? ?/sec 1.01 355.3±1.62ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q24 1.00 29.7±0.33ms ? ?/sec 1.03 30.4±0.35ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q27 1.00 93.5±0.57ms ? ?/sec 1.03 96.1±0.66ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q28 1.00 92.2±0.62ms ? ?/sec 1.01 93.5±0.72ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q30 1.01 26.7±0.31ms ? ?/sec 1.00 26.5±0.41ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q36 1.00 111.1±0.66ms ? ?/sec 1.02 113.5±0.67ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q37 1.00 88.1±0.40ms ? ?/sec 1.02 89.9±0.64ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q38 1.00 31.7±0.27ms ? ?/sec 1.02 32.5±0.32ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q39 1.00 40.3±0.35ms ? ?/sec 1.04 41.8±0.82ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q40 1.02 38.5±0.35ms ? ?/sec 1.00 37.8±0.34ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q41 1.02 28.0±0.45ms ? ?/sec 1.00 27.5±0.25ms ? ?/sec
arrow_reader_clickbench/async_object_store/Q42 1.02 10.4±0.23ms ? ?/sec 1.00 10.2±0.08ms ? ?/sec
arrow_reader_clickbench/sync/Q1 1.02 2.0±0.05ms ? ?/sec 1.00 1961.1±15.71µs ? ?/sec
arrow_reader_clickbench/sync/Q10 1.00 7.6±0.11ms ? ?/sec 1.03 7.8±0.23ms ? ?/sec
arrow_reader_clickbench/sync/Q11 1.00 9.1±0.12ms ? ?/sec 1.01 9.2±0.23ms ? ?/sec
arrow_reader_clickbench/sync/Q12 1.01 29.4±1.32ms ? ?/sec 1.00 29.1±0.59ms ? ?/sec
arrow_reader_clickbench/sync/Q13 1.00 34.2±0.37ms ? ?/sec 1.29 44.2±0.92ms ? ?/sec
arrow_reader_clickbench/sync/Q14 1.00 39.1±0.89ms ? ?/sec 1.03 40.3±0.30ms ? ?/sec
arrow_reader_clickbench/sync/Q19 1.02 4.2±0.04ms ? ?/sec 1.00 4.1±0.03ms ? ?/sec
arrow_reader_clickbench/sync/Q20 1.00 176.2±1.16ms ? ?/sec 1.01 178.7±1.06ms ? ?/sec
arrow_reader_clickbench/sync/Q21 1.00 227.3±5.09ms ? ?/sec 1.03 234.0±1.54ms ? ?/sec
arrow_reader_clickbench/sync/Q22 1.00 472.2±3.33ms ? ?/sec 1.02 481.4±2.91ms ? ?/sec
arrow_reader_clickbench/sync/Q23 1.03 441.5±16.99ms ? ?/sec 1.00 428.7±11.88ms ? ?/sec
arrow_reader_clickbench/sync/Q24 1.00 39.8±0.50ms ? ?/sec 1.00 40.0±0.43ms ? ?/sec
arrow_reader_clickbench/sync/Q27 1.00 150.2±0.97ms ? ?/sec 1.03 154.9±1.13ms ? ?/sec
arrow_reader_clickbench/sync/Q28 1.00 145.1±0.85ms ? ?/sec 1.02 148.1±1.01ms ? ?/sec
arrow_reader_clickbench/sync/Q30 1.00 28.2±0.36ms ? ?/sec 1.00 28.2±0.48ms ? ?/sec
arrow_reader_clickbench/sync/Q36 1.00 149.7±0.99ms ? ?/sec 1.03 153.7±1.41ms ? ?/sec
arrow_reader_clickbench/sync/Q37 1.00 83.9±0.49ms ? ?/sec 1.02 85.5±0.90ms ? ?/sec
arrow_reader_clickbench/sync/Q38 1.00 28.0±0.16ms ? ?/sec 1.01 28.4±0.17ms ? ?/sec
arrow_reader_clickbench/sync/Q39 1.00 33.2±0.49ms ? ?/sec 1.02 34.0±0.53ms ? ?/sec
arrow_reader_clickbench/sync/Q40 1.02 26.1±0.31ms ? ?/sec 1.00 25.7±0.33ms ? ?/sec
arrow_reader_clickbench/sync/Q41 1.00 27.5±0.28ms ? ?/sec 1.01 27.6±0.71ms ? ?/sec
arrow_reader_clickbench/sync/Q42 1.00 11.7±0.07ms ? ?/sec 1.00 11.7±0.12ms ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810563124
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 209.8±4.75ns ? ?/sec 1.32 276.3±6.97ns ? ?/sec
and_sliced_1 1.94 1100.6±18.58ns ? ?/sec 1.00 567.6±34.02ns ? ?/sec
and_sliced_24 1.00 252.3±22.32ns ? ?/sec 1.14 288.7±0.77ns ? ?/sec
not 1.03 146.3±3.48ns ? ?/sec 1.00 142.5±4.17ns ? ?/sec
not_slice_24 1.00 194.2±0.66ns ? ?/sec 1.21 234.5±8.43ns ? ?/sec
not_sliced_1 1.31 620.5±8.65ns ? ?/sec 1.00 473.8±2.23ns ? ?/sec
or 1.00 199.4±4.63ns ? ?/sec 1.28 254.8±0.78ns ? ?/sec
or_sliced_1 1.96 1101.1±26.11ns ? ?/sec 1.00 562.5±4.17ns ? ?/sec
or_sliced_24 1.00 248.6±2.66ns ? ?/sec 1.17 290.1±9.22ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3810540977
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (e2e31ccf608755a1f20e814ec1f3d10df76ec63b) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..e2e31ccf608755a1f20e814ec1f3d10df76ec63b)
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3811686755
run benchmark filter_kernels boolean_kernels arrow_reader arrow_reader_clickbench
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808367599
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, mandatory, no NULLs 1.00 1230.6±17.46µs ? ?/sec 1.04 1278.1±15.28µs ? ?/sec
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, optional, half NULLs 1.00 1271.7±23.06µs ? ?/sec 1.02 1293.6±17.22µs ? ?/sec
arrow_array_reader/BYTE_ARRAY/Decimal128Array/plain encoded, optional, no NULLs 1.00 1235.7±13.40µs ? ?/sec 1.04 1279.3±4.27µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, mandatory, no NULLs 1.00 499.5±16.75µs ? ?/sec 1.11 555.8±4.91µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, optional, half NULLs 1.00 665.8±11.43µs ? ?/sec 1.03 688.9±4.83µs ? ?/sec
arrow_array_reader/BinaryArray/dictionary encoded, optional, no NULLs 1.00 514.1±5.45µs ? ?/sec 1.10 567.1±5.84µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, mandatory, no NULLs 1.00 562.6±4.17µs ? ?/sec 1.02 574.3±16.05µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, optional, half NULLs 1.00 717.9±8.51µs ? ?/sec 1.01 725.1±10.37µs ? ?/sec
arrow_array_reader/BinaryArray/plain encoded, optional, no NULLs 1.00 572.3±9.64µs ? ?/sec 1.02 585.5±7.92µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, mandatory, no NULLs 1.00 162.5±2.13µs ? ?/sec 1.00 162.4±2.91µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, optional, half NULLs 1.00 218.7±6.35µs ? ?/sec 1.05 228.7±3.76µs ? ?/sec
arrow_array_reader/BinaryViewArray/dictionary encoded, optional, no NULLs 1.03 158.5±1.62µs ? ?/sec 1.00 154.0±3.24µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, mandatory, no NULLs 1.09 224.5±4.71µs ? ?/sec 1.00 206.3±8.26µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, mandatory, no NULLs, short string 1.00 194.3±3.16µs ? ?/sec 1.09 211.8±2.64µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, optional, half NULLs 1.00 261.8±5.25µs ? ?/sec 1.01 264.7±5.49µs ? ?/sec
arrow_array_reader/BinaryViewArray/plain encoded, optional, no NULLs 1.06 230.1±2.94µs ? ?/sec 1.00 217.6±5.59µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.00 1026.3±8.45µs ? ?/sec 1.09 1115.0±18.62µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.00 921.3±5.12µs ? ?/sec 1.06 978.5±9.59µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.00 1035.6±6.20µs ? ?/sec 1.09 1126.1±23.96µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, mandatory, no NULLs 1.00 398.4±3.86µs ? ?/sec 1.10 437.0±3.40µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, optional, half NULLs 1.00 616.5±10.65µs ? ?/sec 1.03 637.0±15.58µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Decimal128Array/plain encoded, optional, no NULLs 1.00 407.0±11.42µs ? ?/sec 1.10 449.3±5.44µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, mandatory, no NULLs 1.22 194.7±1.84µs ? ?/sec 1.00 160.0±0.71µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, optional, half NULLs 1.13 338.3±6.82µs ? ?/sec 1.00 299.7±1.29µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/byte_stream_split encoded, optional, no NULLs 1.20 199.2±0.57µs ? ?/sec 1.00 165.7±1.86µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, mandatory, no NULLs 1.55 118.6±1.02µs ? ?/sec 1.00 76.5±0.93µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, optional, half NULLs 1.17 300.0±2.51µs ? ?/sec 1.00 256.7±2.63µs ? ?/sec
arrow_array_reader/FIXED_LEN_BYTE_ARRAY/Float16Array/plain encoded, optional, no NULLs 1.53 123.9±1.80µs ? ?/sec 1.00 80.8±0.63µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, mandatory, no NULLs 1.00 688.0±3.77µs ? ?/sec 1.07 735.9±4.95µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, optional, half NULLs 1.00 586.9±21.25µs ? ?/sec 1.00 589.8±8.33µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/byte_stream_split encoded, optional, no NULLs 1.00 693.8±4.17µs ? ?/sec 1.07 744.5±4.45µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, mandatory, no NULLs 1.00 61.8±5.98µs ? ?/sec 1.08 66.9±7.19µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, optional, half NULLs 1.06 270.6±3.56µs ? ?/sec 1.00 255.7±5.12µs ? ?/sec
arrow_array_reader/FixedLenByteArray(16)/plain encoded, optional, no NULLs 1.00 69.0±7.90µs ? ?/sec 1.04 71.8±5.75µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, mandatory, no NULLs 1.00 85.9±0.64µs ? ?/sec 1.09 94.0±0.38µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, optional, half NULLs 1.00 228.5±1.12µs ? ?/sec 1.02 233.2±4.02µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/byte_stream_split encoded, optional, no NULLs 1.00 90.4±0.44µs ? ?/sec 1.10 99.2±0.54µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, mandatory, no NULLs 1.00 9.1±0.25µs ? ?/sec 1.01 9.2±0.29µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, optional, half NULLs 1.00 189.0±2.40µs ? ?/sec 1.00 189.4±2.21µs ? ?/sec
arrow_array_reader/FixedLenByteArray(2)/plain encoded, optional, no NULLs 1.00 13.7±0.36µs ? ?/sec 1.05 14.3±0.17µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, mandatory, no NULLs 1.00 170.7±3.61µs ? ?/sec 1.08 184.9±3.39µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, optional, half NULLs 1.05 369.7±3.60µs ? ?/sec 1.00 351.8±2.83µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/byte_stream_split encoded, optional, no NULLs 1.00 175.5±1.01µs ? ?/sec 1.08 189.7±4.51µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, mandatory, no NULLs 1.00 13.6±0.37µs ? ?/sec 1.03 14.1±0.33µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, optional, half NULLs 1.09 293.4±4.39µs ? ?/sec 1.00 268.5±3.12µs ? ?/sec
arrow_array_reader/FixedLenByteArray(4)/plain encoded, optional, no NULLs 1.00 19.9±0.79µs ? ?/sec 1.00 19.9±0.55µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, mandatory, no NULLs 1.00 341.4±5.17µs ? ?/sec 1.07 366.7±4.83µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, optional, half NULLs 1.02 401.3±19.84µs ? ?/sec 1.00 394.8±2.27µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/byte_stream_split encoded, optional, no NULLs 1.00 347.3±3.32µs ? ?/sec 1.07 371.7±2.95µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, mandatory, no NULLs 1.00 26.2±0.30µs ? ?/sec 1.01 26.5±0.59µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, optional, half NULLs 1.07 242.4±6.43µs ? ?/sec 1.00 225.9±3.55µs ? ?/sec
arrow_array_reader/FixedLenByteArray(8)/plain encoded, optional, no NULLs 1.00 32.0±0.31µs ? ?/sec 1.02 32.5±0.71µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, mandatory, no NULLs 1.01 108.8±0.47µs ? ?/sec 1.00 108.1±0.61µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, optional, half NULLs 1.00 130.3±0.93µs ? ?/sec 1.03 134.0±1.93µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed skip, optional, no NULLs 1.00 111.7±0.55µs ? ?/sec 1.00 111.8±2.26µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, mandatory, no NULLs 1.01 159.0±2.66µs ? ?/sec 1.00 157.7±1.64µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, optional, half NULLs 1.00 222.0±4.75µs ? ?/sec 1.04 229.9±1.34µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/binary packed, optional, no NULLs 1.01 164.1±0.76µs ? ?/sec 1.00 162.6±0.92µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.00 75.9±1.38µs ? ?/sec 1.02 77.6±0.81µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.00 178.7±2.47µs ? ?/sec 1.05 188.4±1.42µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.00 81.0±1.81µs ? ?/sec 1.00 81.1±0.42µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, mandatory, no NULLs 1.07 144.6±2.30µs ? ?/sec 1.00 134.5±2.01µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, optional, half NULLs 1.00 216.6±1.95µs ? ?/sec 1.02 220.9±6.44µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/dictionary encoded, optional, no NULLs 1.06 149.0±1.12µs ? ?/sec 1.00 139.9±0.58µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, mandatory, no NULLs 1.00 71.8±0.54µs ? ?/sec 1.02 73.4±0.88µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, optional, half NULLs 1.00 175.7±6.88µs ? ?/sec 1.06 186.6±5.93µs ? ?/sec
arrow_array_reader/INT32/Decimal128Array/plain encoded, optional, no NULLs 1.00 75.5±0.80µs ? ?/sec 1.03 78.0±1.12µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, mandatory, no NULLs 1.00 106.9±1.45µs ? ?/sec 1.02 108.7±1.19µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, optional, half NULLs 1.00 121.2±1.59µs ? ?/sec 1.15 139.3±3.96µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed skip, optional, no NULLs 1.00 111.0±0.46µs ? ?/sec 1.01 112.3±1.76µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, mandatory, no NULLs 1.00 162.7±0.53µs ? ?/sec 1.00 162.6±2.79µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, optional, half NULLs 1.00 208.8±8.34µs ? ?/sec 1.16 242.4±5.92µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/binary packed, optional, no NULLs 1.00 167.1±1.30µs ? ?/sec 1.00 167.5±1.43µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, mandatory, no NULLs 1.01 202.5±2.28µs ? ?/sec 1.00 201.0±2.14µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, optional, half NULLs 1.00 225.0±2.98µs ? ?/sec 1.15 258.0±3.56µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/byte_stream_split encoded, optional, no NULLs 1.00 207.8±1.63µs ? ?/sec 1.00 207.1±1.12µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, mandatory, no NULLs 1.00 141.2±1.26µs ? ?/sec 1.09 153.6±3.21µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, optional, half NULLs 1.00 198.9±5.49µs ? ?/sec 1.16 230.7±2.61µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/dictionary encoded, optional, no NULLs 1.00 147.3±1.42µs ? ?/sec 1.06 155.6±3.09µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, mandatory, no NULLs 1.00 107.1±1.66µs ? ?/sec 1.00 107.0±1.37µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, optional, half NULLs 1.00 174.8±2.00µs ? ?/sec 1.19 208.6±1.34µs ? ?/sec
arrow_array_reader/INT64/Decimal128Array/plain encoded, optional, no NULLs 1.01 117.0±2.28µs ? ?/sec 1.00 116.1±1.81µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, mandatory, no NULLs 1.00 77.0±3.33µs ? ?/sec 1.00 76.8±0.47µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, optional, half NULLs 1.00 103.3±1.64µs ? ?/sec 1.04 107.3±0.86µs ? ?/sec
arrow_array_reader/Int16Array/binary packed skip, optional, no NULLs 1.00 79.4±1.40µs ? ?/sec 1.00 79.1±0.74µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, mandatory, no NULLs 1.00 106.3±0.75µs ? ?/sec 1.00 105.8±0.53µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, optional, half NULLs 1.00 174.4±0.60µs ? ?/sec 1.05 182.7±1.32µs ? ?/sec
arrow_array_reader/Int16Array/binary packed, optional, no NULLs 1.01 110.8±0.49µs ? ?/sec 1.00 110.1±0.73µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, mandatory, no NULLs 1.00 40.8±0.44µs ? ?/sec 1.05 42.9±0.17µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, optional, half NULLs 1.00 143.8±1.86µs ? ?/sec 1.05 150.4±1.25µs ? ?/sec
arrow_array_reader/Int16Array/byte_stream_split encoded, optional, no NULLs 1.00 45.4±0.23µs ? ?/sec 1.04 47.3±1.29µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, mandatory, no NULLs 1.09 109.8±0.48µs ? ?/sec 1.00 101.0±0.64µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, optional, half NULLs 1.00 180.4±2.71µs ? ?/sec 1.02 183.4±0.86µs ? ?/sec
arrow_array_reader/Int16Array/dictionary encoded, optional, no NULLs 1.09 115.1±4.00µs ? ?/sec 1.00 105.6±0.52µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, mandatory, no NULLs 1.00 36.9±0.28µs ? ?/sec 1.02 37.5±0.49µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, optional, half NULLs 1.00 140.3±1.80µs ? ?/sec 1.05 147.4±2.56µs ? ?/sec
arrow_array_reader/Int16Array/plain encoded, optional, no NULLs 1.01 41.4±0.55µs ? ?/sec 1.00 41.1±0.22µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, mandatory, no NULLs 1.00 82.3±0.79µs ? ?/sec 1.00 82.2±0.95µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, optional, half NULLs 1.00 101.1±0.63µs ? ?/sec 1.05 106.2±1.41µs ? ?/sec
arrow_array_reader/Int32Array/binary packed skip, optional, no NULLs 1.00 84.7±1.31µs ? ?/sec 1.00 84.5±0.34µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, mandatory, no NULLs 1.00 106.4±0.43µs ? ?/sec 1.00 106.0±3.09µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, optional, half NULLs 1.00 166.1±2.35µs ? ?/sec 1.05 174.5±1.14µs ? ?/sec
arrow_array_reader/Int32Array/binary packed, optional, no NULLs 1.01 111.4±2.91µs ? ?/sec 1.00 109.9±1.47µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, mandatory, no NULLs 1.00 23.1±0.32µs ? ?/sec 1.00 23.2±0.25µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, optional, half NULLs 1.00 122.6±1.13µs ? ?/sec 1.06 130.2±0.97µs ? ?/sec
arrow_array_reader/Int32Array/byte_stream_split encoded, optional, no NULLs 1.00 27.6±0.31µs ? ?/sec 1.00 27.7±0.41µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, mandatory, no NULLs 1.11 91.5±1.84µs ? ?/sec 1.00 82.7±1.23µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, optional, half NULLs 1.00 161.6±3.75µs ? ?/sec 1.01 164.0±0.67µs ? ?/sec
arrow_array_reader/Int32Array/dictionary encoded, optional, no NULLs 1.09 94.6±0.87µs ? ?/sec 1.00 87.1±0.72µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, mandatory, no NULLs 1.01 15.4±0.67µs ? ?/sec 1.00 15.4±0.55µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, optional, half NULLs 1.00 121.3±1.68µs ? ?/sec 1.05 127.8±2.50µs ? ?/sec
arrow_array_reader/Int32Array/plain encoded, optional, no NULLs 1.03 21.6±0.61µs ? ?/sec 1.00 21.0±0.40µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, mandatory, no NULLs 1.00 79.4±0.46µs ? ?/sec 1.00 79.7±0.71µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, optional, half NULLs 1.00 89.9±1.34µs ? ?/sec 1.18 106.5±2.02µs ? ?/sec
arrow_array_reader/Int64Array/binary packed skip, optional, no NULLs 1.01 82.5±0.49µs ? ?/sec 1.00 82.0±0.63µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, mandatory, no NULLs 1.01 107.0±1.16µs ? ?/sec 1.00 105.9±0.59µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, optional, half NULLs 1.00 143.1±1.95µs ? ?/sec 1.27 181.7±10.16µs ? ?/sec
arrow_array_reader/Int64Array/binary packed, optional, no NULLs 1.02 111.5±3.08µs ? ?/sec 1.00 109.7±2.90µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, mandatory, no NULLs 1.00 146.3±0.55µs ? ?/sec 1.00 146.0±0.76µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, optional, half NULLs 1.00 167.1±0.82µs ? ?/sec 1.21 201.9±6.35µs ? ?/sec
arrow_array_reader/Int64Array/byte_stream_split encoded, optional, no NULLs 1.00 151.1±1.38µs ? ?/sec 1.00 150.9±0.53µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, mandatory, no NULLs 1.00 88.0±3.19µs ? ?/sec 1.10 96.6±0.78µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, optional, half NULLs 1.00 134.3±0.86µs ? ?/sec 1.28 171.3±1.05µs ? ?/sec
arrow_array_reader/Int64Array/dictionary encoded, optional, no NULLs 1.00 92.3±0.71µs ? ?/sec 1.09 100.4±1.19µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, mandatory, no NULLs 1.00 38.7±0.96µs ? ?/sec 1.04 40.4±2.85µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, optional, half NULLs 1.00 111.9±1.81µs ? ?/sec 1.29 144.6±3.85µs ? ?/sec
arrow_array_reader/Int64Array/plain encoded, optional, no NULLs 1.00 45.3±0.79µs ? ?/sec 1.07 48.4±3.29µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, mandatory, no NULLs 1.00 81.1±0.70µs ? ?/sec 1.00 80.8±1.38µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, optional, half NULLs 1.00 103.4±0.70µs ? ?/sec 1.04 108.0±0.88µs ? ?/sec
arrow_array_reader/Int8Array/binary packed skip, optional, no NULLs 1.00 83.5±1.22µs ? ?/sec 1.00 83.4±0.91µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, mandatory, no NULLs 1.01 108.7±1.13µs ? ?/sec 1.00 107.5±0.48µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, optional, half NULLs 1.00 172.6±1.43µs ? ?/sec 1.05 180.4±1.16µs ? ?/sec
arrow_array_reader/Int8Array/binary packed, optional, no NULLs 1.01 113.4±1.54µs ? ?/sec 1.00 111.9±0.39µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, mandatory, no NULLs 1.00 34.5±0.14µs ? ?/sec 1.01 35.0±0.92µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, optional, half NULLs 1.00 134.7±2.68µs ? ?/sec 1.05 141.9±3.65µs ? ?/sec
arrow_array_reader/Int8Array/byte_stream_split encoded, optional, no NULLs 1.00 39.0±0.48µs ? ?/sec 1.00 39.0±0.56µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, mandatory, no NULLs 1.09 101.7±1.24µs ? ?/sec 1.00 93.5±1.40µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, optional, half NULLs 1.00 173.7±6.07µs ? ?/sec 1.02 176.3±6.43µs ? ?/sec
arrow_array_reader/Int8Array/dictionary encoded, optional, no NULLs 1.09 107.2±2.03µs ? ?/sec 1.00 98.3±3.20µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, mandatory, no NULLs 1.00 28.7±0.11µs ? ?/sec 1.01 28.9±0.37µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, optional, half NULLs 1.00 132.7±1.29µs ? ?/sec 1.05 139.1±2.54µs ? ?/sec
arrow_array_reader/Int8Array/plain encoded, optional, no NULLs 1.00 33.3±0.16µs ? ?/sec 1.01 33.5±0.31µs ? ?/sec
arrow_array_reader/ListArray/plain encoded optional strings half NULLs 1.00 6.0±0.13ms ? ?/sec 1.00 6.0±0.07ms ? ?/sec
arrow_array_reader/ListArray/plain encoded optional strings no NULLs 1.00 11.9±0.16ms ? ?/sec 1.02 12.2±0.42ms ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, mandatory, no NULLs 1.00 502.7±9.65µs ? ?/sec 1.13 568.0±14.89µs ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, optional, half NULLs 1.00 653.6±2.42µs ? ?/sec 1.09 709.6±83.95µs ? ?/sec
arrow_array_reader/StringArray/dictionary encoded, optional, no NULLs 1.00 503.0±18.75µs ? ?/sec 1.15 579.1±39.16µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, mandatory, no NULLs 1.00 688.4±3.99µs ? ?/sec 1.07 735.4±34.54µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, optional, half NULLs 1.00 791.4±9.95µs ? ?/sec 1.00 792.1±12.56µs ? ?/sec
arrow_array_reader/StringArray/plain encoded, optional, no NULLs 1.00 700.0±7.73µs ? ?/sec 1.06 741.7±22.24µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, mandatory, no NULLs 1.04 335.2±6.63µs ? ?/sec 1.00 321.7±9.40µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, optional, half NULLs 1.00 379.7±8.86µs ? ?/sec 1.13 428.1±60.95µs ? ?/sec
arrow_array_reader/StringDictionary/dictionary encoded, optional, no NULLs 1.05 341.3±9.40µs ? ?/sec 1.00 326.0±2.13µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, mandatory, no NULLs 1.02 153.3±2.41µs ? ?/sec 1.00 149.6±2.41µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, optional, half NULLs 1.00 200.7±3.33µs ? ?/sec 1.06 212.6±5.98µs ? ?/sec
arrow_array_reader/StringViewArray/dictionary encoded, optional, no NULLs 1.00 137.6±2.10µs ? ?/sec 1.03 142.3±2.42µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, mandatory, no NULLs 1.00 364.7±15.49µs ? ?/sec 1.08 393.0±2.82µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, optional, half NULLs 1.00 324.8±4.73µs ? ?/sec 1.08 349.7±2.64µs ? ?/sec
arrow_array_reader/StringViewArray/plain encoded, optional, no NULLs 1.00 372.9±5.71µs ? ?/sec 1.08 401.1±5.50µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, mandatory, no NULLs 1.00 92.1±1.11µs ? ?/sec 1.00 92.5±0.77µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, optional, half NULLs 1.00 111.8±0.98µs ? ?/sec 1.04 116.0±0.59µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed skip, optional, no NULLs 1.00 95.2±0.67µs ? ?/sec 1.00 94.9±0.33µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, mandatory, no NULLs 1.00 126.8±4.54µs ? ?/sec 1.00 126.3±1.63µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, optional, half NULLs 1.00 186.2±0.74µs ? ?/sec 1.04 194.4±2.44µs ? ?/sec
arrow_array_reader/UInt16Array/binary packed, optional, no NULLs 1.01 130.7±0.84µs ? ?/sec 1.00 130.0±0.72µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, mandatory, no NULLs 1.00 40.8±0.21µs ? ?/sec 1.04 42.6±0.25µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, optional, half NULLs 1.00 142.0±3.46µs ? ?/sec 1.05 149.7±4.00µs ? ?/sec
arrow_array_reader/UInt16Array/byte_stream_split encoded, optional, no NULLs 1.00 45.3±0.34µs ? ?/sec 1.03 46.6±0.28µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, mandatory, no NULLs 1.08 109.4±0.53µs ? ?/sec 1.00 101.3±0.50µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, optional, half NULLs 1.00 179.9±2.45µs ? ?/sec 1.02 183.3±2.79µs ? ?/sec
arrow_array_reader/UInt16Array/dictionary encoded, optional, no NULLs 1.09 114.4±1.09µs ? ?/sec 1.00 105.3±0.79µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, mandatory, no NULLs 1.00 36.8±0.20µs ? ?/sec 1.00 36.7±0.13µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, optional, half NULLs 1.00 140.4±0.84µs ? ?/sec 1.05 147.0±2.24µs ? ?/sec
arrow_array_reader/UInt16Array/plain encoded, optional, no NULLs 1.00 41.2±0.29µs ? ?/sec 1.00 41.1±0.18µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, mandatory, no NULLs 1.00 82.1±0.56µs ? ?/sec 1.00 81.9±0.54µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, optional, half NULLs 1.00 101.9±0.83µs ? ?/sec 1.04 106.3±0.81µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed skip, optional, no NULLs 1.00 84.8±0.94µs ? ?/sec 1.00 84.8±1.14µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, mandatory, no NULLs 1.00 106.7±1.34µs ? ?/sec 1.00 106.9±5.81µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, optional, half NULLs 1.00 167.6±1.12µs ? ?/sec 1.04 174.4±0.79µs ? ?/sec
arrow_array_reader/UInt32Array/binary packed, optional, no NULLs 1.01 111.2±1.62µs ? ?/sec 1.00 110.5±2.35µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, mandatory, no NULLs 1.00 21.9±0.42µs ? ?/sec 1.02 22.3±0.40µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, optional, half NULLs 1.00 123.9±5.81µs ? ?/sec 1.06 131.7±3.97µs ? ?/sec
arrow_array_reader/UInt32Array/byte_stream_split encoded, optional, no NULLs 1.00 26.2±0.51µs ? ?/sec 1.02 26.6±0.35µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, mandatory, no NULLs 1.11 91.5±0.47µs ? ?/sec 1.00 82.4±1.09µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, optional, half NULLs 1.00 162.3±2.09µs ? ?/sec 1.01 164.4±1.25µs ? ?/sec
arrow_array_reader/UInt32Array/dictionary encoded, optional, no NULLs 1.11 96.4±2.07µs ? ?/sec 1.00 87.0±0.89µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, mandatory, no NULLs 1.03 19.3±1.13µs ? ?/sec 1.00 18.7±0.73µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, optional, half NULLs 1.00 122.5±4.56µs ? ?/sec 1.04 127.9±1.23µs ? ?/sec
arrow_array_reader/UInt32Array/plain encoded, optional, no NULLs 1.05 23.9±1.32µs ? ?/sec 1.00 22.7±0.56µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, mandatory, no NULLs 1.00 79.8±0.32µs ? ?/sec 1.01 80.4±1.03µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, optional, half NULLs 1.00 90.3±0.75µs ? ?/sec 1.18 106.7±0.66µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed skip, optional, no NULLs 1.00 82.5±1.44µs ? ?/sec 1.00 82.6±0.67µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, mandatory, no NULLs 1.00 107.3±0.99µs ? ?/sec 1.00 107.3±0.70µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, optional, half NULLs 1.00 149.0±1.45µs ? ?/sec 1.18 175.8±1.20µs ? ?/sec
arrow_array_reader/UInt64Array/binary packed, optional, no NULLs 1.01 111.6±1.87µs ? ?/sec 1.00 110.5±0.63µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, mandatory, no NULLs 1.00 146.2±0.76µs ? ?/sec 1.00 146.0±0.56µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, optional, half NULLs 1.00 168.7±1.66µs ? ?/sec 1.19 201.1±3.74µs ? ?/sec
arrow_array_reader/UInt64Array/byte_stream_split encoded, optional, no NULLs 1.01 152.2±2.70µs ? ?/sec 1.00 150.6±0.95µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, mandatory, no NULLs 1.00 87.0±1.77µs ? ?/sec 1.11 96.9±0.91µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, optional, half NULLs 1.00 134.6±1.40µs ? ?/sec 1.28 172.0±2.28µs ? ?/sec
arrow_array_reader/UInt64Array/dictionary encoded, optional, no NULLs 1.00 92.4±3.10µs ? ?/sec 1.10 101.3±0.73µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, mandatory, no NULLs 1.00 38.8±0.92µs ? ?/sec 1.08 41.7±3.24µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, optional, half NULLs 1.00 112.3±1.67µs ? ?/sec 1.28 143.3±0.71µs ? ?/sec
arrow_array_reader/UInt64Array/plain encoded, optional, no NULLs 1.00 46.5±0.89µs ? ?/sec 1.09 50.8±3.42µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, mandatory, no NULLs 1.00 87.9±2.14µs ? ?/sec 1.00 87.4±0.27µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, optional, half NULLs 1.00 107.0±4.69µs ? ?/sec 1.04 111.1±0.44µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed skip, optional, no NULLs 1.00 90.1±1.03µs ? ?/sec 1.00 90.1±0.41µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, mandatory, no NULLs 1.01 117.6±1.57µs ? ?/sec 1.00 117.0±1.13µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, optional, half NULLs 1.00 176.9±2.52µs ? ?/sec 1.05 185.2±2.84µs ? ?/sec
arrow_array_reader/UInt8Array/binary packed, optional, no NULLs 1.00 121.8±2.05µs ? ?/sec 1.00 121.6±1.50µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, mandatory, no NULLs 1.00 34.5±0.16µs ? ?/sec 1.01 34.7±0.13µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, optional, half NULLs 1.00 133.5±0.63µs ? ?/sec 1.06 141.8±1.51µs ? ?/sec
arrow_array_reader/UInt8Array/byte_stream_split encoded, optional, no NULLs 1.00 38.9±0.60µs ? ?/sec 1.00 39.0±2.01µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, mandatory, no NULLs 1.09 101.9±1.61µs ? ?/sec 1.00 93.4±0.74µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, optional, half NULLs 1.00 172.1±1.02µs ? ?/sec 1.02 176.2±1.77µs ? ?/sec
arrow_array_reader/UInt8Array/dictionary encoded, optional, no NULLs 1.09 106.9±1.16µs ? ?/sec 1.00 97.8±0.76µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, mandatory, no NULLs 1.00 28.8±0.25µs ? ?/sec 1.00 28.7±0.09µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, optional, half NULLs 1.00 133.4±2.31µs ? ?/sec 1.04 138.8±0.79µs ? ?/sec
arrow_array_reader/UInt8Array/plain encoded, optional, no NULLs 1.00 33.4±0.13µs ? ?/sec 1.00 33.4±0.20µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, mandatory struct, optional data, half NULLs 1.00 123.7±3.29µs ? ?/sec 1.04 128.6±1.74µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, mandatory struct, optional data, no NULLs 1.02 23.5±1.02µs ? ?/sec 1.00 23.1±0.64µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, optional struct, optional data, half NULLs 1.00 242.1±1.11µs ? ?/sec 1.06 256.2±3.23µs ? ?/sec
arrow_array_reader/struct/Int32Array/plain encoded, optional struct, optional data, no NULLs 1.00 120.0±3.00µs ? ?/sec 1.02 122.8±2.14µs ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808819136
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
and 1.00 208.1±2.44ns ? ?/sec 1.00 208.9±0.97ns ? ?/sec
and_sliced_1 1.00 1097.6±9.44ns ? ?/sec 1.25 1373.7±15.78ns ? ?/sec
and_sliced_24 1.00 247.4±6.83ns ? ?/sec 1.29 320.2±5.97ns ? ?/sec
not 1.00 145.2±2.91ns ? ?/sec 1.35 195.5±0.98ns ? ?/sec
not_slice_24 1.00 193.2±3.45ns ? ?/sec 1.29 248.5±1.36ns ? ?/sec
not_sliced_1 2.49 619.8±12.16ns ? ?/sec 1.00 248.6±3.73ns ? ?/sec
or 1.01 197.2±1.35ns ? ?/sec 1.00 196.1±0.69ns ? ?/sec
or_sliced_1 1.00 1095.3±5.53ns ? ?/sec 1.19 1305.7±15.79ns ? ?/sec
or_sliced_24 1.00 247.9±1.86ns ? ?/sec 1.55 384.5±1.52ns ? ?/sec
```
</p>
</details>
--
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] Optimize `UnalignedBitChunk` [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3808819251
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (af1cdf235bbf4e94e4b8eae21d18bd9fab1c21ae) to bd76edd0f947330bde5b458b32f513f74bdbb1a6 [diff](https://github.com/apache/arrow-rs/compare/bd76edd0f947330bde5b458b32f513f74bdbb1a6..af1cdf235bbf4e94e4b8eae21d18bd9fab1c21ae)
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "Dandandan (via GitHub)" <gi...@apache.org>.
Dandandan commented on code in PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#discussion_r2737766556
##########
arrow-buffer/src/util/bit_chunk_iterator.rs:
##########
@@ -158,23 +158,190 @@ impl<'a> UnalignedBitChunk<'a> {
/// Returns an iterator over the chunks
pub fn iter(&self) -> UnalignedBitChunkIterator<'a> {
- self.prefix
- .into_iter()
- .chain(self.chunks.iter().cloned())
- .chain(self.suffix)
+ UnalignedBitChunkIterator {
+ prefix: self.prefix,
+ chunks: self.chunks,
+ suffix: self.suffix,
+ }
+ }
+
+ /// Returns a zipped iterator over two [`UnalignedBitChunk`]
+ #[inline]
+ pub fn zip(&self, other: &UnalignedBitChunk<'a>) -> UnalignedBitChunkZipIterator<'a> {
+ UnalignedBitChunkZipIterator {
+ left: self.iter(),
+ right: other.iter(),
+ }
}
/// Counts the number of ones
pub fn count_ones(&self) -> usize {
- self.iter().map(|x| x.count_ones() as usize).sum()
+ let prefix_count = self.prefix.map(|x| x.count_ones() as usize).unwrap_or(0);
+ let chunks_count: usize = self.chunks.iter().map(|&x| x.count_ones() as usize).sum();
+ let suffix_count = self.suffix.map(|x| x.count_ones() as usize).unwrap_or(0);
+ prefix_count + chunks_count + suffix_count
+ }
+}
+
+/// An iterator over the chunks of an [`UnalignedBitChunk`]
+#[derive(Debug, Clone)]
+pub struct UnalignedBitChunkIterator<'a> {
+ prefix: Option<u64>,
+ chunks: &'a [u64],
+ suffix: Option<u64>,
+}
+
+impl<'a> Iterator for UnalignedBitChunkIterator<'a> {
+ type Item = u64;
+
+ #[inline]
+ fn next(&mut self) -> Option<Self::Item> {
+ if let Some(prefix) = self.prefix.take() {
+ return Some(prefix);
+ }
+ if let Some((&first, rest)) = self.chunks.split_first() {
+ self.chunks = rest;
+ return Some(first);
+ }
+ self.suffix.take()
+ }
+
+ #[inline]
+ fn size_hint(&self) -> (usize, Option<usize>) {
+ let len = self.len();
+ (len, Some(len))
+ }
+
+ #[inline]
+ fn fold<B, F>(mut self, init: B, mut f: F) -> B
+ where
+ F: FnMut(B, Self::Item) -> B,
+ {
+ let mut acc = init;
+ if let Some(prefix) = self.prefix.take() {
+ acc = f(acc, prefix);
+ }
+ for &chunk in self.chunks {
+ acc = f(acc, chunk);
+ }
+ self.chunks = &[];
+ if let Some(suffix) = self.suffix.take() {
+ acc = f(acc, suffix);
+ }
+ acc
+ }
+}
+
+impl<'a> UnalignedBitChunkIterator<'a> {
+ /// Returns a zipped iterator over two [`UnalignedBitChunkIterator`]
+ #[inline]
+ pub fn zip(self, other: UnalignedBitChunkIterator<'a>) -> UnalignedBitChunkZipIterator<'a> {
+ UnalignedBitChunkZipIterator {
+ left: self,
+ right: other,
+ }
+ }
+}
+
+impl ExactSizeIterator for UnalignedBitChunkIterator<'_> {
+ #[inline]
+ fn len(&self) -> usize {
+ self.prefix.is_some() as usize + self.chunks.len() + self.suffix.is_some() as usize
+ }
+}
+
+impl std::iter::FusedIterator for UnalignedBitChunkIterator<'_> {}
+
+impl<'a> DoubleEndedIterator for UnalignedBitChunkIterator<'a> {
+ #[inline]
+ fn next_back(&mut self) -> Option<Self::Item> {
+ if let Some(suffix) = self.suffix.take() {
+ return Some(suffix);
+ }
+ if let Some((&last, rest)) = self.chunks.split_last() {
+ self.chunks = rest;
+ return Some(last);
+ }
+ self.prefix.take()
+ }
+}
+
+/// An iterator over zipped [`UnalignedBitChunk`]
+#[derive(Debug)]
+pub struct UnalignedBitChunkZipIterator<'a> {
+ left: UnalignedBitChunkIterator<'a>,
+ right: UnalignedBitChunkIterator<'a>,
+}
+
+impl<'a> Iterator for UnalignedBitChunkZipIterator<'a> {
+ type Item = (u64, u64);
+
+ #[inline]
+ fn next(&mut self) -> Option<Self::Item> {
+ Some((self.left.next()?, self.right.next()?))
+ }
+
+ #[inline]
+ fn size_hint(&self) -> (usize, Option<usize>) {
+ self.left.size_hint()
+ }
+
+ #[inline]
+ fn fold<B, F>(mut self, init: B, mut f: F) -> B
Review Comment:
The idea here is to implement an improved `fold` implementation so `from_trusted_len_iter` is fast (I used AI assistance to come up with the implementation, but it seems to look jormal)
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893679812
🤖 `./gh_compare_arrow.sh` [gh_compare_arrow.sh](https://github.com/alamb/datafusion-benchmarking/blob/main/scripts/gh_compare_arrow.sh) Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing optimize_unaligned_bitchunk_iterator (d20ef3573d7205f053b9cbb79c1b63c8c7dcd570) to d6168e526aae79d6fbafe8c11062b5f834021052 [diff](https://github.com/apache/arrow-rs/compare/d6168e526aae79d6fbafe8c11062b5f834021052..d20ef3573d7205f053b9cbb79c1b63c8c7dcd570)
BENCH_NAME=arrow_reader_clickbench
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_reader_clickbench
BENCH_FILTER=
BENCH_BRANCH_NAME=optimize_unaligned_bitchunk_iterator
Results will be posted here when complete
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3894309311
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.001 1.01 259.4±2.34ms ? ?/sec 1.00 256.1±2.20ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.01 1.00 8.0±0.04ms ? ?/sec 1.00 8.0±0.10ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.1 1.00 3.8±0.05ms ? ?/sec 1.02 3.9±0.09ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.8 1.01 3.4±0.02ms ? ?/sec 1.00 3.4±0.02ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.001 1.31 314.4±2.63ms ? ?/sec 1.00 239.6±2.51ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.01 1.02 8.9±0.09ms ? ?/sec 1.00 8.7±0.32ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.1 1.05 4.4±0.12ms ? ?/sec 1.00 4.2±0.11ms ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.8 1.03 4.6±0.03ms ? ?/sec 1.00 4.5±0.04ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.001 1.01 56.2±0.50ms ? ?/sec 1.00 55.8±1.02ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.01 1.00 10.9±0.06ms ? ?/sec 1.00 10.9±0.11ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.1 1.00 9.0±0.33ms ? ?/sec 1.01 9.1±0.29ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.8 1.00 8.4±0.29ms ? ?/sec 1.24 10.4±0.24ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.001 1.01 65.6±2.14ms ? ?/sec 1.00 65.2±1.49ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.01 1.03 12.1±0.15ms ? ?/sec 1.00 11.8±0.09ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.1 1.03 9.4±0.37ms ? ?/sec 1.00 9.2±0.28ms ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.8 1.03 10.0±0.39ms ? ?/sec 1.00 9.7±0.20ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.001 1.02 44.6±0.71ms ? ?/sec 1.00 43.7±0.50ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.01 1.04 5.4±0.03ms ? ?/sec 1.00 5.2±0.03ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.1 1.00 4.0±0.06ms ? ?/sec 1.02 4.1±0.26ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.8 1.05 2.8±0.03ms ? ?/sec 1.00 2.7±0.02ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.001 1.01 54.7±0.40ms ? ?/sec 1.00 54.1±0.24ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.01 1.06 7.4±0.19ms ? ?/sec 1.00 7.0±0.04ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.1 1.05 5.1±0.26ms ? ?/sec 1.00 4.8±0.14ms ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.8 1.07 3.7±0.07ms ? ?/sec 1.00 3.5±0.01ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.001 1.02 39.9±0.28ms ? ?/sec 1.00 39.1±0.19ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.01 1.07 4.2±0.02ms ? ?/sec 1.00 3.9±0.03ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.1 1.02 2.0±0.08ms ? ?/sec 1.00 1964.8±133.06µs ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.8 1.10 1313.3±5.94µs ? ?/sec 1.00 1193.0±9.44µs ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.001 1.00 49.0±0.44ms ? ?/sec 1.00 48.8±0.26ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.01 1.06 6.4±0.03ms ? ?/sec 1.00 6.0±0.03ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.1 1.13 3.5±0.18ms ? ?/sec 1.00 3.1±0.07ms ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.8 1.06 3.7±0.02ms ? ?/sec 1.00 3.5±0.01ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.001 1.00 88.6±0.72ms ? ?/sec 1.00 88.2±0.74ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.01 1.08 8.3±0.03ms ? ?/sec 1.00 7.7±0.05ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.1 1.04 3.1±0.07ms ? ?/sec 1.00 3.0±0.24ms ? ?/sec
filter: primitive, 8192, nulls: 0, selectivity: 0.8 1.12 2.8±0.02ms ? ?/sec 1.00 2.5±0.01ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.001 1.00 116.5±0.57ms ? ?/sec 1.00 116.8±1.06ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.01 1.07 13.9±0.05ms ? ?/sec 1.00 13.0±0.07ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.1 1.09 6.4±0.29ms ? ?/sec 1.00 5.8±0.29ms ? ?/sec
filter: primitive, 8192, nulls: 0.1, selectivity: 0.8 1.06 8.7±0.03ms ? ?/sec 1.00 8.2±0.06ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.001 1.13 63.7±0.46ms ? ?/sec 1.00 56.6±0.18ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.01 1.16 7.3±0.04ms ? ?/sec 1.00 6.3±0.02ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.1 1.02 3.7±0.12ms ? ?/sec 1.00 3.6±0.25ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.8 1.17 1287.3±7.92µs ? ?/sec 1.00 1099.0±5.60µs ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.001 1.17 87.2±2.24ms ? ?/sec 1.00 74.8±1.12ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.01 1.18 11.1±0.04ms ? ?/sec 1.00 9.4±0.04ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.1 1.14 5.2±0.10ms ? ?/sec 1.00 4.5±0.06ms ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.8 1.14 3.8±0.07ms ? ?/sec 1.00 3.3±0.01ms ? ?/sec
```
</p>
</details>
--
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] Optimize boolean operations [arrow-rs]
Posted by "alamb-ghbot (via GitHub)" <gi...@apache.org>.
alamb-ghbot commented on PR #9284:
URL: https://github.com/apache/arrow-rs/pull/9284#issuecomment-3893494754
🤖: Benchmark completed
<details><summary>Details</summary>
<p>
```
group main optimize_unaligned_bitchunk_iterator
----- ---- ------------------------------------
filter context decimal128 (kept 1/2) 1.00 43.2±5.03µs ? ?/sec 1.16 50.1±7.44µs ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024) 1.00 49.8±1.80µs ? ?/sec 1.01 50.3±1.93µs ? ?/sec
filter context decimal128 low selectivity (kept 1/1024) 1.01 233.8±2.12ns ? ?/sec 1.00 230.4±1.37ns ? ?/sec
filter context f32 (kept 1/2) 1.12 87.6±0.77µs ? ?/sec 1.00 77.9±0.26µs ? ?/sec
filter context f32 high selectivity (kept 1023/1024) 1.01 10.0±0.38µs ? ?/sec 1.00 9.9±0.29µs ? ?/sec
filter context f32 low selectivity (kept 1/1024) 1.00 423.8±1.47ns ? ?/sec 1.00 423.6±5.31ns ? ?/sec
filter context fsb with value length 20 (kept 1/2) 1.16 70.6±0.52µs ? ?/sec 1.00 60.6±0.46µs ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024) 1.17 70.6±0.70µs ? ?/sec 1.00 60.6±0.43µs ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024) 1.17 70.6±0.30µs ? ?/sec 1.00 60.6±0.25µs ? ?/sec
filter context fsb with value length 5 (kept 1/2) 1.17 70.6±0.14µs ? ?/sec 1.00 60.6±0.32µs ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024) 1.17 70.9±1.89µs ? ?/sec 1.00 60.6±0.38µs ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024) 1.17 70.8±0.61µs ? ?/sec 1.00 60.8±2.24µs ? ?/sec
filter context fsb with value length 50 (kept 1/2) 1.16 70.6±0.23µs ? ?/sec 1.00 60.6±0.16µs ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024) 1.16 70.6±0.39µs ? ?/sec 1.00 61.1±2.32µs ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024) 1.16 70.6±0.62µs ? ?/sec 1.00 60.9±1.37µs ? ?/sec
filter context i32 (kept 1/2) 1.00 16.5±0.10µs ? ?/sec 1.00 16.5±0.08µs ? ?/sec
filter context i32 high selectivity (kept 1023/1024) 1.00 6.3±0.37µs ? ?/sec 1.03 6.5±0.34µs ? ?/sec
filter context i32 low selectivity (kept 1/1024) 1.00 220.5±3.50ns ? ?/sec 1.01 222.7±2.28ns ? ?/sec
filter context i32 w NULLs (kept 1/2) 1.14 88.2±0.80µs ? ?/sec 1.00 77.5±0.41µs ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024) 1.00 10.0±0.38µs ? ?/sec 1.02 10.2±0.24µs ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024) 1.00 424.6±2.15ns ? ?/sec 1.00 423.8±2.80ns ? ?/sec
filter context mixed string view (kept 1/2) 1.03 117.7±6.58µs ? ?/sec 1.00 114.6±6.53µs ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024) 1.00 54.9±1.67µs ? ?/sec 1.00 55.1±1.72µs ? ?/sec
filter context mixed string view low selectivity (kept 1/1024) 1.00 603.8±1.43ns ? ?/sec 1.01 607.8±12.66ns ? ?/sec
filter context short string view (kept 1/2) 1.15 120.9±6.82µs ? ?/sec 1.00 104.7±3.78µs ? ?/sec
filter context short string view high selectivity (kept 1023/1024) 1.01 56.6±1.58µs ? ?/sec 1.00 55.9±2.62µs ? ?/sec
filter context short string view low selectivity (kept 1/1024) 1.01 476.9±13.09ns ? ?/sec 1.00 472.9±1.48ns ? ?/sec
filter context string (kept 1/2) 1.03 594.9±24.00µs ? ?/sec 1.00 577.2±17.96µs ? ?/sec
filter context string dictionary (kept 1/2) 1.00 16.9±0.04µs ? ?/sec 1.00 17.0±0.13µs ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024) 1.00 6.7±0.21µs ? ?/sec 1.05 7.0±0.28µs ? ?/sec
filter context string dictionary low selectivity (kept 1/1024) 1.00 639.8±21.71ns ? ?/sec 1.00 640.4±4.38ns ? ?/sec
filter context string dictionary w NULLs (kept 1/2) 1.13 88.0±0.50µs ? ?/sec 1.00 78.1±0.56µs ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024) 1.06 11.1±0.32µs ? ?/sec 1.00 10.5±0.31µs ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024) 1.01 861.8±3.45ns ? ?/sec 1.00 852.9±17.43ns ? ?/sec
filter context string high selectivity (kept 1023/1024) 1.00 697.1±20.84µs ? ?/sec 1.00 694.9±17.63µs ? ?/sec
filter context string low selectivity (kept 1/1024) 1.18 1035.9±5.34ns ? ?/sec 1.00 875.0±7.36ns ? ?/sec
filter context u8 (kept 1/2) 1.00 15.0±0.09µs ? ?/sec 1.00 14.9±0.08µs ? ?/sec
filter context u8 high selectivity (kept 1023/1024) 1.00 1797.9±12.52ns ? ?/sec 1.02 1838.5±8.60ns ? ?/sec
filter context u8 low selectivity (kept 1/1024) 1.00 213.9±1.43ns ? ?/sec 1.02 218.6±2.61ns ? ?/sec
filter context u8 w NULLs (kept 1/2) 1.14 86.0±0.57µs ? ?/sec 1.00 75.8±0.17µs ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024) 1.00 5.3±0.08µs ? ?/sec 1.02 5.4±0.03µs ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024) 1.01 422.9±7.59ns ? ?/sec 1.00 419.3±2.93ns ? ?/sec
filter decimal128 (kept 1/2) 1.01 46.9±3.43µs ? ?/sec 1.00 46.6±5.62µs ? ?/sec
filter decimal128 high selectivity (kept 1023/1024) 1.06 55.2±2.01µs ? ?/sec 1.00 52.3±1.70µs ? ?/sec
filter decimal128 low selectivity (kept 1/1024) 1.71 3.1±0.05µs ? ?/sec 1.00 1821.8±28.59ns ? ?/sec
filter f32 (kept 1/2) 1.08 141.5±1.19µs ? ?/sec 1.00 131.1±0.64µs ? ?/sec
filter fsb with value length 20 (kept 1/2) 1.18 138.3±3.03µs ? ?/sec 1.00 116.9±1.18µs ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024) 1.04 73.4±2.93µs ? ?/sec 1.00 70.6±3.65µs ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024) 1.56 3.4±0.03µs ? ?/sec 1.00 2.2±0.03µs ? ?/sec
filter fsb with value length 5 (kept 1/2) 1.16 142.8±0.25µs ? ?/sec 1.00 123.0±1.04µs ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024) 1.10 11.0±0.54µs ? ?/sec 1.00 10.0±0.48µs ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024) 1.64 3.4±0.01µs ? ?/sec 1.00 2.1±0.08µs ? ?/sec
filter fsb with value length 50 (kept 1/2) 1.04 176.4±13.80µs ? ?/sec 1.00 169.5±14.66µs ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024) 1.07 229.8±7.39µs ? ?/sec 1.00 215.6±9.99µs ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024) 1.62 3.4±0.01µs ? ?/sec 1.00 2.1±0.00µs ? ?/sec
filter i32 (kept 1/2) 1.23 36.5±0.08µs ? ?/sec 1.00 29.7±0.73µs ? ?/sec
filter i32 high selectivity (kept 1023/1024) 1.16 8.7±0.36µs ? ?/sec 1.00 7.5±0.23µs ? ?/sec
filter i32 low selectivity (kept 1/1024) 1.34 2.3±0.00µs ? ?/sec 1.00 1751.5±20.57ns ? ?/sec
filter optimize (kept 1/2) 1.29 37.1±0.06µs ? ?/sec 1.00 28.7±0.04µs ? ?/sec
filter optimize high selectivity (kept 1023/1024) 1.72 3.0±0.01µs ? ?/sec 1.00 1750.9±10.71ns ? ?/sec
filter optimize low selectivity (kept 1/1024) 1.00 1844.7±61.02ns ? ?/sec 1.04 1909.4±6.33ns ? ?/sec
filter run array (kept 1/2) 1.00 381.3±16.14µs ? ?/sec 1.20 456.6±2.42µs ? ?/sec
filter run array high selectivity (kept 1023/1024) 1.00 397.3±15.80µs ? ?/sec 1.25 495.2±4.02µs ? ?/sec
filter run array low selectivity (kept 1/1024) 1.00 284.5±2.04µs ? ?/sec 1.34 381.3±4.94µs ? ?/sec
filter single record batch 1.35 39.0±0.19µs ? ?/sec 1.00 29.0±0.48µs ? ?/sec
filter u8 (kept 1/2) 1.46 44.6±0.05µs ? ?/sec 1.00 30.6±1.96µs ? ?/sec
filter u8 high selectivity (kept 1023/1024) 1.40 4.0±0.12µs ? ?/sec 1.00 2.8±0.02µs ? ?/sec
filter u8 low selectivity (kept 1/1024) 1.91 3.2±0.01µs ? ?/sec 1.00 1699.2±29.29ns ? ?/sec
```
</p>
</details>
--
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