pepijnve commented on PR #10161:
URL: https://github.com/apache/arrow-rs/pull/10161#issuecomment-4766317897
> could you post the full benchmark results for reference?
Of course. Here's what I'm seeing on a MBP M2.
| Bench | main | concat_view | Difference |
| -- | -- | -- | -- |
| concat utf8_view all_inline max_str_len=12 null_density=0 | 170.05 µs |
93.549 µs | -45.475% |
| concat utf8_view max_str_len=20 null_density=0 | 181.60 µs | 113.11 µs |
-37.650% |
| concat utf8_view max_str_len=128 null_density=0 | 229.82 µs | 158.62 µs |
-30.546% |
| concat utf8_view all_inline max_str_len=12 null_density=0.2 | 160.90 µs |
90.85 µs | -43.547% |
| concat utf8_view max_str_len=20 null_density=0.2 | 178.43 µs | 104.13 µs
| -41.637% |
| concat utf8_view max_str_len=128 null_density=0.2 | 161.06 µs | 147.52 µs
| −8.3218% |
<details>
<summary>Raw criterion output</summary>
```
pepijn@Flandrien arrow-rs % cargo bench --bench concatenate_elements --
utf8_view
Compiling arrow-string v59.0.0
(/Users/pepijn/RustroverProjects/arrow-rs/arrow-string)
Compiling arrow v59.0.0 (/Users/pepijn/RustroverProjects/arrow-rs/arrow)
Finished `bench` profile [optimized] target(s) in 5.62s
Running benches/concatenate_elements.rs
(target/release/deps/concatenate_elements-3ba9b7123e418511)
concat utf8_view all_inline max_str_len=12 null_density=0
time: [169.57 µs 170.05 µs 170.53 µs]
Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high mild
concat utf8_view max_str_len=20 null_density=0
time: [180.87 µs 181.60 µs 182.34 µs]
concat utf8_view max_str_len=128 null_density=0
time: [227.06 µs 229.82 µs 232.56 µs]
Found 2 outliers among 100 measurements (2.00%)
1 (1.00%) low mild
1 (1.00%) high mild
concat utf8_view all_inline max_str_len=12 null_density=0.2
time: [160.52 µs 160.90 µs 161.27 µs]
Found 5 outliers among 100 measurements (5.00%)
2 (2.00%) low mild
3 (3.00%) high mild
concat utf8_view max_str_len=20 null_density=0.2
time: [177.61 µs 178.43 µs 179.28 µs]
Found 2 outliers among 100 measurements (2.00%)
1 (1.00%) low mild
1 (1.00%) high severe
concat utf8_view max_str_len=128 null_density=0.2
time: [159.62 µs 161.06 µs 162.71 µs]
Found 3 outliers among 100 measurements (3.00%)
3 (3.00%) high mild
pepijn@Flandrien arrow-rs % cargo bench --bench concatenate_elements --
utf8_view
Compiling arrow-string v59.0.0
(/Users/pepijn/RustroverProjects/arrow-rs/arrow-string)
Compiling arrow v59.0.0 (/Users/pepijn/RustroverProjects/arrow-rs/arrow)
Finished `bench` profile [optimized] target(s) in 5.24s
Running benches/concatenate_elements.rs
(target/release/deps/concatenate_elements-3ba9b7123e418511)
concat utf8_view all_inline max_str_len=12 null_density=0
time: [92.899 µs 93.549 µs 94.453 µs]
change: [−45.860% −45.475% −45.079%] (p = 0.00 <
0.05)
Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
4 (4.00%) low mild
1 (1.00%) high severe
concat utf8_view max_str_len=20 null_density=0
time: [112.70 µs 113.11 µs 113.52 µs]
change: [−38.054% −37.650% −37.270%] (p = 0.00 <
0.05)
Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
1 (1.00%) low severe
5 (5.00%) low mild
concat utf8_view max_str_len=128 null_density=0
time: [157.85 µs 158.62 µs 159.50 µs]
change: [−31.641% −30.546% −29.429%] (p = 0.00 <
0.05)
Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
1 (1.00%) high mild
2 (2.00%) high severe
concat utf8_view all_inline max_str_len=12 null_density=0.2
time: [90.539 µs 90.850 µs 91.182 µs]
change: [−43.852% −43.547% −43.263%] (p = 0.00 <
0.05)
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) high mild
concat utf8_view max_str_len=20 null_density=0.2
time: [103.80 µs 104.13 µs 104.46 µs]
change: [−42.146% −41.637% −41.185%] (p = 0.00 <
0.05)
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
2 (2.00%) low mild
2 (2.00%) high mild
concat utf8_view max_str_len=128 null_density=0.2
time: [147.19 µs 147.52 µs 147.89 µs]
change: [−9.1648% −8.3218% −7.4702%] (p = 0.00 <
0.05)
Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
2 (2.00%) low mild
3 (3.00%) high mild
```
</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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
