zhuqi-lucas commented on PR #7962:
URL: https://github.com/apache/arrow-rs/pull/7962#issuecomment-3109036597
> ```
> sort i32 to indices 2^10 1.13
12.9±0.02µs ? ?/sec 1.00 11.4±0.03µs ? ?/sec
> sort i32 to indices 2^12 1.15
63.1±0.25µs ? ?/sec 1.00 54.9±0.13µs ? ?/sec
> s
> ```
>
> Weird -- we get the same results. Maybe there is more code or something
now so cache effects come into play on the test machine 🤔 I am inclined to go
with this PR to get the improvements in general
Thank you @alamb , i changed to use a linux now to reproduce also, but it
can't reproduce also both mac and linux:
```rust
sort i32 to indices 2^10
time: [12.857 µs 12.871 µs 12.886 µs]
change: [−0.8566% −0.6047% −0.3347%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
3 (3.00%) high mild
2 (2.00%) high severe
sort i32 to indices 2^12
time: [57.662 µs 57.817 µs 58.056 µs]
change: [−3.9800% −3.5589% −3.1125%] (p = 0.00 <
0.05)
Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
1 (1.00%) high mild
4 (4.00%) high severe
```
--
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-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
