zjregee opened a new pull request, #14697:
URL: https://github.com/apache/datafusion/pull/14697
## Which issue does this PR close?
- Closes #14610.
## Rationale for this change
## What changes are included in this PR?
By calculating the length in advance and allocating memory accordingly, the
repeat function achieves improved performance to a certain degree.
The following are the local test results:
```txt
repeat 3 times/repeat_string_view [size=1024, repeat_times=3]
time: [40.286 µs 40.438 µs 40.607 µs]
change: [-0.1541% +0.4780% +1.0910%] (p = 0.17 >
0.05)
No change in performance detected.
repeat 3 times/repeat_string [size=1024, repeat_times=3]
time: [38.556 µs 38.744 µs 38.944 µs]
change: [-10.201% -8.3456% -6.4266%] (p = 0.00 <
0.05)
Performance has improved.
repeat 3 times/repeat_large_string [size=1024, repeat_times=3]
time: [30.212 µs 30.365 µs 30.523 µs]
change: [-3.3156% -2.5561% -1.7929%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_string_view [size=1024, repeat_times=30]
time: [74.830 µs 75.354 µs 75.885 µs]
change: [-51.695% -51.232% -50.754%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_string [size=1024, repeat_times=30]
time: [73.079 µs 73.638 µs 74.246 µs]
change: [-53.258% -52.647% -52.008%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_large_string [size=1024, repeat_times=30]
time: [74.278 µs 74.651 µs 75.251 µs]
change: [-52.307% -51.550% -50.794%] (p = 0.00 <
0.05)
Performance has improved.
repeat 1073741824 times/repeat_string overflow [size=1024,
repeat_times=1073741824]
time: [155.57 ns 156.74 ns 157.77 ns]
change: [-29.625% -28.588% -27.670%] (p = 0.00 <
0.05)
Performance has improved.
repeat 3 times/repeat_string_view [size=4096, repeat_times=3]
time: [158.52 µs 159.74 µs 161.16 µs]
change: [-8.5460% -7.5443% -6.4563%] (p = 0.00 <
0.05)
Performance has improved.
repeat 3 times/repeat_string [size=4096, repeat_times=3]
time: [155.23 µs 156.10 µs 156.95 µs]
change: [-10.086% -9.3897% -8.7024%] (p = 0.00 <
0.05)
Performance has improved.
repeat 3 times/repeat_large_string [size=4096, repeat_times=3]
time: [118.43 µs 119.50 µs 120.71 µs]
change: [-13.262% -12.286% -11.215%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_string_view [size=4096, repeat_times=30]
time: [407.53 µs 411.95 µs 416.35 µs]
change: [-38.905% -37.817% -36.784%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_string [size=4096, repeat_times=30]
time: [400.81 µs 404.55 µs 408.14 µs]
change: [-40.494% -39.392% -38.262%] (p = 0.00 <
0.05)
Performance has improved.
repeat 30 times/repeat_large_string [size=4096, repeat_times=30]
time: [407.21 µs 412.32 µs 417.80 µs]
change: [-37.954% -37.020% -36.066%] (p = 0.00 <
0.05)
Performance has improved.
repeat 1073741824 times/repeat_string overflow [size=4096,
repeat_times=1073741824]
time: [150.92 ns 152.68 ns 154.44 ns]
change: [-31.467% -30.488% -29.483%] (p = 0.00 <
0.05)
Performance has improved.
```
## Are these changes tested?
Yes.
## Are there any user-facing changes?
None.
--
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...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
