js8544 commented on issue #13981:
URL: https://github.com/apache/arrow/issues/13981#issuecomment-1228679147
I noticed that I can pass `skip_nulls=true` to `IndexIn` and
`TakeOptions::NoBoundsCheck` to `Take` to optimize them. Here is the update
results:
IndexIn:
| ns/op | op/s | err% | total |
Benchmarking IndexIn
|--------------------:|--------------------:|--------:|----------:|:---------------------
| 351,957.33 | 2,841.25 | 1.0% | 0.01 |
`arrow_compute`
| 90,050.75 | 11,104.85 | 0.9% | 0.01 |
`arrow_raw`
Take:
| ns/op | op/s | err% | total |
Benchmarking Take
|--------------------:|--------------------:|--------:|----------:|:------------------
| 28,328.86 | 35,299.68 | 0.8% | 0.01 |
`arrow_compute`
| 8,873.48 | 112,695.35 | 0.5% | 0.01 |
`arrow_raw`
End to end:
| ns/op | op/s | err% | total |
Benchmarking simple feature
|--------------------:|--------------------:|--------:|----------:|:----------------------------
| 477,005.00 | 2,096.41 | 2.4% | 0.01 |
`arrow_compute`
| 94,738.54 | 10,555.37 | 0.9% | 0.01 |
`arrow_raw`
A bit better but only tiny difference overall.
--
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]
