ShiKaiWi commented on PR #6281:
URL: https://github.com/apache/arrow-rs/pull/6281#issuecomment-2303486659
@Xuanwo @etseidl @alamb Existing benchmarks includes the (de)compression,
and I run it with the current `unsafe` resize implementation and the benchmark
shows a big improvement in decompression compared with the master branch:
```
compress SNAPPY - alphanumeric
time: [54.489 µs 54.591 µs 54.699 µs]
change: [-35.659% -35.356% -35.055%] (p = 0.00 <
0.05)
Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high severe
SNAPPY compressed 1048576 bytes of alphanumeric to 1048627 bytes
decompress SNAPPY - alphanumeric
time: [45.716 µs 46.030 µs 46.348 µs]
change: [-34.833% -34.297% -33.757%] (p = 0.00 <
0.05)
Performance has improved.
```
PS: I run the command `cargo bench --bench compression
--features="experimental default" -- SNAPPY` under the directory `parquet`.
--
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]
