tustvold commented on PR #2038:
URL: https://github.com/apache/arrow-rs/pull/2038#issuecomment-1181960914
Currently this represents a non-trivial performance regression for strings,
```
array_from_vec 128 time: [200.16 ns 200.18 ns 200.20 ns]
change: [-10.896% -10.821% -10.772%] (p = 0.00 <
0.05)
Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
1 (1.00%) low mild
1 (1.00%) high mild
5 (5.00%) high severe
array_from_vec 256 time: [317.37 ns 317.43 ns 317.50 ns]
change: [+35.360% +35.522% +35.637%] (p = 0.00 <
0.05)
Performance has regressed.
Found 8 outliers among 100 measurements (8.00%)
3 (3.00%) low mild
2 (2.00%) high mild
3 (3.00%) high severe
array_from_vec 512 time: [407.97 ns 408.07 ns 408.20 ns]
change: [+2.4341% +2.4621% +2.4892%] (p = 0.00 <
0.05)
Performance has regressed.
Found 10 outliers among 100 measurements (10.00%)
1 (1.00%) low mild
6 (6.00%) high mild
3 (3.00%) high severe
array_string_from_vec 128
time: [3.3538 us 3.3546 us 3.3554 us]
change: [+65.462% +65.526% +65.588%] (p = 0.00 <
0.05)
Performance has regressed.
Found 9 outliers among 100 measurements (9.00%)
4 (4.00%) high mild
5 (5.00%) high severe
array_string_from_vec 256
time: [4.8467 us 4.8477 us 4.8488 us]
change: [+57.833% +57.953% +58.074%] (p = 0.00 <
0.05)
Performance has regressed.
Found 4 outliers among 100 measurements (4.00%)
2 (2.00%) high mild
2 (2.00%) high severe
array_string_from_vec 512
time: [7.5808 us 7.5830 us 7.5855 us]
change: [+52.732% +52.786% +52.842%] (p = 0.00 <
0.05)
Performance has regressed.
Found 5 outliers among 100 measurements (5.00%)
1 (1.00%) low severe
2 (2.00%) high mild
2 (2.00%) high severe
struct_array_from_vec 128
time: [4.6968 us 4.6996 us 4.7025 us]
change: [+52.108% +52.200% +52.281%] (p = 0.00 <
0.05)
Performance has regressed.
struct_array_from_vec 256
time: [6.7720 us 6.7772 us 6.7843 us]
change: [+52.493% +52.585% +52.681%] (p = 0.00 <
0.05)
Performance has regressed.
Found 2 outliers among 100 measurements (2.00%)
1 (1.00%) high mild
1 (1.00%) high severe
struct_array_from_vec 512
time: [10.426 us 10.432 us 10.439 us]
change: [+45.728% +45.796% +45.867%] (p = 0.00 <
0.05)
Performance has regressed.
Found 2 outliers among 100 measurements (2.00%)
2 (2.00%) high severe
struct_array_from_vec 1024
time: [17.381 us 17.391 us 17.404 us]
change: [+41.415% +41.488% +41.575%] (p = 0.00 <
0.05)
Performance has regressed.
Found 5 outliers among 100 measurements (5.00%)
1 (1.00%) low mild
1 (1.00%) high mild
3 (3.00%) high severe
```
I suspect this is down to buffer resizing and should just be a case of
setting the correct capacity for the builder
--
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]
