HaoYang670 commented on PR #2127:
URL: https://github.com/apache/arrow-rs/pull/2127#issuecomment-1194774919
Latest benchmark result: compared with the latest master branch
```
cargo bench --bench builder -- --baseline master
```
## Tested on Intel Ubuntu
```
bench_primitive/bench_primitive
time: [201.59 us 201.64 us 201.71 us]
thrpt: [19.366 GiB/s 19.372 GiB/s 19.377 GiB/s]
change:
time: [-2.5350% -2.3169% -2.1224%] (p = 0.00 <
0.05)
thrpt: [+2.1684% +2.3719% +2.6009%]
Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
2 (2.00%) high mild
11 (11.00%) high severe
bench_primitive_nulls/bench_primitive_nulls
time: [775.12 us 775.51 us 775.92 us]
change: [-1.4140% -1.1018% -0.8333%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 14 outliers among 100 measurements (14.00%)
3 (3.00%) low mild
4 (4.00%) high mild
7 (7.00%) high severe
bench_bool/bench_bool time: [256.99 us 257.43 us 257.90 us]
thrpt: [1.8933 GiB/s 1.8968 GiB/s 1.9000 GiB/s]
change:
time: [-12.722% -12.251% -11.797%] (p = 0.00 <
0.05)
thrpt: [+13.374% +13.962% +14.576%]
Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
9 (9.00%) low mild
3 (3.00%) high mild
1 (1.00%) high severe
Benchmarking bench_primitive/bench_string: Warming up for 3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase
target time to 9.8s, enable flat sampling, or reduce sample count to 50.
bench_primitive/bench_string
time: [1.9121 ms 1.9134 ms 1.9150 ms]
thrpt: [3.3147 GiB/s 3.3175 GiB/s 3.3197 GiB/s]
change:
time: [-5.7654% -5.4834% -5.1914%] (p = 0.00 <
0.05)
thrpt: [+5.4757% +5.8015% +6.1181%]
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
6 (6.00%) high mild
2 (2.00%) high severe
```
## Tested on M1 Pro Mac
```
bench_primitive/bench_primitive
time: [620.30 us 623.83 us 627.90 us]
thrpt: [6.2211 GiB/s 6.2617 GiB/s 6.2973 GiB/s]
change:
time: [-0.5679% +0.7610% +2.1520%] (p = 0.29 >
0.05)
thrpt: [-2.1066% -0.7552% +0.5712%]
No change in performance detected.
Found 9 outliers among 100 measurements (9.00%)
3 (3.00%) high mild
6 (6.00%) high severe
Benchmarking bench_primitive_nulls/bench_primitive_nulls: Warming up for
3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase
target time to 7.0s, enable flat sampling, or reduce sample count to 50.
bench_primitive_nulls/bench_primitive_nulls
time: [1.3842 ms 1.3854 ms 1.3865 ms]
change: [+0.2321% +0.5164% +0.8048%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
1 (1.00%) high mild
4 (4.00%) high severe
bench_bool/bench_bool time: [651.99 us 654.72 us 658.97 us]
thrpt: [758.75 MiB/s 763.69 MiB/s 766.88 MiB/s]
change:
time: [-3.1996% -1.5821% -0.1934%] (p = 0.04 <
0.05)
thrpt: [+0.1938% +1.6075% +3.3053%]
Change within noise threshold.
Found 7 outliers among 100 measurements (7.00%)
2 (2.00%) high mild
5 (5.00%) high severe
bench_primitive/bench_string
time: [2.8055 ms 2.8106 ms 2.8161 ms]
thrpt: [2.2540 GiB/s 2.2585 GiB/s 2.2626 GiB/s]
change:
time: [-1.7947% -1.4838% -1.1946%] (p = 0.00 <
0.05)
thrpt: [+1.2090% +1.5061% +1.8275%]
Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
6 (6.00%) low severe
4 (4.00%) low mild
6 (6.00%) high mild
2 (2.00%) high severe
```
cc @tustvold @viirya @jhorstmann @alamb Please help to review, thank you!
--
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]
