alamb commented on PR #18449:
URL: https://github.com/apache/datafusion/pull/18449#issuecomment-3518017530
Here are the results from the gcp runner (aka I can reproduce my script and
it shows several cases much slower)
```
alamb@aal-dev:~/arrow-datafusion10$ critcmp before in_list
group before
in_list
----- ------
-------
in_list_f32 (1024, 0) IN (1, 0) 1.00 4.2±0.02µs ?
?/sec 1.38 5.9±0.01µs ? ?/sec
in_list_f32 (1024, 0) IN (10, 0) 1.00 4.3±0.05µs ?
?/sec 1.38 5.9±0.04µs ? ?/sec
in_list_f32 (1024, 0) IN (100, 0) 1.00 4.3±0.08µs ?
?/sec 1.37 5.9±0.04µs ? ?/sec
in_list_f32 (1024, 0) IN (3, 0) 1.00 4.3±0.02µs ?
?/sec 1.39 5.9±0.05µs ? ?/sec
in_list_f32 (1024, 0.2) IN (1, 0) 1.00 5.5±0.02µs ?
?/sec 1.61 8.9±0.04µs ? ?/sec
in_list_f32 (1024, 0.2) IN (10, 0) 1.00 5.4±0.02µs ?
?/sec 1.71 9.3±0.06µs ? ?/sec
in_list_f32 (1024, 0.2) IN (100, 0) 1.00 5.5±0.03µs ?
?/sec 1.58 8.8±0.07µs ? ?/sec
in_list_f32 (1024, 0.2) IN (3, 0) 1.00 5.5±0.02µs ?
?/sec 1.64 8.9±0.02µs ? ?/sec
in_list_i32 (1024, 0) IN (1, 0) 1.00 4.2±0.01µs ?
?/sec 1.40 5.9±0.01µs ? ?/sec
in_list_i32 (1024, 0) IN (10, 0) 1.00 4.2±0.01µs ?
?/sec 1.40 5.9±0.02µs ? ?/sec
in_list_i32 (1024, 0) IN (100, 0) 1.00 4.2±0.01µs ?
?/sec 1.40 5.9±0.02µs ? ?/sec
in_list_i32 (1024, 0) IN (3, 0) 1.00 4.2±0.02µs ?
?/sec 1.40 5.9±0.01µs ? ?/sec
in_list_i32 (1024, 0.2) IN (1, 0) 1.00 5.7±0.02µs ?
?/sec 1.58 9.0±0.04µs ? ?/sec
in_list_i32 (1024, 0.2) IN (10, 0) 1.00 5.5±0.04µs ?
?/sec 1.53 8.5±0.04µs ? ?/sec
in_list_i32 (1024, 0.2) IN (100, 0) 1.00 5.5±0.02µs ?
?/sec 1.55 8.5±0.04µs ? ?/sec
in_list_i32 (1024, 0.2) IN (3, 0) 1.00 5.7±0.06µs ?
?/sec 1.57 8.9±0.03µs ? ?/sec
in_list_utf8(10) (1024, 0) IN (1, 0) 1.04 5.5±0.02µs ?
?/sec 1.00 5.3±0.01µs ? ?/sec
in_list_utf8(10) (1024, 0) IN (10, 0) 1.04 5.5±0.01µs ?
?/sec 1.00 5.3±0.01µs ? ?/sec
in_list_utf8(10) (1024, 0) IN (100, 0) 1.05 5.5±0.01µs ?
?/sec 1.00 5.3±0.01µs ? ?/sec
in_list_utf8(10) (1024, 0) IN (3, 0) 1.05 5.5±0.06µs ?
?/sec 1.00 5.3±0.01µs ? ?/sec
in_list_utf8(10) (1024, 0.2) IN (1, 0) 1.00 7.6±0.02µs ?
?/sec 1.06 8.0±0.04µs ? ?/sec
in_list_utf8(10) (1024, 0.2) IN (10, 0) 1.00 7.7±0.02µs ?
?/sec 1.03 7.9±0.06µs ? ?/sec
in_list_utf8(10) (1024, 0.2) IN (100, 0) 1.00 7.9±0.03µs ?
?/sec 1.00 7.9±0.04µs ? ?/sec
in_list_utf8(10) (1024, 0.2) IN (3, 0) 1.00 7.6±0.02µs ?
?/sec 1.05 7.9±0.08µs ? ?/sec
in_list_utf8(20) (1024, 0) IN (1, 0) 1.05 5.5±0.02µs ?
?/sec 1.00 5.3±0.02µs ? ?/sec
in_list_utf8(20) (1024, 0) IN (10, 0) 1.05 5.5±0.05µs ?
?/sec 1.00 5.3±0.03µs ? ?/sec
in_list_utf8(20) (1024, 0) IN (100, 0) 1.04 5.5±0.01µs ?
?/sec 1.00 5.3±0.03µs ? ?/sec
in_list_utf8(20) (1024, 0) IN (3, 0) 1.06 5.6±0.01µs ?
?/sec 1.00 5.3±0.02µs ? ?/sec
in_list_utf8(20) (1024, 0.2) IN (1, 0) 1.00 7.9±0.03µs ?
?/sec 1.01 8.0±0.03µs ? ?/sec
in_list_utf8(20) (1024, 0.2) IN (10, 0) 1.00 7.9±0.04µs ?
?/sec 1.02 8.0±0.02µs ? ?/sec
in_list_utf8(20) (1024, 0.2) IN (100, 0) 1.01 7.9±0.03µs ?
?/sec 1.00 7.8±0.04µs ? ?/sec
in_list_utf8(20) (1024, 0.2) IN (3, 0) 1.01 8.1±0.07µs ?
?/sec 1.00 8.0±0.02µs ? ?/sec
in_list_utf8(5) (1024, 0) IN (1, 0) 1.06 5.6±0.03µs ?
?/sec 1.00 5.3±0.02µs ? ?/sec
in_list_utf8(5) (1024, 0) IN (10, 0) 1.04 5.5±0.05µs ?
?/sec 1.00 5.3±0.04µs ? ?/sec
in_list_utf8(5) (1024, 0) IN (100, 0) 1.05 5.5±0.02µs ?
?/sec 1.00 5.3±0.01µs ? ?/sec
in_list_utf8(5) (1024, 0) IN (3, 0) 1.05 5.5±0.05µs ?
?/sec 1.00 5.3±0.02µs ? ?/sec
in_list_utf8(5) (1024, 0.2) IN (1, 0) 1.00 7.7±0.02µs ?
?/sec 1.06 8.2±0.04µs ? ?/sec
in_list_utf8(5) (1024, 0.2) IN (10, 0) 1.00 7.8±0.04µs ?
?/sec 1.02 8.0±0.02µs ? ?/sec
in_list_utf8(5) (1024, 0.2) IN (100, 0) 1.00 7.6±0.03µs ?
?/sec 1.01 7.7±0.05µs ? ?/sec
in_list_utf8(5) (1024, 0.2) IN (3, 0) 1.00 7.8±0.02µs ?
?/sec 1.04 8.1±0.05µs ? ?/sec
```
I am also going to see if `RUSTFLAGS='-C target-cpu=native'` makes any
difference
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
