haohuaijin commented on PR #10141: URL: https://github.com/apache/arrow-rs/pull/10141#issuecomment-5015837950
> Could we rerun the complete L4–L40 curve in row_selection_cursor on the current head and compare: > > 1. the Selector/Mask crossover against the merge-base; > 2. the strategy selected by Auto at each point; and > 3. Auto's runtime against the faster forced strategy? > > Since this PR adds a second input representation, it would be particularly > useful to run the matrix for both selector-backed and mask-backed > RowSelections. That would show whether Auto should use a different threshold > or cost model when choosing a strategy requires first converting the backing > representation. the command for below figure benchmark that [325d774](https://github.com/apache/arrow-rs/pull/10141/commits/325d774420a49430e05399f401d7945ee93901e1) added the bitmap input representation into row_selection_cursor ``` cargo bench -p parquet --bench row_selection_cursor --features arrow,test_common -- "len-uniform50-uniform50" --save-baseline 10141-auto # selector-backed input critcmp 10141-auto -g '.*?/(.*)' -f "read_(auto|selector|mask)/len-uniform50-uniform50" # mask-backed input critcmp 10141-auto -g '.*?/(.*)' -f "mask_backed/len-uniform50-uniform50" ``` <img width="1182" height="461" alt="image" src="https://github.com/user-attachments/assets/3d983aa9-8dc1-4f9c-a009-2e995e39a650"; /> -- 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]
