benwtrent commented on PR #15500:
URL: https://github.com/apache/lucene/pull/15500#issuecomment-3655967073

   >  want to share that we've seen some weird profiles while comparing 10.2 
and 10.3
   
   @msokolov we have independently seen some similar things. It's sporadic and 
not conclusive. But even then, it seems like we should be using the bulk scorer 
whenever we can. 
   
   > Saying this outloud in case my assumption is wrong. I assume the reason we 
don't need benchmarking here is that we know from prior work at the leaf level 
that there's definitely a benefit to bulk scoring eps here instead of doing an 
early termination check for each entry point.
   
   @john-wagster let me benchmark this. The early-termination check is 
generally pretty cheap, I don't expect the absence of that to actually provide 
anything. The main benefit is the bulk scoring directly.
   
   I should follow my own advice, and benchmark everything :). 


-- 
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]

Reply via email to