Jefffrey commented on PR #20044: URL: https://github.com/apache/datafusion/pull/20044#issuecomment-3827669938
> > Maybe it was already so fast that adding `make_scalar_function()`/altering the match path to get to the hot loop is adding this extra overhead? 🤔 > > you can try `inline(always)` and I found info that some time LLVM can have troubles with > > ``` > buffer[i] = HEX_CHARS_UPPER[(n & 0xF) as usize]; > ``` > > so it needs to prove boundary checks Let me try that out 👍 -- 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]
