Comment #8 on issue 3903 by [email protected]: Math.log10 is
unexpectedly slow
https://code.google.com/p/v8/issues/detail?id=3903
I just looked at the generated code that V8 generates. It actually inlines
the MathLog implementation by calling the FPU instruction. What does not
get inlined is Math.log10 itself, into the loop. So yeah, both your and my
micro benchmark are not only testing log10 performance, but also function
call performance and whether a function gets inlined. A quick hack to get
log10 inlined boosts the performance by 30%, but I'm not sure that's the
right thing to do.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings
--
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
---
You received this message because you are subscribed to the Google Groups "v8-dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
