Comment #10 on issue 3903 by [email protected]: Math.log10 is unexpectedly
slow
https://code.google.com/p/v8/issues/detail?id=3903
Interesting, thanks for the links. (will have to go through the test cases
later)
I added the JS log to my microbenchmark and it came in at 221759 ms, even
with the reciprocal estimate. (OSX/Haswell) So, introduces some new
confounding factors.
I modified the reinterpret-cast functions to avoid typed array creation and
just reuse a global. The time dropped to 25721 ms, about an order of
magnitude difference.
I'm not sure if it's possible to avoid the typed array creation costs as a
threadsafe global function or not.
--
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.
