-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Corroborate early unic-datetime
measurement results
#1
Comments
To perform the measurements on this crate:
|
OK, worked after the setup with the I got:
Does this help you any? |
Can you try with intl-measurements to compare to your results for ICU?
|
ICU bit, working on the rest. Looks like there is quite a bit of startup overhead on my machine, so you may want to account for that . Also, it remains quite a bit slower for this workload than what you have.
|
Next.
|
Last bit:
|
HTH |
Yep, so your results seem to be:
That seems to reproduce my performance differences. Next it would be good to investigate why is Rust version so much faster. |
@sffc ? @srl295? @FrankYFTang? thoughts? |
quick gprof report --- don't read too much into it, I had to change the initial code and compilation results.
|
On Friday I left one bit of code commented out that impacts performance. I now removed obsolete attempts to layout data and re-added ability to test inline. It's still not the final data model (we need Options to handle missing data), but the current results I see are: ICU: 849 us |
I think the code should be very comparable for profiling. |
Continuing from unicode-org/rust-discuss#13, so that we keep rust-discuss a high-level discussion.
The text was updated successfully, but these errors were encountered: