Message 380110 - Python tracker

➜

This issue tracker has been migrated to GitHub, and is currently read-only.
For more information, see the GitHub FAQs in the Python's Developer Guide.

Author	methane
Recipients	Marco Sulla, Mark.Shannon, methane, serhiy.storchaka
Date	2020-11-01.00:49:58
SpamBayes Score	-1.0
Marked as misclassified	Yes
Message-id	<1604191799.01.0.168375056406.issue41835@roundup.psfhosted.org>
In-reply-to

Content
> It should not be affected by the change. Anyway, I run the bench other 10 times, and the lowest value with the CPython code without the PR is not lower than 67.7 ns. With the PR, it reaches 53.5 ns. And I do not understand why. The benchmark is very affected by code placement. Even adding dead function affects speeds. Read vstinner's blog and presentation: * https://vstinner.github.io/journey-to-stable-benchmark-deadcode.html * https://speakerdeck.com/haypo/how-to-run-a-stable-benchmark?slide=9 That's why we recommend PGO+LTO build for benchmarking.

> It should *not* be affected by the change. Anyway, I run the bench other 10 times, and the lowest value with the CPython code without the PR is not lower than 67.7 ns. With the PR, it reaches 53.5 ns. And I do not understand why.

The benchmark is very affected by code placement.
Even adding dead function affects speeds. Read vstinner's blog and presentation:

* https://vstinner.github.io/journey-to-stable-benchmark-deadcode.html
* https://speakerdeck.com/haypo/how-to-run-a-stable-benchmark?slide=9

That's why we recommend PGO+LTO build for benchmarking.

History
Date	User	Action	Args
2020-11-01 00:49:59	methane	set	recipients: + methane, Mark.Shannon, serhiy.storchaka, Marco Sulla
2020-11-01 00:49:59	methane	set	messageid: <1604191799.01.0.168375056406.issue41835@roundup.psfhosted.org>
2020-11-01 00:49:59	methane	link	issue41835 messages
2020-11-01 00:49:58	methane	create