➜

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 scoder
Recipients lukasz.langa, mark.dickinson, pitrou, rhettinger, scoder, serhiy.storchaka, steven.daprano
Date 2018-08-12.12:36:17
SpamBayes Score -1.0
Marked as misclassified Yes
Message-id <1534077377.67.0.56676864532.issue24076@psf.upfronthosting.co.za>
In-reply-to
Content 
FWIW, a PGO build of Py3.7 is now about 20% *faster* here than my Ubuntu 16/04 system Python 2.7, and for some (probably unrelated) reason, the system Python 3.5 is another 2% faster on my side.

IMHO, the only other thing that seems obvious to try would be to inline the unpacking of single digit PyLongs into sum(). I attached a simple patch that does that, in case someone wants to test it out. For non-PGO builds, it's about 17% faster for me. Didn't take the time to benchmark PGO builds with it.
History
Date User Action Args
2018-08-12 12:36:17scodersetrecipients: + scoder, rhettinger, mark.dickinson, pitrou, steven.daprano, lukasz.langa, serhiy.storchaka
2018-08-12 12:36:17scodersetmessageid: <1534077377.67.0.56676864532.issue24076@psf.upfronthosting.co.za>
2018-08-12 12:36:17scoderlinkissue24076 messages
2018-08-12 12:36:17scodercreate