Repository navigation
Faster code for trial quotient in x_divrem #90662
Description
| BPO | 46504 |
|---|---|
| Nosy | @tim-one, @gpshead, @mdickinson |
| PRs |
Note: these values reflect the state of the issue at the time it was migrated and might not reflect the current state.
Show more details
GitHub fields:
assignee = 'https://github.com/tim-one'
closed_at = <Date 2022-01-25.01:07:14.086>
created_at = <Date 2022-01-24.18:46:28.769>
labels = ['interpreter-core', '3.11', 'performance']
title = 'Faster code for trial quotient in x_divrem'
updated_at = <Date 2022-01-25.01:07:14.086>
user = 'https://github.com/tim-one'bugs.python.org fields:
activity = <Date 2022-01-25.01:07:14.086>
actor = 'tim.peters'
assignee = 'tim.peters'
closed = True
closed_date = <Date 2022-01-25.01:07:14.086>
closer = 'tim.peters'
components = ['Interpreter Core']
creation = <Date 2022-01-24.18:46:28.769>
creator = 'tim.peters'
dependencies = []
files = []
hgrepos = []
issue_num = 46504
keywords = ['patch']
message_count = 2.0
messages = ['411505', '411542']
nosy_count = 3.0
nosy_names = ['tim.peters', 'gregory.p.smith', 'mark.dickinson']
pr_nums = ['30856']
priority = 'normal'
resolution = 'fixed'
stage = 'resolved'
status = 'closed'
superseder = None
type = 'performance'
url = 'https://bugs.python.org/issue46504'
versions = ['Python 3.11']
Activity
tim-one commentedon Jan 24, 2022
x_divrem1() was recently (bpo-46406) changed to generate faster code for division, essentially nudging optimizing compilers into recognizing that modern processors compute the quotient and remainder with a single machine instruction.
The same can be done for x_divrem(), although it's less valuable there because the HW division generally accounts for a much smaller percent of its total runtime.
Still, it does cut a multiply and subtract out of the loop, and makes the code more obvious (since it brings x_divrem1() and x_divrem() back into synch).
tim-one commentedon Jan 25, 2022
New changeset 7c26472 by Tim Peters in branch 'main':
bpo-46504: faster code for trial quotient in x_divrem() (GH-30856)
7c26472