GNU bug report logs - #22763
25.1.50; Feature Request -- A faster method to obtain line number at position.

Previous Next

Full log

Message #78 received at 22763 <at> debbugs.gnu.org (full text, mbox):

From: Lars Ingebrigtsen <larsi <at> gnus.org>
To: Eli Zaretskii <eliz <at> gnu.org>
Cc: 22763 <at> debbugs.gnu.org, esq <at> lawlist.com, monnier <at> iro.umontreal.ca
Subject: Re: bug#22763: 25.1.50; Feature Request -- A faster method to
 obtain line number at position.
Date: Sun, 07 Feb 2021 22:52:53 +0100

Eli Zaretskii <eliz <at> gnu.org> writes:

>> Perhaps memchr has gotten faster over the years?
>
> No, it was fast then as well (due to inlining, AFAIR).
>
> I think the main factor is the file used to benchmark this stuff.  I
> don't remember what I used.

I was curious as to how memchr is implemented these days:

https://code.woboq.org/userspace/glibc/string/memchr.c.html

It seems it tests one longword_ptr at a time?  So that's 8 bytes on
64-bit CPUs, I think.  Doesn't look like any SSE/AVX support, though.

-- 
(domestic pets only, the antidote for overdose, milk.)
   bloggy blog: http://lars.ingebrigtsen.no

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.