Date: Thu, 4 Jun 1998 13:48:40 +0200 From: Eivind Eklund <eivind@yes.no> To: Mike Smith <mike@smith.net.au>, Donn Miller <dmm125@bellatlantic.net> Cc: "John S. Dyson" <dyson@FreeBSD.ORG>, hackers@FreeBSD.ORG Subject: Re: Recompiling sources with "-O2 -m486 -pipe" Message-ID: <19980604134839.09175@follo.net> In-Reply-To: <199806040546.WAA00663@antipodes.cdrom.com>; from Mike Smith on Wed, Jun 03, 1998 at 10:46:28PM -0700 References: <Pine.NEB.3.96.980604011707.720A-100000@myname.my.domain> <199806040546.WAA00663@antipodes.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Jun 03, 1998 at 10:46:28PM -0700, Mike Smith wrote:
> > Some postings in DejaNews claim that the -mno-486 runs faster on a Pentium
> > (than -m486). Other postings say just the opposite.
>
> -m486 optimises alignment for the '486 by padding. On the Pentium and
> above alignment is not so significant,
This is a very, very interesting statement. Unfortunately, it is also
false.
The _only_ thing I've found that affect PPro timing much is
alignement, and alignment of inner loops can make a 50% speed
difference. It caused me a lot of hassle until I found out about it
("Why the **** does changing that instruction, which is 20
instructions before the main loop, speed up things by 30%?")
> and the padding wastes space in the cache and time for fetching and
> discarding. Unless you intend to only run on a 486, it is generally
> wrong to use it.
What does it align to? PPro want alignment of the start of inner
loops on a 16-byte boundary, IIRC...
Eivind.
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980604134839.09175>