Date: Thu, 14 Jan 1999 22:56:26 -0700 From: Wes Peters <wes@softweyr.com> To: Jason Thorpe <thorpej@nas.nasa.gov> Cc: Matthew Dillon <dillon@apollo.backplane.com>, "Robert V. Baron" <rvb@cs.cmu.edu>, "Ron G. Minnich" <rminnich@Sarnoff.COM>, zhihuizhang <bf20761@binghamton.edu>, hackers <freebsd-hackers@FreeBSD.ORG> Subject: Re: TSS and context switch Message-ID: <369ED88A.873515B3@softweyr.com> References: <199901150436.UAA08145@lestat.nas.nasa.gov>
next in thread | previous in thread | raw e-mail | index | archive | help
Jason Thorpe wrote:
>
> On Thu, 14 Jan 1999 20:08:32 -0800 (PST)
> Matthew Dillon <dillon@apollo.backplane.com> wrote:
>
> > There are a number of intel instructions which were designed to
> > run fast on a 486, which turn out to be dogs on higher-end cpu's.
> > For example, the ENTER instruction is considerably slower then
> > doing the frame pointer / stack pointer manipulation manually.
> >
> > There are many others.
>
> I distinctly remember there being several instructions on the VAX that
> were like this (perhaps the polynomial evaluation instructions.. it's
> been a while :-) ... you were better off open-coding them than using
> the single instruction :-)
ALL of the instructions on the VAX were like this, and some sucked even
worse. ;^)
Intel's history in this area dates all the way back to the 286 and
PUSHA instruction, which was generally much slower than just pushing
the registers you were going to diddle. Too bad they never grokked
the concept of movem, huh?
--
"Where am I, and what am I doing in this handbasket?"
Wes Peters Softweyr LLC
http://www.softweyr.com/~softweyr wes@softweyr.com
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?369ED88A.873515B3>