Date: Sun, 21 Mar 1999 21:21:52 -0700 From: Wes Peters <wes@softweyr.com> To: Mike Smith <mike@smith.net.au> Cc: Dennis <dennis@etinc.com>, Amancio Hasty <hasty@rah.star-gate.com>, hackers@FreeBSD.ORG Subject: Re: Gigabit ethernet -- what am I doing wrong? Message-ID: <36F5C560.462546F4@softweyr.com> References: <199903220200.SAA02330@dingo.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Mike Smith wrote:
>
> > At 12:13 PM 3/21/99 -0800, you wrote:
> > >
> > >Hmm....
> > >Does anyone know when the faster PCI busses (64bits or 66MHz PCI clock rate)
> > >are going to be availabe ?
> >
> > The "availability" of 66Mhz busses is almost moot. Making ASICs work at 33mhz
> > is a chore....66mhz is a waze off.
>
> That's close, but several of the major ASIC vendors were (or were
> claiming to be) sampling devices with 66MHz PCI macrocells the last time
> I looked.
I guess our 80 Mhz ASICs are a bit of an oddity then?
> > And as far a 64 bit busses.....there
> > arent many
> > processors that can do is, and doubling the bandwidth on a 32bit processor
> > isnt
> > always linear in performance. You have to get a whole new generation of
> > processors before you will see any usable products.
>
> This has nothing whatever to do with reality, however. Most PCI
> peripherals are bus masters, and most memory busses these days are at
> least 64 bits wide, so 64 bit PCI has very real performance benefits.
>
> The processor's internal word size has little or nothing to do with the
> equation.
Especially when the processor doesn't get particularly involved in the
process, like in the case of sendfile().
--
"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?36F5C560.462546F4>