RE: [Nolug] Mac OS X to make an appearance at the next meeting.... maybe.

From: Ron Johnson <ron.l.johnson_at_cox.net>
Date: 04 Nov 2002 12:06:48 -0600
Message-Id: <1036433208.6349.14.camel@haggis>

On Mon, 2002-11-04 at 11:13, Dustin Puryear wrote:
> At 08:48 AM 11/4/2002 -0600, you wrote:
> >standard .omf files in and plays back video preview, while playing back
> >multiple tracks of audio.
> >
> >Yes, motorola chips for mac's are now 1.25 Gh (equivalent to about 1.5 Gh
> >intel and a bit lower AMD.) That is the top. Where as intel and AMD are but
> >going over 3 Gh already. (or by the end of the year) And very soon to 4 Gh.
>
> Let us not forget that the clock rate of a CPU is not the only indicator of
> how fast the chip can move. For example, I'm sure Scott and Hunter would
> jump once you said that a SPARC is inferior to an Intel chip based on a
> comparison of the clock rates. Or IBM's POWER series for that matter.

There comes a point where excessive MHz finally trumps architectural
inefficiencies. x86 has crossed that line, compared to the Mot PPC.

The PPC, POWER, Sparc & Alpha all excel at certain things. Vector
processing or floating point or ... For general work, though, x86
has trumped them, although at a heat penalty.

If I was going to make a screaming cluster and have unlimited money,
then I'd pony up for POWER4 or Alpha processors. Unfortunately,
I think I could get 2-3x as many nodes using x86, thus making it
go lots faster.

-- 
+------------------------------------------------------------+
| Ron Johnson, Jr.     mailto:ron.l.johnson@cox.net          |
| Jefferson, LA  USA   http://members.cox.net/ron.l.johnson  |
|                                                            |
| "they love our milk and honey, but preach about another    |
|  way of living"                                            |
|    Merle Haggard, "The Fighting Side Of Me"                |
+------------------------------------------------------------+
___________________
Nolug mailing list
nolug@nolug.org
Received on 11/04/02

This archive was generated by hypermail 2.2.0 : 12/19/08 EST