Subject: Re: x86 Port outperforms SPARC64 port on NetBSD v2.0.2
To: None <port-sparc64@netbsd.org>
From: James Cornell <unixpenguin2004@earthlink.net>
List: port-sparc64
Date: 10/09/2005 20:44:34
I'm selling my Ultra 2 workstation for under 100 dollars plus s&h.  It has 2 400mhz ultrasparc II's.  I also have lots of extras included, such as the original 200mhz ultras and some disks that need disklabling for use with Solaris.

-----Original Message-----
From: Chris Fuhrman <cfuhrman@gmail.com>
Sent: Oct 5, 2005 8:58 AM
To: David Brownlee <abs@netbsd.org>
Cc: John Nemeth <jnemeth@victoria.tc.ca>, Timo Schoeler <timo.schoeler@riscworks.net>, Philip Jensen <phil_jensen@yahoo.com>, port-sparc64@netbsd.org
Subject: Re: x86 Port outperforms SPARC64 port on NetBSD v2.0.2

On 10/5/05, David Brownlee <abs@netbsd.org> wrote:
>
>
> Not on an SS2, or any sun4/sun4c machine. Compiler optimisation
> for sun4m and later can win because they support hardware
> multiply, so replacing your SS{1,1+,2} with an SS{4,5,10,20} would
> really help ssh.


I can agree with that. I've also run OpenBSD & NetBSD on a SS5 I had. The
speedup was considerable. I currently have an Ultra 1 Enterprise that's used
for the oddjob. Even with a compilation job going, it only took about 5
seconds to log into the box.

One of these days I'd love to see what an Ultra 2 could do. An E450 with 2
400 MHz CPUs running Solaris 9 took 2 seconds to log in. This is under
Solaris 9 using Sun's SSH.

> vtn1% time ssh vifa2 id
> > jnemeth@vifa2's password:
> > uid=139(jnemeth) gid=10(staff) groups=10(staff),0(wheel)
> > 0.0u 0.0s 0:27 0% 0+0k 0+0io 0pf+0w


Ouch.
--
Chris Fuhrman
cfuhrman@gmail.com