LISTSERV - HP3000-L Archives

HP3000-L Archives

February 2003, Week 4

HP3000-L@RAVEN.UTC.EDU

	LISTSERV Archives
	HP3000-L Home
	HP3000-L February 2003, Week 4

	Log In
	Register

	Subscribe or Unsubscribe

	Search Archives

Options:	Use Monospaced Font Show Text Part by Default Show All Mail Headers
Message:	[<< First] [< Prev] [Next >] [Last >>]
Topic:	[<< First] [< Prev] [Next >] [Last >>]
Author:	[<< First] [< Prev] [Next >] [Last >>]

Subject:	Re: N-class - two others
From:	Neil Harvey <[log in to unmask]>
Reply To:	Neil Harvey <[log in to unmask]>
Date:	Thu, 27 Feb 2003 08:35:54 +0200
Content-Type:	text/plain
Parts/Attachments:	text/plain (99 lines)

Thanks to Stan and Allegro for Mipstest.

Remember that it's not just the CPU that suffers - the entire IO is
adversely affected by the extremely crude crippling method.


======================================================================
@(#) MIPSTEST 2002-08-22
Copyright (c) 2002  Allegro Consultants, Inc.     www.allegro.com
HPCPUNAME = SERIES e3000/N4000-100-22

raw MIPS =  210; MIPS scaled by ticks/instr = 437.8; (#i = 10000000)

Note: appears to be a crippled CPU system.

Determining max burp size...

Max burp size about = 383 microsecs (167076 ticks)
raw MIPS =  465; MIPS scaled by ticks/instr = 436.0; (#i =   178178)

Uncrippling would speed the CPU by a factor of    3.4


Attempting to determine length of CPU loss (blink)...
blink ticks:   mean =  222122 ticks


Attempting to determine length of CPU use (burp)...
burp ticks:    mean =  228490 ticks
======================================================================
@(#) MIPSTEST 2002-08-22
Copyright (c) 2002  Allegro Consultants, Inc.     www.allegro.com
HPCPUNAME = SERIES e3000/N4000-100-33

raw MIPS =  317; MIPS scaled by ticks/instr = 439.4; (#i = 10000000)

Note: appears to be a crippled CPU system.

Determining max burp size...
raw MIPS =  339; MIPS scaled by ticks/instr = 439.7; (#i = 10000000)

Max burp size about = 3692 microsecs (1622169 ticks)
raw MIPS =  361; MIPS scaled by ticks/instr = 438.7; (#i =  1334838)
raw MIPS =  370; MIPS scaled by ticks/instr = 438.3; (#i =  1001128)
raw MIPS =  378; MIPS scaled by ticks/instr = 437.3; (#i =   563134)
raw MIPS =  465; MIPS scaled by ticks/instr = 436.0; (#i =   316762)

Uncrippling would speed the CPU by a factor of    1.4


Attempting to determine length of CPU loss (blink)...
blink ticks:   mean =  123579 ticks


Attempting to determine length of CPU use (burp)...
burp ticks:    mean =  327036 ticks
========================================================================
====


-----Original Message-----
From: Neil Harvey 
Sent: 27 February 2003 08:22 AM
To: [log in to unmask]
Subject: Re: N-class


@(#) MIPSTEST 2002-08-22
Copyright (c) 2002  Allegro Consultants, Inc.     www.allegro.com
HPCPUNAME =3D SERIES e3000/N4000-200-44

raw MIPS =3D  460; MIPS scaled by ticks/instr =3D 345.4; (#i =3D =
10000000)


-----Original Message-----
From: KENT WALLACE [mailto:[log in to unmask]]=20
Sent: 26 February 2003 09:19 PM
To: [log in to unmask]
Subject: N-class


We have been on the N-Class 220 since last August.  We have been very =
=3D impressed with the speed.=3D20

The 220 is a slowed down 440.  I wonder what the 440 will do?

Kent Wallace
Boise, Id

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

ATOM RSS1 RSS2

RAVEN.UTC.EDU