🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: net.arch
Article #2589

Re: AT&T MIPS claim

#2589
From: Rex Ballard
Date: Fri, 06 Jun 1986 14:45
46 lines
3127 bytes
In article <266@comm.UUCP> dave@comm.UUCP (Dave Brownell) writes:
>In article <577@scirtp.UUCP> dfh@scirtp.UUCP (David F. Hinnant) writes:
>> ...  They made this interesting claim that the UNIX PC gives
>> you "75% of the power of a VAX 11/780" for "only 7% of the cost".
>> Arrgh.  ...  Is this the MIP rating for the
>> 68010 as compared to the VAX?  Looks like it.  One really couldn't ask
>> for a better example of the Meaningless Index of Performance.  I've seen
>> many a 780 run with more than 20 users.  I'd like to see you put that
>> many on a UNIX PC that I found can barely support one.
>
>This is Apples and Oranges ... a MIP, however meaningless, is a CPU benchmark,
>and a "user" is a rather ill-defined I/O benchmark ... and I do believe
>the I/O on the 7300 is not up to the CPU.  Maybe when someone comes up
>with a realistic I/O benchmark we can really start comparing UNIX hardware.
>(Yes, that marketing claim is absurd.)

You can say that again, I've been enhancing an 8085 box that supports
16 users :-).

What types of support, I/O, and terminals is each supporting?
Is the UNIX PC running bit-mapped video?  Is the VAX driving relatively
smart terminals (VT-100,VT-52,Tektronix,...)?  Are the VAX terminals
connected at 9600 baud?  What types of "Demand Paging" are on the
PC?. How do the disk drives compare?

There are specific applications where "user response time" is an
important factor, and MIPs take a "back seat".  We sell a system
that supports 1000 searches/second on 1 million listings, but
you wouldn't believe the hardware/software that does this.

We also sell a 68012 configuration rated nominally at 2x780, and
some brief exposures to it leave me a believer, but in the "32 user
mode", there is a lot of smarts required by the "Terminals".

A VAX with 20 VT-100's on it, is really running about 6 MIPS,
if you include the CPU power of each of the VT-100's.  A 5/32
with 32 "PowerTerminals" is running about 18 MIPS.  You just don't
look at the MIPS of the terminals, because you don't "Program" them.
In fact, they run at least an ANSI 3.64 interpreter!  The "PT's"
actually run much of the editing functions right on the terminal.

Conversely,  a VAX running bit-mapped graphics and video to
each user would likely "come to it's knees" with fewer than
4 users, if EVERYTHING had to be "painted" on the screen.

MIPs are great.  You can distribute them any way you want?
Technical Details
Message-ID: <448@ccird1.UUCP>
Path: arc1-ca.pugleaf.net!utzoo!watmath!clyde!burl!ulysses!allegra!princeton!caip!lll-crg!seismo!rochester!ritcv!cci632!ccird1!rb
References: <577@scirtp.UUCP> <266@comm.UUCP>

Show Full Headers
Complete Article Headers
Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: arc1-ca.pugleaf.net!utzoo!watmath!clyde!burl!ulysses!allegra!princeton!caip!lll-crg!seismo!rochester!ritcv!cci632!ccird1!rb
From: rb@ccird1.UUCP (Rex Ballard)
Newsgroups: net.arch,net.micro.att
Subject: Re: AT&T MIPS claim
Message-ID: <448@ccird1.UUCP>
Date: Fri, 6-Jun-86 10:45:43 EDT
Article-I.D.: ccird1.448
Posted: Fri Jun  6 10:45:43 1986
Date-Received: Sun, 8-Jun-86 04:15:17 EDT
References: <577@scirtp.UUCP> <266@comm.UUCP>
Reply-To: rb@ccird1.UUCP (Rex Ballard)
Distribution: net
Organization: CCI Rochester Development, Rochester NY
Lines: 46
Summary: Users/system, when it counts, when it doesn't.