NetNews Usenet Archive 1992 #20/NN_1992_20.iso/spool/comp/arch/9395

Internet Message Format | 1992-09-13 | 1.7 KB

Xref: sparky comp.arch:9395 comp.lang.misc:3059
Newsgroups: comp.arch,comp.lang.misc
Path: sparky!uunet!munnari.oz.au!cs.mu.OZ.AU!munta.cs.mu.OZ.AU!fjh
From: [e-mail] (Fergus James HENDERSON)
Subject: Re: Goals, Cost, and Flexibility (was Re: "Training" of programmers)
Message-ID: <[e-mail]>
Sender: [e-mail]
Organization: Computer Science, University of Melbourne, Australia
References: <[e-mail]> <[e-mail]>     <[e-mail]> <[e-mail]> <[e-mail]>
Date: Sun, 13 Sep 1992 22:30:23 GMT
Lines: 20

[e-mail] (Jan Vorbrueggen) writes:

>Not quite that, but look at IBM's VM/HPO. A large part of the virtual machine
>assists and thus of VM is actually done in microcode, probably individually
>for every model series. Saving 25% or more of your 3090's processing power
>is certainly worth a few man year's microcoding slavery.

Well, that may not necessarily be the case.
If those few man-years of microcoding slavery mean that your product takes
six months longer to get to the market then it may not be worth the effort.
As the technology improves processing power is almost doubling every year,
so in those six months, your competition may well introduce a machine that
is 30-40% faster, so your +25% is now looking more like -5% or -10% (to
pluck a few figures out of the air).

--
Fergus Henderson             [e-mail]
This .signature virus is a self-referential statement that is true - but
you will only be able to consistently believe it if you copy it to your own
.signature file!