I still like MIPS. I know, I'm getting old! I believe everything you say
about MIPS being meaningless or whatever, but I still think that if you are
looking at 3 or 4 models of CPUs, the MIPS rating gives you a good feel for
how fast they are, especially if they are all in the same processor group.
z/800 z/900 being one group, z890 z990 being a 2nd group etc. I would think
that if you compared a 100 MIPs machine with a 400 MIPS machine in the same
group, you should be able to get approximately 4 times the work out of the
400 MIPS machine. When I hear a box has so many MSUs, I still don't know
what that means until I look up the MIPS.
I know every time I go to an IBM presentation that contains new hardware,
they still either have MIPS charts in their presentation, or they mention
verbally how many MIPS the boxes are. I always thought that was kind of
strange with their emphasis on MSUs, but then I think they realize that the
term MIPS has been around much longer than MSUs, and most mainframe people
have been around a long time.
Eric Bielefeld
Sr. z/OS Systems Programmer
Milwaukee Wisconsin
414-475-7434
----- Original Message -----
From: "Alan Altmark" <[EMAIL PROTECTED]>
You are hitting on exactly why we don't publish MIPS any more. It simply
leads you down the proverbial garden path. You notice, too, we don't make
a big deal about the cycle rate (GHz), either. Both are pretty much
irrelevant in estimating the affect on your workload. And each generation
of processors changes the mix of silicon, microcode, and millicode so you
can't really depend on knowing how many cycles an instruction takes. Add
pipelining into the mix and it gets worse
.> Alan Altmark
z/VM Development
IBM Endicott
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
