[ih] vm vs. memory

Brian E Carpenter brian.e.carpenter at gmail.com
Tue Oct 24 15:00:39 PDT 2017


On 25/10/2017 10:11, John Levine wrote:
> In article <593e3d78-5af7-e30b-a1ae-ad875ddee643 at gmail.com> you write:
>> I disagree with that evaluation. It started in practice with the
>> famous "one-level storage system" paper from Manchester**, with the
>> specific goal of making a small high-speed memory look like a much
>> larger one. I don't think it was viewed as a work-around, but rather
>> as a brilliant engineering solution to the high cost of high-speed
>> memory, vastly easier to use than explicit overlays.
> 
> But it was a workaround, albeit a much nicer one than explicit
> overlays (this I know, having done digital origami with overlay
> loaders.)  What they really wanted in both cases was enough RAM to run
> the program.  Since they didn't, they had various kludges to fake it.
> 
> VM stopped being a workaround when people realized that you could use
> the same hardware to unify RAM and disk files.  

But that's exactly what ATLAS did. The one-level paper goes into
a lot of detail about the ATLAS o/s, and when you wrote code in
Atlas Autocode you simply didn't know that there was both core
and disk memory. (Atlas Autocode was my first real programming
language, ignoring a brief flurry with Titan Autocode).

> It didn't take long,
> Multics was doing that by 1966 and TSS/360 (badly) in 1967.

Yes, Multics did it really nicely. And then we got Peter Denning's
original paper on working sets (http://denninginstitute.com/pjd/PUBS/Workingsets.html ).
In the third paper on that page, Denning says this:

In 1961 the group at Manchester, England,
published a proposal for a one-level
store on the Atlas computer [F3, K3], a
proposal that has had profound influence
on computer System architecture. Their
idea, known now as virtual memory, gives
the programmer the illusion that he has a
very large main memory at his disposal,
even though the computer actually has a
relatively small main memory. At the heart
of their idea is the notion that "address"
is a concept distinct from "physical location."

  Brian



More information about the Internet-history mailing list