Re: Address bits again, Article on new mainframe use

John Levine <johnl@taugh.com> schrieb:

It is true that the -11 died for lack of address space, but nobody I
know has ever come up with a good design where the address size is
bigger than the word size.  You end up with segments as on the 286
or bank switching which is what later -11's did.

What about the 6502?  That was very much a 8-bit CPU, but
cleverly used its zero page as index registers.  Or all the other
8-bit CPUs, which usually had 16-bit address registers.

People could have built CPUs with 16-bit accumulators and 32-bit
addresses (or 8-bit accumulators and 32-bit addresses).  It is
debatable if these would have counted as a good design, though.

VAX stood for Virtual Address Extension.  The key improvement was the
32 bit addresses.  Everything else was a detail.  Some of those details
were unfortunate but that's a different argument.
>
Also don't forget that back in that era everyone who had disks used
overlays. The IBM mainframe linkers had complicated ways to build
overlays and squeeze programs into 64K or whatever.

Overuse of overlays almost sank OS/360.  Brooks recounts that,
on a high-end machine, the FORTRAN compiler would have compiled
only a few lines per minute.  It was caught in time by simulation.

But the MVS linker was slooooooooooow.  I remember waiting for fifteen
to 30 minutes of wall time for a link step to complete, on a much
later model.

Even though the
address space was 16MB it was a long time before machines had that much
RAM and by then they'd added paging to make the physical memory size less
relevant.

Browsing through Wikipedia, it seems the biggest memory on a /360
was 6 MB.