28 Oct
2010
28 Oct
'10
11:42 a.m.
On 2010 Oct 28, at 10:51 AM, Chuck Guzis wrote:
On 28 Oct 2010 at 13:20, William Donzelli wrote:
How about the notion that the PDP-11 was where several prior but
then-topical innovations coalesced into one machine/architecture?
The VAX was riding on the coattails of the market success of the -11
and provided existing PDP-11 installations with increasing demands with
a way forward, and it grew from there. That's a bit of a tautology, but
it is to say it did exactly what it was designed and marketed for.
On the topic of memory, I would agree with Johnny about "virtual
addresses", but differ on "virtual memory": virtual memory to me has
always meant demand-paging where the RAM address-space seen by the user
can be larger than the physical RAM, distinct from the simple mapping
of addresses, but the use of the term is a matter of definition.
I was initially thinking about just the hardware
architecture when the
machines were being designed, not the software aspect, nor what the
machines did (or influenced) after they were released. The
aforementioned memory mapped I/O, for example.
Not to be too much of a wet blanket, but how many of those DEC-unique
innovations (even if you manage to assert that they originated with
DEC) persist in today's hardware? Do modern PCs use memory-mapped
I/O? The 68K, but for some Freescale relics, is history.
Major innovations, such as virtual memory and orthogonal instruction
sets and hardware-implemented stacks preceded the PDP-11. Perhaps the major contribution of the PDP-11 and VAX
was that they
were comparatively cheap for the processing power.
.. the right product, at the right time, at the right price, from an
established and reliable manufacturer/source.