Re: The Design of Design

John Levine wrote:

According to Stephen Fuld <SFuld@alumni.cmu.edu.invalid>:

I do want to note that another factor in S/360's success was the
quality of the paper peripherals, expecially the 1401 printer, which
was a true marvel in its time.  IBM got that advantage from their
long experience with punch card business systems.

 
I presume you mean the 1403 which was indeed a great printer.  I
printed a lot of term papers on them.

Yes, 1403.  Sorry.

 

All the others, which were word or maybe decimal digit

addressed, died. ...

 

The Univac 1110 (circa 1972), (about a devcade before XA) had
banking, which allowed an instruction to address anywhere within a
262K (approximately 1 MB) "window" into what could be an "address
space" of about 4 GB.  It was a little awkward in that, while you
could have 4 of such "windows" available at any time, changing
windows required executing an, (unprivlidged) instruction.

 
There were a lot of segmented address schemes and as far as I can tell
nobody liked them except maybe the Burroughs machines where the
compilers made it largely invisible. The most famous was the 8086 and
286 but the PDP-10 extended addressing was sort of like that and even
the PDP-8 had a bit to say whether an address was to page 0 or the
current one.

The 1100 series scheme, which was called multi banking, wsn't exactly a
segment scheme, but the differences are subtle.  It certainly wan't a
clean as a single large adress space, but it did make certain things,
like shared libraries (common banks in 1100 terminology) very easy.
And it did eliminate the need for the BALR/Using stuff.  And it didn't
have the issue of having already used the upper bits that caused such
problems with IBM's XA transition.


My point is not that the 1100 scheme was better or worse than the S/360
scheme.  Each had benefits and drawbacks.  But it is that the S/360 CPU
architecture wasn't the only factor in its success.  Other factors,
like marketing and peripherals were a significan't, perhaps the major
factors.





--
 - Stephen Fuld
(e-mail address disguised to prevent spam)