27 Jul
2023
27 Jul
'23
10:30 p.m.
On 7/26/23, Greg 'groggy' Lehey <grog(a)lemis.com> wrote:
That's not the way I remember it. RCA (and UNIVAC with them) and
Interdata had instruction sets that were close to the IBM instruction
set, but my recollection was that they were different enough that IBM
software wouldn't run on them. That's a different situation from
Amdahl, which was almost completely compatible.
As I recall it, the RCA Specra 70 was compatible with the IBM System
360 instruction set. It thus could run S/360 user applications. And
maybe OS/360? The downfall came with S/370. IBM withheld the
privileged portions of the architecture (including dynamic address
translation [DAT; virtual memory]) and so when OS/VS and DOS/VS came
out they wouldn't run on Spectra 70. RCA was forced to develop their
own OS. Over time key IBM applications such as CICS depended on new
features in OS/VS and DOS/VS. It wouldn't surprise me if many of
those dependencies were gratuitous. So RCA was stuck in an endless
cycle of having to add new (D)OS/VS features to their own OS. The big
IT customers who form this market valued stability more than the lower
price for the Spectra vs. S/370, and so RCA lost its market and
eventually gave up.
By the time Amdahl founded his own company, the privileged side of the
S/370 architecture had been revealed. The S/370 architecture allows
for a restricted set of model-dependent behavior and features in areas
such as control register semantics and machine check handling. The
Amdahl CPUs were no different from the S/370s as one model of S/370 is
from another. (D)OS/VS keeps this model-dependent code in separate
modules from the bulk of the OS. Amdahl only had to provide their own
set of model-dependent modules. A smaller--and tractable--task
compared to what had faced RCA and Interdata at the start of the S/370
era.
-Paul W.