Nick Maclaren said:
Believe it or not, the answer was/is often "yes"! Seriously.
OK, I will accept that as your opinion, though I disagree with the
implications. (see below)
The distinction was and is very often whether a development environment
is an essential component.
I don't understand what you are saying here. For IBM mainframes, they have
COBOL compilers, test data generators, interactive editors, profilers, code
repository systems, etc. Some or all of these ar used by the aformentioned
hypothetical COBOL programmer. It is hard to see how they could do their
job without them.
This confusion is one of the many reasons
that IBM and others never went over to a pure business/commercial
product line.
They dropped the vector facility that they used to have for S/370. They
still have binary floating point (indeed, I think it is now standard), but
that is required to meet IBM's strong committment to legacy code, and
doesn't cost much. I think they have pretty much dropped support for the
scientific programming library and program products like linear programming.
It appears that S/390 is essentially a commercial server/commercial
applications processor.
There was more dependence of that on the supposedly
scientific/technical line than the executive suits realised.
Sometimes, as with IBM's PS/2, SAA etc., there is an attempt to set
up a special category of development systems for commercial codes,
but they normally fold very fast, as the market is much smaller than
even the academic programming one. For reasons given in the next
paragraph ....
Both did, however, lead to the catastropic state of affairs where there
may be no debugging facilities whatsoever on the systems that actually
run the 'developed' codes so that, when they bomb out in the field,
the official - and correct - response is that no assistance can
be given unless the customer develops a test that can repeat the
failure on the development system (which may not be marketed).
So your claim is that debugging facilities were developed exclusivly for
scientific/technical environments and any use by commercial programmers was
a "happy accident"? I find that an odd belief, especially from a company
whoose middle name is "Business".
Perhaps we have a different definition of a commercial environment and of
development tools. I regard a typical commercial environment as say a bank
where the programmers write COBOL programs using such environmental tools as
CICS and DB2 (or their equivalents from other vendors) to accomplish the
primary business of the bank (managing accounts). The tools, such as the
ones I mentioned above, support that.
Been there - beat my head against that :-(
I don't doubt your experience, but mine is different in that the major
vendors (in my case more experience with Univac/Sperry than IBM, but IBM as
well) were fairly responsive when it seemed that the problem was theirs and
not ours. We could sometimes elevate serious problems to the point where
"the skys were filled with airplanes" carrying vendor support people to our
site.
