Gil,
Just remember in the olden days that bytes cost money (either in
storage or in memory).
I actually had to work on a software set of programs (system) that
stripped the sign off of all dates and money they were assumed to be
positive).
Ed
On Mar 14, 2013, at 9:25 AM, Paul Gilmartin wrote:
On Wed, 13 Mar 2013 09:47:06 -0400, Gabe Goldberg wrote:
I'm writing about "Back to the Future" for mainframers -- historic
(but
sometimes forgotten) mainframe lessons needed by and best-to-be
learned
by new mainframers (but everyone, really).
Don't underestimate the future.
The Y2K "crisis" might have been mitigated if more designers
had said, "Hey, pretty soon we're going to need 4-digit years.
Let's provide them now." I made such a suggestion for a product
we were working on in 1987. It was brushed off as premature.
And much of the anguish of 24-bit to 31-bit address conversion
might have been avoided if designers had thought to reserve
the top 8 bits of addresses instead of using them for flags.
Instead, many OS interfaces remain 24-bit constrained.
How many programmers are still using 31-bit branch instructions
rather than 64 because z/OS doesn't support execution above
the bar? This year.
-- gil
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN
