On Dec 30, 2007, at 7:58 PM, Shmuel Metz (Seymour J.) wrote:
In <[EMAIL PROTECTED]>, on 12/27/2007
at 09:53 PM, Ed Gould <[EMAIL PROTECTED]> said:
I could be wrong but I think he is talking about the "undocumented"
"option codes" that a diagnose could *really* do.
There may be many such on current processors, but can you cite any
in the
1960's?
Shmuel:
Its been a LONG time... But IIRC the 360/30 POPS had at least some
of them (I presume not all). I ran across them by accident. When I
was helping to optimize someone else's code on the 1419 . The damn
machine had a timing issue and you had to make a pocket selection
decision in x many micro seconds (the micro seconds is a guess) I
have forgotten what the time was . The book actually had
instruction timing specifics for each instruction.
Ed
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
