[inforoots] bits again

[Van Snyder]

On Tue, 2006-11-28 at 09:04 -0800, Michael Albaugh wrote:
> Our own 1401 has the interesting
> optional feature that _any_ transfer of control can be a subroutine
> jump.

It's not clear to me whether the read-and-branch etc., stacker-select-
and-branch, or carriage-control-and-branch instructions leave NSI in the
B-address register.  It would be useful to test these, and then make
sure simh works the same way as the hardware.  I might have asked Heinz
to run these tests at CHM, but if I did, I can't find his reply right
now.  I think I did determine that branch-if-word-mark-or-zone does
leave NSI in the B-address register.  I'm certain that all the "B" op-
code branches leave NSI in the B-address register (if they branch).  I
guess we'll never be able to check branch-if-bit-equal.

-- 
Van Snyder                    |  What fraction of Americans believe 
Van.Snyder at jpl.nasa.gov       |  Wrestling is real and NASA is fake?
Any alleged opinions are my own and have not been approved or
disapproved by JPL, CalTech, NASA, the President, or anybody else.