Thanks, Mark!
That's a wonderful find, and it disproved my theory. :P
I looked a bit closer: the tasks look a lot like BLISS-11 (the register-save helpers are
byte-identical to its SAVREG.MAC), yet the code isn't quite BLISS-11, so I suspect it
could have been BLISS-16 -- which, as far as I can tell, was never recovered.