DEC believed that DMA ("data break") was a
more
cost-effective solution than IBM-style intelligent
channels, going all the way back to the PDP-1 -- at
least that is the impression that I got from the
retrospective papers in "Computer Engineering: A DEC
View of Hardware Systems Design".
And DEC wondered why IBM (and just about every one elses) mainframes blew
them away in the I/O department. It seems to me that they could have made
the -10 line real mainframes (no, IBM and the BUNCH did not consider the
-10 line real) with just a little effort and not much money. Think of
it - the addition of say four -8 powered channels to -10 would have cost
maybe a couple thousand dollars (not much, considering the sticker price
of a -10), but would have put it in the same league as everyone else.
I probably need to read that book again (it has been years).
William Donzelli
aw288 at
osfn.org