1GHz PDP-11 (Re: Prints for an 11/70)

From: Richard Erlacher <edick_at_idcomm.com>
Date: Thu Dec 13 00:15:45 2001

I've always favored hot-rodding. Something like this might be both interesting
and useful.

If someone actually has complete documentation, not just a part of it, perhaps
that includes all the logic to operate the bus. However, I don't remember ever
hearing about a signaling protocol on the UNIBUS that would allow the devices to
determine the speed at which such operations would take place. However, DEC was
prone to use closed-loop signaling, so the rate was dependent on the execution
of a precisely defined handshake. If you can manage that, the bus interface
should be straightforward enough. That should allow mixing of devices of
various speeds, so long as they adhere, absolutely, to the signaling protocol
and there's a timer somewhere in the system that aborts a bus transaction when
it takes too long.

Dick
----- Original Message -----
From: "Jeffrey S. Sharp" <jss_at_subatomix.com>
To: <classiccmp_at_classiccmp.org>
Sent: Wednesday, December 12, 2001 10:46 PM
Subject: Re: 1GHz PDP-11 (Re: Prints for an 11/70)


> On Thu, 13 Dec 2001, Greg Ewing wrote:
>
> > Boatman on the River of Suck <vance_at_ikickass.org>:
> >
> > > And exactly how would you speak to UNIBUS?
> >
> > At that speed, very slowly with pauses betweeen the words. :-)
>
> DUMMY MODE ON
>
> What little I've read about UNIBUS told me that UNIBUS has no set clock
> rate, and that the speed of communication between two devices would be the
> the highest rate that both devices could handle. If you've got nothing
> but Sridhar-made fast devices on the bus, what stops you from having a
> UNIBUS operating at say, 33MHz to 100MHz on average?
>
> Remember that I currently have approximately zero electrical engineering
> (or whatever you choose to call it) knowledge.
>
> DUMMY MODE OFF
>
> --
> Jeffrey S. Sharp
> jss_at_subatomix.com
>
>
Received on Thu Dec 13 2001 - 00:15:45 GMT