yet another pdp-11 in fgpa

allison ajp166 at verizon.net
Wed Jun 30 13:46:08 CDT 2010


On 06/30/2010 11:27 AM, Johnny Billquist wrote:
> "Shoppa, Tim" <tshoppa at wmata.com> wrote:
>
>> "Walter F.J. Mueller" <w.f.j.mueller at gsi.de> wrote:
>>>> Johnny Billquist <bqt at softjar.se> wrote:
>>>> > I wasn't aware that any prototypes ever were produced and came as
>>>> > far as being functional. I thought it was just paper work that
>>>> > had bee done.
>>>>
>>>> The 11/74 wasn't marketed, as pointed out in this thread, but a
>>>> few systems were build by DEC. A picture of such 11/74 system
>>>> was made available by Tim Shoppa, see
>>>>
>>>>    http://www.trailing-edge.com/~shoppa/1174Xopen.jpg
>>>>
>>>> You'll nicely see the four CPUs.
>>
>>> Yes, I know of these systems. However, that is not an 11/74 on that 
>>> picture, but an 11/70mP. There is a difference...
>>> As pointed out, the 11/70mP was marketed as an 11/74, but it's a 
>>> different CPU.
>>
>>> The easiest way to see that this is a picture of an 11/70mP is by 
>>> looking at the lower rotary switch, which only have four positions, 
>>> and not eight (which the 11/74 have). So no CIS on this machine.
>>
>>> The only 11/74 picture I've seen so far is the silk screen panel 
>>> picture posted a few days ago. Unfortunately I've already forgotten 
>>> the name (I'm lousy with names, sorry) of the person who posted it, 
>>> and who also worked on the 11/74 CIS microcode.
>>
>>> The machine on that picture is probably CASTOR:: by the way.
>>
>> The people who work with/maintain CASTOR:: call it a 11/74, FWIW.
>
> Yes, I know.
> I'll reply to this one last time, and then I'll give up.
>
> Don North reported that he had been a part of the team that had 
> written the CIS microcode for the 11/74 CPU.
>
> I commented that I thought the 11/74 CPU had only been a paper product.
>
> Don North also pointed out that marketing "stole" the 11/74 moniker 
> for the 11/70mP system.
>
> Now, throughout this discussion, we need some way of separating what 
> we are talking about. DEC internal project papers seems like a good 
> start.
> There we have the 11/70mP, which is a modified 11/70 with just the 
> addition of the ASRB cache bypass and memory interlock, as well as the 
> cache bypass bit in the PDR, and a cache bypass bit and flush control 
> in the cache control CSR.
> The 11/74 is a total redesign of the 11/70 CPU, with the same 
> modifications as the 11/70mP, but also the addition of the CIS, 
> removal of one Massbus, and redesign of a whole bunch of CPU boards, 
> including removing one clock signal not used, and the addition of new 
> clock signals and control signals required by the CIS.
>
> I'm only talking CPUs here, not systems.
>
> Another way to name them would perhaps be:
>
> KB11-B    - Old 11/70 CPU with synch FPP.
> KB11-C    - New 11/70 CPU with asynch FPP.
> KB11-CM   - MP modified KB11-C
> KB11-E(?) - The new 11/74 CPU with asynch FPP and CIS.
>
> I seem to remember reading somewhere that the 11/74 CPU were to be 
> called KB11-E, but I also have this nagging feeling that KB11-E might 
> have been the 11/44, or possibly the 11/60.
>
> Now, as I myself pointed out, RSX regards the 11/70mP as an 11/74, and 
> that is also what the CPU identification code in RSX calls it.
>
> But if we call this an 11/74, what shall we call the 11/70 with CIS?
>
> So, for the purpose of this thread, I decided to go with Don Norths 
> naming, and call the 11/70 modified for multiprocessor operations the 
> 11/70mP. If you look at the picture on your site, Tim, you'll also 
> notice that the text on the front panel actually says something like 
> "PDP-11/74 MP". (Not sure about the /74, but you definitely see the 
> "MP" part. (http://www.trailing-edge.com/~shoppa/1174Xopen.jpg)
>
> Now, compare that to Don Norths picture of the 11/74 front panel: 
> http://www.ak6dn.com/stuff/1174.jpg.
>
>> They never used the term "11/70mP" in front of me for sure. I would 
>> occasionally elicit comments about multiprocessing on 73's or 93's 
>> but it always came back to "our 11/74 does it THIS WAY" because that 
>> was the working example.
>
> I'm not disagreeing with you, Tim. I'm just trying to point out that 
> we have two different CPUs here, one of which I thought was never 
> made, but Don actually claims that it did exist, even if just as one 
> prototype.
>
> The system was called an 11/74 everywhere, but for the purpose of this 
> discussion, we need to make a distinction between the CPUs.
>
>> I'm not saying that "11/70mP" is wrong, indeed it's used in some of 
>> the drawings and memos to describe what was commonly called the 11/74.
>
> Yes.
>
>> CIS was real important to some DECcies circa late 70's for some Cobol 
>> requirement but coming from the real-time side none of us ever cared. 
>> We'd just run across machines that had this unneeded option.
>
> Indeed. And the 11/70 don't have it, nor does the 11/74 systems that 
> ever were used.
>
> CASTOR:: was 4 CPUs, by the way, while PHEANX:: was only 2, if I 
> remember right.
>
>     Johnny
>

I can't add too much to this regarding what parts and what DEC 
designators applied
but here are memories of the time frame.

The first multiprocessor 11/70 was built with existing hardware and a few
wire wrap and jumper mods.  Memory said there were 4 total, three inside DEC
and one at CMU that they hacked together possibly with DEC help.   It 
would evolve
to a design project to make that buildable as marketing felt they could 
sell it.
However at the same time VAX/11/780 was real and also the various product
groups were feeling the  effects of FCCs new class A and B limits for 
RFI/EMI.
That and the high end market had been moving to more addressable memory
for bigger datasets and computationally wider data words as the tasks were
getting bigger.  At that time the big calculations that were important were
atomic physics and weather models and both were associated with massive
[by that eras measure] datasets.  In many respects the same pressures 
repeated
themselves in the 32bit to 64bit evolution [Alpha].

It was my understanding that the 11/70 continued as a grandfathered
EMI and the new multiple cpu died due to EMI issues (plethora of cables
and multiple racks) and it was a faster number cruncher than VAX-11/780.
The VAX had higher potential as the new reigning super minicomputer.  It
wasn't long after that I'd seen a VAX-11/782, 785 and VAXclusters.

There were several of the PDP11 flavors that would die or morph as a
result of manufacturing and serviceability issues.


Allison



More information about the cctech mailing list