>> On May 20, 2017, at 12:00 PM, Paul Koning <[email protected]> wrote:
>>
>> Interesting.  So you have the two CPUs as two processes?  I wonder if doing 
>> them as threads in a single process might be more straightforward.  I did an 
>> implementation of dual CPU CDC 6000 emulation that way (an extension to Tom 
>> Hunter's DtCyber).  Posix threads (pthread) work nicely, and semaphores 
>> (which aren't strictly part of pthreads but are often found alongside such 
>> implementations) often come in handy as well.
>>
>>  
Yes that's correct. The reason I implemented the VAX-11/782 in this way
is that it more closely replicates the arrangement of the physical
hardware. The real VAX-11/782 is two separate VAX-11/780 systems and the
only connection between them is the MA780 shared memory. For the
VAX-11/782 multi-processing configuration, the secondary VAX-11/780
(attached processor) boots from the shared memory and does not interact
with the console. For the VAX-11/784 each VAX-11/780 system boots from
it's own system disk and interacts with the console normally.
Multi-processing is then achieved via user written code that interacts
via the MA780 shared memory. It would be difficult to simulate the
VAX-11/784 via threads. The other reason for this choosing this
implementation is that it requires minimal changes to the existing VAX
simulator code.

Matt
_______________________________________________
Simh mailing list
[email protected]
http://mailman.trailing-edge.com/mailman/listinfo/simh

Reply via email to