[Simh] PDP-11 -- MFPI, etc, with memory mgmt off

[Johnny Billquist]

Thanks. Then I got how you meant it. And that makes total sense.

   Johnny

On 2019-09-22 19:57, Bob Supnik wrote:
> If the MMU is enabled, the instructions use PSW<prev_mode> to compute 
> the source/destination operand physical address (if memory) or the stack 
> pointer to use (if SP). If the MMU is off, PSW<prev_mode> only matters 
> if the source/destination operand is SP.
> 
> /Bob
> 
> On 9/22/2019 12:00 PM, simh-request at trailing-edge.com wrote:
>> Message: 4
>> Date: Sun, 22 Sep 2019 09:01:42 +0200
>> From: Johnny Billquist<bqt at softjar.se>
>> To:simh at trailing-edge.com
>> Subject: Re: [Simh] PDP-11 -- MFPI, etc, with memory mgmt off
>> Message-ID:<158acaa4-22c1-bb9c-ecdf-3c2b5d273f70 at softjar.se>
>> Content-Type: text/plain; charset=utf-8; format=flowed
>>
>> Well, technically, on a Unibus, even with the Unibus map, a DMA device
>> still only sees an 18-bit address. Or am I confused? But if the map is
>> enabled, then it will end up being able to access all 4M of memory 
>> anyhow.
>>
>> But your answer made me wonder. Are you saying that M[TF]P[DI] are not
>> using the previous mode bits in the PSW (when MMU is enabled)? Oh, maybe
>> you are saying that even if MMU is disabled, the selection of which R6
>> to use is still happening, based on PSW.
>>
>>     Johnny
>>
> 
> _______________________________________________
> Simh mailing list
> Simh at trailing-edge.com
> http://mailman.trailing-edge.com/mailman/listinfo/simh

-- 
Johnny Billquist                  || "I'm on a bus
                                   ||  on a psychedelic trip
email: bqt at softjar.se             ||  Reading murder books
pdp is alive!                     ||  tryin' to stay hip" - B. Idol