[Info-vax] Y3K for PDP-11 Operating Systems

[Johnny Billquist]

On 2011-05-09 17.05, vandys at vsta.org wrote:
> In alt.sys.pdp11 Johnny Billquist<bqt at softjar.se>  wrote:
>> I wouldn't be so sure on string handling, since the VAX have lots of
>> native instructions to deal with that, which the 11/70 do not. Integer
>> on the other hand, yes.
>
> I think it was most competetive when you used multiple of its more optimized
> instructions.  For instance, my recollection is that the single-instruction
> bulk string ops ran slower than the hand coded move/loop constructs.  (Most
> of my time was on 750's and the odd 780, and this no doubt changed as DEC
> fleshed out their Vax line.)

I know that for some things, actually coding using more primitive 
instructions on the (older) VAXen turned out to be faster than to use 
the fancy instructions, but I would not have thought that was true for 
things like MOVC or LOCC, but I might very well be wrong.

>> The VAX have a single instruction for that, while the
>> PDP-11 needs to manually handle both processor registers and MMU
>> registers.
>
> Having a single instruction does not mean you have a *fast* single
> instruction.  That was definitely the case for bulk string ops.  I don't
> recall actual task switch performance; that was not an area which caused
> me problems.

Indeed. Which is why I said I'm not sure in this area. The save/load 
context instructions are doing a *lot* of things.
But doing a context switch on the PDP-11 is no little task either. But 
from a performance point of view, it is rather relevant, since a lot of 
context switches happens all the time. (The big win, however, was 
obviously the loads of actual code needed to do a context switch which 
was reduced to just a few bytes on a VAX. :-) )

	Johnny