🚀 go-pugleaf

"Heinz W. Wiggeshoff" wrote:
> 
> > In article <6aie7.52269$e%3.8...@news2-win.server.ntlworld.com>,
> > Chris Bigos wrote:
> >
> >>I wouldn't be surprised if the RPSB instruction (Repack Symbols) takes the
> >>prize for the most complex instruction ever implemented in the history of
> >>mainframe computing - certainly of the era. Any comments? (I guess this
> >>should be a new thread - if there isn't one on this topic already.)
> 
>   In the very early 70's, I read about a GE 6xx(?) list processing machine
>   instruction.  Someone commented that complier writers like those types
>   of instructions.  Any GE experts in a.f.c-land?

The 600 Series had (has? since the architecture lives on)
3 "repeat" instructions that were sort of a poor man's
vector mode.  You can arrange that the next instruction
is repeatedly executed until a count is reached, or a
condition code satisfied.  An index register is advanced
so that you step through memory.
   RPT repeats one instruction, 
       typical use add up a set of numbers of do a linear search
   RPD "repeat double" repeats two instructions
       if the instructions were load and store this could be used
       for a block move.  This use was generally superceded when
       character and bit vector block move instrctions were added
       to the architecture.
   RPL "repeat link"
       This was the primary list processing variation.
With effort you can also use the repeat double to run down a list.
I don't know of any compiler that uses repeat link, for generated
code, and RPT and RPD are sometimes generated to do the case lookup
for B/C/Pascal switch statements.  Other than that compilers generally
can't find a use for these instructions.  There is some library code
that uses them.  The C library memory allocator is the principal
user of RPL and RPD to manage its free list.

None of the repeat instructions is particulary complex, and they are
all a lot simpler than the "move edit" instruction which is used
by the Cobol compiler.  Even more complex is the interdomain
call/return instruction.  (Calls to the OS for supervisor services
are just part of its use.)