🚀 go-pugleaf

In article <26207@ames.arc.nasa.gov> lamaster@ames.arc.nasa.gov (Hugh LaMaster) writes:
>I would like to make a request here- I think the time has come
>for micro people to consider mainframe architectural requirements.  Some
>nice micros have come out in recent years which could have been extended
>to mainframe architectures except for various flaws which, if remedied, would
>have had little or no effect on the performance or usability as micros.

THis is true.  It is amazing the number of "state of the art" processors
with migration difficulties on the market today.  The lack of scoreboarding
has been discussed here.  Other important features include:

	Multiprocessor support

	The ability to use 4 gigabytes of virtual memory (without
	cludging the software around)

	The ability to use 4 gigs of physical memory (without 
	cludging the software around)


>Next time, while designing a new architecture, ask if anything will stop you
>from building a high performance implementation with:

>a clearly and completely defined instruction set architecture 
>support for a large number of processors in a symmetric arrangement
>separate caches for each processor
>a high bandwidth multi-port multi-bank central memory
>high bandwidth I/O
>provable encapsulation/virtualization
>It is my belief that adding the above would cost little, but would buy
>potential customers a great deal.  I note that some recent micros my
>indeed be capable of all of the above, but not all of them do.

True there are many guilty here.  THis is why DG chose the 88K.  It
supports these issues directly.  However, not many others do.

>  Hugh LaMaster, m/s 233-9,  UUCP ames!lamaster
>  NASA Ames Research Center  ARPA lamaster@ames.arc.nasa.gov
>  Moffett Field, CA 94035     
>  Phone:  (415)694-6117       

Robert Cousins
Dept. Mgr, Workstation Dev't.
Data General Corp.

Speaking for myself alone.