Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!husc6!cmcl2!beta!hc!ames!sdcsvax!amos!mr-frog
From: mr-frog@amos.ling.ucsd.edu (Dave Pare)
Newsgroups: comp.sys.atari.st,comp.sys.misc,comp.sys.amiga
Subject: Re: Atari Transputers ? (Really: stack machines)
Message-ID: <4044@sdcsvax.UCSD.EDU>
Date: Wed, 7-Oct-87 14:48:55 EDT
Article-I.D.: sdcsvax.4044
Posted: Wed Oct  7 14:48:55 1987
Date-Received: Sat, 10-Oct-87 10:16:51 EDT
References: <8709181728.AA13664@ucbvax.Berkeley.EDU>
Sender: nobody@sdcsvax.UCSD.EDU
Reply-To: mr-frog@amos.UUCP (Dave Pare)
Organization: Univ. of Calif., San Diego
Lines: 18
Keywords: context switch
Xref: mnetor comp.sys.atari.st:5536 comp.sys.misc:906 comp.sys.amiga:9170

> Second, One of the hallmarks of a true-blue RISC chip, however, is
> *LOTS* of registers.  The Am29000, for instance, has 192.  Only large
> structs and arrays need to go off-chip.

Is this per-context, or are they shared between all the running processes?
After all, the transputer is not a single-process machine!

> Thus, the assumption that *everything* is in a register is perfectly
> valid, even in situations where other architectures would go off-chip.

As I understand it, RISC machines have difficulties once the number
of runnable processes gets above the number of "hardware" contexts
available to it.  I think that if you have a task that fires off 30
processes, the transputer will blow the doors off anything else,
because its switching overhead is 10% of most other machines.
What is the switch time of the Am29000?

Dave Pare