Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!rutgers!apple!well!jax
From: jax@well.UUCP (Jack J. Woehr)
Newsgroups: comp.lang.forth
Subject: Re: FORTH, RISC, and other new architectures
Summary: Well, Howdy There, AMD!
Keywords: 29000, stack, depth, RISC
Message-ID: <12989@well.UUCP>
Date: 3 Aug 89 04:48:16 GMT
References: <385@ryn.esg.dec.com> <975@key.COM> <26573@amdcad.AMD.COM>
Reply-To: jax@well.UUCP (Jack J. Woehr)
Organization: Whole Earth 'Lectronic Link, Sausalito, CA
Lines: 65

In article <26573@amdcad.AMD.COM> tim@amd.com (Tim Olson) writes:
	... original posting deleted, but yes the transputer is not
a very effective Forth engine ...
>
>Yes, large standard register files are not very effective in speeding up
>FORTH.  However, the Am29000 register file is different.  There are 128
>local registers, which are offset from the register stack pointer
>(global register 1).  Thus, the local register file can act like a stack
>cache, holding the top (or all!) of the operand stack.
>
>FORTH primatives (compiled in-line) then look like:
>
>	+			DUP			SWAP
>add lr1, lr1, lr0	add lr127, lr0, 0	add tmp, lr0, 0
>add gr1, gr1, 4		sub gr1, gr1, 4		add lr0, lr1, 0
>						add lr1, tmp, 0
>
>with lr0 pointing to the top of stack, lr1 the next of stack, etc.  A
>"smart" FORTH compiler would be able to remove the extraneous
>stack-adjustment instructions and change the local variable references
>accordingly.
>
	VERY Interesting!!! Just got hold of the 29000 User's Manual
today, thanx to AMD's eager and friendly marketing division. Is this
to be taken to mean that you have a Forth up and running on some 29000-based
boards or machines? More info, please!

>The FORTH notion of separate operand and control stacks can also be
>implemented by splitting the local register file into two 64-register
>chunks, and keeping two shadow stack pointers, swapping the correct
>pointer into the real stack pointer when required.
>
>This raises a couple of questions:
>
>First, are 64 words of control and operand stack enough?  How deeply
>nested to FORTH words typically get?

	Well, one opinion on that is expressed in the Forth 83-Standard,
q.v. (downloadable from RCFB, phonenum below). But answer is qualified
yes.

>Second, does a typical FORTH program (coded with in-line primatives and
>call-threaded) spend most of its time executing FORTH primatives or
>executing the thread of control for user-written words? 
>

	Depends on the programmer, the system, etc., but the answer would
tend towards the latter.

	Not all Forths are threaded the same. The new Forth Stack/RISC
chips like the SC32 are VERY efficient in this respect.

	At the opposite extreme, an indirect-threaded Forth can spend
1/3 of its life executing the threading routine NEXT.

	There is all sorts of middle ground in this. Tell us more about
what you are doing with the 29000!

{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}
{}                                                                        {}
{} jax@well     ." Sysop, Realtime Control and Forth Board"      FIG      {}
{} jax@chariot  ." (303) 278-0364 3/12/2400 8-n-1 24 hrs."     Chapter    {}
{} JAX on GEnie       ." Tell them JAX sent you!"             Coordinator {}
{}                                                                        {}
{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}{}