Re: Why is GForth-ITC fast?

On May 1, 12:30 pm, brian....@[EMAIL PROTECTED]
 wrote:
> I have been dis-assembling pieces of GForth and I don't understand why
> it is generally faster than other ITC Forths that are written in
> Assembler like CI-Forth or my old 16 bit HS/Forth.  The Assembler
> primitives seem to be so much smaller from what I can see.  Is the C
> compiler smarter than we are?
>
> Here are some examples
> CIFORTH (Albert van der Horst)

I've been meaning to take a look at this myself but am very busy IRL
to check this out among other things I'm currently trying to do.

*** Can you post some tests?

A number of suggestions

1. As you know ciforth is really really small. I am wondering about
cache issues. As you know a lot of modern pentia are von Neumann
outside but actually are Harvard internally. I believe from memory the
separate L1 data/instr caches of a CORE are 32 k bytes or something
like that. I can't remember sizes of cache lines but as you know data
and executable IA-32 code are definitely within this 20-30k area...

How's about ALLOTing something like Ox8000 and putting your data above
this and seeing if that makes a difference to your code?

2. Most of ciforth is actually written in forth. I wonder if it's the
same in gforth. Maybe rewriting more of ciforth into asm might give
you a speed boost but that defeats some of the advantages ciforth has
I guess.

3. I've heard some say that lodsw (ie for NEXT) is slow on modern
pentia and I've been wondering about whether changing that to an idiom
like doing a manual load of EAX from [ESI], bumping it up and then jmp
ing to [EAX] may be better. Don't know. On my long list of things I
would like to test.

Be interested to see what results you're getting Brian.

PS: Albert, I'll get back to you with your list of to-dos. Really busy
IRL. Also have had some words with some guys on teh Apple kernel list.
Will have to write more later. Tot laters

> Brian Fox

Robert Spykerman