Re: Why is GForth-ITC fast?

In article <2008May1.125445@[EMAIL PROTECTED]
>,
Anton Ertl <anton@[EMAIL PROTECTED]
> wrote:
>Robert Spykerman <robert.spykerman@[EMAIL PROTECTED]
> writes:
>>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.
>
>It is?  On what hardware?  On what benchmarks?  How much?

I have a few measure point here.
Pentium 90
lina 4.0.6
gforth 0.6.2

ISO-Forth prime benchmark GILBREATH ("byte benchmark")
lina   53 mS
gforth 42 mS

Nesting benchmark 10 levels : A0 ; .. : A7 A6 A6 ; .. : AA A9 A9 ;
Time for AA
lina   0.539 mS
gForth 0.70 ms

The benchmarks show significant differences, but they are not substantial.

The result of the nesting is remarkable, because lina uses the
infamous LODS instruction in next.

I expect lina to do worse on real life code than gforth, because
of less assembler primitives.
The Gilbreath benchmark uses words that are primitives on any Forth
including lina.
Compilation speed on gforth is spectacularly better (better
algorithm).

<SNIP>

>- anton


--
-- 
Albert van der Horst, UTRECHT,THE NETHERLANDS
Economic growth -- like all pyramid schemes -- ultimately falters.
albert@[EMAIL PROTECTED]
 &=n http://home.hccnet.nl/a.w.m.van.der.horst