Date: Tue, 10 Jan 1995 14:53:11 EST
From: THE MASKED PROGRAMMER <badcoe AT bsa DOT bristol DOT ac DOT uk>
To: djgpp AT sun DOT soe DOT clarkson DOT edu
Cc: badcoe AT bsa DOT bristol DOT ac DOT uk

Hi,

dj wrote:

>> So how's it done ?  How do I find the real-address of a protected-mode address ?
>
>You don't.  The page lookup takes no extra time, so just use the
>linear address space, not the real address space.  Pages aren't
>allocated linearly anyway.

It's not the page lookup that I wanted to avoid.

It's the addition of the offsets to the base address.  If the lower
part of the base address is 0x0000 then I can simply load the offset
into (say) dx (or dh and dl depending whether they're already together)
with the two high-bytes already in the top of edx.

I can then do the lookup with the simple form of address calculation
(I think, I'm pretty much a beginner with the 386 <wow! aren't they
complicated !>) which might be a bit faster.

I suspect that it wouldn't be fast enough even so.  I'm only following
this thread for completeness (my best attempt so far is ~10-fold too
slow and that's after trying about 10 diff asm strategies).

>Have you actually looked at the code that "gcc -O3" produces for
>foo[x][y] when the dimensions are 256x256?  It might already be
>optimal - gcc is a real good optimizer.

Hmmm, is it really that good ?  I'll be very impressed if it is.

	Thanks,


	Badders (Hoping to be impressed in the near future.)