Re: [AD] malloc

[ Thread Index | Date Index | More lists.liballeg.org/allegro-developers Archives ]


On Sunday 20 November 2005 08:08 pm, aj wrote:
> i wouldn't be  accessing [0][1]    SSE is 128bits wide, pixels are 32,
> so i can process 4 pixels at once.
> then the next load would be [0][4] (aligned again).

Allegro processing things per-pixel. If you do bmp_write32(addr+(x*4), color); 
it won't be an aligned access if x isn't a multiple of 4.

> >etc). Plus, you can't gaurantee the alignment of video bitmaps since the
> >system allocates/maps them, not your program.
>
> video cards dont have SSE.
> why would you write SSE code for video bitmaps?

You wouldn't (nor shouldn't, directly). The compiler would. And since memory 
and video bitmap types are abstracted, if you access a bitmap you'll have no 
idea if the pointer the system gives you is aligned or not.

> nor will i386 instructions, so should we not bother with MMX either, as
> i386 is good enough.

I never said don't bother with SSE. I just said MMX isn't going anywhere, and 
that it might not be a totally technical reason that Intel is pushing SSE and 
downplaying MMX.




Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/