Re: [AD] Memory Bitmap to Display blit slow?

[Thomas Fjellstrom <tfjellstrom@xxxxxxxxxx>]

On Mon March 9 2009, Peter Wang wrote:
> 2009/3/1 Trent Gamblin <trent@xxxxxxxxxx>:
> > On Sat, February 28, 2009 2:58 pm, Thomas Fjellstrom said:
> >> Anyone else have any ideas? As it is, bliting memory bitmaps to a
> >> display is unusable on my system right now.
> >
> > I believe it was Peter who already filed a bug report on the slowness of
> > the memory blenders. They aren't optimized at all. They are very very
> > generic. They could be made much faster, which would be easy but
> > time consuming considering all the different pixel formats. Assuming
> > We do blending with only 1 format (converting to and from that format
> > with the conversion functions that exist), we would still need ~16
> > optimized memory blenders. So if anyone wants to do that go ahead.
>
> Alternatively, we should be able generate blenders on demand at runtime.
> For portability and maintainability, perhaps we wouldn't generate machine
> code but some form of threaded code? Would be a very interesting task for
> anyone who wants to tackle it.
>
> Probably pre-generated blenders could be faster, so we might want
> pre-generated blenders for the most common src/dest formats, then do
> runtime generation for everything else.
>
> Or does someone know of a library (with a compatible licence) we could use?
>
> Peter
>
> ---------------------------------------------------------------------------
>---

I only know of two useful code generating "libraries", GNU Lightning (iirc), and LLVM. No idea if either are compatible.

--
Thomas Fjellstrom
tfjellstrom@xxxxxxxxxx