[Xorg-driver-geode] Plans for next releases

[Kevin Callahan]

Hi,

These questions are slightly off-topic but don't know where else I could
ask:

If I'm using the LX800 is there currently no method to utilise the
hardware acceleration at all? I understand that only video -> video RAM
will be accelerated.

I'm using an embedded board and have been using the LX800 kernel FB
driver (using the Allegro lib) which doesn't appear to give me any
performance increase over standard FB drivers (nsc, vesa, etc).. 
I do have X running, but again see no performance increase whatever I
do.

Is there an available datasheet of registers that gives me the info to
allow me to access the hardware acceleration registers (under linux) so
that I could create a basic hardware accelerated blitting function? Or
is this simplifying the problem too much? I take it the hardware
acceleration is just DMA like (say) the blitters in the Atari & Amiga
machines in the 80s?

Pardon my (probably complete) lack of understanding of all this ;)

> To the best of my knowledge, only the reserved for video memory RAM
> portion can be used for hardware acceleration (at least there the
result
> must be put, but to my knowledge also the source, not 100% sure on the
> latter).
> However as the video memory is just a reserved area of RAM, the CPU
> ought to be able to access it quite nicely, and so we ought to be able
> to do the software fallback straight in video memory, provided it is
> serialized correctly between software and hardware touching
> (gp_wait_until_idle() has been called, ourselves if necessary or via
EXA
> WaitMarker hook if this is/can be handled in generic EXA code).
> That is, we shouldn't need to download this pixmap back to system
memory
> - but do the software fallback, that touches the pixmap whose latest
> copy is in video memory, straight in video memory without migrating it
> out first. (However, if the pixmap needing swfallback is already in
> system memory, don't migrate to video memory first, etc)
<snip>