State of Linux graphics

[Jon Smirl]

On 8/31/05, Ian Romanick <idr at us.ibm.com> wrote:
> If we implement a couple fast-path functions and the X-server gets a
> significant performance boost from them, the hardware vendors will
> support them.  There's even a good chance they could get incorporated in
> a future core version of OpenGL.  This has happened with Mesa extensions
> in the past (GL_MESA_window_pos became GL_ARB_window_pos, which was
> incorporated into OpenGL 1.4).

BrianP has said that he will present out extension proposals to the OpenGL ARB.

For example, how should you handle a card that only accelerates
bitblt? Should it be an OGL extension or should it look like a texture
unit that can only accelerate copy?

>From what I've read the area of partially accelerated OGL on low end
hardware has not been explored very well. I do know that there is a
100KB integer only, proprietary OpenGL ES stack. That implies that an
equivalent open source version could be written if we choose to expend
the resources. If you combine that stack with some scheme for
accelerating things likes fills and bitblt, it should have
approximately the same performance as an XAA driver for the same types
of calls.

-- 
Jon Smirl
jonsmirl at gmail.com