Around 10 o'clock on Aug 15, Vadim Plessky wrote:

> Point was that if RENDER is not hardware-accelerated, there is no reason to 
> use it, instead of libart.

There are a couple of significant advantages to using even a software
implementation of Render, the first is that you can get reasonable
performance for applications over a network.  The second is that when
compositing images with window contents, placing the compositing software
right next to the frame buffer means that only the pixels which are
translucent in the source image need be read from the frame buffer.  As the
performance of software rendering is essentially limited by the speed of
reading from the frame buffer, this optimization can actually make things
dramatically faster.

So, using Render should be no slower than using libart, and will be faster
in networked environments, when using images that contain few translucent
pixels and when we get X servers with hardware acceleration for the
extension.  The later is largely a matter of architecture; a new XAA layer
is being designed which will provide some more help for writing Render
acceleration.

Of course, you could also look at the Matrox code and implement similar 
acceleration for whatever video card you like; that will make Render a lot 
faster, and doing some of the common cases isn't really that much work.

Keith Packard        XFree86 Core Team        HP Cambridge Research Lab


_______________________________________________
Render mailing list
[EMAIL PROTECTED]
http://XFree86.Org/mailman/listinfo/render

Reply via email to