Re: Linux Graphics Architecture (format fixed)

Albert D. Cahalan (acahalan@cs.uml.edu)
Sun, 7 Feb 1999 18:32:36 -0500 (EST)


David Schleef writes:
> On Sun, Feb 07, 1999 at 12:00:55AM -0500, Ben Bridgwater wrote:
>
>> Much more than that! :) I'm really looking for a complete solution.
>> It's no good having your X server happily coexist with the
>> framebuffer if the whole thing snarfs up when I run some game
>> that directly accesses the graphics hardware. We need to provide
>> an efficient low level device driver that even games writers will
>> be happy to use. I think it would be a shame to put a lot of
>> effort into an X-only solution.
>
> Will this "efficient low level device driver" work over a network as
> well as X does?

Asking that is like asking if the parallel port driver provides
network printing services.

> Given that gigabit ethernet is just around the corner,
> bandwidth is _not_ a problem.

1600x1200x32x30 = 1.8 Gb/s = 2 point-to-point gigabit Ethernets

Gee, that sounds like a great way to spend your money.
I'd like to see the beefy server that handles multiple clients.
Hint: local CPU power is cheaper because you don't have to pay
the premium of high-end server CPUs like the latest Xeon or 21264.

Ethernet was not designed to be a point-to-point graphics bus.

> I wouldn't like to see a situation
> develop where game writers choose a limiting, non-standard interface
> to get short-term performance increase. There already is a complete
> solution. It's called X.

I'm sick of this paranoid fear. Games written to the GGI API will
run in X just fine, assuming X can provide the needed performance.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/