Re: GGI, EGCS/PGCC, Kernel source

Nate Tuck (nate.tuck@raycer.com)
Tue, 24 Feb 1998 11:14:54 -0800


At 02:19 PM 2/24/98 +0800, Michael O'Reilly wrote:
>"Nate Tuck" <nate.tuck@raycer.com> writes:
>> Umm... You still have to copy the data from the application, into the
>> shared memory and then out from the shared memory into the video card.
>> This sucks three times the system memory bandwidth of going out of the
>> application memory directly to the video card. Am I missing something?
>
>Yes, you build the data in the shared mem directly. Use
>get_shared_mem() instead of malloc(). :)

This isn't realistic for the current graphics API's du jour, OpenGL and
Direct3D.

Consider the call: glVertex3f(a, b, c);
How do I figure out where a, b and c came from while inside the vertex call?

Or for those calls which you actually pass a pointer, like glVertex3fv(&foo);
do you require that every piece of data used be built using get_shared_mem?
Does this sound burdensome to you, or am I the only one who is shuddering
here?

It sounds like what you are proposing works fine in theory, but falls down
in practice.

nate

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu