[ale] Nvidia Magic for dual head

James P. Kinney III jkinney at localnetsolutions.com
Fri Feb 7 13:53:03 EST 2003


I concur.

1024x768x24bitx30frames per second= 566,231,040 bits per second
through-put on the graphics subsystem. Using 8-bit words, that is 70MHz
clock (70.77 MHZ).

Assuming a 320x240 frame at 8 bit color, and using an 8 bit word
transfer chunk, the clock would have to be a whopping 768 MHz! 

I don't think even SGI has that kind of graphics bandwidth.

At this point, I suspect that the error here is in the units. I wonder
if fps is really tps (triangle per second). 10k tps is actually a
realistic number for a graphics card that costs under $2k.

On Fri, 2003-02-07 at 13:32, Vernard Martin wrote:
> On Fri, 2003-02-07 at 11:25, Joe wrote:
> > So I repeat my question: What's the point? There is no perceptible
> > difference, AFAICT, between 10000fps and 100fps. Normal NTCS video is
> > 30fps, and the discreteness of the signal is nearly imperceptible even
> > at that rate. Why on earth would you ever need 10000fps for human
> > eyeball consumption? And what kind of Tyranno-monitor do you need in
> > order to accept that signal? (Jeez, the dot rate on that card probably
> > overflows the value of a 32-bit integer...) Why should I waste my
> > money on a 10000fps card as opposed to a 100fps card?
> 
> 
> I can assure you that this is not doing 10,000 frames per second. I
> don't care WHAT the software is saying its doing.
> 
> Sorry, but 10,000 FPS exceeds the theoretical bandwidth that the Ti4200
> cards can sustain. So its can't be right. I also have one of these
> cards.
> 
> V
-- 
James P. Kinney III          \Changing the mobile computing world/
CEO & Director of Engineering \          one Linux user         /
Local Net Solutions,LLC        \           at a time.          /
770-493-8244                    \.___________________________./
http://www.localnetsolutions.com

GPG ID: 829C6CA7 James P. Kinney III (M.S. Physics) <jkinney at localnetsolutions.com>
Fingerprint = 3C9E 6366 54FC A3FE BA4D 0659 6190 ADC3 829C 6CA7 

 This is a digitally signed message part




More information about the Ale mailing list