Article: Parallelism at HotPar 2010
By: David Hess (davidwhess.delete@this.gmail.com), August 4, 2010 11:31 am
Room: Moderated Discussions
Mark Roulo (nothanks@xxx.com) on 8/4/10 wrote:
---------------------------
>
>Without arguing whether or not the sub-$100 GPU market can vanish and be replaced
>by on-chip GPUs, does anyone have a feel for this question:
>
>
Why not ask instead at price point would equivalence of integrated GPUs and discrete GPUs prevent higher end GPUs from being economical? Buying a $60 card to get four times the performance is a much different situation for nVidia then if you need to pay $200 for twice the performance. (I guess I spent $200 for greater than 6 times the performance since my main system has embedded video and will drive two monitors.)
How many discrete GPUs go into upgrading systems even if the old GPU card is never used again? I have at least twice as many spare video cards now than I have systems but that includes cards going back to the Matrox G200.
---------------------------
>
>Without arguing whether or not the sub-$100 GPU market can vanish and be replaced
>by on-chip GPUs, does anyone have a feel for this question:
>
>
>If the sub-$100 discrete GPU market goes away, can nVidia survive on the high
>end (and, I suppose, embedded) chips alone? Or do they need the volume of the low
>end to justify the ongoing development?
>
Why not ask instead at price point would equivalence of integrated GPUs and discrete GPUs prevent higher end GPUs from being economical? Buying a $60 card to get four times the performance is a much different situation for nVidia then if you need to pay $200 for twice the performance. (I guess I spent $200 for greater than 6 times the performance since my main system has embedded video and will drive two monitors.)
How many discrete GPUs go into upgrading systems even if the old GPU card is never used again? I have at least twice as many spare video cards now than I have systems but that includes cards going back to the Matrox G200.