SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : Intel Corporation (INTC)
INTC 49.07+0.7%2:14 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: ptanner who wrote (151048)12/4/2001 8:56:16 PM
From: Joe NYC  Read Replies (1) of 186894
 
PT,

Wouldn't it be easier just to integrate both the graphics and graphics memory into one chip rather than adding a separate memory controller (which seems more complex to me)?

I think this may be the holy grail of the graphics chip makers, since this would basically allow virtually unlimited bandwidth, since the internal bus can be say 1024 or more bits wide, and much faster than external buses.

The problem is that you need some 32 or 64 MB of memory for today's high end cards. Placing this much memory plus all the logic of the GPU would make a HUGE chip.

When this is done, it will first be done on the very high end graphics chips, and it will take a while until it gets down to low end solutions.

Joe
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext