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 : Advanced Micro Devices - Moderated (AMD)
AMD 243.98+4.5%3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: survivin who wrote (29827)2/28/2001 8:43:20 AM
From: Dan3Read Replies (3) of 275872
 
Re: Intel set to use PC1600, skip PC2100 until Brookdale

P4's QDR bus and asynchronous memory must be a pretty tough nut to crack. Does anyone know what kind of control lines are associated with that bus? Tenchusatsu?

I think they're just sending two control signals (top and bottom of the wave) for each 4 data bits. There is no shared bus clock or control line to keep the other two bits coherent. Interfacing to an asynchronous memory bus would likely cause some bits to arrive a few ns early and others a few ns late. Without a control line to enable early or late latching of the data, there would likely be lost data. If they can get their QDR bus up to 133MHZ the clocks at both ends should be enough to let it work OK with PC2100, PC1066 (or interleaved PC133, for that matter).

Until then, they're probably better off accepting the modestly lower data rate.

OTOH, not shipping at least one data corrupting chipset for P4 would be quite a break with recent Intel tradition - do they want to be that radical?

:-)

Regards,

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