Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Steve Porter who wrote (39413)	10/15/1998 4:29:00 PM
From: Tenchusatsu	Read Replies (1) \| Respond to of 1588639

Steve, thanks for the info. I've printed out your recommendation, and when I have time (like next year or something), I'll look at the book. <However, that said I believe that Slot M (Merced slot, whatever that will be) will probably end up being P2P.> Nope, Intel's Merced chipset is going to have a 4-way multiprocessor bus. I'm still wondering why AMD is going P2P, when even Merced is sticking to the MP bus. One reason could be that Intel is trying to push even farther into the enterprise server market with potential 8-way and 16-way Xeon systems. That's not too hard to do; all you have to do is link up multiple 4-way buses and validate cache coherency, deadlock/livelock issues, etc. You can bet that such 16-way solutions would be a nightmare to implement with P2P. As for AMD going with P2P, I really don't think it was AMD's choice to begin with, technical stuff aside. They needed to borrow someone else's platform technology so that they wouldn't have to develop it themselves. I'm sure AMD would have made their K7 compatible with Slot 1 or Slot 2 in an instant if Intel allowed them to. Tenchusatsu