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: Dan3 who wrote (116390)	6/19/2000 12:25:00 AM
From: Elmer	Respond to of 1571802

Re: "That does make some sense, although since they aren't marketed as SMP chips, they can hardly be called defective. Maybe the reason they are being so conservative with the L2 in Thunderbird is to simplify solving cache coherency problems." I tried to be clear in saying they are "SMP defective". Re: "It was a long time ago, but my recollection is that Intel had trouble with these issues (cache coherency) in the early Pentium MMX systems. I remember boards that supported Pentium but not Pentium MMX for multiprocessor systems. It's evidently not an easy capability to design for" It wasn't easy for socket7 processors and not all Intel chipsets/processors supported it. No AMD processor ever did. The move to the P6 bus architecture was in part to simplify SMP design which is now effortless for the designer and an enormous success in the server business. AMD was caught without a license for the P6 bus and lacking resources of their own they licensed Alpha's instead. The claim at the time was the EV6 architecture was superior to Intel's bus and AMDroids weren't sophisticated enough to see through the bologna. As Intel and it's customers ship 2-way, 4-way, 8-way, 16-way and higher systems, AMD has never been able to ship a simple 2-way Athlon with it's "superior" EV6 architecture and already available MBs. I don't think my theory of "SMP defective Athlons" is unwarranted. Re: "But at least AMD didn't ship what they had, when it was almost (but not quite) working perfectly. And both revenues and profits at AMD are going up like rockets." Which is why I continue to believe that AMD is a good investment over the short term and I remain long on AMD and short AMD puts. EP