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.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: andreas_wonisch who wrote (45075)	6/25/2001 1:10:07 PM
From: Charles R	Read Replies (1) \| Respond to of 275872

Andreas, <It almost feels like AMD likes to play second fiddle to Intel.> It all comes from the leadership. <With today's news x86-64 seems to be DOA. Who else would commit to Hammer servers if not Compaq? > Well, there are always some el-cheapo Linux-box guys. And there may be some other outside-the-US guys. As far as US corporate business is concerned, start setting sights low. And, I mean "real low"... The long-shot is Sun (especially since Intel and Sun had some nasty things to say about each other) but with the way AMD has been slipping, it is tough to take that option seriously. Chuck

To: andreas_wonisch who wrote (45075)	6/26/2001 4:22:38 PM
From: fyodor_	Read Replies (1) \| Respond to of 275872

Andreas, from the article you linked to at overclockers.com: Of course, your motherboard has to know that. With the latest beta bios, the Master does, but most others don't at the moment. If your mobo doesn't know it can do SSE, it won't, and you won't. Are they serious? Why on earth would the motherboard need to know that the processor can do SSE? My K6-2 (including the 3DNow!) ran just fine in a motherboard from before 3DNow! was even close to being introduced - and I certainly didn't hear anything about "3DNow! compatible" motherboards / BIOSes. And then there's their whole memory bandwidth test. Suffice to say, what they are doing is completely and utterly irrelevant. (What they do is slow down the memory and benchmark it in various programs against one with "fast" memory. They then proceed to conclude that the "extra memory bandwidth" provided by the Athlon MP over the regular Athlon (really do to prefetching, of course) is only worth anything in the benchmarks that show a big increase in performance in the aforementioned test of fast vs slow memory. In reality, of course, any program that uses memory AT ALL in a predictable fashion (and it doesn't have to require any significant bandwidth!!!!) will benefit from the hardware prefetching. In fact, one could argue the exact opposite of what they claim: programs that require a lot of bandwidth - in an UNpredictable manner - would actually run slower with hardware prefetching, since it would take up some of the bandwidth making poor predictions.) -fyo