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 215.18-2.1%Dec 2 3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: rsi_boy who wrote (74182)3/11/2002 11:09:38 AM
From: that_crazy_dougRead Replies (2) of 275872
 
<< Not entirely true! There was a time when the K-6 3 (at 450) beat everything Intel had including the Xeon (then at 500mhz). >>

Beat it in what? How fast it loaded office? It got smoked in anything that was floating point based, which was where the biggest and most interesting bottlenecks were at the time.

<< When the K6-2 first came out, at 300 MHz (with 100MHZ fsb vs. p2 300's 66 MHz fsb) and with 3D NOW! It did very well, matching or beating the Pentium II in most benchmarks. Of course, past 300 MHz the k6-2 scaled pretty badly because of the onboard L2 cache stuck at FSB speed. >>

Same argument with the k6-2, it won meaningless office benchmarks while getting trounced in FP, it was nice for awhile because it was so cheap, but that didn't last too long once AMD made inroads into Intel's market share and the 300a came out.

With either of these cases, I'd hardly say Intel made a chip that required wierd optimizations to outperform the AMD chip that worked on most current software, if anything the reverse was true. AMD chips would work better if people made the 3dnow optimizations, but intel chips worked better on existing software. (which was the original point I was discussing).
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext