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 : All About Sun Microsystems

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: I_Banker who wrote (62216)10/27/2004 10:59:46 PM
From: Charles Tutt  Read Replies (1) of 64865
 
FLOPS and SpecFP don't have much relevance to the enterprise market, which isn't usually floating point intensive. Perhaps SpecInt ought to be a more useful metric, but computer makers have gamed it until its results aren't as valuable as one might expect. I think that's why Sun has moved toward enterprise application based benchmarks in recent years.

The increased availability of resources in the case of high volume commodity chips is offset somewhat in real cases (I'm thinking especially of X86) by the need to maintain compatibility with legacy software, which consumes some (many?) of those resources.

As for continued enhancement of X86, my take is that implicit in Intel's decision to create Itanium was a judgment that the architecture did not lend itself to continued enhancement (although I recognize that other issues, like control of IP, may also have contributed to their decision). They have probably rethought that decision somewhat in light of the Opteron, but it may not have been far from the mark.

JMHO.

Charles Tutt (SM)
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext