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 203.76-1.1%Nov 21 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: TigerPaw who wrote (76286)4/3/2002 9:07:26 AM
From: combjellyRead Replies (1) of 275872
 
"Why should there be a limit to 1 or 2 way servers?"

Worst case, mainly limited by the market. The base of the whole discussion is the email from "Microprocessor Report" that the Intel supporters are crowing about that questions the viability of the SledgeHammer with the major OEMs since they have all committed to Itanium.

I personally don't buy it. Considering the RAS features being built into the SledgeHammer, the likely performance level, and the ease of making a SMP system, it should be compelling. The point that is often ignored is that because HTT simplifies all of the interconnections so much, signal integrity should be higher, thus making the whole system more reliable.

In addition, even if none of the major OEMs ever uses SledgeHammer, that still leaves a growing market of the smaller OEMs. They will be able to use SledgeHammer to move out of the 1 and 2 way servers and small clusters that they sell now. Itanium seems to need truly huge caches to work well, and the Hammers in general should not. So there will always be a big cost advantage...
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext