[prev in list] [next in list] [prev in thread] [next in thread] 

List:       opensolaris-discuss
Subject:    Re: [osol-discuss] Another [OT] Hardware Post
From:       Bohdan Tashchuk <btashchuk () yahoo ! com>
Date:       2011-02-28 2:14:40
Message-ID: 927088729.1251298888113612.JavaMail.Twebapp () sf-app1
[Download RAW message or body]

> Here's how Intel does product differentiation:
> 
> If the product is an "iN" something or other (e.g.
> i3/i5/i7 or the 
> like), regardless of the underlying architecture, the
> memory controller 
> DOES NOT support ECC.
> 
> If the product is labeled "Xeon" something or other,
> it DOES support ECC.

To keep beating a dead horse, it is possible to get ECC in an Intel iN processor. \
Here, for example, is a PDF from Intel with some details \
http://download.intel.com/pressroom/kits/embedded/pdfs/Core_i5-660_Corei3-540.pdf The \
relevant quote is " Error correcting code (ECC) memory is supported on both \
processors when paired with the Intel 3450 chipset."

So what's happening is that Intel wants everyone to think they must have a Xeon to \
get ECC, but there are at least two Intel iN processors that support it. Of course \
you need a corresponding motherboard to take advantage of ECC.

I'm not sure of the practical value of the above, since, seeing as Sandy Bridge stuff \
is either here or right around the corner, it would probably make sense to see how \
Intel's Sandy Bridge ECC strategy settles out. From links previously posted here, it \
looks like ECC will be much more widely supported on the new iN chips w/o requiring a \
                Xeon branding.
-- 
This message posted from opensolaris.org
_______________________________________________
opensolaris-discuss mailing list
opensolaris-discuss@opensolaris.org


[prev in list] [next in list] [prev in thread] [next in thread]