Date: Sun, 21 Mar 2010 05:03:15 +0200 From: Andriy Gapon <avg@icyb.net.ua> To: "Matthew D. Fuller" <fullermd@over-yonder.net> Cc: freebsd-stable@freebsd.org Subject: Re: hardware for home use large storage Message-ID: <4BA58C73.90806@icyb.net.ua> In-Reply-To: <4B715AC7.2090201@icyb.net.ua> References: <4B6F9A8D.4050907@langille.org> <201002081556.54782.doconnor@gsoft.com.au> <20100209053002.GA9449@over-yonder.net> <201002091637.52002.doconnor@gsoft.com.au> <20100209103228.GB9449@over-yonder.net> <4B715AC7.2090201@icyb.net.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
on 09/02/2010 14:53 Andriy Gapon said the following: > on 09/02/2010 12:32 Matthew D. Fuller said the following: >> On Tue, Feb 09, 2010 at 04:37:50PM +1030 I heard the voice of >> Daniel O'Connor, and lo! it spake thus: >>> Probably the result of idiotic penny pinching though :-/ >> Irritating. One of my favorite parts of AMD's amd64 chips is that I >> no longer have to spend through the nose or be a detective (or, often, >> both) to get ECC. So far, it seems like there are relatively few >> hidden holes on that path, and I haven't stepped in one, but every new >> one I hear about increases my terror of the day when there are more >> holes than solid ground :( > > Yep. > For sure, Gigabyte BIOS on this board is completely missing ECC initialization > code. I mean not only the menus in setup, but the code that does memory > controller programming. > Not sure about the physical lanes though. BTW, not 100% sure if I my test method was correct, but it seems that ECC pins of DIMM sockets (CB0, CB1, etc) of my motherboard (GA-MA780G-UD3H) are not connected to anywhere. So looks like Gigabyte is saving some cents on this. -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4BA58C73.90806>