Date: Sat, 16 Aug 2003 14:50:45 -0700 (PDT) From: Don Lewis <truckman@FreeBSD.org> To: oberman@es.net Cc: stable@FreeBSD.org Subject: Re: Strange things going on with 4.8 Message-ID: <200308162150.h7GLojM7024139@gw.catspoiler.org> In-Reply-To: <20030816213016.A94015D08@ptavv.es.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On 16 Aug, Kevin Oberman wrote: >> Date: Fri, 15 Aug 2003 15:48:02 -0700 (PDT) >> From: Don Lewis <truckman@FreeBSD.org> >> Sender: owner-freebsd-stable@freebsd.org >> >> On 11 Aug, Robert Gray wrote: >> > Until I hear otherwise, I'll continue to spend extra >> > for the redundant, error-checking memories. >> >> Me too, but I've found there is a distinct lack of ECC capable >> motherboards for the newer versions of the AMD Athlon XP. > > OK. Are yo aware of ANY Athlon XP (Socket A) mobo that supports ECC > PC2700 or PC3200 memory with a 333 or 400 MHz FSB? I have been looking > and have found ZIP! I find if hard to believe that there is not enough > market, but I am starting to wonder. None that I'm aware of. The documentation for the older VIA chipsets claimed that they supported of ECC, but I never found a motherboard with one of these chipsets that supported ECC, and the last time I checked, the chipset documentation was only available to VIA's "parters" under NDA. The only Athlon motherboards that I found with ECC support were the AMD 760 and 761, and those don't support anything faster than PC2100. I've been wanting to drop a note to AMD's marketing department that they should lean on their chipset and motherboard suppliers to get them to support ECC RAM if they want to be taken seriously in a somewhat higher end market that cares about data integrity. I suspect that AMD wants to migrate this part of the market to the Hammer.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200308162150.h7GLojM7024139>