Date: Mon, 26 Jun 2000 14:01:53 +0200 From: Michel TALON <talon@lpthe.jussieu.fr> To: FreeBSD-STABLE <freebsd-stable@FreeBSD.ORG> Subject: Re: Compatibility Question Message-ID: <20000626140153.A11131@lpthe.jussieu.fr> In-Reply-To: <Pine.BSF.4.21.0006260733330.2314-100000@epsilon.lucida.qc.ca>; from matt@ARPA.MAIL.NET on Mon, Jun 26, 2000 at 07:42:50AM -0400 References: <v0422080ab57cec840cc3@[195.238.1.121]> <Pine.BSF.4.21.0006260733330.2314-100000@epsilon.lucida.qc.ca>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Jun 26, 2000 at 07:42:50AM -0400, Matt Heckaman wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > On Mon, 26 Jun 2000, Brad Knowles wrote: > > : It's been my experience that when you start talking about > : significant amounts of RAM (anything over 128-256MB), you really, > : *really*, *REALLY* want to be using ECC. > > Interesting, I've always personally thought ECC to be somewhat overrated > and certaintly overpriced. Granted I do not have that much expierence in > comparison to some, but I have a machine here running 512M of non-ECC for > over a year now without any ram-related problems. (HD did die once though) Here in our lab, we have ~20 biprocessors doing heavy numerical computations with 512 Megs of non ECC memory. They work night and day, all days of the year without a single problem. Is the memory adding some entropy to the results? I don't know. -- Michel TALON To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000626140153.A11131>