Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!tut.cis.ohio-state.edu!ucbvax!hplabs!hpl-opus!jewett
From: jewett@hpl-opus.HP.COM (Bob Jewett)
Newsgroups: comp.lsi
Subject: Re: Transient faults in memories
Message-ID: <62680002@hpl-opus.HP.COM>
Date: 19 Oct 89 19:40:20 GMT
References: <28172@shemp.CS.UCLA.EDU>
Organization: HP Labs, High Speed Electronics Dept., Palo Alto, CA
Lines: 13

> Does anybody actually have a reference on this "fact"?

None at hand, but there are lots of references.  Try a search on "soft
error rate" and "alpha particle induced errors" in the various IEEE
circuit-related journals (ED, EDL, JSSC, ...).

The actual experience in this department, is that there is about one "soft
error" in each 400 megabyte-months of DRAM use.  Since we have about 400
megabytes of DRAM installed in various workstations, there is roughly one
parity error per month.  Some of those are in ECC RAM, so it doesn't result
in a system crash.

Bob Jewett