Path: utzoo!attcan!uunet!husc6!uwvax!rutgers!mailrus!csd4.milw.wisc.edu!nic.MR.NET!shamash!raspail!bga
From: bga@raspail.UUCP (Bruce Albrecht)
Newsgroups: comp.arch
Subject: Re: Cray Quotations
Message-ID: <1112@raspail.UUCP>
Date: 22 Dec 88 15:05:56 GMT
References: <2496@ficc.uu.net> <8841@sequent.UUCP> <2523@ficc.uu.net>
Organization: Control Data Corporation, Arden Hills, MN
Lines: 12

In article <2523@ficc.uu.net>, karl@ficc.uu.net (karl lehenbauer #) writes:
> I know the CDC 6600, Cyber 70 and 170 series machines did not have parity.
> From what I heard Seymour felt that parity didn't buy much -- detection
> of a parity error meant death for the running program at the least and
> maybe even for the OS.  There was always the chance that the parity error 
> would occur in the parity bit, causing a parity error when there was
> no actual data error.

The Cyber 170s have single error correction, double error detection.  The
170s also had parity on the channels, extended memory and the PPs.  I think
most of the design (if not all) for the 170s were done after Cray left CDC,
so maybe that was a factor.