Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.milw.wisc.edu!lll-winken!uunet!steinmetz!davidsen
From: davidsen@steinmetz.ge.com (Wm. E. Davidsen Jr)
Newsgroups: comp.arch
Subject: Re: Drum memory
Message-ID: <13447@steinmetz.ge.com>
Date: 27 Mar 89 15:45:57 GMT
References: <21976@lll-winken.LLNL.GOV> <28411@ucbvax.BERKELEY.EDU> <1487@wpi.wpi.edu> <95741@sun.Eng.Sun.COM>
Reply-To: davidsen@crdos1.UUCP (bill davidsen)
Organization: General Electric CRD, Schenectady, NY
Lines: 18

In the late 60's GE had two projects running as possible replacements
for the GECOS o/s. These were the based on modified GE-600 computers.
The one here was a 605 (why the 605 came after the 635 I don't know),
and the one at MIT was the 645, running Multics.

The 605 had a drum which transferred a 72 bit double word in 7 us, which
was really brisk for those times. The Multics system used a faster drum
yet. I can't remember the model numbers, I think ours was an xxx-10, but
the code names were "garden hose" (ours) and "fire hose" (MIT's).

GE also made a head-per-track disk called the 270, which didn't have a
high transfer rate, but had a very good seek time. We also made a disk
with four arm assumblies, which could do seeks on three arms while doing
i/o on the other.
-- 
	bill davidsen		(wedu@crd.GE.COM)
  {uunet | philabs}!steinmetz!crdos1!davidsen
"Stupidity, like virtue, is its own reward" -me