[comp.misc] Cooling Big Iron

esf00@amdahl.UUCP (10/02/87)

In article <4673@nsc.nsc.com> woolsey@nsc.UUCP (Jeff Woolsey) writes:
>Cray cooling uses water or freon (I forget which) pumped through the
>aluminum columns.

Corporate approaches to cooling big iron have stayed constant for
the last 20 or so years:

	CRAY = FREON (tm) [CRAY-1, X/MP, CRAY-2, Y/MP ... ]
	CDC (originally S. Cray designs) = FREON [6600, 7600, Cyber 203,
		Cyber 205, ... ]
	Amdahl = air [470V/6, 470V/8, 580, 5890, ... ]
	IBM = water [360/91, 360/195, 370/165, 370/168, 308x, 3090 ... ]

-- 

Elliott S Frank    ...!{hplabs,ames,sun}!amdahl!esf00     (408) 746-6384
               or ....!{bnrmtv,drivax,hoptoad}!amdahl!esf00

[the above opinions are strictly mine, if anyone's.]
[the above signature may or may not be repeated, depending upon some
inscrutable property of the mailer-of-the-week.]

alan@mn-at1.UUCP (Alan Klietz) (10/04/87)

In article <15469@amdahl.amdahl.com> esf00@amdahl.amdahl.com (Elliott S. Frank) writes:
<Corporate approaches to cooling big iron have stayed constant for
<the last 20 or so years:
<
<	CRAY = FREON (tm) [CRAY-1, X/MP, CRAY-2, Y/MP ... ]

Technically, the CRAY-2 is immersed in a bath of Fluroinert(tm), 
an odorless, colorless, tasteless, non-corrosive, etc. viscous
fluid produced by 3M company.  I believe its primary use is as
a liquid base for artificial blood plasma. 

It's damn expensive (~$100/gal).  Several gallons evaporate away every
time the machine opened for repair (due to its low vapor pressure).

--
Alan Klietz
Minnesota Supercomputer Center (*)
1200 Washington Avenue South
Minneapolis, MN  55415    UUCP:  ..rutgers!meccts!mn-at1!alan
Ph: +1 612 626 1836              ..ihnp4!dicome!mn-at1!alan (beware ihnp4)
                          ARPA:  alan@uc.msc.umn.edu  (was umn-rei-uc.arpa)

(*) An affiliate of the University of Minnesota

mccarthy@uxe.cso.uiuc.edu (10/07/87)

Written  1:29 pm  Oct  4, 1987 by alan@mn-at1.UUCP (Alan Klietz)
>Technically, the CRAY-2 is immersed in a bath of Fluroinert(tm), 
....
>It's damn expensive (~$100/gal).  Several gallons evaporate away every
>time the machine opened for repair (due to its low vapor pressure).

Don't they drain the stuff into some reservoirs before they open the
Cray up?  All the pictures I've seen of Cray-2's have either a bunch of
clear plastic cylinders or a clear-and-black thing about the size of a
jukebox behind it, that I thought were for Fluroinert(tm) storage when
the inside of the Cray-2 needed getting into.  It seems like if you lost
several hundred dollars each time you open it, you could rack up a rather
big loss in a hurry, especially if you open it as often as we open the
X-MP we have here. (at least 3x/week for preventative maintenence.)

BTW, we're getting a Cray-2 soon, so maybe I can find out for myself.
_____
D. J. McCarthy

tel@moby.UUCP (Tom Lowe) (10/09/87)

> Written  1:29 pm  Oct  4, 1987 by alan@mn-at1.UUCP (Alan Klietz)
> >Technically, the CRAY-2 is immersed in a bath of Fluroinert(tm), 
> ....
> >It's damn expensive (~$100/gal).  Several gallons evaporate away every
> >time the machine opened for repair (due to its low vapor pressure).

I get the impression that if you can afford the electric bills for the
beast, then a few hundred dollars to open the cabinet is a small drop
in a rather large bucket!  Even if you open it a couple times a week.

Anyone have any ideas how much the electric bills are just to run and 
cool the beast?

-- 
Tom Lowe {rutgers,gatech,huscb,burdvax,ihnp4,cbosgd}!psuvax1!moby!tel
AT&T National Systems Support Center, S. Plainfield, NJ  (1-800-922-0354)
  Please call only if you have an AT&T computer under Warranty or if you
  have an AT&T Maintenance Contract on your equipment.