Path: utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!ncrlnk!ncrcae!hubcap!Marshall
From: cline@cheetah.ece.clarkson.edu (Marshall Cline)
Newsgroups: comp.parallel
Subject: Re: scalability of n-cubes, meshes (was: IPSC Communications)
Message-ID: <7490@hubcap.clemson.edu>
Date: 19 Dec 89 18:32:41 GMT
Sender: fpst@hubcap.clemson.edu
Lines: 31
Approved: parallel@hubcap.clemson.edu

In article <7480@hubcap.clemson.edu> cleary@cpsc.ucalgary.ca (John Cleary) writes:

>In article <7427@hubcap.clemson.edu>, landman@hanami.Eng.Sun.COM (Howard A. Landman x61391) writes:
>It worth noting however that the temperature of a 3D cube rises very slowly
>with the number of nodes.  The heat lost by radiation (probably the only
>feasible mechanism in the limit) is porportional to A*T^4 where A is the
>surface area and T is the temperature.  If the radius of the 3D body is R then
>A scales as R^2 and the number of processors (N) and hence the total heat (per
>unit time) as R^3.  The result is that T scales as N^(1/12) pretty slow.
...
>	John G. Cleary

In case anyone doubts John's analysis, a quick example from nature
should help.  Small animals are generally very active and have high
metabolisms (consider a bird's heart-rate vs a grizzly bear's).  Why?
Ans: small animals have a low body_volume/surface_area ratio (R^3 /
R^2 gets small for small R).  But if you drag a whale up on a beach,
it will literally *cook* from its own body heat, having more pounds
per square inch.

The problem of designing big computers that don't cook themselves
therefore isn't new -- God had the same problem when designing big
animals!  The solution thus appears to be that big computers will need
better cooling systems.

Marshall
--
___________________________________________________________________
Marshall Cline/ECE Dept/Clarkson Univ/Potsdam NY 13676/315-268-3868
Internet: cline@sun.soe.clarkson.edu -or- bh0w@clutx.clarkson.edu
BitNet: bh0w@clutx  Usenet: uunet!sun.soe.clarkson.edu!cline