Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!uwm.edu!rpi!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!emory!hubcap!landman
From: landman@hanami.Eng.Sun.COM (Howard A. Landman x61391)
Newsgroups: comp.parallel
Subject: Re: scalability of n-cubes, meshes (was: IPSC Communications)
Message-ID: <7427@hubcap.clemson.edu>
Date: 14 Dec 89 15:45:59 GMT
Sender: fpst@hubcap.clemson.edu
Lines: 22
Approved: parallel@hubcap.clemson.edu

>In article <7274@hubcap.clemson.edu> gene@cs.bu.edu (Gene Itkis) writes:
>%One problem with 3D mesh is that as the processors work the heat is
>%generated(*).....

In article <7373@hubcap.clemson.edu> bjornl@tds.kth.se (Bj|rn Lisper) writes:
>You implicitly assume that the 3D mesh is a solid body. This is not
>necessarily true. It could for instance consist of a stack of cards, with
>air flowing between them, or have channels with coolant flowing through. In
>this way, you get the same cooling area as for the 2D mesh.

No, he doesn't assume that.  This is important.  At some point the heat must
exit the surface of the 3D cube.  Regardless of what method you use, it will
have some limit per area, and so the surface area limits the amount of heat
you can dissipate.  Even if the machine is spewing out white-hot steam at the
speed of light, this limit exists.

As noted by Gene, you either figure out how to do reversible computation that
doesn't dissipate a fixed amount of heat per operation, or you live with the
limit.

	Howard A. Landman
	landman%hanami@eng.sun.com