Path: utzoo!news-server.csri.toronto.edu!rutgers!gatech!udel!rochester!pt.cs.cmu.edu!gandalf.cs.cmu.edu!lindsay
From: lindsay@gandalf.cs.cmu.edu (Donald Lindsay)
Newsgroups: comp.arch
Subject: Re: massive parallelism, was  CDC 6600 and TI ASC
Message-ID: <12315@pt.cs.cmu.edu>
Date: 11 Mar 91 03:39:15 GMT
References: <781@llnl.LLNL.GOV>
Organization: Carnegie Mellon
Lines: 14

In article <781@llnl.LLNL.GOV> 
	brooks@physics.llnl.gov (Eugene D. Brooks III) writes:
>Scatter/gather is the equivalent of the communication on the CM.  On
>a Cray XMP or YMP the scatter/gather bandwidth matches the cpu speed
>just fine and does not represent a bottleneck.  It is certainly not
>as hampered as the "router" functionality on the CM-2 which is a severe
>mismatch for the PE computational bandwidth.

It was mismatched on the CM-1, too. Would anyone care to comment on
why the CM-2 didn't improve in this area? Is there something
intrinsic to their design, or their implementation strategy?

-- 
Don		D.C.Lindsay .. temporarily at Carnegie Mellon Robotics