Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!uflorida!gatech!prism!loligo!mccalpin
From: mccalpin@loligo.cc.fsu.edu (John McCalpin)
Newsgroups: comp.arch
Subject: Re: CDC 205 et al
Message-ID: <657@loligo.cc.fsu.edu>
Date: 2 May 89 11:06:31 GMT
References: <568309@vaxa.uwa.oz>
Reply-To: mccalpin@loligo.cc.fsu.edu (John McCalpin)
Organization: Supercomputer Computations Research Institute
Lines: 18

In article <568309@vaxa.uwa.oz> g_ahrendt@vaxa.uwa.oz writes:
>... the following gives a more accurate picture, 
>based on machines actually available, and not scheduled for production.
                   ^^^^^^^^^^^^^^^^^^
>1. ETA               US 10-G       10.3 Billion Instructions per Second 

Not quite.  The above figure is for an 8-cpu ETA-10G, and there exists
no such machine. The only ETA-10G in the world is the 4-cpu machine at
Florida State University.  The 10.3 GFLOPS is also a ridiculously optimistic
estimate.  The peak performance on our 4-cpu machine is about 4.5 GFLOPS.
To get that number up to 5.15 GFLOPS requires an extremely implausible
workload in the scalar processor operating concurrently with the vector
units and never accessing main memory....
-- 
----------------------   John D. McCalpin   ------------------------
Dept of Oceanography & Supercomputer Computations Research Institute
mccalpin@masig1.ocean.fsu.edu		mccalpin@nu.cs.fsu.edu
--------------------------------------------------------------------