Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!ukma!rutgers!orstcs!sagen@nucthy.physics.orst.edu
From: sagen@nucthy.physics.orst.edu (Milt Sagen)
Newsgroups: comp.sys.mac
Subject: Byte Me and SE/30
Message-ID: <8628@orstcs.CS.ORST.EDU>
Date: 2 Feb 89 04:15:16 GMT
Sender: usenet@orstcs.CS.ORST.EDU
Reply-To: sagen@nucthy.physics.orst.edu (Milt Sagen)
Organization: Dept. of Physics, Oregon State University
Lines: 31

A direct quote from the Byte Magazine article describing the new SE/30

         ...Clearly, this machine is in a whole different league
         than the standard Mac SE.
            In particular, note that processor-intensive tests, such
         as the Sieve, String Move, and floating-point tests, show
         the SE/30 sometimes outperforming the standard SE by almost
         and order of magnitude.  To be fair, I should note that the
         standard SE does not have an FPU.
         
ALMOST AN ORDER OF MAGNITUDE FASTER, ALMOST...a 16 MHz 68030 with a 
16 MHz 68882 is NOT EVEN AN ORDER OF MAGNITUDE FASTER than a <12 MHz 68000
WITHOUT a floating point coprocessor?  Is this for real?


The floating point benchmarks for the SE/30 and SE where

                           SE/30 (sec)                      SE (sec)

math(?)                    147.6                            891.3

trapezoidal rule: sin(x)    73.3                            598.0

trapezoidal rule: exp(x)    97.9                            720.7



Milt Sagen                    Internet: sagen@nucthy.physics.orst.edu
Department of Physics
Oregon State University
Corvallis, OR  97331          Tele: (503) 754-4631