From: baron@clifton.hobby.nl (Wim van Dorst)
Newsgroups: comp.os.linux.announce
Subject: Bogomips Information Sheet
Date: 18 Jan 1994 22:22:50 +0200
Approved: linux-announce@tc.cornell.edu (Lars Wirzenius)
Message-ID: <2hhgeq$3s1@klaava.Helsinki.FI>

[ Moderator's note: This is LaTeX code, for those who don't recognize it at
  sight.  --liw ]

\documentstyle[a4,longtable,dcolumn]{article}
\setlongtables
\begin{document}
\begin{center}
{\em BOGOMIPS(tm) INFORMATION SHEET} \\
Wim C.A. van Dorst {\tt <baron@clifton.hobby.nl>}
\end{center}

>From Lars Wirzenius' mail of 9 September 1993, explaining Bogomips:

\begin{quote}
MIPS is short for Millions of Instructions Per Second.  It is a
measure for the computation speed of a program.  Like most such
measures, it is more often abused than used properly (it is very
difficult to justly compare MIPS for different kinds of computers).

BogoMips are Linus's invention.  The kernel (or was it a device
driver?) needs a timing loop (the time is too short and/or needs to be
too exact for a non-busy-loop method of waiting), which must be
calibrated to the processor speed of the machine.  Hence, the kernel
measures at boot time how fast a certain kind of busy loop runs on a
computer.  "Bogo" comes from "bogus", i.e, something which is a fake.
(See the Jargon File for more information.)  Hence, the BogoMips value
gives some indication of the processor speed, but it is way too
unscientific to be called anything but BogoMips.

The reasons (there are two) it is printed during bootup is that a) it
is slightly useful for debugging and for checking that the computers
caches and turbo button work, and b) Linus loves to chuckle when he
sees confused people on the news.
\end{quote}

>From Daniel Quinlan's mail of 1 October 1993 about his conclusion:

\begin{quote}
Nevertheless, I (being bored and curious) collected all of the
postings for non-odd processors and BogoMip(tm) scores and calculated
a rough linear standard deviation.

for a 386dx (no coprocessor): BogoMips(tm) = (clock rate) * 0.24 - 1.9

for a 486dx (not chip doubled): BogoMips(tm) = (clock rate) * 0.5
\end{quote}


>From Ian Jackson's List of Frequently asked questions, of 3 January 1994:

\begin{quote}
Question 6.3.  What is a BogoMip ?

`BogoMips' is a contraction of `Bogus MIPS'.  MIPS stands for (depending
who you listen to) Millions of Instructions per Second, or Meaningless
Indication of Processor Speed.

The number printed at boot-time is the result of a kernel timing
calibration, used for delay loops by some device drivers.

As a very approximate guide for a 486DX (not clock doubled), the BogoMips
will be approximately the clock rate * 0.5; for a 386DX (no coprocessor)
it will be more like the clock rate * 0.24 - 1.9.

If the number you're seeing is wildly lower than this you may have the
Turbo button or CPU speed set incorrectly, or have some kind of caching
problem [as described in Q6.6 `When I add more memory it slows to a
crawl.'.]
\end{quote}

Let me add that there are only two reasons for paying attention
to the Bogomips rate that is presented on booting Linux:

\begin{enumerate}
\item To see whether it is in the proper range for the particular
processor, its clock frequency, and the potentially present cache.
Especially 486 systems are prone to faulty setups of RAM caching,
turbo-buttons, and such things.
\item To see whether your system is faster than mine. Of course
this is completely wrong, unreliable, ill-founded, and utterly
useless, but all benchmarks suffer from this same problem. So
why not use it? This inherent stupidity has never before stopped people
from using benchmarks, has it? :-)
\end{enumerate}

\clearpage
The following are some reported Bogomips rates for various systems. 


\begin{longtable}[c]{@{}l D{.}{.}{4} l@{}}
\em System & \multicolumn{1}{c}{\em Bogomips} & \em Reporter \\
\\
\multicolumn{3}{@{}l}{\em Oddly or faulty configured 386 systems} \\
386DX/16 387 nocache      &  0.57 & hpa@ahab.eecs.nwu.edu (H. Peter Anvin) \\
386/16 Zenith             &  0.67 & hpa@ahab.eecs.nwu.edu (H. Peter Anvin)  \\
\\
\multicolumn{3}{@{}l}{\em Normal 386 SX systems} \\
386SX/16 Packard Bell     &  2.05 & root@Belvedere\%hip-hop.suvl.ca.us  \\
386SX/16                  &  2.23 & acb@yoyo.cc.monash.edu.au (Andrew Bulhak) \\
386SX/16 nocache          &  2.43 & adamc@loose.apana.org.au (Adam Clarke) \\
386SXL/25 AMD             &  2.9  & pratt@Sunburn.Stanford.EDU (Vaughan R. Pratt) \\
386SX/25 AMD nocache      &  3.06 & kenny@festival.ed.ac.uk (K.J. MacDonald) \\
386SX/25 AMD              &  3.38 & hamish@zot.apana.org.au (Hamish Coleman) \\
386SL/25 Intel            &  3.57 & harris@teaching.physics.ox.ac.uk (Stephen Harris) \\
386SX/25 AMD              &  3.62 & harris@teaching.physics.ox.ac.uk (Stephen Harris) \\
386SX/33 Intel            &  4.06 & ken@PSUEDVAX.PSU.EDU (Kenneth J. Hoover) \\
386SX/33                  &  4.71 & apkom@l.ukrcom.kherson.ua (Alexander Pet. Komlik) \\
\\
\multicolumn{3}{@{}l}{\em Normal 386 DX systems} \\
386DX/20 Intel            &  3.08 & harris@teaching.physics.ox.ac.uk (Stephen Harris) \\
386DX/20                  &  3.67 & jhelberg@nlsun8.oracle.nl (Joost Helberg) \\
386DX/25                  &  3.91 & imcclogh@cs.ucsd.edu (Ian McCloghrie) \\
386DX/25                  &  3.95 & grante@aquarius.rosemount.com (Grant Edwards) \\
386DX/25 32cache          &  4.53 & jmalahti@klaava.Helsinki.FI (Jussi M.A. Lahtinen) \\
386DX/33                  &  5.86 & timla@microsoft.com (Tim Lacy) \\
386DX/33 64cache          &  5.99 & wirzeniu@kruuna.Helsinki.FI (Lars Wirzenius) \\
386DX/33 Intel            &  5.99 & hpasanen@cs.hut.fi (Harri Pasanen) \\
386DX/33 no387            &  6.03 & levin@bbn.com (Joel B.Levin) \\
386DX/33 387              &  6.03 & peter@fns.greenie.muc.de (Peter Bechtold) \\
386DX/33 387 256cache     &  6.65 & baron@clifton.hobby.nl (Wim van Dorst) \\
386DX/40                  &  6.99 & wilcox@math.psu.edu (Ken Wilcox) \\
386DX/40 AMD              &  7.10 & kperson@plains.NoDak.edu (Kerry Person) \\
386DX/40 128cache         &  7.23 & jfd0@aber.ac.uk (Julian Francis Day) \\
386DX/40 AMD 128cache     &  7.23 & rabe@akela.informatik.rwth-aachen.de (Ralf Bergs) \\
386DX/40                  &  7.29 & ericg@nickel.ucs.indiana.edu (Eric Chris Garrison) \\
386DX/40                  &  7.29 & cowan@rubicon.org (Darin Cowan) \\
386DX/40                  &  7.29 & bonne@cs.utwente.nl (Bonne van Dijk) \\
\\
\multicolumn{3}{@{}l}{\em Oddly or faulty configured 486 systems} \\
486DX/33 nocache          &  1.45 & vatavian@gvu1.gatech.edu (Mark Gray) \\
486SX/33 noturbo          &  5.21 & sdh@fishmonger.nouucp (Scott D. Heavner) \\
486DX/33 256c noturbo     &  4.25 & wlieftin@cs.vu.nl (Wouter Liefting) \\
486DX/33                  &  4.66 & vatavian@gvu1.gatech.edu (Mark Gray) \\
486Rx2 Cyrix 25/50        &  4.85 & cosc19v2@menudo.uh.edu  \\
486SX/20 DECpc420sx       &  9.98 & pfau@cnj.digex.com (Thomas Pfau) \\
486DLC/33 Cx 386hybrid    & 11.2  & freed@europa.orion.adobe.com (Alex Freed) \\
\\
\multicolumn{3}{@{}l}{\em 486 systems} \\
486SX/25                  & 12.24 & Michael Buchenrieder (mibu@scrum.greenie.muc.de)  \\
486SX25                   & 12.42 & mlindsey@nyx.cs.du.edu (Mark R. Lindsey) \\
486DRx2/40 Cyrix 20/40    & 13.10 & root@fusion.cuc.ab.ca \\
486DRx2/40 Cyrix          & 13.10 & clau@acs.ucalgary.ca (Christopher Lau) \\
486DLC/40 487 cyrix       & 13.21 & iav@po.CWRU.Edu (Ian A. Verschuren) \\
486SLC2/50 25Mhz          & 14.6  & pratt@Sunburn.Stanford.EDU (Vaughan R. Pratt) \\
486DX/33                  & 15.8  & hpa@ahab.eecs.nwu.edu (H. Peter Anvin) \\
486DX/33 64cache          & 16.1  & hpa@ahab.eecs.nwu.edu (H. Peter Anvin) \\
486DX/33 256c DIY         & 16.44 & wlieftin@cs.vu.nl (Wouter Liefting) \\
486DX/33 Intel 128c       & 16.44 & g1krakow@cdf.toronto.edu (Rafal Kustra) \\
486DX/33                  & 16.5  & freed@europa.orion.adobe.com (Alex Freed) \\
486DX/33                  & 16.6  & pratt@Sunburn.Stanford.EDU (Vaughan R. Pratt) \\
486DX/33 noturbo          & 16.61 & cbvetter@rbg.informatik.th-darmstadt.de (Chris Vetter) \\
486DX/33                  & 16.61 & jnewbern@athena.mit.edu (Jeffrey L. Newbern) \\
486SLC2/66                & 19.02 & mangalam@uci.edu (Harry Mangalam) \\
486DX/40 Intel            & 19.97 & vspr@teppic.sun.ac.za (Paul van Spronsen) \\
486DX/40                  & 19.97 & ulf@rio70.bln.sni.de (Ulf Tietz) \\
486DX/40                  & 19.97 & Eberhard\_Moenkeberg@p27.rollo.central.de (E. Moenkeberg) \\
486DX/33 turbo            & 19.98 & cbvetter@rbg.informatik.th-darmstadt.de (Chris Vetter) \\
486DX/50                  & 24.48 & arnd@rea (Arnd Gehrmann) \\
486DX/50 DTK              & 24.85 & randyc@lna.oz.au (Randolph Christophers) \\
486DX2/50                 & 25.0  & choltje@ux1.cso.uiuc.edu (Christian Holtje) \\
486dx2/66                 & 33    & alecm@uk-usenet.uk.sun.com (Alec Muffett) \\
486DX2/66                 & 33    & sjt@enlil.museum.upenn.edu (Steve Tinney) \\
486DX2/66                 & 33.2  & hpa@ahab.eecs.nwu.edu (H. Peter Anvin) \\
486DX2/66                 & 33.20 & arnd@rea (Arnd Gehrmann) \\
486DX2/66 256cache        & 33.4  & hpa@ahab.eecs.nwu.edu (H. Peter Anvin) \\
486DX2/66                 & 33.5  & mr2@netcom.com (Jongyoon Lee) \\
486DX2/66                 & 33.55 & al-b@minster.york.ac.uk  \\
486DX2/66 ICL ErgoPRO     & 33.55 & mathias@solomon.technet.sg (Mathias Koerber) \\
486dx2/66 256c Intel      & 33.81 & harris@teaching.physics.ox.ac.uk (Stephen Harris) \\
486DX2/66                 & 34.06 & aclark@netcom.com (Al Clark) \\
486dx2/80                 & 39.94 & danny@caution.cistron.nl.mugnet.org (Danny ter Haar) \\
\\
\em Pentium systems \\
Pentium                   & 23.96 & jhelberg@nlsun8.oracle.nl (Joost Helberg) \\
Pentium                   & 23.96 & ulf@rio70.bln.sni.de (Ulf Tietz) \\
\end{longtable}

This overview was compiled by me, quite lonely this sunday evening 9
January 1994 because my wife is off to the US for a business trip.

Met vriendelijke groeten, Wim van Dorst.
\begin{verbatim}
---------------------------------------------------------------------
Blue Baron = Wim van Dorst, Voice (+31) 074-443937, (+31) 02152-42319
(-: baron@clifton.hobby.nl  tgcpwd@urc.tue.nl  WvD@Akzo.400net.nl :-)
---------------------------------------------------------------------
\end{verbatim}
\end{document}
---------------------------------------------------------------------
Blue Baron = Wim van Dorst, Voice (+31) 074-443937, (+31) 02152-42319
(-: baron@clifton.hobby.nl  tgcpwd@urc.tue.nl  WvD@Akzo.400net.nl :-)
---------------------------------------------------------------------

--
Mail submissions for comp.os.linux.announce to: linux-announce@tc.cornell.edu
PLEASE remember Keywords: and a short description of the software.
