home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 1996 November
/
Chip 11-96.iso
/
workshop
/
howto
/
bogomips
< prev
next >
Wrap
INI File
|
1996-05-25
|
16KB
|
287 lines
[]
BOGOMIPS(tm) mini-HOWTO
Wim C.A. van Dorst <baron@clifton.hobby.nl>
11 June 1994
This text gives a little information about BogoMips, compiled
from various sources by news and mail.
The Lowest: H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
386DX/16 387 nocache
0.57 BogoMips
The Highest: Rick Brown <ccastrb@prism.gatech.edu>
486DX2/80
40.0 BogoMips
>From Lars Wirzenius' mail of 9 September 1993, explaining Bogomips:
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. 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.
>From an setup in Ian Jackson's List of Frequently asked questions, of
23 January 1994, and from mail from Przemek Klosowski at 29 March 1994,
updated for current data:
As a very approximate guide the BogoMips will be:
System BogoMips Index
386SX clock * (0.14 plusminus 0.01) 0.76
386DX clock * (0.18 plusminus 0.01) 1 (definition)
486Cyrix/IBM clock * (0.33 plusminus 0.04) 1.84
486SX/DX/DX2 clock * (0.50 plusminus 0.01) 2.80
Pentium clock * (0.39 plusminus 0.01) 2.21
Note that the BogoMips calculation loop is not optimized
for the parallelism of the Pentium processor.
>From Linus Torvalds, explaining about the variation one may see
in the BogoMips rating, in col.development, at 28 April 1994
The BogoMips calculation loop is "quantizised", so you're
most likely to get the exact same number all the time.
You usually will get different numbers only if the speed
is just on the "edge", when small variations (different
time for interrupt ticks etc) will make it jump from one
value to the other.
>From the readme file of the standalone BogoMips program
by Jeff Tranter.
Tired of rebooting your system so you can see how many
BogoMIPS it's running at today? [...] "Bogomips" is a
standalone program that displays your system performance
using one of the world's most recognized benchmarks. It
uses the same code that is used in the Linux kernel while
booting, but runs as a user program. [...] Version 1.3 of
BogoMIPs is now portable and should run on any system
that supports an ANSI C compiler and library.
Note that due to system load values calculated with the
standalone program may be lower than from the booting
sequence, and thus than registered in the list below.
Let me add that there are only two reasons for paying attention
to the BogoMips rating that is presented on booting Linux:
1. 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.
2. 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? :-)
The following table gives some reported BogoMips ratings for
various systems. Note that the ratings here are from the Linux
actual boot sequence.
A. Oddly or faultly configured 386 systems
System BogoMips Reporter
386DX/16 387 nocache 0.57 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
386/16 Zenith 0.67 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
386DX/25 0.82 Philip Wright <philip.wright@purplet.demon.co.uk>
386DX/25 nocache 1.03 Mark A. Horton <mahmha@crl.com>
386SX/16 1.5 Stefan Kromer <sk@galaxy.sunflower.sub.org>
386SX/20 1.87 Paul C. Dulany <pcdulany@wam.umd.edu>
386DX/25(?) 128c 6.03 Chuck Meo <meo@solbourne.com>
B. Normal 386 SX systems
System BogoMips Reporter
386SX/16 Packard Bell 2.05 <root@Belvedere\%hip-hop.suvl.ca.us>
386SX/16 2.15 Warren Stevens <wgsteven@undergrad.math.uwaterloo.co>
386SX/16 2.2 Lech Marcinkowski <puolalm@tekla.fi>
386SX/16 2.23 Andrew Bulhak <acb@yoyo.cc.monash.edu.au>
386SX/16 2.23 Steven M. Gallo <smgallo@cs.buffalo.edu>
386SX/16 turbo 2.38 Andrew Haylett <ajh@gec-mrc.co.uk>
386SX/16 nocache 2.43 Adam Clarke <adamc@loose.apana.org.au>
386SX/20 2.7 Alex Strasheim <astrashe@nyx.cs.du.edu>
386SXL/25 AMD 2.9 Vaughan R. Pratt <pratt@Sunburn.Stanford.EDU>
386SX/25 AMD nocache 3.06 K.J. MacDonald <kenny@festival.ed.ac.uk>
386SX/25 AMD 3.38 Hamish Coleman <hamish@zot.apana.org.au>
386SL/25 Intel 3.57 Stephen Harris <harris@teaching.physics.ox.ac.uk>
386SX/25 AMD 3.62 Stephen Harris <harris@teaching.physics.ox.ac.uk>
386SX/33 Intel 4.06 Kenneth J. Hoover <ken@PSUEDVAX.PSU.EDU>
386SX/33 4.71 Alexander Pet. Komlik <apkom@l.ukrcom.kherson.ua>
C. Normal 386 DX systems
System BogoMips Reporter
386DX/20 Intel 3.0 Malcolm Reeves <reeves@rocky1.usask.cs>
386DX/20 Intel 3.08 Stephen Harris <harris@teaching.physics.ox.ac.uk>
386DX/20 Nec Powermate 3.22 David J Dawkins <davidd@isl.co.uki>
386DX/20 3.67 Joost Helberg <jhelberg@nlsun8.oracle.nl>
386DX/25 3.91 Ian McCloghrie <imcclogh@cs.ucsd.edu>
386DX/25 3.95 Grant Edwards <grante@aquarius.rosemount.com>
386DX/25 32cache 4.53 Jussi M.A. Lahtinen <jmalahti@klaava.Helsinki.FI>
386DX/33 5.86 Tim Lacy <timla@microsoft.com>
386DX/33 64cache 5.99 Lars Wirzenius <wirzeniu@kruuna.Helsinki.FI>
386DX/33 Intel 5.99 Harri Pasanen <hpasanen@cs.hut.fi>
386DX/33 no387 6.03 Joel B.Levin <levin@bbn.com>
386DX/33 387 6.03 Peter Bechtold <peter@fns.greenie.muc.de>
386DX/33 387 256cache 6.65 Wim van Dorst <baron@clifton.hobby.nl>
386DX/40 6.99 Ken Wilcox <wilcox@math.psu.edu>
386DX/40 AMD 7.10 Kerry Person <kperson@plains.NoDak.edu>
386DX/40 7.10 Dhaliwal Bikram Singh <a336dhal@cdf.toronto.edu>
386DX/40 128cache 7.23 Julian Francis Day <jfd0@aber.ac.uk>
386DX/40 bogoboosted 7.23 Pat St Jean <stjean@math.enmu.edu>
386DX/40 AMD 128cache 7.23 Ralf Bergs <rabe@akela.informatik.rwth-aachen.de>
386DX/40 slow DRAM 7.26 John Lockwood <lockwood@pan.vlsi.uiuc.eu>
386DX/40 128c 7.29 Karsten Friese <ftdkafr@ftd.ericsson.se>
386DX/40 7.29 Eric Chris Garrison <ericg@nickel.ucs.indiana.edu>
386DX/40 7.29 Darin Cowan <cowan@rubicon.org>
386DX/40 7.29 Bonne van Dijk <bonne@cs.utwente.nl>
386DX/40 AMD 387 64c 7.91 <wires@gnu.ai.mit.edu>
396DX/40 64c 7.98 Dean Junk <dpjunk@mm.com>
386DX/40 AMD 32c 7.98 Tommy Olsen <tommyo@ifi.uio.no>
386DX/40 7.98 Christian Nelson <cnelson@csugrad.cs.vt.edu>
D. Oddly or faultly configured 486 systems
System BogoMips Reporter
486DX/33 nocache 1.45 Mark Gray <vatavian@gvu1.gatech.edu>
486DLC/40 nocache 2.45 Steven Schendel <sschend@magnus.acs.ohio-state.edu>
486DX/33 3.61 Marten van de Laan <marten@cs.rug.nl>
486DX/33 noturbo 3.61 Dimitris Evmorfopoulos <devmorfo@mtu.edu>
486DX/33 256c noturbo 4.25 Wouter Liefting <wlieftin@cs.vu.nl>
486DX/33 4.66 Mark Gray <vatavian@gvu1.gatech.edu>
486Rx2 Cyrix 25/50 4.85 <cosc19v2@menudo.uh.edu>
486SX/33 noturbo 5.21 Scott D. Heavner <sdh@fishmonger.nouucp>
486SLC Cyrix 7 Pieter Verhaeghe <pive@uia.ac.be>
486DLC/33 387DX/40 9.47 Denis Solaro <drzob@vectrex.login.qc.ca>
486SLC2/25 14.6 Vaughan R. Pratt <pratt@Sunburn.Stanford.EDU>
486DX/33 turbo 19.98 Chris Vetter <cbvetter@rbg.informatik.th-darmstadt.de>
E. Cyrix/IBM configured 486 systems
System BogoMips Reporter
486DLC/33 Cyrix 386 11.2 Alex Freed <freed@europa.orion.adobe.com>
486DLC/40 256c 11.33 Steven Schendel <sschend@magnus.acs.ohio-state.edu>
486DRx2/40 Cyrix 13.10 Christopher Lau <clau@acs.ucalgary.ca>
486DLC/40 bogoboost 13.21 Harry Pasanen <ps@tekla.fi>
486DLC/40 487 Cyrix 13.21 Ian A. Verschuren <iav@po.CWRU.Edu>
486DCL Cyrix 13.3 Tracer Bullet P.I. <ges@earth.baylor.edu>
486DLC/40 13.31 Adam Frampton <frampton@access2.digex.net>
486DLC/40 13.31 Rick Chow <crc@cacs.usl.edu>
486DLC/40 TI 128c 15.97 Philip K. Roban <phil@seal.micro.umn.edu>
486DRx2 20/40 15.99 Christopher Lau <lauc@fusion.cuc.ab.ca>
486SLC2/66 IBM 64c 18.95 Sujat Jamil <sujat@shasta.ee.umn.edu>
486SLC2/66 IBM 128c 18.95 Sujat Jamil <sujat@shasta.ee.umn.edu>
486SLC2/66 19.02 Harry Mangalam <mangalam@uci.edu>
F. Normal 486 systems
System BogoMips Reporter
486SX/20 DECpc 9.98 Thomas Pfau <pfau@cnj.digex.com>
486SX/25 12.24 Michael Buchenrieder <mibu@scrum.greenie.muc.de>
486SX/25 12.42 Mark R. Lindsey <mlindsey@nyx.cs.du.edu>
486DX/25 12.5 Phillip Hardy <phillip@mserve.kiwi.gen.nz>
486DX/33 15.8 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
486DX/33 64cache 16.1 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
486DX/33 256c 16.33 Eric Kemminan <ekemmina@pms709.ms.ford.com>
486DX/33 16.35 Christopher L. Morrow <cm43@andrew.cmu.edu>
486DX/33 256c DIY 16.44 Wouter Liefting <wlieftin@cs.vu.nl>
486DX/33 Intel 128c 16.44 Rafal Kustra <g1krakow@cdf.toronto.edu>
486DX/33 16.5 Alex Freed <freed@europa.orion.adobe.com>
486DX/33 16.6 Vaughan R. Pratt <pratt@Sunburn.Stanford.EDU>
486DX/33 noturbo 16.61 Chris Vetter <cbvetter@rbg.informatik.th-darmstadt.de>
486DX/33 16.61 Jeffrey L. Newbern <jnewbern@athena.mit.edu>
486DX/33 16.61 M. Heuler <heuler@cip.informatik.uni-wuerzburg.edu>
486DX/33 16.61 Frank Lofaro <ftlofaro@unlv.edu>
486DX/40 19.8 Jose Calhariz <cal@minerva.inesc.pt>
486DX/40 19.91 M. Heuler <heuler@cip.informatik.uni-wuerzburg.edu>
486DX/40 Intel 19.97 Paul van Spronsen <vspr@teppic.sun.ac.za>
486DX/40 19.97 Ulf Tietz <ulf@rio70.bln.sni.de>
486DX/40 19.97 <Eberhard\_Moenkeberg@p27.rollo.central.de>
486DX/40 AMD 20 Chuck Munro <chuckm@canada.hp.com>
486DX/50 24.48 Arnd Gehrmann <arnd@rea>
486DX/50 AMD 24.85 Klaas Hemstra <hst@mh.nl>
486DX/50 DTK 24.85 Randolph Christophers <randyc@lna.oz.au>
486DX/50 24.85 Kevin Lentin <kevinl@bruce.cs.monash.edu.au>
486DX2/50 24.85 Jason Matthew <jmatthew@kn.pacbell.com>
486DX/50 25 Robert Herzog <rherzog@rc1.vub.ac.be>
486DX2/50 25.0 Christian Holtje <choltje@ux1.cso.uiuc.edu>
486DX2/50 DECpc 25.04 Thomas Pfau <pfau@cnj.digex.com>
486DX/50 25.10 M. Heuler <heuler@cip.informatik.uni-wuerzburg.edu>
486DX2/66 33 Alec Muffett <alecm@uk-usenet.uk.sun.com>
486DX2/66 33 Steve Tinney <sjt@enlil.museum.upenn.edu>
486DX2/66 Intel 33 Chuck Munro <chuckm@canada.hp.com>
486DX2/66 33.2 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
486DX2/66 33.20 Arnd Gehrmann <arnd@rea>
486DX2/66 33.22 Brian Ricker <gt2327c@prism.gatech.edu>
486DX2/66 33.22 Chien-An Chen <giant@nwu.edu>
486DX2/66 Eisa/VL 33.22 Serge <sviznyuk@magnus.acs.ohio-state.edu>
486DX2/66 AMD 33.22 Wayne Robinson <wayner@renoir.cftnet.com>
486DX2/66 33.3 Devon Tuck <devon@netcom.com>
486DX2/66 256cache 33.4 H. Peter Anvin <hpa@ahab.eecs.nwu.edu>
486DX2/66 33.5 Jongyoon Lee <mr2@netcom.com>
486DX2/66 33.55 <al-b@minster.york.ac.uk>
486DX2/66 ICL 33.55 Mathias Koerber <mathias@solomon.technet.sg>
486DX2/66 256c Intel 33.81 Stephen Harris <harris@teaching.physics.ox.ac.uk>
486DX2/66 34.06 Al Clark <aclark@netcom.com>
486/66 overclocked 39.94 Mario L. Guttierez <mgutier@mentor.sdu.edu>
486DX2/80 39.94 Danny ter Haar <danny@caution.cistron.nl.mugnet.org>
486DX2/80 40.0 Rick Brown <ccastrb@prism.gatech.edu>
G. Normal Pentium systems
System BogoMips Reporter
Pentium/60 23 Chien-An Chen <giant@nwu.edu>
Pentium 23.96 Joost Helberg <jhelberg@nlsun8.oracle.nl>
Pentium 23.96 Ulf Tietz <ulf@rio70.bln.sni.de>
Pentium/60 Gateway 23.96 Manoj Kasichainula <mvkasich@eos.ncsu.edu>
Pentium/60 NCR 3455 24 Mathias Koerber <mathias@solomon.technet.sg>
Pentium/66 25 Chuck Munro <chuckm@canada.hp.com>
Pentium/90 36 Larry Auton <lda@nfa.research.att.com>
Pentium/90 Zeos 36.08 Chris Laurel <claurel@mr.net>
H. Other systems
System BogoMips Reporter
68030/25 Amiga 3000 6.21 Hamish Macdonald <hamish@bnr.ca>
68040/24 Amiga 4000/40 16.6 Hamish Macdonald <hamish@bnr.ca>
Isolde is now one month (plus one day) old. She has discovered
that when you start screaming earlier than seven o' clock in
the morning, you might even get an extra bottle.
Met vriendelijke groeten, Wim van Dorst.
---------------------------------------------------------------------
Blue Baron = Wim van Dorst, Voice (+31) 074-443937, (+31) 02152-42319
(-: baron@clifton.hobby.nl WvD@Akzo.nl :-)
---------------------------------------------------------------------