🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: comp.lang.oberon
Article #1344

Oberon Cycles Per Second

#1344
From: Doug Danforth
Date: Wed, 17 Apr 1996 19:16
55 lines
2672 bytes
OBERON CYCLES PER SECOND

Below is a rank ordering of the number of Oberon Cycles that can be executed
per second under various operation systems and Oberon versions.  The term
cycles is used rather than tasks since it is assumed that many tasks can be
executed in a single cycle of the Oberon loop and not substantially change
the number of cycles per second.  More explicity it is assumed that if the
user has installed three tasks,abc, then the following happens

H0: OabcOabcOabc...

where "O" is an implicit task that frees time to the operating system so that
other non Oberon task can run.  If, however, we have

H1: OaObOcOaObOc ...

then, indeed, the time would grow as the number of tasks increases (I have
been assuming that Time(O) >>> Time(x)  for x=a,b,c...  This seems not to be
the case for Emi Zeller's Multi system).

In any case the reported number of cycles per second are:


O/S    Oberon      CPS                Reported by
------ ------     -----------         ------------------
Win95  Multi      124,000             Emi Zeller
Win3.x S3          13,800 (1)         Emi Zeller
Win95  S3           5,800             Doug Danforth
DOS    S3           1,400 (2)         Frank Hrebabetsky	
Linux  V4             167             Wojtek Skulski
Win95  V4              20             Doug Danforth

(1) uncertain whether this is Win3.x or Win95.
(2) best value reported (of all mouse locations on screen).

We seem to see a factor of 60,000 difference between the best and worst.
Even if we exclude the Multi system there is still a factor of almost
700 between best and worst.

Unless this analysis is all wet, it says to me that one should avoid spitting
procedures into tasks on Win95 V4.

Comments?

-Doug

-- 
-----------------------------------------------------------------------------
  Douglas G. Danforth, Ph.D.                       danforth@csli.stanford.edu
  Visiting Scholar                                 (415)723-2487 x332 vox  
  Applied Speech Technology Lab                    (415)725-2166 fax
  Center for the Study of Language and Information
  Ventura Hall                    
  Stanford University, Stanford CA.  94305-4115             
-----------------------------------------------------------------------------
Technical Details
Message-ID: <danforth.829768485@Turing.Stanford.EDU>
Path: arc1-ca.pugleaf.net!Turing.Stanford.EDU!danforth

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!Turing.Stanford.EDU!danforth
From: danforth@Turing.Stanford.EDU (Doug Danforth)
Newsgroups: comp.lang.oberon
Subject: Oberon Cycles Per Second
Date: 17 Apr 1996 12:16:34 -0700
Organization: Stanford University
Message-ID: <danforth.829768485@Turing.Stanford.EDU>
NNTP-Posting-Host: turing.stanford.edu
X-Newsreader: NN version 6.5.0 #1 (NOV)