Newsgroups: comp.lang.smalltalk
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!oitnews.harvard.edu!purdue!lerc.nasa.gov!magnus.acs.ohio-state.edu!math.ohio-state.edu!howland.reston.ans.net!torn!nott!cunews!dbuck
From: dbuck@superior.carleton.ca (Dave Buck)
Subject: Re: Smalltalk vs C vs C++ benchmark results
X-Nntp-Posting-Host: superior.carleton.ca
Message-ID: <DEHD8t.4AF@cunews.carleton.ca>
Sender: news@cunews.carleton.ca (News Administrator)
Organization: Carleton University, Ottawa, Canada
References: <DEDsF1.3I8@cunews.carleton.ca> <42hrt7$o6a@sundog.tiac.net>
Date: Wed, 6 Sep 1995 11:00:29 GMT
Lines: 33

In article <42hrt7$o6a@sundog.tiac.net>,
Joe Kinsella  <jkinsella@procd.com> wrote:
>David,
>
>Those numbers are quite difficult to believe.  Maybe you could 
>post your ST, C and C++ source to this group so we can make a 
>more objective look at it.
>
>Joe
>

It's a bit too much code to post on the net, I think.  Is it difficult
to believe that Smalltalk is so fast?  Keep in mind that in these
tests, Smalltalk has the opportunity to dynamically compile all of the
test code and take full advantage of method caching.  What I can say
is that I ran the tests on two different systems with different OS'es
and different C++ compilers.  The results posted in my last message
were the results that were the least favorable for Smalltalk.

If you have a specific test you'd like to question, I can post the C,
C++, and Smalltalk code for that one test.

David Buck
dbuck@ccs.carleton.ca

_________________________________
| David K. Buck                 |
| dbuck@ccs.carleton.ca         |
| The Object People             |
|_______________________________|



