Date:	Wed, 16 Jun 1999 16:45:39 +0300 (IDT)
From:	Eli Zaretskii <eliz AT is DOT elta DOT co DOT il>
X-Sender:	eliz AT is
To:	salvador <salvador AT inti DOT gov DOT ar>
cc:	djgpp AT delorie DOT com, allegro AT canvaslink DOT com, balug-lst AT balug DOT org DOT ar
Subject:	Re: Compilers comparisson, some opinions about the generated , assembler
In-Reply-To:	<37679FA2.6F2B3BAD@inti.gov.ar>
Message-ID:	<Pine.SUN.3.91.990616163656.10392A-100000@is>
MIME-Version:	1.0
Reply-To:	djgpp AT delorie DOT com
X-Mailing-List:	djgpp AT delorie DOT com
X-Unsubscribes-To:	listserv AT delorie DOT com

On Wed, 16 Jun 1999, salvador wrote:

> 2) If I run only one task in Win95 (and the scheduler didn't get crazy) I get
> the same speed in W95, the difference is too small (under 2%)

My notion of slow-down when running on Windows is taken from configuring
and building large GNU packages, those where it takes more than 10 minutes
to run the configure scripts and Make.  Overall, on the same machine which
is higly optimized for DJGPP programs both in DOS and in Windows, I
usually get 30%-40% slow-down for the same task when running from
Windows.  That's running only one active DOS box under Windows, and no
other Windows programs.  For example, what takes 20 minutes from Windows 
would usually take about 12 minutes from DOS.

I have never been able to figure out just what it is in Windows that takes
so many CPU cycles.  Interestingly enough, if I do something else while 
the compilation runs, like read my mail with Emacs, or type some code 
into the editor, the compilation time is unchanged.  So apparently 
multi-tasking other virtual machines is NOT what steals the CPU cycles.

- Raw text -