From: sandmann AT clio DOT rice DOT edu (Charles Sandmann)
Message-Id: <10301310328.AA12200@clio.rice.edu>
Subject: Unix vs DJGPP speed [was Re: small solve...]
To: djgpp-workers AT delorie DOT com
Date: Thu, 30 Jan 2003 21:28:00 -0600 (CST)
In-Reply-To: <3E39923A.3040907@mif.vu.lt> from "Laurynas Biveinis" at Jan 30, 2003 09:59:38 PM
X-Mailer: ELM [version 2.5 PL2]
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Reply-To: djgpp-workers AT delorie DOT com
Errors-To: nobody AT delorie DOT com
X-Mailing-List: djgpp-workers AT delorie DOT com
X-Unsubscribes-To: listserv AT delorie DOT com
Precedence: bulk

> On a unrelated note, why does OpenBSD with Pentium MMX 200 Mhz and
> 16 MB RAM run configure scripts *much* faster than DJGPP on my desktop
> Pentium II 375 Mhz 192 RAM with W2K ? I can provide bash running
> profiles if anyone is interested...

The DJGPP libc does lots of additional operations for compatibility, in
some cases we need to make 10 interrupt calls (which then must be reflected
through a virtual OS on Win2K) compared to a direct single kernel call
on Unixy OSes.  Remember, most of the GNU code is optimized for unix I/O
calls (as is the standard libc/posix API calls).

Someday I may release my "fast" libc, especially if we get dynamic libc
support, for comparison.  It is not as Unixy compatible - it was a branch
based on the original V2.00 beta libc I wrote.  It's currently in the 
CD stack as it's not comptible with anything, not even V2.00 release...