X-Authentication-Warning: delorie.com: mail set sender to djgpp-bounces using -f
From: Rugxulo <rugxulo AT gmail DOT com>
Newsgroups: comp.os.msdos.djgpp
Subject: Re: PB on CPU Atom
Date: Fri, 26 Nov 2010 17:48:36 -0800 (PST)
Organization: http://groups.google.com
Lines: 49
Message-ID: <e9683889-a26e-42e9-81b5-31b3c40091e0@i41g2000vbn.googlegroups.com>
References: <4e67d035-8f32-4e9e-a78c-2370909f9ffb AT k11g2000vbf DOT googlegroups DOT com>
 <c85fca63-338e-4f0d-987d-c78972bd9561 AT 12g2000prq DOT googlegroups DOT com> <beb4d0eb-5be6-4a05-97ed-7f9377d01d79 AT c17g2000prm DOT googlegroups DOT com>
NNTP-Posting-Host: 65.13.115.246
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Trace: posting.google.com 1290822517 11507 127.0.0.1 (27 Nov 2010 01:48:37 GMT)
X-Complaints-To: groups-abuse AT google DOT com
NNTP-Posting-Date: Sat, 27 Nov 2010 01:48:37 +0000 (UTC)
Complaints-To: groups-abuse AT google DOT com
Injection-Info: i41g2000vbn.googlegroups.com; posting-host=65.13.115.246; posting-account=p5rsXQoAAAB8KPnVlgg9E_vlm2dvVhfO
User-Agent: G2/1.0
X-HTTP-UserAgent: Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US)
 AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.44 Safari/534.7,gzip(gfe)
Bytes: 3068
To: djgpp AT delorie DOT com
DJ-Gateway: from newsgroup comp.os.msdos.djgpp
Reply-To: djgpp AT delorie DOT com

Hi,

On Nov 26, 5:19=A0am, philippe <philippe DOT meyn DOT  DOT  DOT  AT gmail DOT com> wrote:
>
> thanks for your response.
> so I use DJGPP 2.03 with gcc 3.4.1.

3.4.1 ?? At least use 3.4.4, which is latest DJGPP has available for
that branch.   ;-)

I know 2.03p2 is "stable", but you could also try 2.04 "beta". Not
sure if it will help, though, but personally I would recommend it, at
least temporarily to test.

> when I compile with gcc4.4.4 I
> have a error, gcc 4.2.3 it's OK

What error? I do vaguely recall that G++ 4.2.3 was the last to have
some "backwards" compatible headers (for some odd reason).

> but I have no amelioration.

No improvement? Did you use -mtune or -march at all?? BTW, last I
checked, GCC did support "pentium_m".

http://gcc.gnu.org/onlinedocs/gcc/i386-and-x86_002d64-Options.html

> CWSDPMI r5 and freedos kernel 2036.

Try r7 and 2038 (at least worth an attempt). 2039 is also available
(and with COUNTRY.SYS support again, like 2037) but "unstable" (a few
rare regressions).

http://homer.rice.edu/~sandmann/cwsdpmi/csdpmi7b.zip

http://sourceforge.net/projects/freedos/files/Kernel/2038/kernel2038-fat32-=
binary.zip/download

> I discovered that: When I used a call who is in another source file
> that my source file test then the program is very slow but when I put
> the call function in the same file that the source test then the
> program is very fast. Why?

Whole program optimization?? Try -fwhole-program and --combine with
your files. (Or manually go and insert "inline" or "static" in key
places.) I dunno, optimization is a mess.   :-/

Oh, and BTW, please recompile without -O3 (not that you've mentioned
exactly what flags) since that often hinders instead of helps.