X-Authentication-Warning:	delorie.com: mail set sender to djgpp-bounces using -f
X-Recipient:	djgpp AT delorie DOT com
DKIM-Signature:	v=1; a=rsa-sha256; c=relaxed/relaxed;
	d=gmail.com; s=gamma;
	h=domainkey-signature:received:received:from:to:references
	:in-reply-to:subject:date:message-id:mime-version:content-type
	:content-transfer-encoding:x-mailer:thread-index:x-mimeole;
	bh=dxxGUjhSK6kPe0EdaRmmgLpfOy4NqKNqyqKupJug5uc=;
	b=LzKjh/gMudB13J8HR4+0lf57da1sbkkJhs47OHEd8YVs/d8qZ6npHAfkCo5YXcqgC2
	4QtHhEiteshBnf6XqjCe6r7VHVgAFe18ai/zykoRiU2H1xpCfFNe7kj7jr0luGXZmPTP
	q7nKCjx/L0yqcJtrjD6Ix9roLUKGoW2x9luws=
DomainKey-Signature:	a=rsa-sha1; c=nofws;
	d=gmail.com; s=gamma;
	h=from:to:references:in-reply-to:subject:date:message-id:mime-version
	:content-type:content-transfer-encoding:x-mailer:thread-index
	:x-mimeole;
	b=QGZTvmxUs91DWegtEHkO/8Lq0VsrjaX8lU/xTIzcY/u7YY5COXV6nc4K1cIhjc3Wrm
	Fsh8mly06OM7soZpT+HMlvFUMt8ARfn65kJVi9nqQlnjQFbJfUr+K8/sERNUhT240T58
	xM1X2kxe8nQQWWHalAsPsiB8SDmp/DiNQRUtI=
From:	"Matthew Petricoen" <strstream AT gmail DOT com>
To:	<djgpp AT delorie DOT 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> <e9683889-a26e-42e9-81b5-31b3c40091e0 AT i41g2000vbn DOT googlegroups DOT com> <e0a39940-61ac-4916-90f4-5a7b06c05a9d AT i25g2000prd DOT googlegroups DOT com>
In-Reply-To:	<e0a39940-61ac-4916-90f4-5a7b06c05a9d@i25g2000prd.googlegroups.com>
Subject:	RE: PB on CPU Atom
Date:	Tue, 4 Jan 2011 14:03:39 -0500
Message-ID:	<6E29B11AEA054C17BD1E1A3A89AAC207@KAIN>
MIME-Version:	1.0
X-Mailer:	Microsoft Office Outlook 11
thread-index:	AcusLtrUlDQE+BT+Qq6/7yrfAEkKVAAEpFyw
X-MimeOLE:	Produced By Microsoft MimeOLE V6.1.7600.16543
Reply-To:	djgpp AT delorie DOT com

Hello. I'm not sure if someone has suggested this before, but have you tried
to inline "affcarinchtest". That seems to be a fairly long loop. Depending
on gcc, you might have to use something along the lines of
__attribute__((always_inline)). I don't think "inline" alone works like it
used to.

-----Original Message-----
From: philippe [mailto:philippe DOT meynard AT gmail DOT com] 
Sent: Tuesday, January 04, 2011 11:25 AM
To: djgpp AT delorie DOT com
Subject: Re: PB on CPU Atom

> 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?


Hi, everybody and happy new year.
I come back on my problem and in fact I discovered this.
my test program use 2 source file. see :

test1.c

vois test1(void)
{
                char a;
	uint64 debclock1,finclock1;
	uint64 tpscalc;
	long tpscalc2;
	char chaine[80];
	int i;

	init_cpu_speed();
                printf("start\n");
                debclock1=get_rdtsc();
	for(i=0;i<3200000;i++){
		affcarinchtest2(a,chaine);
		a++;
		if(a>'Z') a=65;
	}
	finclock1=get_rdtsc();
	tpscalc=finclock1-debclock1;
	tpscalc2=(long)(((tpscalc*MULT_COUNT_US)/COUNT_CPU_BY_SECOND));
	printf("time 1: %ld\n",((long)tpscalc2));
}

test2.c

void affcarinchtest(char chaine,char *ptrch)
{
	*ptrch=chaine;
}

when I compile this only 2 files I have a executed time correct, but
When I compile this file with another source files and who create a
big program (> 3Mo) then I have a executed time very long (10 time
longer!)  I suppose that the problem is the call function is different
if the call is short or long ?
I test with many different option(like Rugxulo suggest : mtune,
without O3, etc), without succes. With different version of gcc,
without succces
I haven't test with -Atom option of gcc because it's only implemented
on gcc 4.5 and not on djgpp.
Have you a suggestion?

No virus found in this incoming message.
Checked by AVG - www.avg.com 
Version: 9.0.872 / Virus Database: 271.1.1/3358 - Release Date: 01/04/11
02:34:00

- Raw text -