public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "paulthomas2 at wanadoo dot fr" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug c++/14563] octave built under Cygwin very slow
Date: Wed, 31 Mar 2004 00:21:00 -0000 [thread overview]
Message-ID: <20040331002122.12164.qmail@sources.redhat.com> (raw)
In-Reply-To: <20040312233606.14563.paulthomas2@wanadoo.fr>
------- Additional Comments From paulthomas2 at wanadoo dot fr 2004-03-31 00:21 -------
Subject: Re: octave built under Cygwin very slow
I realise from the silence that it cannot have been apparent from the
last forward that we have understood where the problem lies with
gcc-3.3.1 (cygming special). It has nothing to do with sjlj, inspite of
the profiling. A significant difference has creapt in between new and
malloc. Normally, on just about every system that we have tested, new
is about 50% slower than malloc. In gcc 3.3.1-3 (cygming special) it is
about 6-10 times slower. We have no idea why.
The following scrap of code demonstrates it (have used -O2 for compilation):
#include <iostream>
#include <stdio.h>
#include <time.h>
#include <vector>
using namespace std;
int main()
{
long t1 = clock();
for (int iloop = 0; iloop < 10000000; iloop++)
{
double *myarray;
if ((myarray = new double [1]) == NULL)
{
cout << "unable to allocate my array at iloop=" << iloop << endl;
exit(1);
}
delete [] myarray;
}
long t2 = clock();
double delt1 = (double)( t2 - t1 )/ (double)(CLOCKS_PER_SEC);
cout << "done looping time 1=" << delt1 << endl;
long t3 = clock();
for (int iloop = 0; iloop < 10000000; iloop++)
{
double *myarray = (double *)malloc(sizeof(double));
if (myarray== NULL) { printf("alloc failed\n"); exit(1); }
else free (myarray);
}
long t4 = clock();
double delt2 = (double)( t4 - t3 )/ (double)(CLOCKS_PER_SEC);
cout << "done looping time 2=" << delt2 << endl;
return 0;
}
Best regards
Paul Thomas
bangerth at dealii dot org wrote:
>------- Additional Comments From bangerth at dealii dot org 2004-03-25 14:36 -------
>SJLJ stands for "setjmp/longjmp". I'm not an expert in this field
>(as I know virtually nothing about the gcc interiors anyway, I'm
>just the bug database dude), but here's the idea: when you call
>a function that may or may not throw an exception, and the calling
>function needs to run destructors of local objects in case an exception
>is thrown, you need to put down the address of the cleanup code somewhere.
>One way to do this is to set this address via setjmp, and throwing an
>exception then transfers control to this place via longjmp. This is expensive
>since you have to call setjmp every time a cleanup is necessary.
>
>The other possibility is to use lookup tables that the compiler generates
>statically, so this is cheap at run-time, but incurs some code overhead. If
>you generate an exception, you have to somehow look up where to transfer
>execution. Don't ask me how exactly this works, but it is to my best
>knowledge how dwarf2 exception unwinding works. Corrections on this topic
>my more knowledgable people are certainly welcome.
>
>Now back to the question how we can figure out what the problem is: if
>using -fno-exceptions doesn't work, is there a possibility you repeat
>your experiments with an octave version prior to the introduction of
>exceptions?
>
>W.
>
>
>
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=14563
next prev parent reply other threads:[~2004-03-31 0:21 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-03-12 23:36 [Bug c++/14563] New: " paulthomas2 at wanadoo dot fr
2004-03-13 7:24 ` [Bug c++/14563] " pinskia at gcc dot gnu dot org
2004-03-13 8:06 ` paulthomas2 at wanadoo dot fr
2004-03-14 20:33 ` bangerth at dealii dot org
2004-03-24 9:52 ` paulthomas2 at wanadoo dot fr
2004-03-24 15:57 ` bangerth at dealii dot org
2004-03-24 16:38 ` paulthomas2 at wanadoo dot fr
2004-03-24 17:03 ` bangerth at dealii dot org
2004-03-24 21:07 ` Ben dot Diedrich at noaa dot gov
2004-03-24 22:58 ` dannysmith at users dot sourceforge dot net
2004-03-25 6:40 ` paulthomas2 at wanadoo dot fr
2004-03-25 13:43 ` bangerth at dealii dot org
2004-03-25 14:16 ` Ben dot Diedrich at noaa dot gov
2004-03-25 14:17 ` paulthomas2 at wanadoo dot fr
2004-03-25 14:26 ` paulthomas2 at wanadoo dot fr
2004-03-25 14:37 ` bangerth at dealii dot org
2004-03-25 15:37 ` Ben dot Diedrich at noaa dot gov
2004-03-25 16:41 ` paulthomas2 at wanadoo dot fr
2004-03-28 21:19 ` paulthomas2 at wanadoo dot fr
2004-03-28 22:28 ` pkienzle at users dot sf dot net
2004-03-31 0:21 ` paulthomas2 at wanadoo dot fr [this message]
2004-04-02 17:43 ` paulthomas2 at wanadoo dot fr
2004-04-02 19:55 ` bangerth at dealii dot org
2004-04-02 20:35 ` dannysmith at users dot sourceforge dot net
2004-04-02 20:41 ` pcarlini at suse dot de
2004-04-02 20:44 ` bangerth at dealii dot org
2004-04-03 9:10 ` paulthomas2 at wanadoo dot fr
2004-04-03 17:19 ` epanelelytha at kellertimo dot de
2004-04-03 17:54 ` paulthomas2 at wanadoo dot fr
2004-04-03 18:00 ` epanelelytha at kellertimo dot de
2004-04-03 18:24 ` paulthomas2 at wanadoo dot fr
2004-07-12 14:50 ` [Bug libstdc++/14563] new/delete much slower than malloc/free pinskia at gcc dot gnu dot org
2004-07-12 19:21 ` paulthomas2 at wanadoo dot fr
2004-07-12 20:55 ` bangerth at dealii dot org
2004-07-13 4:17 ` paulthomas2 at wanadoo dot fr
2004-07-28 2:50 ` ron_hylton at hotmail dot com
2004-07-28 3:57 ` ron_hylton at hotmail dot com
2004-07-28 6:03 ` [Bug target/14563] " pinskia at gcc dot gnu dot org
2004-07-29 4:23 ` ron_hylton at hotmail dot com
2004-08-08 9:24 ` paulthomas2 at wanadoo dot fr
2004-11-10 8:21 ` [Bug target/14563] [3.3/3.4/4.0 Regression] new/delete much slower than malloc/free because of sjlj exceptions giovannibajo at libero dot it
2004-11-10 8:21 ` giovannibajo at libero dot it
2004-11-10 9:10 ` dannysmith at users dot sourceforge dot net
2004-11-10 12:46 ` [Bug target/14563] " pinskia at gcc dot gnu dot org
2004-11-10 16:20 ` ron_hylton at hotmail dot com
2004-11-10 17:05 ` kjd at duda dot org
2004-11-13 11:03 ` paulthomas2 at wanadoo dot fr
2004-11-14 17:03 ` ken dot duda at gmail dot com
2004-11-14 18:04 ` paulthomas2 at wanadoo dot fr
2004-11-14 22:40 ` ken dot duda at gmail dot com
2005-05-12 14:53 ` pinskia at gcc dot gnu dot org
2005-05-12 14:54 ` pinskia at gcc dot gnu dot org
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20040331002122.12164.qmail@sources.redhat.com \
--to=gcc-bugzilla@gcc.gnu.org \
--cc=gcc-bugs@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).