Smalltalk › Pharo › Pharo Smalltalk Developers

Linux VM microbenchmarks

_‹ Previous Topic Next Topic _›

Classic

List

Threaded

15 messages Options

laurent laffont

Linux VM microbenchmarks

Hi,

Thanks to people who send the results of tinyBenchmarks for various CPU, here's the report.

What I want to know is whether these results are crap or "normal". It seems that all people succeed in compiling the VM with the source provided. So it may be a candidate for Pharo 1.0 ?

The procedure to build the VM was:

wget http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-src.tar.gz

tar -xvzf Squeak-3.11.3.2135-pharo-src.tar.gz

cd Squeak-3.11.3.2135-pharo-src/

mkdir build && cd build

../unix/cmake/configure --CFLAGS="-O2"

make

The results:

Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz

64 bits

===============================================

432 M bytecodes/sec; 13 M sends/sec

Intel(R) Core(TM)2 Duo CPU T8300 @ 2.40GHz

64 bits

===============================================

424 M bytecodes/sec; 13 M sends/sec

Intel(R) Core(TM)2 Duo CPU T7500 @ 2.20GHz

32 bits

===============================================

389 M bytecodes/sec; 10.5 M sends/sec

Intel(R) Core(TM)2 CPU T7200 @ 2.00GHz

32 bits

===============================================

330 M bytecodes/sec; 9.2 M sends/sec

Intel(R) Core(TM)2 CPU 4300 @ 1.80GHz

64 bits (CFLAGS = -O3)

===============================================

331 M bytecodes/sec; 8.9 M sends/sec

Intel(R) Core(TM)2 CPU 4300 @ 1.80GHz

64 bits (CFLAGS = -O2)

===============================================

106 M bytecodes/sec; 3.4 M sends/sec

Intel(R) Core(TM)2 CPU 6420 @ 2.13GHz

32 bits

===============================================

220 M bytecodes/sec; 7.6 M sends/sec

Intel(R) Pentium(R) 4 CPU 3.00GHz

32 bits

===============================================

93 M bytecodes/sec; 5.5 M sends/sec

AMD Athlon(tm) 64 Processor 3000+

===============================================

87 M bytecodes/sec; 4.5 M sends/sec

Laurent Laffont

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

johnmci

Re: Linux VM microbenchmarks

On 2010-04-03, at 9:27 AM, laurent laffont wrote:

Hi,

Thanks to people who send the results of tinyBenchmarks for various CPU, here's the report.

What I want to know is whether these results are crap or "normal". It seems that all people succeed in compiling the VM with the source provided. So it may be a candidate for Pharo 1.0 ?

The procedure to build the VM was:

wget http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-src.tar.gz

tar -xvzf Squeak-3.11.3.2135-pharo-src.tar.gz
cd Squeak-3.11.3.2135-pharo-src/
mkdir build && cd build
../unix/cmake/configure --CFLAGS="-O2"
make

The results:

Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz
64 bits
===============================================
432 M bytecodes/sec; 13 M sends/sec

Optimal on a Intel(r) Core(TM)2 duo CPU @ 2.33Ghz is

587 M bytecodes/sec; 14.7 M sends/sec

===========================================================================

John M. McIntosh <[hidden email]> Twitter: squeaker68882

Corporate Smalltalk Consulting Ltd. http://www.smalltalkconsulting.com

===========================================================================

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

smime.p7s (3K) Download Attachment

laurent laffont

Re: Linux VM microbenchmarks

2010/4/3 John M McIntosh <[hidden email]>

On 2010-04-03, at 9:27 AM, laurent laffont wrote:

Hi,

Thanks to people who send the results of tinyBenchmarks for various CPU, here's the report.

What I want to know is whether these results are crap or "normal". It seems that all people succeed in compiling the VM with the source provided. So it may be a candidate for Pharo 1.0 ?

The procedure to build the VM was:

wget http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-src.tar.gz

tar -xvzf Squeak-3.11.3.2135-pharo-src.tar.gz
cd Squeak-3.11.3.2135-pharo-src/
mkdir build && cd build
../unix/cmake/configure --CFLAGS="-O2"
make

The results:

Intel(R) Core(TM)2 CPU 6600 @ 2.40GHz
64 bits
===============================================
432 M bytecodes/sec; 13 M sends/sec

Optimal on a Intel(r) Core(TM)2 duo CPU @ 2.33Ghz is
587 M bytecodes/sec; 14.7 M sends/sec

Is "Optimal" means special CFLAGS, GCC version / Intel compiler, or source code changes ? I understand you cannot tell how you optimize the VM. But with the VM source I provide, maybe you can tell that compiling it with your "secret weapons" you obtain near optimal results ?

Laurent Laffont

--
===========================================================================

John M. McIntosh <[hidden email]> Twitter: squeaker68882

Corporate Smalltalk Consulting Ltd. http://www.smalltalkconsulting.com

===========================================================================

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

hilaire

Re: Linux VM microbenchmarks

CONTENTS DELETED

The author has deleted this message.

hilaire

Re: Linux VM microbenchmarks

In reply to this post by laurent laffont

CONTENTS DELETED

The author has deleted this message.

laurent laffont

Re: Linux VM microbenchmarks

Thanks Hilaire.

Could you try with this source ? It has gnuification (using Gnuified.st). On my machine it's a little slower but may be it makes a big difference on yours.

On my machine, I have almost the same result with Exupery and Squeak VM :(

wget http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-gnuified-src.tar.gz

Laurent Laffont

On Sat, Apr 3, 2010 at 10:19 PM, Hilaire Fernandes <[hidden email]> wrote:

Laurent,

I runned the same benchmark with Exupery, here is

Exupery
202371541 bytecodes/sec; 5948654 sends/sec
201574803 bytecodes/sec; 5948654 sends/sec
201416207 bytecodes/sec; 5933632 sends/sec
202531645 bytecodes/sec; 5903814 sends/sec
201892744 bytecodes/sec; 5938631 sends/sec

-O2 (compiled source code from the archive you provided)
87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

You better check with Bryce.

Hilaire

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

hilaire

Re: Linux VM microbenchmarks

CONTENTS DELETED

The author has deleted this message.

laurent laffont

Re: Linux VM microbenchmarks

Thanks a lot Hilaire. And if you still have some courage :) here's one with awk gnuification. (You need to have gawk package installed:

apt-get install gawk)

http://lolgzs.free.fr/pharo/squeak-vm/squeakvm-pharo-2151-src.tar.gz

Laurent Laffont

On Sun, Apr 4, 2010 at 7:57 PM, Hilaire Fernandes <[hidden email]> wrote:

Here are my numbers

Hilaire

-O1
82527401 bytecodes/sec; 4334942 sends/sec
82580645 bytecodes/sec; 4326332 sends/sec
82633957 bytecodes/sec; 4334942 sends/sec
82156611 bytecodes/sec; 4330633 sends/sec
81841432 bytecodes/sec; 4352264 sends/sec

-O2

87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

-O3
80655324 bytecodes/sec; 4300707 sends/sec
80250783 bytecodes/sec; 4304957 sends/sec
80050031 bytecodes/sec; 4279584 sends/sec
80351537 bytecodes/sec; 4292233 sends/sec
80452545 bytecodes/sec; 4304957 sends/sec

-O2; gnuified
118738404 bytecodes/sec; 5217731 sends/sec
118959107 bytecodes/sec; 5210018 sends/sec
118959107 bytecodes/sec; 5202328 sends/sec
118299445 bytecodes/sec; 5213872 sends/sec
118848653 bytecodes/sec; 5198491 sends/sec

Exupery
201099764 bytecodes/sec; 5840227 sends/sec
201099764 bytecodes/sec; 5903814 sends/sec
200469851 bytecodes/sec; 5908763 sends/sec
200784313 bytecodes/sec; 5879195 sends/sec
201416207 bytecodes/sec; 5898874 sends/sec

laurent laffont a écrit :

Thanks Hilaire.

Could you try with this source ? It has gnuification (using Gnuified.st). On my machine it's a little slower but may be it makes a big difference on yours.
On my machine, I have almost the same result with Exupery and Squeak VM :(
wget http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-gnuified-src.tar.gz

Laurent Laffont

On Sat, Apr 3, 2010 at 10:19 PM, Hilaire Fernandes <[hidden email] <mailto:[hidden email]>> wrote:

Laurent,

I runned the same benchmark with Exupery, here is

Exupery
202371541 bytecodes/sec; 5948654 sends/sec
201574803 bytecodes/sec; 5948654 sends/sec
201416207 bytecodes/sec; 5933632 sends/sec
202531645 bytecodes/sec; 5903814 sends/sec
201892744 bytecodes/sec; 5938631 sends/sec

-O2 (compiled source code from the archive you provided)
87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

You better check with Bryce.

Hilaire

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>

http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

------------------------------------------------------------------------

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

hilaire

Re: Linux VM microbenchmarks

CONTENTS DELETED

The author has deleted this message.

hilaire

Re: Linux VM microbenchmarks

In reply to this post by laurent laffont

CONTENTS DELETED

The author has deleted this message.

Bryce Kampjes

Re: Linux VM microbenchmarks

In reply to this post by hilaire

On Sat, 2010-04-03 at 22:19 +0200, Hilaire Fernandes wrote:

> Laurent,
>
> I runned the same benchmark with Exupery, here is
>
> Exupery
> 202371541 bytecodes/sec; 5948654 sends/sec
> 201574803 bytecodes/sec; 5948654 sends/sec
> 201416207 bytecodes/sec; 5933632 sends/sec
> 202531645 bytecodes/sec; 5903814 sends/sec
> 201892744 bytecodes/sec; 5938631 sends/sec
>
>
> -O2 (compiled source code from the archive you provided)
> 87372013 bytecodes/sec; 4436220 sends/sec
> 86544962 bytecodes/sec; 4501376 sends/sec
> 86253369 bytecodes/sec; 4507132 sends/sec
> 86253369 bytecodes/sec; 4487049 sends/sec
> 87372013 bytecodes/sec; 4498503 sends/sec
>
> You better check with Bryce.

The Exupery build is just whatever ./config/configure decides to use,
nothing special here. I do make sure that the gawk gnuification runs.
It's a very vanilla but a bit dated C VM build environment.

Bryce

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

laurent laffont

Re: Linux VM microbenchmarks

In reply to this post by hilaire

On Mon, Apr 5, 2010 at 11:56 AM, Hilaire Fernandes <[hidden email]> wrote:

With gawk

gawk, -O2
195121951 bytecodes/sec; 6490934 sends/sec
195569136 bytecodes/sec; 6526995 sends/sec
195569136 bytecodes/sec; 6533044 sends/sec
196168582 bytecodes/sec; 6496917 sends/sec
194086429 bytecodes/sec; 6508915 sends/sec

What this latest change to the source code of the VM ?

Hi Hilaire,

this is the revision 2151 of squeak-vm (as described in Adrian's post: http://www.adrian-lienhard.ch/blog?article=building-a-pharo-squeak-vm-from-first-principles)

The 2 patch I've applied:
- http://lolgzs.free.fr/pharo/ft2plugin.patch which makes build of FT2Plugin works
- http://lolgzs.free.fr/pharo/CFLAGS.patch which resolve multiple CFLAGS options to work

Then I take a Pharo Core 1.0 image, load VMMaker in:

Gofer new
squeaksource: 'MetacelloRepository';
package: 'ConfigurationOfVMMaker';
load.

(Smalltalk at:#ConfigurationOfVMMaker) project lastVersion load.

Correct header in FTPlugin class>>declareCVarsIn: cg
...
cg addHeaderFile: '<freetype/tttables.h>'.
...

All plugins but UUID external (if UUID external, my VM crashes, so I put it internal and it works).

Then apply the procedure http://magaloma.blogspot.com/2010/03/how-i-build-squeak-vm-on-archlinux.html (I will write an update)

Laurent Laffont

Hilaire

laurent laffont a écrit :

Thanks a lot Hilaire. And if you still have some courage :) here's one with awk gnuification. (You need to have gawk package installed:

apt-get install gawk)

http://lolgzs.free.fr/pharo/squeak-vm/squeakvm-pharo-2151-src.tar.gz

Laurent Laffont

On Sun, Apr 4, 2010 at 7:57 PM, Hilaire Fernandes <[hidden email] <mailto:[hidden email]>> wrote:

Here are my numbers

Hilaire

-O1
82527401 bytecodes/sec; 4334942 sends/sec
82580645 bytecodes/sec; 4326332 sends/sec
82633957 bytecodes/sec; 4334942 sends/sec
82156611 bytecodes/sec; 4330633 sends/sec
81841432 bytecodes/sec; 4352264 sends/sec

-O2

87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

-O3
80655324 bytecodes/sec; 4300707 sends/sec
80250783 bytecodes/sec; 4304957 sends/sec
80050031 bytecodes/sec; 4279584 sends/sec
80351537 bytecodes/sec; 4292233 sends/sec
80452545 bytecodes/sec; 4304957 sends/sec

-O2; gnuified
118738404 bytecodes/sec; 5217731 sends/sec
118959107 bytecodes/sec; 5210018 sends/sec
118959107 bytecodes/sec; 5202328 sends/sec
118299445 bytecodes/sec; 5213872 sends/sec
118848653 bytecodes/sec; 5198491 sends/sec

Exupery
201099764 bytecodes/sec; 5840227 sends/sec
201099764 bytecodes/sec; 5903814 sends/sec
200469851 bytecodes/sec; 5908763 sends/sec
200784313 bytecodes/sec; 5879195 sends/sec
201416207 bytecodes/sec; 5898874 sends/sec

laurent laffont a écrit :

Thanks Hilaire.

Could you try with this source ? It has gnuification (using
Gnuified.st). On my machine it's a little slower but may be it
makes a big difference on yours.
On my machine, I have almost the same result with Exupery and
Squeak VM :(
wget
http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-gnuified-src.tar.gz

Laurent Laffont

On Sat, Apr 3, 2010 at 10:19 PM, Hilaire Fernandes
<[hidden email]
<mailto:[hidden email]>
<mailto:[hidden email]
<mailto:[hidden email]>>>
wrote:

Laurent,

I runned the same benchmark with Exupery, here is

Exupery
202371541 bytecodes/sec; 5948654 sends/sec
201574803 bytecodes/sec; 5948654 sends/sec
201416207 bytecodes/sec; 5933632 sends/sec
202531645 bytecodes/sec; 5903814 sends/sec
201892744 bytecodes/sec; 5938631 sends/sec

-O2 (compiled source code from the archive you provided)
87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

You better check with Bryce.

Hilaire

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
<mailto:[hidden email]
<mailto:[hidden email]>>

http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

------------------------------------------------------------------------

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

------------------------------------------------------------------------

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

laurent laffont

Re: Linux VM microbenchmarks

In reply to this post by hilaire

On Mon, Apr 5, 2010 at 11:57 AM, Hilaire Fernandes <[hidden email]> wrote:

btw, in all the version you provided there is no free type pluglin

? Should be here... What's the output of your ../unix/cmake/configure command ?

Laurent Laffont

Hilaire

laurent laffont a écrit :

Thanks a lot Hilaire. And if you still have some courage :) here's one with awk gnuification. (You need to have gawk package installed:

apt-get install gawk)

http://lolgzs.free.fr/pharo/squeak-vm/squeakvm-pharo-2151-src.tar.gz

Laurent Laffont

On Sun, Apr 4, 2010 at 7:57 PM, Hilaire Fernandes <[hidden email] <mailto:[hidden email]>> wrote:

Here are my numbers

Hilaire

-O1
82527401 bytecodes/sec; 4334942 sends/sec
82580645 bytecodes/sec; 4326332 sends/sec
82633957 bytecodes/sec; 4334942 sends/sec
82156611 bytecodes/sec; 4330633 sends/sec
81841432 bytecodes/sec; 4352264 sends/sec

-O2

87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

-O3
80655324 bytecodes/sec; 4300707 sends/sec
80250783 bytecodes/sec; 4304957 sends/sec
80050031 bytecodes/sec; 4279584 sends/sec
80351537 bytecodes/sec; 4292233 sends/sec
80452545 bytecodes/sec; 4304957 sends/sec

-O2; gnuified
118738404 bytecodes/sec; 5217731 sends/sec
118959107 bytecodes/sec; 5210018 sends/sec
118959107 bytecodes/sec; 5202328 sends/sec
118299445 bytecodes/sec; 5213872 sends/sec
118848653 bytecodes/sec; 5198491 sends/sec

Exupery
201099764 bytecodes/sec; 5840227 sends/sec
201099764 bytecodes/sec; 5903814 sends/sec
200469851 bytecodes/sec; 5908763 sends/sec
200784313 bytecodes/sec; 5879195 sends/sec
201416207 bytecodes/sec; 5898874 sends/sec

laurent laffont a écrit :

Thanks Hilaire.

Could you try with this source ? It has gnuification (using
Gnuified.st). On my machine it's a little slower but may be it
makes a big difference on yours.
On my machine, I have almost the same result with Exupery and
Squeak VM :(
wget
http://lolgzs.free.fr/pharo/squeak-vm/Squeak-3.11.3.2135-pharo-gnuified-src.tar.gz

Laurent Laffont

On Sat, Apr 3, 2010 at 10:19 PM, Hilaire Fernandes
<[hidden email]
<mailto:[hidden email]>
<mailto:[hidden email]
<mailto:[hidden email]>>>
wrote:

Laurent,

I runned the same benchmark with Exupery, here is

Exupery
202371541 bytecodes/sec; 5948654 sends/sec
201574803 bytecodes/sec; 5948654 sends/sec
201416207 bytecodes/sec; 5933632 sends/sec
202531645 bytecodes/sec; 5903814 sends/sec
201892744 bytecodes/sec; 5938631 sends/sec

-O2 (compiled source code from the archive you provided)
87372013 bytecodes/sec; 4436220 sends/sec
86544962 bytecodes/sec; 4501376 sends/sec
86253369 bytecodes/sec; 4507132 sends/sec
86253369 bytecodes/sec; 4487049 sends/sec
87372013 bytecodes/sec; 4498503 sends/sec

You better check with Bryce.

Hilaire

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
<mailto:[hidden email]
<mailto:[hidden email]>>

http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

------------------------------------------------------------------------

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
<mailto:[hidden email]>
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

------------------------------------------------------------------------

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

hilaire

Re: Linux VM microbenchmarks

CONTENTS DELETED

The author has deleted this message.

laurent laffont

Re: Linux VM microbenchmarks

On Tue, Apr 6, 2010 at 11:45 AM, Hilaire Fernandes <[hidden email]> wrote:

laurent laffont a écrit :

btw, in all the version you provided there is no free type pluglin

? Should be here... What's the output of your ../unix/cmake/configure command ?

-- checking for module 'freetype2'
-- package 'freetype2' not found

Do you have packages libfreetype6-dev and libfreetype6 installed ?

Laurent Laffont

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project

_______________________________________________
Pharo-project mailing list
[hidden email]
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project