2010/4/3 John M McIntosh <johnmci@smalltalkconsulting.com>

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:

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 <johnmci@smalltalkconsulting.com> �� Twitter: ��squeaker68882
Corporate Smalltalk Consulting Ltd.����http://www.smalltalkconsulting.com
===========================================================================





_______________________________________________
Pharo-project mailing list
Pharo-project@lists.gforge.inria.fr
http://lists.gforge.inria.fr/cgi-bin/mailman/listinfo/pharo-project